Maryam Pishgar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Maryam Pishgar has a total of 84 co-authors. Here are the top co-authors by number of shared publications:
Kamiar Alaei
Department of Health Science, California State University, Long Beach, Long Beach, CA 90840, USA
34 shared publicationsGreg Placencia
27 shared publicationsElham Pishgar
22 shared publicationsShuheng Chen
21 shared publicationsJunyi Fan
19 shared publications- Negin Ashrafi
University of Southern California
17 shared publications
Latest Publications
- Open Access
Cross-database adaptation of machine learning models for predicting sustained antibiotic exposure among patients with intracerebral hemorrhage in intensive care units
Background: Patients with intracerebral hemorrhage (ICH) in intensive care units (ICUs) frequently receive antibiotics early in critical illness. Such exposure reflects suspected infection, physiological deterioration, monitoring intensity, and clinical management and may vary across institutions and electronic health record databases. We evaluated target-domain adaptation for modeling sustained antibiotic exposure in critically ill patients with ICH. Methods: We analyzed derived ICH cohorts from MIMIC-IV and the eICU Collaborative Research Database. MIMIC-IV included 2,024 ICU stays and served as the source cohort. The eICU cohort comprised 1,277 stays and was divided, at the ICU-stay level, into a development subset (766 stays) and a held-out evaluation subset (511 stays). The eICU outcome was sustained antibiotic exposure on at least two ICU days. Candidate models incorporated demographic, comorbidity, physiological, laboratory, neurologic, respiratory, temporal, and measurementprocess features. Timestamped observations for static and temporal tabular families were censored at the recorded first-antibiotic time when available, whereas the compact sequence component and explicit measurement-density features used the full first 24 hours. For base-model families using eICU development data, meta-learner inputs were generated by five-fold stratified cross-fitting. A 42-input L2-penalized logistic meta-learner combined 16 model probabilities with model-summary, clinical, availability, and measurement-density features. Results: The held-out eICU subset contained 48 positive outcomes (9.39%). The adapted ensemble achieved an area under the receiver operating characteristic curve (AUROC) of 0.841 (95% CI 0.775–0.899) and an average precision (AP) of 0.540 (95% CI 0.399–0.676), with a Brier score of 0.063 and expected calibration error of 0.029. The MIMIC-IV source-only stack achieved an AUROC of 0.782; the paired AUROC difference was 0.059 (95% CI 0.003–0.112). In a separate patient-grouped five-fold out-of-fold sensitivity analysis of 503 linked eICU stays, AUROC was 0.807 (95% CI 0.691–0.910). Conclusions: Target-domain adaptation improved held-out discrimination relative to a source-only stack for sustained antibiotic exposure. Because some model components and measurement-process features used information from the broader first 24 hours, the model should be interpreted as a first-24-hour treatment-association model rather than a strictly prospective pre-treatment infection predictor.
Open AccessCross-database adaptation of machine learning models for predicting sustained antibiotic exposure among patients with intracerebral hemorrhage in intensive care units
Background: Patients with intracerebral hemorrhage (ICH) in intensive care units (ICUs) frequently receive antibiotics early in critical illness. Such exposure reflects suspected infection, physiological deterioration, monitoring intensity, and clinical management and may vary across institutions and electronic health record databases. We evaluated target-domain adaptation for modeling sustained antibiotic exposure in critically ill patients with ICH. Methods: We analyzed derived ICH cohorts from MIMIC-IV and the eICU Collaborative Research Database. MIMIC-IV included 2,024 ICU stays and served as the source cohort. The eICU cohort comprised 1,277 stays and was divided, at the ICU-stay level, into a development subset (766 stays) and a held-out evaluation subset (511 stays). The eICU outcome was sustained antibiotic exposure on at least two ICU days. Candidate models incorporated demographic, comorbidity, physiological, laboratory, neurologic, respiratory, temporal, and measurementprocess features. Timestamped observations for static and temporal tabular families were censored at the recorded first-antibiotic time when available, whereas the compact sequence component and explicit measurement-density features used the full first 24 hours. For base-model families using eICU development data, meta-learner inputs were generated by five-fold stratified cross-fitting. A 42-input L2-penalized logistic meta-learner combined 16 model probabilities with model-summary, clinical, availability, and measurement-density features. Results: The held-out eICU subset contained 48 positive outcomes (9.39%). The adapted ensemble achieved an area under the receiver operating characteristic curve (AUROC) of 0.841 (95% CI 0.775–0.899) and an average precision (AP) of 0.540 (95% CI 0.399–0.676), with a Brier score of 0.063 and expected calibration error of 0.029. The MIMIC-IV source-only stack achieved an AUROC of 0.782; the paired AUROC difference was 0.059 (95% CI 0.003–0.112). In a separate patient-grouped five-fold out-of-fold sensitivity analysis of 503 linked eICU stays, AUROC was 0.807 (95% CI 0.691–0.910). Conclusions: Target-domain adaptation improved held-out discrimination relative to a source-only stack for sustained antibiotic exposure. Because some model components and measurement-process features used information from the broader first 24 hours, the model should be interpreted as a first-24-hour treatment-association model rather than a strictly prospective pre-treatment infection predictor.
