Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints

Prediction of gestational diabetes mellitus at the first trimester: machine-learning algorithms

PURPOSE

Short- and long-term complications of gestational diabetes mellitus (GDM) involving pregnancies and offspring warrant the development of an effective individualized risk prediction model to reduce and prevent GDM together with its associated co-morbidities. The aim is to use machine learning (ML) algorithms to study data gathered throughout the first trimester in order to predict GDM.

METHODS

Two independent cohorts with forty-five features gathered through first trimester were included. We constructed prediction models based on three different algorithms and traditional logistic regression, and deployed additional two ensemble algorithms to identify the importance of individual features.

RESULTS

4799 and 2795 pregnancies were included in the Xinhua Hospital Chongming branch (XHCM) and the Shanghai Pudong New Area People's Hospital (SPNPH) cohorts, respectively. Extreme gradient boosting (XGBoost) predicted GDM with moderate performance (the area under the receiver operating curve (AUC) = 0.75) at pregnancy initiation and good-to-excellent performance (AUC = 0.99) at the end of the first trimester in the XHCM cohort. The trained XGBoost showed moderate performance in the SPNPH cohort (AUC = 0.83). The top predictive features for GDM diagnosis were pre-pregnancy BMI and maternal abdominal circumference at pregnancy initiation, and FPG and HbA1c at the end of the first trimester.

CONCLUSION

Our work demonstrated that ML models based on the data gathered throughout the first trimester achieved moderate performance in the external validation cohort.

Bleeding Scoring Systems in Neonates: A Systematic Review

We conducted a systematic review aiming to summarize the data on the current hemorrhage prediction models and evaluate their potential for generalized application in the neonatal population. The electronic databases PubMed and Scopus were searched, up to September 20, 2023, for studies that focused on development and/or validation of a prediction model for bleeding risk in neonates, and described the process of model building. Nineteen studies fulfilled the inclusion criteria for the present review. Eighteen bleeding risk prediction models in the neonatal population were identified, four of which were internally validated, one temporally and one externally validated. The existing prediction models for neonatal hemorrhage are mostly based on clinical variables and do not take into account the clinical course and hemostatic profile of the neonates. Most studies aimed at predicting the risk of intraventricular hemorrhage (IVH) reflecting the fact that IVH is the most frequent and serious bleeding complication in preterm neonates. A justification for the study sample size for developing the prediction model was given only by one study. Prediction and stratification of risk of hemorrhage in neonates is yet to be optimized. To this end, qualitative standards for model development need to be further improved. The assessment of the risk of bleeding incorporating platelet count, coagulation parameters, and a set of relevant clinical variables is crucial. Large, rigorous, collaborative cohort studies are warranted to develop a robust prediction model to inform the need for transfusion, which is a fundamental step towards personalized transfusion therapy in neonates.

Machine-Learning Assisted Screening of Correlated Covariates: Application to Clinical Data of Desipramine

Stepwise covariate modeling (SCM) has a high computational burden and can select the wrong covariates. Machine learning (ML) has been proposed as a screening tool to improve the efficiency of covariate selection, but little is known about how to apply ML on actual clinical data. First, we simulated datasets based on clinical data to compare the performance of various ML and traditional pharmacometrics (PMX) techniques with and without accounting for highly-correlated covariates. This simulation step identified the ML algorithm and the number of top covariates to select when using the actual clinical data. A previously developed desipramine population-pharmacokinetic model was used to simulate virtual subjects. Fifteen covariates were considered with four having an effect included. Based on the F1 score (an accuracy measure), ridge regression was the most accurate ML technique on 200 simulated datasets (F1 score = 0.475 ± 0.231), a performance which almost doubled when highly-correlated covariates were accounted for (F1 score = 0.860 ± 0.158). These performances were better than forwards selection with SCM (F1 score = 0.251 ± 0.274 and 0.499 ± 0.381 without/with correlations respectively). In terms of computational cost, ridge regression (0.42 ± 0.07 seconds/simulated dataset, 1 thread) was ~20,000 times faster than SCM (2.30 ± 2.29 hours, 15 threads). On the clinical dataset, prescreening with the selected ML algorithm reduced SCM runtime by 42.86% (from 1.75 to 1.00 days) and produced the same final model as SCM only. In conclusion, we have demonstrated that accounting for highly-correlated covariates improves ML prescreening accuracy. The choice of ML method and the proportion of important covariates (unknown a priori) can be guided by simulations.

Machine learning-based preoperative analytics for the prediction of anastomotic leakage in colorectal surgery: a swiss pilot study

BACKGROUND

Anastomotic leakage (AL), a severe complication following colorectal surgery, arises from defects at the anastomosis site. This study evaluates the feasibility of predicting AL using machine learning (ML) algorithms based on preoperative data.

METHODS

We retrospectively analyzed data including 21 predictors from patients undergoing colorectal surgery with bowel anastomosis at four Swiss hospitals. Several ML algorithms were applied for binary classification into AL or non-AL groups, utilizing a five-fold cross-validation strategy with a 90% training and 10% validation split. Additionally, a holdout test set from an external hospital was employed to assess the models' robustness in external validation.

RESULTS

Among 1244 patients, 112 (9.0%) suffered from AL. The Random Forest model showed an AUC-ROC of 0.78 (SD: ± 0.01) on the internal test set, which significantly decreased to 0.60 (SD: ± 0.05) on the external holdout test set comprising 198 patients, including 7 (3.5%) with AL. Conversely, the Logistic Regression model demonstrated more consistent AUC-ROC values of 0.69 (SD: ± 0.01) on the internal set and 0.61 (SD: ± 0.05) on the external set. Accuracy measures for Random Forest were 0.82 (SD: ± 0.04) internally and 0.87 (SD: ± 0.08) externally, while Logistic Regression achieved accuracies of 0.81 (SD: ± 0.10) and 0.88 (SD: ± 0.15). F1 Scores for Random Forest moved from 0.58 (SD: ± 0.03) internally to 0.51 (SD: ± 0.03) externally, with Logistic Regression maintaining more stable scores of 0.53 (SD: ± 0.04) and 0.51 (SD: ± 0.02).

CONCLUSION

In this pilot study, we evaluated ML-based prediction models for AL post-colorectal surgery and identified ten patient-related risk factors associated with AL. Highlighting the need for multicenter data, external validation, and larger sample sizes, our findings emphasize the potential of ML in enhancing surgical outcomes and inform future development of a web-based application for broader clinical use.

A Stepwise Approach to Analyzing Musculoskeletal Imaging Data With Artificial Intelligence

The digitization of medical records and expanding electronic health records has created an era of "Big Data" with an abundance of available information ranging from clinical notes to imaging studies. In the field of rheumatology, medical imaging is used to guide both diagnosis and treatment of a wide variety of rheumatic conditions. Although there is an abundance of data to analyze, traditional methods of image analysis are human resource intensive. Fortunately, the growth of artificial intelligence (AI) may be a solution to handle large datasets. In particular, computer vision is a field within AI that analyzes images and extracts information. Computer vision has impressive capabilities and can be applied to rheumatologic conditions, necessitating a need to understand how computer vision works. In this article, we provide an overview of AI in rheumatology and conclude with a five step process to plan and conduct research in the field of computer vision. The five steps include (1) project definition, (2) data handling, (3) model development, (4) performance evaluation, and (5) deployment into clinical care.

An integrated molecular risk score early in life for subsequent childhood asthma risk

BACKGROUND

Numerous children present with early wheeze symptoms, yet solely a subgroup develops childhood asthma. Early identification of children at risk is key for clinical monitoring, timely patient-tailored treatment, and preventing chronic, severe sequelae. For early prediction of childhood asthma, we aimed to define an integrated risk score combining established risk factors with genome-wide molecular markers at birth, complemented by subsequent clinical symptoms/diagnoses (wheezing, atopic dermatitis, food allergy).

METHODS

Three longitudinal birth cohorts (PAULINA/PAULCHEN, n = 190 + 93 = 283, PASTURE, n = 1133) were used to predict childhood asthma (age 5-11) including epidemiological characteristics and molecular markers: genotype, DNA methylation and mRNA expression (RNASeq/NanoString). Apparent (ap) and optimism-corrected (oc) performance (AUC/R2) was assessed leveraging evidence from independent studies (Naïve-Bayes approach) combined with high-dimensional logistic regression models (LASSO).

RESULTS

Asthma prediction with epidemiological characteristics at birth (maternal asthma, sex, farm environment) yielded an ocAUC = 0.65. Inclusion of molecular markers as predictors resulted in an improvement in apparent prediction performance, however, for optimism-corrected performance only a moderate increase was observed (upto ocAUC = 0.68). The greatest discriminate power was reached by adding the first symptoms/diagnosis (up to ocAUC = 0.76; increase of 0.08, p = .002). Longitudinal analysis of selected mRNA expression in PASTURE (cord blood, 1, 4.5, 6 years) showed that expression at age six had the strongest association with asthma and correlation of genes getting larger over time (r = .59, p < .001, 4.5-6 years).

CONCLUSION

Applying epidemiological predictors alone showed moderate predictive abilities. Molecular markers from birth modestly improved prediction. Allergic symptoms/diagnoses enhanced the power of prediction, which is important for clinical practice and for the design of future studies with molecular markers.

Cell-free DNA assay for malignancy classification of high-risk lung nodules

OBJECTIVE

Although low-dose computed tomography has been proven effective to reduce lung cancer-specific mortality, a considerable proportion of surgically resected high-risk lung nodules were still confirmed pathologically benign. There is an unmet need of a novel method for malignancy classification in lung nodules.

METHODS

We recruited 307 patients with high-risk lung nodules who underwent curative surgery, and 247 and 60 cases were pathologically confirmed malignant and benign lung lesions, respectively. Plasma samples from each patient were collected before surgery and performed low-depth (5×) whole-genome sequencing. We extracted cell-free DNA characteristics and determined radiomic features. We built models to classify the malignancy using our data and further validated models with 2 independent lung nodule cohorts.

