Predictive Approaches for Acute Dialysis Requirement and Death in COVID-19

Classification and Regression Trees analysis identifies patients at high risk for kidney function decline following hospitalization

Estimated glomerular filtration rate (eGFR) decline is associated with negative health outcomes, but the use of decision tree algorithms to predict eGFR decline is underreported. Among patients hospitalized during the first year of the COVID-19 pandemic, it remains unclear which individuals are at the greatest risk of eGFR decline after discharge. We conducted a retrospective cohort study on patients hospitalized at Stony Brook University Hospital in 2020 who were followed for 36 months post discharge. Random Forest (RF) identified the top ten features associated with fast eGFR decline. Logistic regression (LR) and Classification and Regression Trees (CART) were then employed to uncover the relative importance of these top features and identify the highest risk patients. In the cohort of 1,747 hospital survivors, 61.6% experienced fast eGFR decline, which was associated with younger age, higher baseline eGFR, and acute kidney injury (AKI). Multivariate LR analysis showed that older age was associated with lower odds of fast eGFR decline whereas length of hospitalization and vasopressor use with greater odds. CART analysis identified length of hospitalization as the most important factor and that patients with AKI and hospitalization of 27 days or more were at highest risk. After grouping by ICU and COVID-19 status and propensity score matching for demographics, these risk factors of fast eGFR decline remained consistent. CART analysis can help identify patient subgroups with the highest risk of post-discharge eGFR decline. Clinicians should consider the length of hospitalization in post-discharge monitoring of kidney function.

Development and validation of machine learning-based prediction model for severe pneumonia: A multicenter cohort study

Severe pneumonia (SP) is a prevalent respiratory ailment characterized by high mortality and poor prognosis. Current scoring systems for pneumonia are not only time-consuming but also exhibit limitations in early SP prediction. To address this gap, this study aimed to develop a machine-learning model using inflammatory markers from peripheral blood for early prediction of SP. A total of 204 pneumonia patients from seven medical centers were studied, with 143 (68 SP cases) in the training cohort and 61 (32 SP cases) in the test cohort. Clinical characteristics and laboratory test results were collected at diagnosis. Various models including Logistic Regression, Random Forest, Naïve Bayes, XGBoost, Support Vector Machine, and Decision Tree were built and evaluated. Seven predictors-age, sex, WBC count, T-lymphocyte count, NLR, CRP, TNF-α, IL-4/IFN-γ ratio, IL-6/IL-10 ratio-were selected through LASSO regression and clinical insight. The XGBoost model, exhibiting best performance, achieved an AUC of 0.901 (95 % CI: 0.827 to 0.985) in the test cohort, with an accuracy of 0.803, sensitivity of 0.844, specificity of 0.759, and F1_score of 0.818. Indeed, SHAP analysis emphasized the significance of elevated WBC counts, older age, and elevated CRP as the top predictors. The use of inflammatory biomarkers in this concise predictive model shows significant potential for the rapid assessment of SP risk, thereby facilitating timely preventive interventions.

Predictive approach for liberation from acute dialysis in ICU patients using interpretable machine learning

Renal recovery following dialysis-requiring acute kidney injury (AKI-D) is a vital clinical outcome in critical care, yet it remains an understudied area. This retrospective cohort study, conducted in a medical center in Taiwan from 2015 to 2020, enrolled patients with AKI-D during intensive care unit stays. We aimed to develop and temporally test models for predicting dialysis liberation before hospital discharge using machine learning algorithms and explore early predictors. The dataset comprised 90 routinely collected variables within the first three days of dialysis initiation. Out of 1,381 patients who received acute dialysis, 27.3% experienced renal recovery. The cohort was divided into the training group (N = 1135) and temporal testing group (N = 251). The models demonstrated good performance, with an area under the receiver operating characteristic curve of 0.85 (95% CI, 0.81-0.88) and an area under the precision-recall curve of 0.69 (95% CI, 0.62-0.76) for the XGBoost model. Key predictors included urine volume, Charlson comorbidity index, vital sign derivatives (trend of respiratory rate and SpO2), and lactate levels. We successfully developed early prediction models for renal recovery by integrating early changes in vital signs and inputs/outputs, which have the potential to aid clinical decision-making in the ICU.

