A Comparison of LASSO Regression and Tree-Based Models for Delayed Cerebral Ischemia in Elderly Patients With Subarachnoid Hemorrhage

Development and Validation of Machine Learning Models for Outcome Prediction in Patients with Poor-Grade Aneurysmal Subarachnoid Hemorrhage Following Endovascular Treatment

Background

Endovascular treatment (EVT) has been recommended as a superior modality for the treatment of intracranial aneurysm. However, there still exists a worse percentage of poor functional outcome in patients with poor-grade aneurysmal subarachnoid hemorrhage (aSAH) undergoing EVT. Therefore, it is urgently needed to investigate the risk factors and develop a critical decision model in the subtype of such patients.

Methods

We extracted the target variables from an ongoing registry cohort study, PROSAH-MPC, which was conducted in multiple centers in China. We randomly assigned these patients to training and validation cohorts with a ratio of 7:3. Univariate and multivariate logistic regressions were performed to find the potential factors, and then nine machine learning models and a stack ensemble model were developed with optimized variables. The performance of these models was evaluated through several indicators, including area under the receiver operating characteristic curve (AUC-ROC). We further use Shapley Additive Explanations (SHAP) methods for the distribution of feature visualization based on the optimal models.

Results

A total of 226 eligible patients with poor-grade aSAH undergoing EVT were enrolled, while 89 (39.4%) has a poor 12-month outcome. Age (Adjusted OR [aOR], 1.08; 95% CI: 1.03-1.13; p = 0.002), subarachnoid hemorrhage volume (aOR, 1.02; 95% CI: 1.00-1.05; p = 0.033), World Federation of Neurosurgical Societies grade (WFNS) (aOR, 2.03; 95% CI: 1.05-3.93; p = 0.035), and Hunt-Hess grade (aOR, 2.36; 95% CI: 1.13-4.93; p = 0.022) were identified as the independent risk factors of the poor outcome. Then, the prediction models developed have revealed that LightGBM algorithm has a superior performance with an AUC-ROC value of 0.842 in the validation cohort, while the SHAP results showed that age is the most important risk factor affecting functional outcomes.

Conclusion

The LightGBM model holds immense potential in facilitating risk stratification for poor-grade aSAH patients undergoing endovascular treatment who are at risk of adverse outcomes, thereby enhancing clinical decision-making processes.

Trial Registration

PROSAH-MPC. NCT05738083. Registered 16 November 2022 - Retrospectively registered, https://clinicaltrials.gov/study/NCT05738083.

Predicting Mortality in Subarachnoid Hemorrhage Patients Using Big Data and Machine Learning: A Nationwide Study in Türkiye

Background/Objective: Subarachnoid hemorrhage (SAH) is associated with high morbidity and mortality rates, necessitating prognostic algorithms to guide decisions. Our study evaluates the use of machine learning (ML) models for predicting 1-month and 1-year mortality among SAH patients using national electronic health records (EHR) system. Methods: Retrospective cohort of 29,274 SAH patients, identified through national EHR system from January 2017 to December 2022, was analyzed, with mortality data obtained from central civil registration system in Türkiye. Variables included (n = 102) pre- (n = 65) and post-admission (n = 37) data, such as patient demographics, clinical presentation, comorbidities, laboratory results, and complications. We employed logistic regression (LR), decision trees (DTs), random forests (RFs), and artificial neural networks (ANN). Model performance was evaluated using area under the curve (AUC), average precision, and accuracy. Feature significance analysis was conducted using LR. Results: The average age was 56.23 ± 16.45 years (47.8% female). The overall mortality rate was 22.8% at 1 month and 33.3% at 1 year. One-month mortality increased from 20.9% to 24.57% (p < 0.001), and 1-year mortality rose from 30.85% to 35.55% (p < 0.001) in the post-COVID period compared to the pre-COVID period. For 1-month mortality prediction, the ANN, LR, RF, and DT models achieved AUCs of 0.946, 0.942, 0.931, and 0.916, with accuracies of 0.905, 0.901, 0.893, and 0.885, respectively. For 1-year mortality, the AUCs were 0.941, 0.927, 0.926, and 0.907, with accuracies of 0.884, 0.875, 0.861, and 0.851, respectively. Key predictors of mortality included age, cardiopulmonary arrest, abnormal laboratory results (such as abnormal glucose and lactate levels) at presentation, and pre-existing comorbidities. Incorporating post-admission features (n = 37) alongside pre-admission features (n = 65) improved model performance for both 1-month and 1-year mortality predictions, with average AUC improvements of 0.093 ± 0.011 and 0.089 ± 0.012, respectively. Conclusions: Our study demonstrates the effectiveness of ML models in predicting mortality in SAH patients using big data. LR models' robustness, interpretability, and feature significance analysis validate its importance. Including post-admission data significantly improved all models' performances. Our results demonstrate the utility of big data analytics in population-level health outcomes studies.