RESULTS

Our models using one type of profile were able to distinguish lung cancer and benign lung nodules at an area under the curve metrics of 0.69 to 0.91 in the study cohort. Integrating all the 5 base models using cell-free DNA profiles, the cell-free DNA-based ensemble model achieved an area under the curve of 0.95 (95% CI, 0.92-0.97) in the study cohort and 0.98 (95% CI, 0.96-1.00) in the validation cohort. At a specificity of 95.0%, the sensitivity reached 80.0% in the study cohort. With the same threshold, the specificity and sensitivity had similar performances in both validation cohorts. Furthermore, the performance of area under the curve reached 0.97 in both the study and validation cohorts when considering the radiomic profile.

CONCLUSIONS

The cell-free DNA profiles-based method is an efficient noninvasive tool to distinguish malignancies and high-risk but pathologically benign lung nodules.

Predicting non-muscle invasive bladder cancer outcomes using artificial intelligence: a systematic review using APPRAISE-AI

Accurate prediction of recurrence and progression in non-muscle invasive bladder cancer (NMIBC) is essential to inform management and eligibility for clinical trials. Despite substantial interest in developing artificial intelligence (AI) applications in NMIBC, their clinical readiness remains unclear. This systematic review aimed to critically appraise AI studies predicting NMIBC outcomes, and to identify common methodological and reporting pitfalls. MEDLINE, EMBASE, Web of Science, and Scopus were searched from inception to February 5th, 2024 for AI studies predicting NMIBC recurrence or progression. APPRAISE-AI was used to assess methodological and reporting quality of these studies. Performance between AI and non-AI approaches included within these studies were compared. A total of 15 studies (five on recurrence, four on progression, and six on both) were included. All studies were retrospective, with a median follow-up of 71 months (IQR 32-93) and median cohort size of 125 (IQR 93-309). Most studies were low quality, with only one classified as high quality. While AI models generally outperformed non-AI approaches with respect to accuracy, c-index, sensitivity, and specificity, this margin of benefit varied with study quality (median absolute performance difference was 10 for low, 22 for moderate, and 4 for high quality studies). Common pitfalls included dataset limitations, heterogeneous outcome definitions, methodological flaws, suboptimal model evaluation, and reproducibility issues. Recommendations to address these challenges are proposed. These findings emphasise the need for collaborative efforts between urological and AI communities paired with rigorous methodologies to develop higher quality models, enabling AI to reach its potential in enhancing NMIBC care.

Examining the role of artificial intelligence to advance knowledge and address barriers to research in eating disorders

OBJECTIVE

To provide a brief overview of artificial intelligence (AI) application within the field of eating disorders (EDs) and propose focused solutions for research.

METHOD

An overview and summary of AI application pertinent to EDs with focus on AI's ability to address issues relating to data sharing and pooling (and associated privacy concerns), data augmentation, as well as bias within datasets is provided.

RESULTS

In addition to clinical applications, AI can utilize useful tools to help combat commonly encountered challenges in ED research, including issues relating to low prevalence of specific subpopulations of patients, small overall sample sizes, and bias within datasets.

DISCUSSION

There is tremendous potential to embed and utilize various facets of artificial intelligence (AI) to help improve our understanding of EDs and further evaluate and investigate questions that ultimately seek to improve outcomes. Beyond the technology, issues relating to regulation of AI, establishing ethical guidelines for its application, and the trust of providers and patients are all needed for ultimate adoption and acceptance into ED practice.

PUBLIC SIGNIFICANCE

Artificial intelligence (AI) offers a promise of significant potential within the realm of eating disorders (EDs) and encompasses a broad set of techniques that offer utility in various facets of ED research and by extension delivery of clinical care. Beyond the technology, issues relating to regulation, establishing ethical guidelines for application, and the trust of providers and patients are needed for the ultimate adoption and acceptance of AI into ED practice.

Evaluation of Differential Diagnostics Potential of Uniform Data Set 2 Neuropsychology Battery Using Alzheimer's Disease Biomarkers

OBJECTIVE

This study aims to evaluate the efficacy of the Uniform Data Set (UDS) 2 battery in distinguishing between individuals with mild cognitive impairment (MCI) attributable to Alzheimer's disease (MCI-AD) and those with MCI due to other causes (MCI-nonAD), based on contemporary AT(N) biomarker criteria. Despite the implementation of the novel UDS 3 battery, the UDS 2 battery is still used in several non-English-speaking countries.

METHODS

We employed a cross-sectional design. A total of 113 Czech participants with MCI underwent a comprehensive diagnostic assessment, including cerebrospinal fluid biomarker evaluation, resulting in two groups: 45 individuals with prodromal AD (A+T+) and 68 participants with non-Alzheimer's pathological changes or normal AD biomarkers (A-). Multivariable logistic regression analyses were employed with neuropsychological test scores and demographic variables as predictors and AD status as an outcome. Model 1 included UDS 2 scores that differed between AD and non-AD groups (Logical Memory delayed recall), Model 2 employed also Letter Fluency and Rey's Auditory Verbal Learning Test (RAVLT). The two models were compared using area under the receiver operating characteristic curves. We also created separate logistic regression models for each of the UDS 2 scores.

RESULTS

Worse performance in delayed recall of Logical Memory significantly predicted the presence of positive AD biomarkers. In addition, the inclusion of Letter Fluency RAVLT into the model significantly enhanced its discriminative capacity.

CONCLUSION

Our findings demonstrate that using Letter Fluency and RAVLT alongside the UDS 2 battery can enhance its potential for differential diagnostics.

Microbiome-based classification models for fresh produce safety and quality evaluation

Small sample sizes and loss of sequencing reads during the microbiome data preprocessing can limit the statistical power of differentiating fresh produce phenotypes and prevent the detection of important bacterial species associated with produce contamination or quality reduction. Here, we explored a machine learning-based k-mer hash analysis strategy to identify DNA signatures predictive of produce safety (PS) and produce quality (PQ) and compared it against the amplicon sequence variant (ASV) strategy that uses a typical denoising step and ASV-based taxonomy strategy. Random forest-based classifiers for PS and PQ using 7-mer hash data sets had significantly higher classification accuracy than those using the ASV data sets. We also demonstrated that the proposed combination of integrating multiple data sets and leveraging a 7-mer hash strategy leads to better classification performance for PS and PQ compared to the ASV method but presents lower PS classification accuracy compared to the feature-selected ASV-based taxonomy strategy. Due to the current limitation of generating taxonomy using the 7-mer hash strategy, the ASV-based taxonomy strategy with remarkably less computing time and memory usage is more efficient for PS and PQ classification and applicable for important taxa identification. Results generated from this study lay the foundation for future studies that wish and need to incorporate and/or compare different microbiome sequencing data sets for the application of machine learning in the area of microbial safety and quality of food.

IMPORTANCE

Identification of generalizable indicators for produce safety (PS) and produce quality (PQ) improves the detection of produce contamination and quality decline. However, effective sequencing read loss during microbiome data preprocessing and the limited sample size of individual studies restrain statistical power to identify important features contributing to differentiating PS and PQ phenotypes. We applied machine learning-based models using individual and integrated k-mer hash and amplicon sequence variant (ASV) data sets for PS and PQ classification and evaluated their classification performance and found that random forest (RF)-based models using integrated 7-mer hash data sets achieved significantly higher PS and PQ classification accuracy. Due to the limitation of taxonomic analysis for the 7-mer hash, we also developed RF-based models using feature-selected ASV-based taxonomic data sets, which performed better PS classification than those using the integrated 7-mer hash data set. The RF feature selection method identified 480 PS indicators and 263 PQ indicators with a positive contribution to the PS and PQ classification.

Machine Learning-Based Clinical Prediction Models for Acute Ischemic Stroke Based on Serum Xanthine Oxidase Levels

OBJECTIVE

Early prediction of the onset, progression and prognosis of acute ischemic stroke (AIS) is helpful for treatment decision-making and proactive management. Although several biomarkers have been found to predict the progression and prognosis of AIS, these biomarkers have not been widely used in routine clinical practice. Xanthine oxidase (XO) is a form of xanthine oxidoreductase (XOR), which is widespread in various organs of the human body and plays an important role in redox reactions and ischemia‒reperfusion injury. Our previous studies have shown that serum XO levels on admission have certain clinical predictive value for AIS. The purpose of this study was to utilize serum XO levels and clinical data to establish machine learning models for predicting the onset, progression, and prognosis of AIS.

METHODS

We enrolled 328 consecutive patients with AIS and 107 healthy controls from October 2020 to September 2021. Serum XO levels and stroke-related clinical data were collected. We established 5 machine learning models-the logistic regression (LR), support vector machine (SVM), decision tree, random forest, and K-nearest neighbor (KNN) models-to predict the onset, progression, and prognosis of AIS. The area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, negative predictive value, and positive predictive value were used to evaluate the predictive performance of each model.

RESULTS

Among the 5 machine learning models predicting AIS onset, the AUROC values of 4 prediction models were over 0.7, while that of the KNN model was lower (AUROC = 0.6708, 95% CI 0.576-0.765). The LR model showed the best AUROC value (AUROC = 0.9586, 95% CI 0.927-0.991). Although the 5 machine learning models showed relatively poor predictive value for the progression of AIS (all AUROCs <0.7), the LR model still showed the highest AUROC value (AUROC = 0.6543, 95% CI 0.453-0.856). We compared the value of 5 machine learning models in predicting the prognosis of AIS, and the LR model showed the best predictive value (AUROC = 0.8124, 95% CI 0.715-0.910).

CONCLUSIONS

The tested machine learning models based on serum levels of XO could predict the onset and prognosis of AIS. Among the 5 machine learning models, we found that the LR model showed the best predictive performance. Machine learning algorithms improve accuracy in the early diagnosis of AIS and can be used to make treatment decisions.

Change in employment status and its causal effect on suicidal ideation and depressive symptoms: A marginal structural model with machine learning algorithms

OBJECTIVE

This study aimed to assess the causal effect of a change in employment status on suicidal ideation and depressive symptoms by applying marginal structural models (MSM) with machine-learning (ML) algorithms.