Prediction of substantial closed-globe injuries in orbital wall fractures

PURPOSE

To determine risk factors for substantial closed-globe injuries in orbital fractures (SCGI) and to develop the best multivariate model for the prediction of SCGI.

METHODS

A retrospective study was performed on patients diagnosed with orbital fractures at Farabi Hospital between 2016 and 2022. Patients with a comprehensive ophthalmologic examination and orbital CT scan were included. Predictive signs or imaging findings for SCGI were identified by logistic regression (LR) analysis. Support vector machine (SVM), random forest regression (RFR), and extreme gradient boosting (XGBoost) were also trained using a fivefold cross-validation method.

RESULTS

A total of 415 eyes from 403 patients were included. Factors associated with an increased risk of SCGI were reduced uncorrected visual acuity (UCVA), increased difference between UCVA of the traumatic eye from the contralateral eye, older age, male sex, grade of periorbital soft tissue trauma, trauma in the occupational setting, conjunctival hemorrhage, extraocular movement restriction, number of fractured walls, presence of medial wall fracture, size of fracture, intraorbital emphysema and retrobulbar hemorrhage. The area under the curve of the receiver operating characteristic for LR, SVM, RFR, and XGBoost for the prediction of SCGI was 57.2%, 68.8%, 63.7%, and 73.1%, respectively.

CONCLUSIONS

Clinical and radiographic findings could be utilized to efficiently predict SCGI. XGBoost outperforms the logistic regression model in the prediction of SCGI and could be incorporated into clinical practice.

Prediction of the acceptance of telemedicine among rheumatic patients: a machine learning-powered secondary analysis of German survey data

Telemedicine (TM) has augmented healthcare by enabling remote consultations, diagnosis, treatment, and monitoring of patients, thereby improving healthcare access and patient outcomes. However, successful adoption of TM depends on user acceptance, which is influenced by technical, socioeconomic, and health-related factors. Leveraging machine learning (ML) to accurately predict these adoption factors can greatly contribute to the effective utilization of TM in healthcare. The objective of the study was to compare 12 ML algorithms for predicting willingness to use TM (TM try) among patients with rheumatic and musculoskeletal diseases (RMDs) and identify key contributing features. We conducted a secondary analysis of RMD patient data from a German nationwide cross-sectional survey. Twelve ML algorithms, including logistic regression, random forest, extreme gradient boosting (XGBoost), and neural network (deep learning) were tested on a subset of the dataset, with the inclusion of only RMD patients who answered "yes" or "no" to TM try. Nested cross-validation was used for each model. The best-performing model was selected based on area under the receiver operator characteristic (AUROC). For the best-performing model, a multinomial/multiclass ML approach was undertaken with the consideration of the three following classes: "yes", "no", "do not know/not answered". Both one-vs-one and one-vs-rest strategies were considered. The feature importance was investigated using Shapley additive explanation (SHAP). A total of 438 RMD patients were included, with 26.5% of them willing to try TM, 40.6% not willing, and 32.9% undecided (missing answer or "do not know answer"). This dataset was used to train and test ML models. The mean accuracy of the 12 ML models ranged from 0.69 to 0.83, while the mean AUROC ranged from 0.79 to 0.90. The XGBoost model produced better results compared with the other models, with a sensitivity of 70%, specificity of 91% and positive predictive value of 84%. The most important predictors of TM try were the possibility that TM services were offered by a rheumatologist, prior TM knowledge, age, self-reported health status, Internet access at home and type of RMD diseases. For instance, for the yes vs. no classification, not wishing that TM services were offered by a rheumatologist, self-reporting a bad health status and being aged 60-69 years directed the model toward not wanting to try TM. By contrast, having Internet access at home and wishing that TM services were offered by a rheumatologist directed toward TM try. Our findings have significant implications for primary care, in particular for healthcare professionals aiming to implement TM effectively in their clinical routine. By understanding the key factors influencing patients' acceptance of TM, such as their expressed desire for TM services provided by a rheumatologist, self-reported health status, availability of home Internet access, and age, healthcare professionals can tailor their strategies to maximize the adoption and utilization of TM, ultimately improving healthcare outcomes for RMD patients. Our findings are of high interest for both clinical and medical teaching practice to fit changing health needs caused by the growing number of complex and chronically ill patients.