Machine Learning for the Early Prediction of Delayed Cerebral Ischemia in Patients With Subarachnoid Hemorrhage: Systematic Review and Meta-Analysis

BACKGROUND

Delayed cerebral ischemia (DCI) is a primary contributor to death after subarachnoid hemorrhage (SAH), with significant incidence. Therefore, early determination of the risk of DCI is an urgent need. Machine learning (ML) has received much attention in clinical practice. Recently, some studies have attempted to apply ML models for early noninvasive prediction of DCI. However, systematic evidence for its predictive accuracy is still lacking.

OBJECTIVE

The aim of this study was to synthesize the prediction accuracy of ML models for DCI to provide evidence for the development or updating of intelligent detection tools.

METHODS

PubMed, Cochrane, Embase, and Web of Science databases were systematically searched up to May 18, 2023. The risk of bias in the included studies was assessed using PROBAST (Prediction Model Risk of Bias Assessment Tool). During the analysis, we discussed the performance of different models in the training and validation sets.

RESULTS

We finally included 48 studies containing 16,294 patients with SAH and 71 ML models with logistic regression as the main model type. In the training set, the pooled concordance index (C index), sensitivity, and specificity of all the models were 0.786 (95% CI 0.737-0.835), 0.77 (95% CI 0.69-0.84), and 0.83 (95% CI 0.75-0.89), respectively, while those of the logistic regression models were 0.770 (95% CI 0.724-0.817), 0.75 (95% CI 0.67-0.82), and 0.71 (95% CI 0.63-0.78), respectively. In the validation set, the pooled C index, sensitivity, and specificity of all the models were 0.767 (95% CI 0.741-0.793), 0.66 (95% CI 0.53-0.77), and 0.78 (95% CI 0.71-0.84), respectively, while those of the logistic regression models were 0.757 (95% CI 0.715-0.800), 0.59 (95% CI 0.57-0.80), and 0.80 (95% CI 0.71-0.87), respectively.

CONCLUSIONS

ML models appear to have relatively desirable power for early noninvasive prediction of DCI after SAH. However, enhancing the prediction sensitivity of these models is challenging. Therefore, efficient, noninvasive, or minimally invasive low-cost predictors should be further explored in future studies to improve the prediction accuracy of ML models.

TRIAL REGISTRATION

PROSPERO (CRD42023438399); https://tinyurl.com/yfuuudde.

Assessing the risk of concurrent mycoplasma pneumoniae pneumonia in children with tracheobronchial tuberculosis: retrospective study

Objective

This study aimed to create a predictive model based on machine learning to identify the risk for tracheobronchial tuberculosis (TBTB) occurring alongside Mycoplasma pneumoniae pneumonia in pediatric patients.

Methods

Clinical data from 212 pediatric patients were examined in this retrospective analysis. This cohort included 42 individuals diagnosed with TBTB and Mycoplasma pneumoniae pneumonia (combined group) and 170 patients diagnosed with lobar pneumonia alone (pneumonia group). Three predictive models, namely XGBoost, decision tree, and logistic regression, were constructed, and their performances were assessed using the receiver's operating characteristic (ROC) curve, precision-recall curve (PR), and decision curve analysis (DCA). The dataset was divided into a 7:3 ratio to test the first and second groups, utilizing them to validate the XGBoost model and to construct the nomogram model.

Results

The XGBoost highlighted eight significant signatures, while the decision tree and logistic regression models identified six and five signatures, respectively. The ROC analysis revealed an area under the curve (AUC) of 0.996 for XGBoost, significantly outperforming the other models (p < 0.05). Similarly, the PR curve demonstrated the superior predictive capability of XGBoost. DCA further confirmed that XGBoost offered the highest AIC (43.226), the highest average net benefit (0.764), and the best model fit. Validation efforts confirmed the robustness of the findings, with the validation groups 1 and 2 showing ROC and PR curves with AUC of 0.997, indicating a high net benefit. The nomogram model was shown to possess significant clinical value.