METHODS

We analyzed data from the 8-15th waves (2013-2020) of the Korean Welfare Panel Study, a nationally representative longitudinal dataset. Our analysis included 13 294 observations from 3621 participants who had standard employment at baseline (2013-2019). Based on employment status at follow-up year (2014-2020), respondents were classified into two groups: (i) maintained standard employment (reference group), (ii) changed to non-standard employment. Suicidal ideation during the past year and depressive symptoms during the past week were assessed through self-report questionnaire. To apply the ML algorithms to the MSM, we conducted eight ML algorithms to build the propensity score indicating a change in employment status. Then, we applied the MSM to examine the causal effect by using inverse probability weights calculated based on the propensity score from ML algorithms.

RESULTS

The random forest algorithm performed best among all algorithms, showing the highest area under the curve 0.702, 95% confidence interval (CI) 0.686-0.718. In the MSM with the random forest algorithm, workers who changed from standard to non-standard employment were 2.07 times more likely to report suicidal ideation compared to those who maintained standard employment (95% CI 1.16-3.70). A similar trend was observed in the analysis of depressive symptoms.

CONCLUSIONS

This study found that a change in employment status could lead to a higher risk of suicidal ideation and depressive symptoms.

An evaluation of the replicability of analyses using synthetic health data

Synthetic data generation is being increasingly used as a privacy preserving approach for sharing health data. In addition to protecting privacy, it is important to ensure that generated data has high utility. A common way to assess utility is the ability of synthetic data to replicate results from the real data. Replicability has been defined using two criteria: (a) replicate the results of the analyses on real data, and (b) ensure valid population inferences from the synthetic data. A simulation study using three heterogeneous real-world datasets evaluated the replicability of logistic regression workloads. Eight replicability metrics were evaluated: decision agreement, estimate agreement, standardized difference, confidence interval overlap, bias, confidence interval coverage, statistical power, and precision (empirical SE). The analysis of synthetic data used a multiple imputation approach whereby up to 20 datasets were generated and the fitted logistic regression models were combined using combining rules for fully synthetic datasets. The effects of synthetic data amplification were evaluated, and two types of generative models were used: sequential synthesis using boosted decision trees and a generative adversarial network (GAN). Privacy risk was evaluated using a membership disclosure metric. For sequential synthesis, adjusted model parameters after combining at least ten synthetic datasets gave high decision and estimate agreement, low standardized difference, as well as high confidence interval overlap, low bias, the confidence interval had nominal coverage, and power close to the nominal level. Amplification had only a marginal benefit. Confidence interval coverage from a single synthetic dataset without applying combining rules were erroneous, and statistical power, as expected, was artificially inflated when amplification was used. Sequential synthesis performed considerably better than the GAN across multiple datasets. Membership disclosure risk was low for all datasets and models. For replicable results, the statistical analysis of fully synthetic data should be based on at least ten generated datasets of the same size as the original whose analyses results are combined. Analysis results from synthetic data without applying combining rules can be misleading. Replicability results are dependent on the type of generative model used, with our study suggesting that sequential synthesis has good replicability characteristics for common health research workloads.

Questionable Effects of Electronic Cigarette Use on Cardiovascular Diseases From the National Health Interview Survey (NHIS, 2014-2021)

BACKGROUND

Electronic cigarettes (e-cigarettes) and cardiovascular health risks have gained attention among tobacco researchers. While the cardiovascular risks from e-cigarettes are still unclear, a recent paper by Alzahrani in Cureus claimed that current usage of e-cigarettes increases the risks of cardiovascular diseases, such as myocardial infarction and stroke, in subjects who were never cigarette smokers.

METHODS

The National Health Interview Survey (NHIS) data from 2014 to 2021 and logistic regression models were used to replicate and extend Alzahrani's analysis.

RESULTS

Only 12 never smokers who were current e-cigarette users had a myocardial infarction in all eight years. The crude odds ratio (OR) for e-cigarette use was 0.42 (95%CI: 0.24, 0.75). After adjusting for age and other confounding factors and health conditions, the OR of e-cigarette use increased to 2.48 (95%CI: 1.35, 4.55). The omission of age while adjusting for all other risk factors resulted in an OR of 0.80 (95%CI: 0.45, 1.43). In addition, the adjusted ORs for coronary heart disease and stroke were 1.12 (95%CI: 0.58, 2.17) and 1.13 (95%CI: 0.55, 2.29), respectively.

CONCLUSIONS

The findings indicate that Alzahrani's study is scientifically unreliable. The association between e-cigarette use and heart attack reported by Alzahrani was substantially driven by age, and the very small number of exposed cases makes the association very unstable. Given the nature of cross-sectional NHIS data, it is impossible to establish a robust association or causal claim that e-cigarette use "increases" the risks of any disease.

Socioexposomics of COVID-19 across New Jersey: a comparison of geostatistical and machine learning approaches

BACKGROUND

Disparities in adverse COVID-19 health outcomes have been associated with multiple social and environmental stressors. However, research is needed to evaluate the consistency and efficiency of methods for studying these associations at local scales.

OBJECTIVE

To assess socioexposomic associations with COVID-19 outcomes across New Jersey and evaluate consistency of findings from multiple modeling approaches.

METHODS

We retrieved data for COVID-19 cases and deaths for the 565 municipalities of New Jersey up to the end of the first phase of the pandemic, and calculated mortality rates with and without long-term-care (LTC) facility deaths. We considered 84 spatially heterogeneous environmental, demographic and socioeconomic factors from publicly available databases, including air pollution, proximity to industrial sites/facilities, transportation-related noise, occupation and commuting, neighborhood and housing characteristics, age structure, racial/ethnic composition, poverty, etc. Six geostatistical models (Poisson/Negative-Binomial regression, Poison/Negative-Binomial mixed effect model, Poisson/Negative-Binomial Bersag-York-Mollie spatial model) and two Machine Learning (ML) methods (Random Forest, Extreme Gradient Boosting) were implemented to assess association patterns. The Shapley effects plot was established for explainable ML and change of support validation was introduced to compare performances of different approaches.

RESULTS

We found robust positive associations of COVID-19 mortality with historic exposures to NO2, population density, percentage of minority and below high school education, and other social and environmental factors. Exclusion of LTC deaths does not significantly affect correlations for most factors but findings can be substantially influenced by model structures and assumptions. The best performing geostatistical models involved flexible structures representing data variations. ML methods captured association patterns consistent with the best performing geostatistical models, and furthermore detected consistent nonlinear associations not captured by geostatistical models.

SIGNIFICANCE

The findings of this work improve the understanding of how social and environmental disparities impacted COVID-19 outcomes across New Jersey.

Machine Learning Models for Predicting Sudden Sensorineural Hearing Loss Outcome: A Systematic Review

BACKGROUND

Machine Learning models have been applied in various healthcare fields, including Audiology, to predict disease outcomes. The prognosis of sudden sensorineural hearing loss is difficult to predict due to the variable course of the disease. Hence, researchers have attempted to utilize ML models to predict the outcome of patients with sudden sensorineural hearing loss. The objectives of this study were to review the performance of these machine learning models and assess their applicability in real-world settings.

METHODS

A systematic search was conducted in PubMed, Web of Science and Scopus. Only studies that built machine learning prediction models were included, and studies that used algorithms such as logistic regression only for the purpose of adjusting for confounding variables were excluded. The risk of bias was assessed using the Prediction model Risk of Bias Assessment Tool (PROBAST).

RESULTS

After screening, a total of 7 papers were eligible for synthesis. In total, these studies built 48 ML models. The most common utilized algorithms were Logistic Regression, Support Vector Machine (SVM) and boosting. The area under the curve of the receiver operating characteristic curve ranged between 0.59 and 0.915. All of the included studies had a high risk of bias; hence there are concerns regarding their applicability.

CONCLUSION

Although these models showed great performance and promising results, future studies are still needed before these models can be applied in a real-world setting. Future studies should employ multiple cohorts, different feature selection methods, and external validation to further validate the models' applicability.

Lung- and diaphragm-protective strategies in acute respiratory failure: an in silico trial

BACKGROUND

Lung- and diaphragm-protective (LDP) ventilation may prevent diaphragm atrophy and patient self-inflicted lung injury in acute respiratory failure, but feasibility is uncertain. The objectives of this study were to estimate the proportion of patients achieving LDP targets in different modes of ventilation, and to identify predictors of need for extracorporeal carbon dioxide removal (ECCO2R) to achieve LDP targets.

METHODS

An in silico clinical trial was conducted using a previously published mathematical model of patient-ventilator interaction in a simulated patient population (n = 5000) with clinically relevant physiological characteristics. Ventilation and sedation were titrated according to a pre-defined algorithm in pressure support ventilation (PSV) and proportional assist ventilation (PAV+) modes, with or without adjunctive ECCO2R, and using ECCO2R alone (without ventilation or sedation). Random forest modelling was employed to identify patient-level factors associated with achieving targets.

RESULTS

After titration, the proportion of patients achieving targets was lower in PAV+ vs. PSV (37% vs. 43%, odds ratio 0.78, 95% CI 0.73-0.85). Adjunctive ECCO2R substantially increased the probability of achieving targets in both PSV and PAV+ (85% vs. 84%). ECCO2R alone without ventilation or sedation achieved LDP targets in 9%. The main determinants of success without ECCO2R were lung compliance, ventilatory ratio, and strong ion difference. In silico trial results corresponded closely with the results obtained in a clinical trial of the LDP titration algorithm (n = 30).

CONCLUSIONS

In this in silico trial, many patients required ECCO2R in combination with mechanical ventilation and sedation to achieve LDP targets. ECCO2R increased the probability of achieving LDP targets in patients with intermediate degrees of derangement in elastance and ventilatory ratio.

Machine learning/artificial intelligence in sports medicine: state of the art and future directions

Machine learning (ML) is changing the way health care is practiced and recent applications of these novel statistical techniques have started to impact orthopaedic sports medicine. Machine learning enables the analysis of large volumes of data to establish complex relationships between "input" and "output" variables. These relationships may be more complex than could be established through traditional statistical analysis and can lead to the ability to predict the "output" with high levels of accuracy. Supervised learning is the most common ML approach for healthcare data and recent studies have developed algorithms to predict patient-specific outcome after surgical procedures such as hip arthroscopy and anterior cruciate ligament reconstruction. Deep learning is a higher-level ML approach that facilitates the processing and interpretation of complex datasets through artificial neural networks that are inspired by the way the human brain processes information. In orthopaedic sports medicine, deep learning has primarily been used for automatic image (computer vision) and text (natural language processing) interpretation. While applications in orthopaedic sports medicine have been increasing exponentially, one significant barrier to widespread adoption of ML remains clinician unfamiliarity with the associated methods and concepts. The goal of this review is to introduce these concepts, review current machine learning models in orthopaedic sport medicine, and discuss future opportunities for innovation within the specialty.