Predicting COVID-19 prognosis in hospitalized patients based on early status

IMPORTANCE

COVID-19 remains the fourth leading cause of death in the United States. Predicting COVID-19 patient prognosis is essential to help efficiently allocate resources, including ventilators and intensive care unit beds, particularly when hospital systems are strained. Our PLABAC and PRABLE models are unique because they accurately assess a COVID-19 patient's risk of death from only age and five commonly ordered laboratory tests. This simple design is important because it allows these models to be used by clinicians to rapidly assess a patient's risk of decompensation and serve as a real-time aid when discussing difficult, life-altering decisions for patients. Our models have also shown generalizability to external populations across the United States. In short, these models are practical, efficient tools to assess and communicate COVID-19 prognosis.

Temporal validation of the MMCD score to predict kidney replacement therapy and in-hospital mortality in COVID-19 patients

BACKGROUND

Acute kidney injury has been described as a common complication in patients hospitalized with COVID-19, which may lead to the need for kidney replacement therapy (KRT) in its most severe forms. Our group developed and validated the MMCD score in Brazilian COVID-19 patients to predict KRT, which showed excellent performance using data from 2020. This study aimed to validate the MMCD score in a large cohort of patients hospitalized with COVID-19 in a different pandemic phase and assess its performance to predict in-hospital mortality.

METHODS

This study is part of the "Brazilian COVID-19 Registry", a retrospective observational cohort of consecutive patients hospitalized for laboratory-confirmed COVID-19 in 25 Brazilian hospitals between March 2021 and August 2022. The primary outcome was KRT during hospitalization and the secondary was in-hospital mortality. We also searched literature for other prediction models for KRT, to assess the results in our database. Performance was assessed using area under the receiving operator characteristic curve (AUROC) and the Brier score.

RESULTS

A total of 9422 patients were included, 53.8% were men, with a median age of 59 (IQR 48-70) years old. The incidence of KRT was 8.8% and in-hospital mortality was 18.1%. The MMCD score had excellent discrimination and overall performance to predict KRT (AUROC: 0.916 [95% CI 0.909-0.924]; Brier score = 0.057). Despite the excellent discrimination and overall performance (AUROC: 0.922 [95% CI 0.914-0.929]; Brier score = 0.100), the calibration was not satisfactory concerning in-hospital mortality. A random forest model was applied in the database, with inferior performance to predict KRT requirement (AUROC: 0.71 [95% CI 0.69-0.73]).

CONCLUSION

The MMCD score is not appropriate for in-hospital mortality but demonstrates an excellent predictive ability to predict KRT in COVID-19 patients. The instrument is low cost, objective, fast and accurate, and can contribute to supporting clinical decisions in the efficient allocation of assistance resources in patients with COVID-19.

An optimized machine learning model for predicting hospitalization for COVID-19 infection in the maintenance dialysis population