Conclusion

Compared to machine learning approaches, the XGBoost model demonstrated superior predictive efficacy in identifying pediatric patients at risk of concurrent TBTB and Mycoplasma pneumoniae pneumonia. The model's identification of critical signatures provides valuable insights into the pathogenesis of these conditions.

Explainable machine learning in outcome prediction of high-grade aneurysmal subarachnoid hemorrhage

OBJECTIVE

Accurate prognostic prediction in patients with high-grade aneruysmal subarachnoid hemorrhage (aSAH) is essential for personalized treatment. In this study, we developed an interpretable prognostic machine learning model for high-grade aSAH patients using SHapley Additive exPlanations (SHAP).

METHODS

A prospective registry cohort of high-grade aSAH patients was collected in one single-center hospital. The endpoint in our study is a 12-month follow-up outcome. The dataset was divided into training and validation sets in a 7:3 ratio. Machine learning algorithms, including Logistic regression model (LR), support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost), were employed to develop a prognostic prediction model for high-grade aSAH. The optimal model was selected for SHAP analysis.

RESULTS

Among the 421 patients, 204 (48.5%) exhibited poor prognosis. The RF model demonstrated superior performance compared to LR (AUC = 0.850, 95% CI: 0.783-0.918), SVM (AUC = 0.862, 95% CI: 0.799-0.926), and XGBoost (AUC = 0.850, 95% CI: 0.783-0.917) with an AUC of 0.867 (95% CI: 0.806-0 .929). Primary prognostic features identified through SHAP analysis included higher World Federation of Neurosurgical Societies (WFNS) grade, higher modified Fisher score (mFS) and advanced age, were found to be associated with 12-month unfavorable outcome, while the treatment of coiling embolization for aSAH drove the prediction towards favorable prognosis. Additionally, the SHAP force plot visualized individual prognosis predictions.

CONCLUSIONS

This study demonstrated the potential of machine learning techniques in prognostic prediction for high-grade aSAH patients. The features identified through SHAP analysis enhance model interpretability and provide guidance for clinical decision-making.

Prediction model based on radiomics and clinical features for preoperative lymphovascular invasion in gastric cancer patients

Background: We explored whether a model based on contrast-enhanced computed tomography radiomics features and clinicopathological factors can evaluate preoperative lymphovascular invasion (LVI) in patients with gastric cancer (GC) with Lauren classification. Methods: Based on clinical and radiomic characteristics, we established three models: Clinical + Arterial phase_Radcore, Clinical + Venous phase_Radcore and a combined model. The relationship between Lauren classification and LVI was analyzed using a histogram. Results: We retrospectively analyzed 495 patients with GC. The areas under the curve of the combined model were 0.8629 and 0.8343 in the training and testing datasets, respectively. The combined model showed a superior performance to the other models. Conclusion: CECT-based radiomics models can effectively predict preoperative LVI in GC patients with Lauren classification.

Construction and validation of a nomogram model for predicting the overall survival of colorectal cancer patients

BACKGROUND

Colorectal cancer (CRC) is a frequent cancer worldwide with varied survival outcomes.

OBJECTIVE

We aimed to develop a nomogram model to predict the overall survival (OS) of CRC patients after surgery.

DESIGN

This is a retrospective study.

SETTING

This study was conducted from 2015 to 2016 in a single tertiary center for CRC.

PATIENTS

CRC patients who underwent surgery between 2015 and 2016 were enrolled and randomly assigned into the training (n = 480) and validation (n = 206) groups. The risk score of each subject was calculated based on the nomogram. All participants were categorized into two subgroups according to the median value of the score.

MAIN OUTCOME MEASURES

The clinical characteristics of all patients were collected, significant prognostic variables were determined by univariate analysis. Least absolute shrinkage and selection operator (LASSO) regression was applied for variable selection. The tuning parameter (λ) for LASSO regression was determined by cross-validation. Independent prognostic variables determined by multivariable analysis were used to establish the nomogram. The predictive capacity of the model was assessed by risk group stratification.