Multivariate word properties in fluency tasks reveal markers of Alzheimer's dementia

INTRODUCTION

Verbal fluency tasks are common in Alzheimer's disease (AD) assessments. Yet, standard valid response counts fail to reveal disease-specific semantic memory patterns. Here, we leveraged automated word-property analysis to capture neurocognitive markers of AD vis-à-vis behavioral variant frontotemporal dementia (bvFTD).

METHODS

Patients and healthy controls completed two fluency tasks. We counted valid responses and computed each word's frequency, granularity, neighborhood, length, familiarity, and imageability. These features were used for group-level discrimination, patient-level identification, and correlations with executive and neural (magnetic resonanance imaging [MRI], functional MRI [fMRI], electroencephalography [EEG]) patterns.

RESULTS

Valid responses revealed deficits in both disorders. Conversely, frequency, granularity, and neighborhood yielded robust group- and subject-level discrimination only in AD, also predicting executive outcomes. Disease-specific cortical thickness patterns were predicted by frequency in both disorders. Default-mode and salience network hypoconnectivity, and EEG beta hypoconnectivity, were predicted by frequency and granularity only in AD.

DISCUSSION

Word-property analysis of fluency can boost AD characterization and diagnosis.

HIGHLIGHTS

We report novel word-property analyses of verbal fluency in AD and bvFTD. Standard valid response counts captured deficits and brain patterns in both groups. Specific word properties (e.g., frequency, granularity) were altered only in AD. Such properties predicted cognitive and neural (MRI, fMRI, EEG) patterns in AD. Word-property analysis of fluency can boost AD characterization and diagnosis.

Comparing the performance of statistical, machine learning, and deep learning algorithms to predict time-to-event: A simulation study for conversion to mild cognitive impairment

Mild Cognitive Impairment (MCI) is a condition characterized by a decline in cognitive abilities, specifically in memory, language, and attention, that is beyond what is expected due to normal aging. Detection of MCI is crucial for providing appropriate interventions and slowing down the progression of dementia. There are several automated predictive algorithms for prediction using time-to-event data, but it is not clear which is best to predict the time to conversion to MCI. There is also confusion if algorithms with fewer training weights are less accurate. We compared three algorithms, from smaller to large numbers of training weights: a statistical predictive model (Cox proportional hazards model, CoxPH), a machine learning model (Random Survival Forest, RSF), and a deep learning model (DeepSurv). To compare the algorithms under different scenarios, we created a simulated dataset based on the Alzheimer NACC dataset. We found that the CoxPH model was among the best-performing models, in all simulated scenarios. In a larger sample size (n = 6,000), the deep learning algorithm (DeepSurv) exhibited comparable accuracy (73.1%) to the CoxPH model (73%). In the past, ignoring heterogeneity in the CoxPH model led to the conclusion that deep learning methods are superior. We found that when using the CoxPH model with heterogeneity, its accuracy is comparable to that of DeepSurv and RSF. Furthermore, when unobserved heterogeneity is present, such as missing features in the training, all three models showed a similar drop in accuracy. This simulation study suggests that in some applications an algorithm with a smaller number of training weights is not disadvantaged in terms of accuracy. Since algorithms with fewer weights are inherently easier to explain, this study can help artificial intelligence research develop a principled approach to comparing statistical, machine learning, and deep learning algorithms for time-to-event predictions.

Predicting Depression Risk in Patients With Cancer Using Multimodal Data: Algorithm Development Study

BACKGROUND

Patients with cancer starting systemic treatment programs, such as chemotherapy, often develop depression. A prediction model may assist physicians and health care workers in the early identification of these vulnerable patients.

OBJECTIVE

This study aimed to develop a prediction model for depression risk within the first month of cancer treatment.

METHODS

We included 16,159 patients diagnosed with cancer starting chemo- or radiotherapy treatment between 2008 and 2021. Machine learning models (eg, least absolute shrinkage and selection operator [LASSO] logistic regression) and natural language processing models (Bidirectional Encoder Representations from Transformers [BERT]) were used to develop multimodal prediction models using both electronic health record data and unstructured text (patient emails and clinician notes). Model performance was assessed in an independent test set (n=5387, 33%) using area under the receiver operating characteristic curve (AUROC), calibration curves, and decision curve analysis to assess initial clinical impact use.

RESULTS

Among 16,159 patients, 437 (2.7%) received a depression diagnosis within the first month of treatment. The LASSO logistic regression models based on the structured data (AUROC 0.74, 95% CI 0.71-0.78) and structured data with email classification scores (AUROC 0.74, 95% CI 0.71-0.78) had the best discriminative performance. The BERT models based on clinician notes and structured data with email classification scores had AUROCs around 0.71. The logistic regression model based on email classification scores alone performed poorly (AUROC 0.54, 95% CI 0.52-0.56), and the model based solely on clinician notes had the worst performance (AUROC 0.50, 95% CI 0.49-0.52). Calibration was good for the logistic regression models, whereas the BERT models produced overly extreme risk estimates even after recalibration. There was a small range of decision thresholds for which the best-performing model showed promising clinical effectiveness use. The risks were underestimated for female and Black patients.

CONCLUSIONS

The results demonstrated the potential and limitations of machine learning and multimodal models for predicting depression risk in patients with cancer. Future research is needed to further validate these models, refine the outcome label and predictors related to mental health, and address biases across subgroups.

Identifying the process and agency characteristics associated with poor utilization outcomes in home healthcare

This study identified the process and agency characteristics associated with poor utilization outcomes - higher percentages of patients (i) admitted to an acute care organization and (ii) visited an emergency room (ER) unplanned without hospitalization - for home health agencies (HHAs) in the United States. We conducted a secondary analysis of data about HHAs' various characteristics, process adherence levels, and utilization outcomes collected from disparate public repositories for 2010-2022. We developed descriptive tree-based models using HHAs' hospital admission or ER visit percentages as response variables. Across the board, hospital admission percentages have steadily improved while ER percentages deteriorated for an extended period. Recently, checking for fall risks and depression was associated with improved outcomes for urban agencies. In general, rural HHAs had worse utilization outcomes than urban HHAs. Targeted investments and improvement initiatives can help rural HHAs close the urban-rural gap in the future.

Logistic Regression Is Non-Inferior to the Response Surface Model in Patient Response Prediction of Video-Assisted Thoracoscopic Surgery

Response surface models (RSMs) are a new trend in modern anesthesia. RSMs have demonstrated significant applicability in the field of anesthesia. However, the comparative analysis between RSMs and logistic regression (LR) in different surgeries remains relatively limited in the current literature. We hypothesized that using a total intravenous anesthesia (TIVA) technique with the response surface model (RSM) and logistic regression (LR) would predict the emergence from anesthesia in patients undergoing video-assisted thoracotomy surgery (VATS). This study aimed to prove that LR, like the RSM, can be used to improve patient safety and achieve enhanced recovery after surgery (ERAS). This was a prospective, observational study with data reanalysis. Twenty-nine patients (American Society of Anesthesiologists (ASA) class II and III) who underwent VATS for elective pulmonary or mediastinal surgery under TIVA were enrolled. We monitored the emergence from anesthesia, and the precise time point of regained response (RR) was noted. The influence of varying concentrations was examined and incorporated into both the RSM and LR. The receiver operating characteristic (ROC) curve area for Greco and LR models was 0.979 (confidence interval: 0.987 to 0.990) and 0.989 (confidence interval: 0.989 to 0.990), respectively. The two models had no significant differences in predicting the probability of regaining response. In conclusion, the LR model was effective and can be applied to patients undergoing VATS or other procedures of similar modalities. Furthermore, the RSM is significantly more sophisticated and has an accuracy similar to that of the LR model; however, the LR model is more accessible. Therefore, the LR model is a simpler tool for predicting arousal in patients undergoing VATS under TIVA with Remifentanil and Propofol.

Supervised machine learning algorithms to predict the duration and risk of long-term hospitalization in HIV-infected individuals: a retrospective study

Objective

The study aimed to use supervised machine learning models to predict the length and risk of prolonged hospitalization in PLWHs to help physicians timely clinical intervention and avoid waste of health resources.

Methods

Regression models were established based on RF, KNN, SVM, and XGB to predict the length of hospital stay using RMSE, MAE, MAPE, and R2, while classification models were established based on RF, KNN, SVM, NN, and XGB to predict risk of prolonged hospital stay using accuracy, PPV, NPV, specificity, sensitivity, and kappa, and visualization evaluation based on AUROC, AUPRC, calibration curves and decision curves of all models were used for internally validation.

Results

In regression models, XGB model performed best in the internal validation (RMSE = 16.81, MAE = 10.39, MAPE = 0.98, R2 = 0.47) to predict the length of hospital stay, while in classification models, NN model presented good fitting and stable features and performed best in testing sets, with excellent accuracy (0.7623), PPV (0.7853), NPV (0.7092), sensitivity (0.8754), specificity (0.5882), and kappa (0.4672), and further visualization evaluation indicated that the largest AUROC (0.9779), AUPRC (0.773) and well-performed calibration curve and decision curve in the internal validation.

Conclusion

This study showed that XGB model was effective in predicting the length of hospital stay, while NN model was effective in predicting the risk of prolonged hospitalization in PLWH. Based on predictive models, an intelligent medical prediction system may be developed to effectively predict the length of stay and risk of HIV patients according to their medical records, which helped reduce the waste of healthcare resources.