COVID-19 has a high rate of infection in dialysis patients and poses a serious risk to human health. Currently, there are no dialysis centers in China that have analyzed the prevalence of COVID-19 infection in dialysis patients and the mortality rate. Although machine learning-based disease prediction methods have proven to be effective, redundant attributes in the data and the interpretability of the predictive models are still worth investigating. Therefore, this paper proposed a wrapper feature selection classification model to achieve the prediction of the risk of COVID-19 infection in dialysis patients. The method was used to optimize the feature set of the sample through an enhanced JAYA optimization algorithm based on the dispersed foraging strategy and the greedy levy mutation strategy. Then, the proposed method combines fuzzy K-nearest neighbor for classification prediction. IEEE CEC2014 benchmark function experiments as well as prediction experiments on the uremia dataset are used to validate the proposed model. The experimental results showed that the proposed method has a high prediction accuracy of 95.61% for the prevalence risk of COVID-19 infection in dialysis patients. Furthermore, it was shown that proalbumin, CRP, direct bilirubin, hemoglobin, albumin, and phosphorus are of great value for clinical diagnosis. Therefore, the proposed method can be considered as a promising method.

Machine learning algorithms assist early evaluation of enteral nutrition in ICU patients

Background

This study applied machine learning (ML) algorithms to construct a model for predicting EN initiation for patients in the intensive care unit (ICU) and identifying populations in need of EN at an early stage.

Methods

This study collected patient information from the Medical Information Mart for Intensive Care IV database. All patients enrolled were split randomly into a training set and a validation set. Six ML models were established to evaluate the initiation of EN, and the best model was determined according to the area under curve (AUC) and accuracy. The best model was interpreted using the Local Interpretable Model-Agnostic Explanations (LIME) algorithm and SHapley Additive exPlanation (SHAP) values.

Results

A total of 53,150 patients participated in the study. They were divided into a training set (42,520, 80%) and a validation set (10,630, 20%). In the validation set, XGBoost had the optimal prediction performance with an AUC of 0.895. The SHAP values revealed that sepsis, sequential organ failure assessment score, and acute kidney injury were the three most important factors affecting EN initiation. The individualized forecasts were displayed using the LIME algorithm.

Conclusion

The XGBoost model was established and validated for early prediction of EN initiation in ICU patients.

Indications for and Timing of Initiation of KRT

KRT is considered for patients with severe AKI and associated complications. The exact indications for initiating KRT have been debated for decades. There is a general consensus that KRT should be considered in patients with AKI and medically refractory complications ("urgent indications"). "Relative indications" are more common but defined with less precision. In this review, we summarize the latest evidence from recent landmark clinical trials, discuss strategies to anticipate the need for KRT in individual patients, and propose an algorithm for decision making. We emphasize that the decision to consider KRT should be made in conjunction with other forms of organ support therapies and important nonkidney factors, including the patient's preferences and overall goals of care. We also suggest future research to differentiate patients who benefit from timely initiation of KRT from those with imminent recovery of kidney function. Until then, efforts are needed to optimize the initiation and delivery of KRT in routine clinical practice, to minimize nonessential variation, and to ensure that patients with persistent AKI or progressive organ failure affected by AKI receive KRT in a timely manner.

Accuracy of clinicians' ability to predict the need for renal replacement therapy: a prospective multicenter study

PURPOSE

Identifying patients who will receive renal replacement therapy (RRT) during intensive care unit (ICU) stay is a major challenge for intensivists. The objective of this study was to evaluate the performance of physicians in predicting the need for RRT at ICU admission and at acute kidney injury (AKI) diagnosis.

METHODS

Prospective, multicenter study including all adult patients hospitalized in 16 ICUs in October 2020. Physician prediction was estimated at ICU admission and at AKI diagnosis, according to a visual Likert scale. Discrimination, risk stratification and benefit of physician estimation were assessed. Mixed logistic regression models of variables associated with risk of receiving RRT, with and without physician estimation, were compared.

RESULTS

Six hundred and forty-nine patients were included, 270 (41.6%) developed AKI and 77 (11.8%) received RRT. At ICU admission and at AKI diagnosis, a model including physician prediction, the experience of the physician, SOFA score, serum creatinine and diuresis to determine need for RRT performed better than a model without physician estimation with an area under the ROC curve of 0.90 [95% CI 0.86-0.94, p < 0.008 (at ICU admission)] and 0.89 [95% CI 0.83-0.93, p = 0.0014 (at AKI diagnosis)]. In multivariate analysis, physician prediction was strongly associated with the need for RRT, independently of creatinine levels, diuresis, SOFA score and the experience of the doctor who made the prediction.