RESULTS

Infiltration depth, macroscopic classification, BRAF, carbohydrate antigen 19 - 9 (CA-199) levels, N stage, M stage, TNM stage, carcinoembryonic antigen levels, number of positive lymph nodes, vascular tumor thrombus, and lymph node metastasis were independent prognostic factors. The nomogram established based on these factors exhibited good discriminatory capacity. The concordance indices for the training and validation groups were 0.796 and 0.786, respectively. The calibration curve suggested favorable agreement between predictions and observations. Moreover, the OS of different risk subgroups was significantly different.

LIMITATIONS

The limitations of this work included small sample size and single-center design. Also, some prognostic factors could not be included due to the retrospective design.

CONCLUSIONS

A prognostic nomogram for predicting the OS of CRC patients after surgery was developed, which might be helpful for evaluating the prognosis of CRC patients.

Identification of risk factors for infection after mitral valve surgery through machine learning approaches

Background

Selecting features related to postoperative infection following cardiac surgery was highly valuable for effective intervention. We used machine learning methods to identify critical perioperative infection-related variables after mitral valve surgery and construct a prediction model.

Methods

Participants comprised 1223 patients who underwent cardiac valvular surgery at eight large centers in China. The ninety-one demographic and perioperative parameters were collected. Random forest (RF) and least absolute shrinkage and selection operator (LASSO) techniques were used to identify postoperative infection-related variables; the Venn diagram determined overlapping variables. The following ML methods: random forest (RF), extreme gradient boosting (XGBoost), Support Vector Machine (SVM), Gradient Boosting Decision Tree (GBDT), AdaBoost, Naive Bayesian (NB), Logistic Regression (LogicR), Neural Networks (nnet) and artificial neural network (ANN) were developed to construct the models. We constructed receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC) was calculated to evaluate model performance.

Results

We identified 47 and 35 variables with RF and LASSO, respectively. Twenty-one overlapping variables were finally selected for model construction: age, weight, hospital stay, total red blood cell (RBC) and total fresh frozen plasma (FFP) transfusions, New York Heart Association (NYHA) class, preoperative creatinine, left ventricular ejection fraction (LVEF), RBC count, platelet (PLT) count, prothrombin time, intraoperative autologous blood, total output, total input, aortic cross-clamp (ACC) time, postoperative white blood cell (WBC) count, aspartate aminotransferase (AST), alanine aminotransferase (ALT), PLT count, hemoglobin (Hb), and LVEF. The prediction models for infection after mitral valve surgery were established based on these variables, and they all showed excellent discrimination performance in the test set (AUC > 0.79).

Conclusions

Key features selected by machine learning methods can accurately predict infection after mitral valve surgery, guiding physicians in taking appropriate preventive measures and diminishing the infection risk.

Preoperative prognostic nutrition index can independently predict the 6-month prognosis of elderly patients undergoing neurosurgical clipping for aneurysmal subarachnoid hemorrhage

The number of elderly patients with aneurysmal subarachnoid hemorrhage (aSAH) is increasing annually. The prognostic nutritional index (PNI) is used as a novel and valuable prognostic marker for various neoplastic diseases and other critical illnesses. This study aimed to identify the short-term prognostic value of preoperative PNI in elderly patients who underwent neurosurgical clipping for aSAH. This retrospective study included elderly patients with aSAH who underwent neurosurgical clipping from January 2018 to December 2020. Clinical variables and 6-month outcomes were collected and compared. Epidemiological data and effect factors of prognosis were evaluated. Multivariate logistic regression and receiver operating characteristics (ROC) curve analyses were used to evaluate the predictive value of preoperative PNI. Multiple logistic regression was performed to establish a nomogram. A total of 124 elderly patients were enrolled. Multivariate logistic regression analysis showed that preoperative PNI (odds ratio (OR), 0.779; 95% confidence interval (CI), 0.689-0.881; P < 0.001), Hunt-Hess grade (OR, 3.291; 95%CI, 1.816-5.966; P < 0.001), and hydrocephalus (OR, 9.423; 95%CI, 2.696-32.935; P < 0.001) were significant predictors. The area under the ROC curve of PNI was 0.829 (95% CI, 0.755-0.903; P < 0.001) with a sensitivity and specificity of 68.4% and 83.3%, respectively, and the cutoff value was 46.36. Patients with preoperative PNI of < 46.36 had a significantly unfavorable 6-months prognosis (F = 40.768, P < 0.001). Preoperative PNI is independently correlated with the 6-month prognosis in elderly patients who undergo neurosurgical clipping for aSAH.