Unskilled, underperforming, or unaware? Testing three accounts of individual differences in metacognitive monitoring

Many studies show that competence (e.g., skill, expertise, natural ability) influences individuals' capabilities of monitoring their item-level performance. However, debate persists about how best to explain these individual differences in metacognition. The competence-based account ascribes differences in monitoring to individuals' objective ability level, arguing that the same skills necessary to perform a task are required to effectively monitor performance. The performance-based account attributes differences in monitoring to changes in overall task performance - no individual differences in competence required. Finally, the metacognitive awareness account proposes that alignment between an individuals' self-assessed and objective ability leads to differences in monitoring. In this study, 603 participants completed a self-assessment of face recognition ability, a lineup identification task, and an objective assessment of face recognition ability. We manipulated the number of encoding repetitions and delay between encoding and test to produce varying levels of task performance across objective face recognition ability. Following each lineup decision, participants provided both a numeric confidence rating and a written expression of verbal confidence. We transformed verbal confidence into a quantitative value using machine learning techniques. When matched on overall identification accuracy, objectively stronger face recognizers used numeric and verbal confidence that a) better discriminates between correct and filler lineup identifications than weaker recognizers, and b) shows better calibration to accuracy. Participants with greater self-assessed ability used higher levels of confidence, irrespective of trial accuracy. These results support the competence-based account.

Prediction of Complications and Prognostication in Perioperative Medicine: A Systematic Review and PROBAST Assessment of Machine Learning Tools

BACKGROUND

The utilization of artificial intelligence and machine learning as diagnostic and predictive tools in perioperative medicine holds great promise. Indeed, many studies have been performed in recent years to explore the potential. The purpose of this systematic review is to assess the current state of machine learning in perioperative medicine, its utility in prediction of complications and prognostication, and limitations related to bias and validation.

METHODS

A multidisciplinary team of clinicians and engineers conducted a systematic review using the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) protocol. Multiple databases were searched, including Scopus, Cumulative Index to Nursing and Allied Health Literature (CINAHL), the Cochrane Library, PubMed, Medline, Embase, and Web of Science. The systematic review focused on study design, type of machine learning model used, validation techniques applied, and reported model performance on prediction of complications and prognostication. This review further classified outcomes and machine learning applications using an ad hoc classification system. The Prediction model Risk Of Bias Assessment Tool (PROBAST) was used to assess risk of bias and applicability of the studies.

RESULTS

A total of 103 studies were identified. The models reported in the literature were primarily based on single-center validations (75%), with only 13% being externally validated across multiple centers. Most of the mortality models demonstrated a limited ability to discriminate and classify effectively. The PROBAST assessment indicated a high risk of systematic errors in predicted outcomes and artificial intelligence or machine learning applications.

CONCLUSIONS

The findings indicate that the development of this field is still in its early stages. This systematic review indicates that application of machine learning in perioperative medicine is still at an early stage. While many studies suggest potential utility, several key challenges must be first overcome before their introduction into clinical practice.

EDITOR’S PERSPECTIVE

Prediction of Diabetes Using Data Mining and Machine Learning Algorithms: A Cross-Sectional Study

OBJECTIVES

This study aimed to develop a model to predict fasting blood glucose status using machine learning and data mining, since the early diagnosis and treatment of diabetes can improve outcomes and quality of life.

METHODS

This crosssectional study analyzed data from 3376 adults over 30 years old at 16 comprehensive health service centers in Tehran, Iran who participated in a diabetes screening program. The dataset was balanced using random sampling and the synthetic minority over-sampling technique (SMOTE). The dataset was split into training set (80%) and test set (20%). Shapley values were calculated to select the most important features. Noise analysis was performed by adding Gaussian noise to the numerical features to evaluate the robustness of feature importance. Five different machine learning algorithms, including CatBoost, random forest, XGBoost, logistic regression, and an artificial neural network, were used to model the dataset. Accuracy, sensitivity, specificity, accuracy, the F1-score, and the area under the curve were used to evaluate the model.

RESULTS

Age, waist-to-hip ratio, body mass index, and systolic blood pressure were the most important factors for predicting fasting blood glucose status. Though the models achieved similar predictive ability, the CatBoost model performed slightly better overall with 0.737 area under the curve (AUC).

CONCLUSIONS

A gradient boosted decision tree model accurately identified the most important risk factors related to diabetes. Age, waist-to-hip ratio, body mass index, and systolic blood pressure were the most important risk factors for diabetes, respectively. This model can support planning for diabetes management and prevention.

Machine learning-based monosaccharide profiling for tissue-specific classification of Wolfiporia extensa samples

Machine learning (ML) has been used for many clinical decision-making processes and diagnostic procedures in bioinformatics applications. We examined eight algorithms, including linear discriminant analysis (LDA), logistic regression (LR), k-nearest neighbor (KNN), random forest (RF), gradient boosting machine (GBM), support vector machine (SVM), Naïve Bayes classifier (NB), and artificial neural network (ANN) models, to evaluate their classification and prediction capabilities for four tissue types in Wolfiporia extensa using their monosaccharide composition profiles. All 8 ML-based models were assessed as exemplary models with AUC exceeding 0.8. Five models, namely LDA, KNN, RF, GBM, and ANN, performed excellently in the four-tissue-type classification (AUC > 0.9). Additionally, all eight models were evaluated as good predictive models with AUC value > 0.8 in the three-tissue-type classification. Notably, all 8 ML-based methods outperformed the single linear discriminant analysis (LDA) plotting method. For large sample sizes, the ML-based methods perform better than traditional regression techniques and could potentially increase the accuracy in identifying tissue samples of W. extensa.

Replicability and reproducibility of predictive models for diagnosis of depression among young adults using Electronic Health Records

BACKGROUND

Recent advances in machine learning combined with the growing availability of digitized health records offer new opportunities for improving early diagnosis of depression. An emerging body of research shows that Electronic Health Records can be used to accurately predict cases of depression on the basis of individual's primary care records. The successes of these studies are undeniable, but there is a growing concern that their results may not be replicable, which could cast doubt on their clinical usefulness.

METHODS

To address this issue in the present paper, we set out to reproduce and replicate the work by Nichols et al. (2018), who trained predictive models of depression among young adults using Electronic Healthcare Records. Our contribution consists of three parts. First, we attempt to replicate the methodology used by the original authors, acquiring a more up-to-date set of primary health care records to the same specification and reproducing their data processing and analysis. Second, we test models presented in the original paper on our own data, thus providing out-of-sample prediction of the predictive models. Third, we extend past work by considering several novel machine-learning approaches in an attempt to improve the predictive accuracy achieved in the original work.

RESULTS

In summary, our results demonstrate that the work of Nichols et al. is largely reproducible and replicable. This was the case both for the replication of the original model and the out-of-sample replication applying NRCBM coefficients to our new EHRs data. Although alternative predictive models did not improve model performance over standard logistic regression, our results indicate that stepwise variable selection is not stable even in the case of large data sets.

CONCLUSION

We discuss the challenges associated with the research on mental health and Electronic Health Records, including the need to produce interpretable and robust models. We demonstrated some potential issues associated with the reliance on EHRs, including changes in the regulations and guidelines (such as the QOF guidelines in the UK) and reliance on visits to GP as a predictor of specific disorders.

Multiclass risk models for ovarian malignancy: an illustration of prediction uncertainty due to the choice of algorithm

BACKGROUND

Assessing malignancy risk is important to choose appropriate management of ovarian tumors. We compared six algorithms to estimate the probabilities that an ovarian tumor is benign, borderline malignant, stage I primary invasive, stage II-IV primary invasive, or secondary metastatic.

METHODS

This retrospective cohort study used 5909 patients recruited from 1999 to 2012 for model development, and 3199 patients recruited from 2012 to 2015 for model validation. Patients were recruited at oncology referral or general centers and underwent an ultrasound examination and surgery ≤ 120 days later. We developed models using standard multinomial logistic regression (MLR), Ridge MLR, random forest (RF), XGBoost, neural networks (NN), and support vector machines (SVM). We used nine clinical and ultrasound predictors but developed models with or without CA125.

RESULTS

Most tumors were benign (3980 in development and 1688 in validation data), secondary metastatic tumors were least common (246 and 172). The c-statistic (AUROC) to discriminate benign from any type of malignant tumor ranged from 0.89 to 0.92 for models with CA125, from 0.89 to 0.91 for models without. The multiclass c-statistic ranged from 0.41 (SVM) to 0.55 (XGBoost) for models with CA125, and from 0.42 (SVM) to 0.51 (standard MLR) for models without. Multiclass calibration was best for RF and XGBoost. Estimated probabilities for a benign tumor in the same patient often differed by more than 0.2 (20% points) depending on the model. Net Benefit for diagnosing malignancy was similar for algorithms at the commonly used 10% risk threshold, but was slightly higher for RF at higher thresholds. Comparing models, between 3% (XGBoost vs. NN, with CA125) and 30% (NN vs. SVM, without CA125) of patients fell on opposite sides of the 10% threshold.

CONCLUSION

Although several models had similarly good performance, individual probability estimates varied substantially.

Performances of machine learning algorithms in discriminating sacroiliitis features on MRI: a systematic review

OBJECTIVES

Summarise the evidence of the performance of the machine learning algorithm in discriminating sacroiliitis features on MRI and compare it with the accuracy of human physicians.

METHODS

MEDLINE, EMBASE, CIHNAL, Web of Science, IEEE, American College of Rheumatology and European Alliance of Associations for Rheumatology abstract archives were searched for studies published between 2008 and 4 June 2023. Two authors independently screened and extracted the variables, and the results are presented using tables and forest plots.

RESULTS

Ten studies were selected from 2381. Over half of the studies used deep learning models, using Assessment of Spondyloarthritis International Society sacroiliitis criteria as the ground truth, and manually extracted the regions of interest. All studies reported the area under the curve as a performance index, ranging from 0.76 to 0.99. Sensitivity and specificity were the second-most commonly reported indices, with sensitivity ranging from 0.56 to 1.00 and specificity ranging from 0.67 to 1.00; these results are comparable to a radiologist's sensitivity of 0.67-1.00 and specificity of 0.78-1.00 in the same cohort. More than half of the studies showed a high risk of bias in the analysis domain of quality appraisal owing to the small sample size or overfitting issues.