CONCLUSION

As physicians are able to stratify patients at high risk of RRT, physician judgement should be taken into account when designing new randomized studies focusing on RRT initiation during AKI.

Application of Machine Learning to Improve Appropriateness of Treatment in an Orthopaedic Setting of Personalized Medicine

The rise of personalized medicine and its remarkable advancements have revealed new requirements for the availability of appropriate medical decision-making models. Computer science is an area that plays an essential role in the field of personalized medicine, where one of the goals is to provide algorithms and tools to extrapolate knowledge and improve the decision-support process. The minimum clinically important difference (MCID) is the smallest change in PROM scores that patients perceive as meaningful. Treatment that does not achieve the minimum level of improvement is considered inappropriate as well as a potential waste of resources. Using the MCID threshold to identify patients who fail to achieve the minimum change in PROM that results in a meaningful outcome may aid in pre-surgical shared decision-making. The decision tree algorithm is a method for extracting valuable information and providing further meaningful information to the domain expert that supports the decision-making. In the present study, different tools based on machine learning were developed. On the one hand, we compared three XGBoost models to predict the non-achievement of the MCID at six months post-operation in the SF-12 physical score. The prediction score threshold was set to 0.75 to provide three decision-making areas on the basis of the high confidence (HC) intervals; the minority class was re-balanced by weighting the positive class to penalize the loss function (XGBoost cost-sensitive), oversampling the minority class (XGBoost with SMOTE), and re-sampling the negative class (XGBoost with undersampling). On the other hand, we modeled the data through a decision tree (assessment tree), based on different complexity levels, to identify the hidden pattern and to provide a new way to understand possible relationships between the gathered features and the several outcomes. The results showed that all the proposed models were effective as binary classifiers, as they showed moderate predictive performance both regarding the minority or positive class (i.e., our targeted patients, those who will not benefit from surgery) and the negative class. The decision tree visualization can be exploited during the patient assessment status to better understand if those patients will benefit or not from the medical intervention. Both of these tools can come in handy for increasing knowledge about the patient’s psychophysical state and for creating an increasingly specialized assessment of the individual patient.

Development of a machine learning-based risk prediction model for cerebral infarction and comparison with nomogram model

BACKGROUND

Development of a cerebral infarction (CI) risk prediction model by mining routine test big data with machine learning algorithms.

METHODS

Cohort 1 included 2017 CI patients and health checkers, and the optimal machine learning algorithms in Extreme gradient Boosting (XgBoost), Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF) were selected to mine all routine test data of the enrolled subjects for screening CI model features. Cohort 2 included patients with CI and Non-CI from 2018 to 2020 to develop an early warning model for CI and was analyzed in subgroups with a cutoff of 50 years. Cohort 3 included CI patients versus Non-CI patients in 2021, and a nomogram models was developed for comparison with the machine learning model.

RESULTS

The optimal algorithm XgBoost was used to develop a CI risk prediction model CI-Lab8 containing eight characteristics of fibrinogen, age, glucose, mean erythrocyte hemoglobin concentration, albumin, neutrophil absolute value, activated partial thromboplastin time, and triglycerides. The model had an AUC of 0.823 in cohort 2, significantly higher than the FIB (AUC = 0.737), which ranked first in feature importance. CI-Lab8 also had higher diagnostic accuracy in CI patients <50 years of age (AUC = 0.800), slightly lower than in CI patients ≥50 years of age (AUC = 0.856). Receiver operating characteristic curve, calibration curve, and decision curve analysis in cohort 3 showed CI-Lab8 to be superior to nomogram.

CONCLUSION

In this study, the CI risk prediction model developed by XgBoost algorithm outperformed the nomogram model and had higher diagnostic accuracy for CI patients in both <50 and ≥50 years old, which may assist clinical assessment for CI.