CONCLUSION

The performance of machine learning algorithms in discriminating sacroiliitis features on MRI varied owing to the high heterogeneity between studies and the small sample sizes, overfitting, and under-reporting issues of individual studies. Further well-designed and transparent studies are required.

Prediction models in prehospital and emergency medicine research: How to derive and internally validate a clinical prediction model

Clinical prediction models are created to help clinicians with medical decision making, aid in risk stratification, and improve diagnosis and/or prognosis. With growing availability of both prehospital and in-hospital observational registries and electronic health records, there is an opportunity to develop, validate, and incorporate prediction models into clinical practice. However, many prediction models have high risk of bias due to poor methodology. Given that there are no methodological standards aimed at developing prediction models specifically in the prehospital setting, the objective of this paper is to describe the appropriate methodology for the derivation and validation of clinical prediction models in this setting. What follows can also be applied to the emergency medicine (EM) setting. There are eight steps that should be followed when developing and internally validating a prediction model: (1) problem definition, (2) coding of predictors, (3) addressing missing data, (4) ensuring adequate sample size, (5) variable selection, (6) evaluating model performance, (7) internal validation, and (8) model presentation. Subsequent steps include external validation, assessment of impact, and cost-effectiveness. By following these steps, researchers can develop a prediction model with the methodological rigor and quality required for prehospital and EM research.

Predicting survival of advanced laryngeal squamous cell carcinoma: comparison of machine learning models and Cox regression models

Laryngeal squamous cell carcinoma (LSCC) is a common tumor type. High recurrence rates remain an important factor affecting the survival and quality of life of advanced LSCC patients. We aimed to build a new nomogram and a random survival forest model using machine learning to predict the risk of LSCC progress. The study included 671 patients with AJCC stages III-IV LSCC. To develop a prognostic model, Cox regression analyses were used to assess the relationship between clinic-pathologic factors and disease-free survival (DFS). RSF analysis was also used to predict the DFS of LSCC patients. The ROC curve revealed that the Cox model exhibited good sensitivity and specificity in predicting DFS in the training and validation cohorts (1 year, validation AUC = 0.679, training AUC = 0.693; 3 years, validation AUC = 0.716, training AUC = 0.655; 5 years, validation AUC = 0.717, training AUC = 0.659). Random survival forest analysis showed that N stage, clinical stage, and postoperative chemoradiotherapy were prognostically significant variables associated with survival. The random forest model exhibited better prediction ability than the Cox regression model in the training cohort; however, the two models showed similar prediction ability in the validation cohort.

A scoping review of artificial intelligence-based methods for diabetes risk prediction

The increasing prevalence of type 2 diabetes mellitus (T2DM) and its associated health complications highlight the need to develop predictive models for early diagnosis and intervention. While many artificial intelligence (AI) models for T2DM risk prediction have emerged, a comprehensive review of their advancements and challenges is currently lacking. This scoping review maps out the existing literature on AI-based models for T2DM prediction, adhering to the PRISMA extension for Scoping Reviews guidelines. A systematic search of longitudinal studies was conducted across four databases, including PubMed, Scopus, IEEE-Xplore, and Google Scholar. Forty studies that met our inclusion criteria were reviewed. Classical machine learning (ML) models dominated these studies, with electronic health records (EHR) being the predominant data modality, followed by multi-omics, while medical imaging was the least utilized. Most studies employed unimodal AI models, with only ten adopting multimodal approaches. Both unimodal and multimodal models showed promising results, with the latter being superior. Almost all studies performed internal validation, but only five conducted external validation. Most studies utilized the area under the curve (AUC) for discrimination measures. Notably, only five studies provided insights into the calibration of their models. Half of the studies used interpretability methods to identify key risk predictors revealed by their models. Although a minority highlighted novel risk predictors, the majority reported commonly known ones. Our review provides valuable insights into the current state and limitations of AI-based models for T2DM prediction and highlights the challenges associated with their development and clinical integration.

Developing a machine learning algorithm to predict the probability of aseptic loosening of the glenoid component after anatomical total shoulder arthroplasty: protocol for a retrospective, multicentre study

INTRODUCTION

Despite technological advancements in recent years, glenoid component loosening remains a common complication after anatomical total shoulder arthroplasty (ATSA) and is one of the main causes of revision surgery. Increasing emphasis is placed on the prevention of glenoid component failure. Previous studies have successfully predicted range of motion, patient-reported outcomes and short-term complications after ATSA using machine learning methods, but an accurate predictive model for (glenoid component) revision is currently lacking. This study aims to use a large international database to accurately predict aseptic loosening of the glenoid component after ATSA using machine learning algorithms.

METHODS AND ANALYSIS

For this multicentre, retrospective study, individual patient data will be compiled from previously published studies reporting revision of ATSA. A systematic literature search will be performed in Medline (PubMed) identifying all studies reporting outcomes of ATSA. Authors will be contacted and invited to participate in the Machine Learning Consortium by sharing their anonymised databases. All databases reporting revisions after ATSA will be included, and individual patients with a follow-up less than 2 years or a fracture as the indication for ATSA will be excluded. First, features (predictive variables) will be identified using a random forest feature selection. The resulting features from the compiled database will be used to train various machine learning algorithms (stochastic gradient boosting, random forest, support vector machine, neural network and elastic-net penalised logistic regression). The developed and validated algorithms will be evaluated across discrimination (c-statistic), calibration, the Brier score and the decision curve analysis. The best-performing algorithm will be used to create an open-access online prediction tool.

ETHICS AND DISSEMINATION

Data will be collected adhering to the WHO regulation on data sharing. An Institutional Review Board review is not applicable. The study results will be published in a peer-reviewed journal.

Prognostic models for surgical-site infection in gastrointestinal surgery: systematic review

BACKGROUND

Identification of patients at high risk of surgical-site infection may allow clinicians to target interventions and monitoring to minimize associated morbidity. The aim of this systematic review was to identify and evaluate prognostic tools for the prediction of surgical-site infection in gastrointestinal surgery.

METHODS

This systematic review sought to identify original studies describing the development and validation of prognostic models for 30-day SSI after gastrointestinal surgery (PROSPERO: CRD42022311019). MEDLINE, Embase, Global Health, and IEEE Xplore were searched from 1 January 2000 to 24 February 2022. Studies were excluded if prognostic models included postoperative parameters or were procedure specific. A narrative synthesis was performed, with sample-size sufficiency, discriminative ability (area under the receiver operating characteristic curve), and prognostic accuracy compared.

RESULTS

Of 2249 records reviewed, 23 eligible prognostic models were identified. A total of 13 (57 per cent) reported no internal validation and only 4 (17 per cent) had undergone external validation. Most identified operative contamination (57 per cent, 13 of 23) and duration (52 per cent, 12 of 23) as important predictors; however, there remained substantial heterogeneity in other predictors identified (range 2-28). All models demonstrated a high risk of bias due to the analytic approach, with overall low applicability to an undifferentiated gastrointestinal surgical population. Model discrimination was reported in most studies (83 per cent, 19 of 23); however, calibration (22 per cent, 5 of 23) and prognostic accuracy (17 per cent, 4 of 23) were infrequently assessed. Of externally validated models (of which there were four), none displayed 'good' discrimination (area under the receiver operating characteristic curve greater than or equal to 0.7).

CONCLUSION

The risk of surgical-site infection after gastrointestinal surgery is insufficiently described by existing risk-prediction tools, which are not suitable for routine use. Novel risk-stratification tools are required to target perioperative interventions and mitigate modifiable risk factors.

A quantitative analysis framework of placenta accreta spectrum: placenta subtype, intraoperative bleeding, and hysterectomy risk evaluation based on magnetic resonance imaging-anatomical-clinical features

Background

Placenta accreta spectrum (PAS) is a significant contributor to maternal morbidity and mortality. Our objective was to develop a quantitative analysis framework utilizing magnetic resonance imaging (MRI)-anatomical-clinical features to predict 3 clinically significant parameters in patients with PAS: placenta subtype (invasive vs. non-invasive placenta), intraoperative bleeding (≥1,500 vs. <1,500 mL), and hysterectomy risk (hysterectomy vs. non-hysterectomy).

Methods

A total of 125 pregnant women with PAS from 2 medical centers were enrolled into an internal training set and an external testing set. Some 21 MRI-anatomical-clinical features were integrated as input into the framework. The proposed quantitative analytic framework contains mainly 3 classifiers built by extreme gradient boosting (XGBoost) and their testing in external datasets. We also further compared the accuracy of placenta subtype prediction between the proposed model and 4 radiologists. A quantitative model interpretation method called SHapley Additive exPlanations (SHAP) was conducted to explore the contribution of each feature.

Results

The placenta subtype (invasive vs. non-invasive), intraoperative bleeding (≥1,500 vs. <1,500 mL), and hysterectomy risk (hysterectomy vs. non-hysterectomy) demonstrated impressive area under the receiver operating characteristic curve (AUROC) values of 0.93, 0.88, and 0.90, respectively, in the internal validation set. Even in the external testing set, these metrics maintained their strength, achieving AUROC values of 0.91, 0.82, and 0.82, respectively. Comparing our proposed framework to the 4 radiologists, our model exhibited superior accuracy, specificity, and sensitivity in predicting placental subtypes within the external testing cohort. The features associated with intraplacental dark T2 bands played a crucial role in the decision-making process of all 3 prediction models.

Conclusions

The quantitative analysis framework can provide a robust method for classification of placenta subtype (invasive vs. non-invasive placenta), intraoperative bleeding (≥1,500 vs. <1,500 mL), and hysterectomy risk (hysterectomy vs. non-hysterectomy) based on MRI-anatomical-clinical features in PAS.

Predicting lung cancer survival based on clinical data using machine learning: A review

Machine learning has gained popularity in predicting survival time in the medical field. This review examines studies utilizing machine learning and data-mining techniques to predict lung cancer survival using clinical data. A systematic literature review searched MEDLINE, Scopus, and Google Scholar databases, following reporting guidelines and using the COVIDENCE system. Studies published from 2000 to 2023 employing machine learning for lung cancer survival prediction were included. Risk of bias assessment used the prediction model risk of bias assessment tool. Thirty studies were reviewed, with 13 (43.3%) using the surveillance, epidemiology, and end results database. Missing data handling was addressed in 12 (40%) studies, primarily through data transformation and conversion. Feature selection algorithms were used in 19 (63.3%) studies, with age, sex, and N stage being the most chosen features. Random forest was the predominant machine learning model, used in 17 (56.6%) studies. While the number of lung cancer survival prediction studies is limited, the use of machine learning models based on clinical data has grown since 2012. Consideration of diverse patient cohorts and data pre-processing are crucial. Notably, most studies did not account for missing data, normalization, scaling, or standardized data, potentially introducing bias. Therefore, a comprehensive study on lung cancer survival prediction using clinical data is needed, addressing these challenges.

AOA Critical Issues Symposium: Shaping the Impact of Artificial Intelligence within Orthopaedic Surgery

ABSTRACT

Artificial intelligence (AI) is a broad term that is widely used but inconsistently understood. It refers to the ability of any machine to exhibit human-like intelligence by making decisions, solving problems, or learning from experience. With its ability to rapidly process large amounts of information, AI has already transformed many industries such as entertainment, transportation, and communications through consumer-facing products and business-to-business applications. Given its potential, AI is also anticipated to impact the practice of medicine and the delivery of health care. Interest in AI-based techniques has grown rapidly within the orthopaedic community, resulting in an increasing number of publications on this topic. Topics of interest have ranged from the use of AI for imaging interpretation to AI-based techniques for predicting postoperative outcomes.The highly technical and data-driven nature of orthopaedic surgery creates the potential for AI, and its subdisciplines machine learning (ML) and deep learning (DL), to fundamentally transform our understanding of musculoskeletal care. However, AI-based techniques are not well known to most orthopaedic surgeons, nor are they taught with the same level of insight and critical thinking as traditional statistical methodology. With a clear understanding of the science behind AI-based techniques, orthopaedic surgeons will be able to identify the potential pitfalls of the application of AI to musculoskeletal health. Additionally, with increased understanding of AI, surgeons and their patients may have more trust in the results of AI-based analytics, thereby expanding the potential use of AI in clinical care and amplifying the impact it could have in improving quality and value. The purpose of this American Orthopaedic Association (AOA) symposium was to facilitate understanding and development of AI and AI-based techniques within orthopaedic surgery by defining common terminology related to AI, demonstrating the existing clinical utility of AI, and presenting future applications of AI in surgical care.

Prognostic models for predicting clinical disease progression, worsening and activity in people with multiple sclerosis

BACKGROUND

Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system that affects millions of people worldwide. The disease course varies greatly across individuals and many disease-modifying treatments with different safety and efficacy profiles have been developed recently. Prognostic models evaluated and shown to be valid in different settings have the potential to support people with MS and their physicians during the decision-making process for treatment or disease/life management, allow stratified and more precise interpretation of interventional trials, and provide insights into disease mechanisms. Many researchers have turned to prognostic models to help predict clinical outcomes in people with MS; however, to our knowledge, no widely accepted prognostic model for MS is being used in clinical practice yet.

OBJECTIVES

To identify and summarise multivariable prognostic models, and their validation studies for quantifying the risk of clinical disease progression, worsening, and activity in adults with MS.

SEARCH METHODS

We searched MEDLINE, Embase, and the Cochrane Database of Systematic Reviews from January 1996 until July 2021. We also screened the reference lists of included studies and relevant reviews, and references citing the included studies.

SELECTION CRITERIA

We included all statistically developed multivariable prognostic models aiming to predict clinical disease progression, worsening, and activity, as measured by disability, relapse, conversion to definite MS, conversion to progressive MS, or a composite of these in adult individuals with MS. We also included any studies evaluating the performance of (i.e. validating) these models. There were no restrictions based on language, data source, timing of prognostication, or timing of outcome.

DATA COLLECTION AND ANALYSIS

Pairs of review authors independently screened titles/abstracts and full texts, extracted data using a piloted form based on the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS), assessed risk of bias using the Prediction Model Risk Of Bias Assessment Tool (PROBAST), and assessed reporting deficiencies based on the checklist items in Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD). The characteristics of the included models and their validations are described narratively. We planned to meta-analyse the discrimination and calibration of models with at least three external validations outside the model development study but no model met this criterion. We summarised between-study heterogeneity narratively but again could not perform the planned meta-regression.

MAIN RESULTS

We included 57 studies, from which we identified 75 model developments, 15 external validations corresponding to only 12 (16%) of the models, and six author-reported validations. Only two models were externally validated multiple times. None of the identified external validations were performed by researchers independent of those that developed the model. The outcome was related to disease progression in 39 (41%), relapses in 8 (8%), conversion to definite MS in 17 (18%), and conversion to progressive MS in 27 (28%) of the 96 models or validations. The disease and treatment-related characteristics of included participants, and definitions of considered predictors and outcome, were highly heterogeneous amongst the studies. Based on the publication year, we observed an increase in the percent of participants on treatment, diversification of the diagnostic criteria used, an increase in consideration of biomarkers or treatment as predictors, and increased use of machine learning methods over time. Usability and reproducibility All identified models contained at least one predictor requiring the skills of a medical specialist for measurement or assessment. Most of the models (44; 59%) contained predictors that require specialist equipment likely to be absent from primary care or standard hospital settings. Over half (52%) of the developed models were not accompanied by model coefficients, tools, or instructions, which hinders their application, independent validation or reproduction. The data used in model developments were made publicly available or reported to be available on request only in a few studies (two and six, respectively). Risk of bias We rated all but one of the model developments or validations as having high overall risk of bias. The main reason for this was the statistical methods used for the development or evaluation of prognostic models; we rated all but two of the included model developments or validations as having high risk of bias in the analysis domain. None of the model developments that were externally validated or these models' external validations had low risk of bias. There were concerns related to applicability of the models to our research question in over one-third (38%) of the models or their validations. Reporting deficiencies Reporting was poor overall and there was no observable increase in the quality of reporting over time. The items that were unclearly reported or not reported at all for most of the included models or validations were related to sample size justification, blinding of outcome assessors, details of the full model or how to obtain predictions from it, amount of missing data, and treatments received by the participants. Reporting of preferred model performance measures of discrimination and calibration was suboptimal.

AUTHORS' CONCLUSIONS

The current evidence is not sufficient for recommending the use of any of the published prognostic prediction models for people with MS in clinical routine today due to lack of independent external validations. The MS prognostic research community should adhere to the current reporting and methodological guidelines and conduct many more state-of-the-art external validation studies for the existing or newly developed models.

Combinatorial Use of Machine Learning and Logistic Regression for Predicting Carotid Plaque Risk Among 5.4 Million Adults With Fatty Liver Disease Receiving Health Check-Ups: Population-Based Cross-Sectional Study

BACKGROUND

Carotid plaque can progress into stroke, myocardial infarction, etc, which are major global causes of death. Evidence shows a significant increase in carotid plaque incidence among patients with fatty liver disease. However, unlike the high detection rate of fatty liver disease, screening for carotid plaque in the asymptomatic population is not yet prevalent due to cost-effectiveness reasons, resulting in a large number of patients with undetected carotid plaques, especially among those with fatty liver disease.

OBJECTIVE

This study aimed to combine the advantages of machine learning (ML) and logistic regression to develop a straightforward prediction model among the population with fatty liver disease to identify individuals at risk of carotid plaque.

METHODS

Our study included 5,420,640 participants with fatty liver from Meinian Health Care Center. We used random forest, elastic net (EN), and extreme gradient boosting ML algorithms to select important features from potential predictors. Features acknowledged by all 3 models were enrolled in logistic regression analysis to develop a carotid plaque prediction model. Model performance was evaluated based on the area under the receiver operating characteristic curve, calibration curve, Brier score, and decision curve analysis both in a randomly split internal validation data set, and an external validation data set comprising 32,682 participants from MJ Health Check-up Center. Risk cutoff points for carotid plaque were determined based on the Youden index, predicted probability distribution, and prevalence rate of the internal validation data set to classify participants into high-, intermediate-, and low-risk groups. This risk classification was further validated in the external validation data set.

RESULTS

Among the participants, 26.23% (1,421,970/5,420,640) were diagnosed with carotid plaque in the development data set, and 21.64% (7074/32,682) were diagnosed in the external validation data set. A total of 6 features, including age, systolic blood pressure, low-density lipoprotein cholesterol (LDL-C), total cholesterol, fasting blood glucose, and hepatic steatosis index (HSI) were collectively selected by all 3 ML models out of 27 predictors. After eliminating the issue of collinearity between features, the logistic regression model established with the 5 independent predictors reached an area under the curve of 0.831 in the internal validation data set and 0.801 in the external validation data set, and showed good calibration capability graphically. Its predictive performance was comprehensively competitive compared with the single use of either logistic regression or ML algorithms. Optimal predicted probability cutoff points of 25% and 65% were determined for classifying individuals into low-, intermediate-, and high-risk categories for carotid plaque.

CONCLUSIONS

The combination of ML and logistic regression yielded a practical carotid plaque prediction model, and was of great public health implications in the early identification and risk assessment of carotid plaque among individuals with fatty liver.

APPRAISE-AI Tool for Quantitative Evaluation of AI Studies for Clinical Decision Support

Importance

Artificial intelligence (AI) has gained considerable attention in health care, yet concerns have been raised around appropriate methods and fairness. Current AI reporting guidelines do not provide a means of quantifying overall quality of AI research, limiting their ability to compare models addressing the same clinical question.

Objective

To develop a tool (APPRAISE-AI) to evaluate the methodological and reporting quality of AI prediction models for clinical decision support.

Design, Setting, and Participants

This quality improvement study evaluated AI studies in the model development, silent, and clinical trial phases using the APPRAISE-AI tool, a quantitative method for evaluating quality of AI studies across 6 domains: clinical relevance, data quality, methodological conduct, robustness of results, reporting quality, and reproducibility. These domains included 24 items with a maximum overall score of 100 points. Points were assigned to each item, with higher points indicating stronger methodological or reporting quality. The tool was applied to a systematic review on machine learning to estimate sepsis that included articles published until September 13, 2019. Data analysis was performed from September to December 2022.