Development and validation of the MMCD score to predict kidney replacement therapy in COVID-19 patients

BACKGROUND

Acute kidney injury (AKI) is frequently associated with COVID-19, and the need for kidney replacement therapy (KRT) is considered an indicator of disease severity. This study aimed to develop a prognostic score for predicting the need for KRT in hospitalised COVID-19 patients, and to assess the incidence of AKI and KRT requirement.

METHODS

This study is part of a multicentre cohort, the Brazilian COVID-19 Registry. A total of 5212 adult COVID-19 patients were included between March/2020 and September/2020. Variable selection was performed using generalised additive models (GAM), and least absolute shrinkage and selection operator (LASSO) regression was used for score derivation. Accuracy was assessed using the area under the receiver operating characteristic curve (AUC-ROC).

RESULTS

The median age of the model-derivation cohort was 59 (IQR 47-70) years, 54.5% were men, 34.3% required ICU admission, 20.9% evolved with AKI, 9.3% required KRT, and 15.1% died during hospitalisation. The temporal validation cohort had similar age, sex, ICU admission, AKI, required KRT distribution and in-hospital mortality. The geographic validation cohort had similar age and sex; however, this cohort had higher rates of ICU admission, AKI, need for KRT and in-hospital mortality. Four predictors of the need for KRT were identified using GAM: need for mechanical ventilation, male sex, higher creatinine at hospital presentation and diabetes. The MMCD score had excellent discrimination in derivation (AUROC 0.929, 95% CI 0.918-0.939) and validation (temporal AUROC 0.927, 95% CI 0.911-0.941; geographic AUROC 0.819, 95% CI 0.792-0.845) cohorts and good overall performance (Brier score: 0.057, 0.056 and 0.122, respectively). The score is implemented in a freely available online risk calculator ( https://www.mmcdscore.com/ ).

CONCLUSIONS

The use of the MMCD score to predict the need for KRT may assist healthcare workers in identifying hospitalised COVID-19 patients who may require more intensive monitoring, and can be useful for resource allocation.

Artificial Intelligence in Acute Kidney Injury Prediction

The use of artificial intelligence (AI) in nephrology and its associated clinical research is growing. Recent years have seen increased interest in utilizing AI to predict the development of hospital-based acute kidney injury (AKI). Several AI techniques have been employed to improve the ability to detect AKI across a variety of hospitalized settings. This review discusses the evolutions of AKI risk prediction discussing the static risk assessment models of yesteryear as well as the more recent trend toward AI and advanced learning techniques. We discuss the relative improvement in AKI detection as well as the relative dearth of data around the clinical implementation and patient outcomes using these models. The use of AI for AKI detection and clinical care is in its infancy, and this review describes how we arrived at our current position and hints at the promise of the future.

Recent Advances and Future Perspectives in the Use of Machine Learning and Mathematical Models in Nephrology

We reviewed some of the latest advancements in the use of mathematical models in nephrology. We looked over 2 distinct categories of mathematical models that are widely used in biological research and pointed out some of their strengths and weaknesses when applied to health care, especially in the context of nephrology. A mechanistic dynamical system allows the representation of causal relations among the system variables but with a more complex and longer development/implementation phase. Artificial intelligence/machine learning provides predictive tools that allow identifying correlative patterns in large data sets, but they are usually harder-to-interpret black boxes. Chronic kidney disease (CKD), a major worldwide health problem, generates copious quantities of data that can be leveraged by choice of the appropriate model; also, there is a large number of dialysis parameters that need to be determined at every treatment session that can benefit from predictive mechanistic models. Following important steps in the use of mathematical methods in medical science might be in the intersection of seemingly antagonistic frameworks, by leveraging the strength of each to provide better care.

A Comparison of XGBoost, Random Forest, and Nomograph for the Prediction of Disease Severity in Patients With COVID-19 Pneumonia: Implications of Cytokine and Immune Cell Profile

BACKGROUND AND AIMS

The aim of this study was to apply machine learning models and a nomogram to differentiate critically ill from non-critically ill COVID-19 pneumonia patients.