Main Outcomes and Measures

The primary outcomes were interrater and intrarater reliability and the correlation between APPRAISE-AI scores and expert scores, 3-year citation rate, number of Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) low risk-of-bias domains, and overall adherence to the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) statement.

Results

A total of 28 studies were included. Overall APPRAISE-AI scores ranged from 33 (low quality) to 67 (high quality). Most studies were moderate quality. The 5 lowest scoring items included source of data, sample size calculation, bias assessment, error analysis, and transparency. Overall APPRAISE-AI scores were associated with expert scores (Spearman ρ, 0.82; 95% CI, 0.64-0.91; P < .001), 3-year citation rate (Spearman ρ, 0.69; 95% CI, 0.43-0.85; P < .001), number of QUADAS-2 low risk-of-bias domains (Spearman ρ, 0.56; 95% CI, 0.24-0.77; P = .002), and adherence to the TRIPOD statement (Spearman ρ, 0.87; 95% CI, 0.73-0.94; P < .001). Intraclass correlation coefficient ranges for interrater and intrarater reliability were 0.74 to 1.00 for individual items, 0.81 to 0.99 for individual domains, and 0.91 to 0.98 for overall scores.

Conclusions and Relevance

In this quality improvement study, APPRAISE-AI demonstrated strong interrater and intrarater reliability and correlated well with several study quality measures. This tool may provide a quantitative approach for investigators, reviewers, editors, and funding organizations to compare the research quality across AI studies for clinical decision support.

Effectiveness and Safety of Palbociclib Plus Endocrine Therapy in Patients with Advanced Breast Cancer: A Multi-Center Study in China

BACKGROUND

Palbociclib has been approved for marketing in China. However, its effectiveness, safety, and latent variables in the Chinese population require further investigation.

METHODS

Information was retrieved from 397 patients with metastatic breast cancer (mBC) who received at least two cycles of palbociclib plus endocrine therapy (PAL plus ET) at eight clinical sites in China. The patients' demographic characteristics, treatment patterns, and adverse events (AEs) were analyzed.

RESULTS

The objective response rate (ORR) and clinical benefit rate (CBR) for PAL plus ET were 28.97% and 66.25%, respectively. The median PFS was 14.2 months in the whole population. In addition to protein Ki-67 status and sensitivity to ETs, no liver metastases, fewer metastatic sites, an earlier line of therapy, and treatment combined with AI instead of FUL were also considered as independent prognostic factors for PAL treatment. Administration of PAL was generally well tolerated in patients with hormone-receptor-positive and human-epidermal-growth-factor-receptor-2-negative (HR+/HER2-) advanced breast cancer (ABC). The therapy was safe in the elderly population, which is consistent with the outcomes of the whole population and previous reports.

CONCLUSIONS

In this most widely distributed study in China to date, palbociclib combined with ET proved its effectiveness for HR+/HER2- ABC treatment, and adverse events were manageable. Here, we identified some independent prognosis factors, but the mechanism by which these factors influence effectiveness requires further verification.

Hepatic Involvement across the Metabolic Syndrome Spectrum: Non-Invasive Assessment and Risk Prediction Using Machine Learning

Metabolic-dysfunction-associated steatotic liver disease (MASLD) and metabolic syndrome (MetS) are inextricably linked conditions, both of which are experiencing an upward trend in prevalence, thereby exerting a substantial clinical and economic burden. The presence of MetS should prompt the search for metabolic-associated liver disease. Liver fibrosis is the main predictor of liver-related morbidity and mortality. Non-invasive tests (NIT) such as the Fibrosis-4 index (FIB4), aspartate aminotransferase-to-platelet ratio index (APRI), aspartate aminotransferase-to-alanine aminotransferase ratio (AAR), hepatic steatosis index (HIS), transient elastography (TE), and combined scores (AGILE3+, AGILE4) facilitate the detection of liver fibrosis or steatosis. Our study enrolled 217 patients with suspected MASLD, 109 of whom were diagnosed with MetS. We implemented clinical and biological evaluations complemented by transient elastography (TE) to discern the most robust predictors for liver disease manifestation patterns. Patients with MetS had significantly higher values of FIB4, APRI, HSI, liver stiffness, and steatosis parameters measured by TE, as well as AGILE3+ and AGILE4 scores. Machine-learning algorithms enhanced our evaluation. A two-step cluster algorithm yielded three clusters with reliable model quality. Cluster 1 contained patients without significant fibrosis or steatosis, while clusters 2 and 3 showed a higher prevalence of significant liver fibrosis or at least moderate steatosis as measured by TE. A decision tree algorithm identified age, BMI, liver enzyme levels, and metabolic syndrome characteristics as significant factors in predicting cluster membership with an overall accuracy of 89.4%. Combining NITs improves the accuracy of detecting patterns of liver involvement in patients with suspected MASLD.

Geometric morphometrics and machine learning from three-dimensional facial scans for difficult mask ventilation prediction

Background

Unanticipated difficult mask ventilation (DMV) is a potentially life-threatening event in anesthesia. Nevertheless, predicting DMV currently remains a challenge. This study aimed to verify whether three dimensional (3D) facial scans could predict DMV in patients scheduled for general anesthesia.

Methods

The 3D facial scans were taken on 669 adult patients scheduled for elective surgery under general anesthesia. Clinical variables currently used as predictors of DMV were also collected. The DMV was defined as the inability to provide adequate and stable ventilation. Spatially dense landmarks were digitized on 3D scans to describe sufficient details for facial features and then processed by 3D geometric morphometrics. Ten different machine learning (ML) algorithms, varying from simple to more advanced, were introduced. The performance of ML models for DMV prediction was compared with that of the DIFFMASK score. The area under the receiver operating characteristic curves (AUC) with its 95% confidence interval (95% CI) as well as the specificity and sensitivity were used to evaluate the predictive value of the model.

Results

The incidence of DMV was 35/669 (5.23%). The logistic regression (LR) model performed best among the 10 ML models. The AUC of the LR model was 0.825 (95% CI, 0.765-0.885). The sensitivity and specificity of the model were 0.829 (95% CI, 0.629-0.914) and 0.733 (95% CI, 0.532-0.819), respectively. The LR model demonstrated better predictive performance than the DIFFMASK score, which obtained an AUC of 0.785 (95% CI, 0.710-0.860) and a sensitivity of 0.686 (95% CI, 0.578-0.847). Notably, we identified a significant morphological difference in the mandibular region between the DMV group and the easy mask ventilation group.

Conclusion

Our study indicated a distinct morphological difference in the mandibular region between the DMV group and the easy mask ventilation group. 3D geometric morphometrics with ML could be a rapid, efficient, and non-invasive tool for DMV prediction to improve anesthesia safety.

Cognitive function and cardiovascular health in the elderly: network analysis based on hypertension, diabetes, cerebrovascular disease, and coronary heart disease

Introduction

Cognitive decline in the elderly population is a growing concern, and vascular factors, such as hypertension, diabetes, cerebrovascular disease, and coronary heart disease, have been associated with cognitive impairments. This study aims to provide deeper insights into the structure of cognitive function networks under these different vascular factors and explore their potential associations with specific cognitive domains.

Methods

Cognitive function was assessed using a modified Chinese version of the mini-mental state examination (MMSE) scale, and intensity centrality and side weights were estimated by network modeling. The network structure of cognitive function was compared across subgroups by including vascular factors as subgroup variables while controlling for comorbidities and confounders.

Results

The results revealed that cerebrovascular disease and coronary heart disease had a more significant impact on cognitive function. Cerebrovascular disease was associated with weaker centrality in memory and spatial orientation, and a sparser cognitive network structure. Coronary heart disease was associated with weaker centrality in memory, repetition, executive function, recall, attention, and calculation, as well as a sparser cognitive network structure. The NCT analyses further highlighted significant differences between the cerebrovascular disease and coronary heart disease groups compared to controls in terms of overall network structure and connection strength.

Conclusion

Our findings suggest that specific cognitive domains may be more vulnerable to impairments in patients with cerebrovascular disease and coronary heart disease. These insights could be used to improve the accuracy and sensitivity of cognitive screening in these patient populations, inform personalized cognitive intervention strategies, and provide a better understanding of the potential mechanisms underlying cognitive decline in patients with vascular diseases.

Stratified care in hip arthroscopy: can we predict successful and unsuccessful outcomes? Development and external temporal validation of multivariable prediction models

OBJECTIVE

Although hip arthroscopy is a widely adopted treatment option for hip-related pain, it is unknown whether preoperative clinical information can be used to assist surgical decision-making to avoid offering surgery to patients with limited potential for a successful outcome. We aimed to develop and validate clinical prediction models to identify patients more likely to have an unsuccessful or successful outcome 1 year post hip arthroscopy based on the patient acceptable symptom state.

METHODS

Patient records were extracted from the Danish Hip Arthroscopy Registry (DHAR). A priori, 26 common clinical variables from DHAR were selected as prognostic factors, including demographics, radiographic parameters of hip morphology and self-reported measures. We used 1082 hip arthroscopy patients (surgery performed 25 April 2012 to 4 October 2017) to develop the clinical prediction models based on logistic regression analyses. The development models were internally validated using bootstrapping and shrinkage before temporal external validation was performed using 464 hip arthroscopy patients (surgery performed 5 October 2017 to 13 May 2019).

RESULTS

The prediction model for unsuccessful outcomes showed best and acceptable predictive performance on the external validation dataset for all multiple imputations (Nagelkerke R2 range: 0.25-0.26) and calibration (intercept range: -0.10 to -0.11; slope range: 1.06-1.09), and acceptable discrimination (area under the curve range: 0.76-0.77). The prediction model for successful outcomes did not calibrate well, while also showing poor discrimination.

CONCLUSION

Common clinical variables including demographics, radiographic parameters of hip morphology and self-reported measures were able to predict the probability of having an unsuccessful outcome 1 year after hip arthroscopy, while the model for successful outcome showed unacceptable accuracy. The externally validated prediction model can be used to support clinical evaluation and shared decision making by informing the orthopaedic surgeon and patient about the risk of an unsuccessful outcome, and thus when surgery may not be appropriate.