METHODS

Clinical symptoms and signs, laboratory parameters, cytokine profile, and immune cellular data of 63 COVID-19 pneumonia patients were retrospectively reviewed. Outcomes were followed up until Mar 12, 2020. A logistic regression function (LR model), Random Forest, and XGBoost models were developed. The performance of these models was measured by area under receiver operating characteristic curve (AUC) analysis.

RESULTS

Univariate analysis revealed that there was a difference between critically and non-critically ill patients with respect to levels of interleukin-6, interleukin-10, T cells, CD4+ T, and CD8+ T cells. Interleukin-10 with an AUC of 0.86 was most useful predictor of critically ill patients with COVID-19 pneumonia. Ten variables (respiratory rate, neutrophil counts, aspartate transaminase, albumin, serum procalcitonin, D-dimer and B-type natriuretic peptide, CD4+ T cells, interleukin-6 and interleukin-10) were used as candidate predictors for LR model, Random Forest (RF) and XGBoost model application. The coefficients from LR model were utilized to build a nomogram. RF and XGBoost methods suggested that Interleukin-10 and interleukin-6 were the most important variables for severity of illness prediction. The mean AUC for LR, RF, and XGBoost model were 0.91, 0.89, and 0.93 respectively (in two-fold cross-validation). Individualized prediction by XGBoost model was explained by local interpretable model-agnostic explanations (LIME) plot.

CONCLUSIONS

XGBoost exhibited the highest discriminatory performance for prediction of critically ill patients with COVID-19 pneumonia. It is inferred that the nomogram and visualized interpretation with LIME plot could be useful in the clinical setting. Additionally, interleukin-10 could serve as a useful predictor of critically ill patients with COVID-19 pneumonia.

Using sequence clustering to identify clinically relevant subphenotypes in patients with COVID-19 admitted to the intensive care unit

OBJECTIVE

The novel coronavirus disease 2019 (COVID-19) has heterogenous clinical courses, indicating that there might be distinct subphenotypes in critically ill patients. Although prior research has identified these subphenotypes, the temporal pattern of multiple clinical features has not been considered in cluster models. We aimed to identify temporal subphenotypes in critically ill patients with COVID-19 using a novel sequence cluster analysis and associate them with clinically relevant outcomes.

MATERIALS AND METHODS

We analyzed 1036 confirmed critically ill patients with laboratory-confirmed SARS-COV-2 infection admitted to the Mount Sinai Health System in New York city. The agglomerative hierarchical clustering method was used with Levenshtein distance and Ward's minimum variance linkage.

RESULTS

We identified four subphenotypes. Subphenotype I (N = 233 [22.5%]) included patients with rapid respirations and a rapid heartbeat but less need for invasive interventions within the first 24 hours, along with a relatively good prognosis. Subphenotype II (N = 418 [40.3%]) represented patients with the least degree of ailments, relatively low mortality, and the highest probability of discharge from the hospital. Subphenotype III (N = 259 [25.0%]) represented patients who experienced clinical deterioration during the first 24 hours of intensive care unit admission, leading to poor outcomes. Subphenotype IV (N = 126 [12.2%]) represented an acute respiratory distress syndrome trajectory with an almost universal need for mechanical ventilation.

CONCLUSION

We utilized the sequence cluster analysis to identify clinical subphenotypes in critically ill COVID-19 patients who had distinct temporal patterns and different clinical outcomes. This study points toward the utility of including temporal information in subphenotyping approaches.

Artificial intelligence's role in vascular surgery decision-making

Artificial intelligence (AI) is the next great advance informing medical science. Several disciplines, including vascular surgery, use AI-based decision-making tools to improve clinical performance. Although applied widely, AI functions best when confronted with voluminous, accurate data. Consistent, predictable analytic technique selection also challenges researchers. This article contextualizes AI analyses within evidence-based medicine, focusing on "big data" and health services research, as well as discussing opportunities to improve data collection and realize AI's promise.