- Open Access
Development and Cross-Database External Validation of 24-Hour Landmark Models for ICU Mortality After Intracerebral Hemorrhage: Incremental Value of Routine Coagulation Markers
Background: Intracerebral hemorrhage (ICH) is associated with high early mortality. Although routine coagulation markers are clinically relevant, their incremental value for mortality prediction beyond neurologic and physiologic information is uncertain. We developed and externally validated models using first-24-hour ICU data and evaluated the added predictive value of routine coagulation measurements. Methods: We used MIMIC-IV for model development and eICU-CRD for external validation. The development cohort included 2,669 adults with nontraumatic ICH and 388 ICU deaths. Logistic regression, random forest, and XGBoost were evaluated using a patient-level 70:30 holdout split and 5-fold stratified cross-validation. External validation used a high-specificity primary eICU cohort (396 patients; 39 deaths) and a broader secondary hemorrhagicstroke/likely-ICH cohort (1,555 patients; 168 deaths). Performance was assessed using AUROC, AUPRC, Brier score, calibration, and paired bootstrap comparisons. GCS-only and age-plus-GCS models served as clinical benchmarks. Coagulation-only, clinical-only, and combined XGBoost models were compared to assess incremental value. Results: In the internal holdout cohort, AUROCs were 0.870 for logistic regression, 0.859 for random forest, and 0.867 for XGBoost. In the primary external cohort, corresponding AUROCs were 0.804, 0.839, and 0.817; AUPRCs were 0.342, 0.419, and 0.406; and Brier scores were 0.080, 0.072, and 0.074. In the broader cohort, AUROCs were 0.826, 0.848, and 0.838. Random forest showed the numerically strongest external performance, but pairwise AUROC differences among multivariable models were not clearly supported. GCS-only achieved AUROCs of 0.780 and 0.813 in the primary and broader cohorts. Coagulationonly XGBoost showed weak discrimination (AUROC 0.598 internally, 0.598 primary external, and 0.566 broader external). Adding coagulation variables to the clinical model produced AUROC differences of 0.014 (95% CI − 0.009 to 0.037) and 0.003 (95% CI − 0.007 to 0.013) in the two external cohorts. Conclusions: Multivariable models based on first-24-hour ICU data retained useful discrimination across external cohorts and provided modest gains over simple GCS-based benchmarks. Routine coagulation markers alone were weak predictors and did not provide clearly supported incremental discrimination beyond broader clinical information. Cross-database transportability should be interpreted together with phenotype alignment and calibration.
Open AccessDevelopment and Cross-Database External Validation of 24-Hour Landmark Models for ICU Mortality After Intracerebral Hemorrhage: Incremental Value of Routine Coagulation Markers
Background: Intracerebral hemorrhage (ICH) is associated with high early mortality. Although routine coagulation markers are clinically relevant, their incremental value for mortality prediction beyond neurologic and physiologic information is uncertain. We developed and externally validated models using first-24-hour ICU data and evaluated the added predictive value of routine coagulation measurements. Methods: We used MIMIC-IV for model development and eICU-CRD for external validation. The development cohort included 2,669 adults with nontraumatic ICH and 388 ICU deaths. Logistic regression, random forest, and XGBoost were evaluated using a patient-level 70:30 holdout split and 5-fold stratified cross-validation. External validation used a high-specificity primary eICU cohort (396 patients; 39 deaths) and a broader secondary hemorrhagicstroke/likely-ICH cohort (1,555 patients; 168 deaths). Performance was assessed using AUROC, AUPRC, Brier score, calibration, and paired bootstrap comparisons. GCS-only and age-plus-GCS models served as clinical benchmarks. Coagulation-only, clinical-only, and combined XGBoost models were compared to assess incremental value. Results: In the internal holdout cohort, AUROCs were 0.870 for logistic regression, 0.859 for random forest, and 0.867 for XGBoost. In the primary external cohort, corresponding AUROCs were 0.804, 0.839, and 0.817; AUPRCs were 0.342, 0.419, and 0.406; and Brier scores were 0.080, 0.072, and 0.074. In the broader cohort, AUROCs were 0.826, 0.848, and 0.838. Random forest showed the numerically strongest external performance, but pairwise AUROC differences among multivariable models were not clearly supported. GCS-only achieved AUROCs of 0.780 and 0.813 in the primary and broader cohorts. Coagulationonly XGBoost showed weak discrimination (AUROC 0.598 internally, 0.598 primary external, and 0.566 broader external). Adding coagulation variables to the clinical model produced AUROC differences of 0.014 (95% CI − 0.009 to 0.037) and 0.003 (95% CI − 0.007 to 0.013) in the two external cohorts. Conclusions: Multivariable models based on first-24-hour ICU data retained useful discrimination across external cohorts and provided modest gains over simple GCS-based benchmarks. Routine coagulation markers alone were weak predictors and did not provide clearly supported incremental discrimination beyond broader clinical information. Cross-database transportability should be interpreted together with phenotype alignment and calibration.
- Open Access
Temporal Clinical Features for 24-Hour Landmark Prediction of In-Hospital Mortality in ICU Patients With Diabetic Neuropathy: A MIMIC-IV Study
Diabetic neuropathy is associated with substantial systemic disease burden, but short-term mortality risk among affected intensive care unit (ICU) patients remains difficult to characterize. We evaluated whether temporal information from the first 24 hours of ICU care improves post-landmark mortality prediction beyond severity scores and static clinical summaries. Patients aged > 18 years with diabetic neuropathy were identified in MIMIC-IV v3.1. A 24-hour landmark was used: only patients alive and still hospitalized at 24 hours were included, and the outcome was subsequent in-hospital death. The final cohort included 1,347 patients, including 83 deaths (6.16%). Data were divided into an 80% development set and a locked 20% test set. Feature selection, hyperparameter tuning, calibration, and threshold selection were restricted to development data. Logistic regression, random forest, and XGBoost were evaluated. Random forest had the highest development cross-validated PR-AUC and was selected for interpretation. On the locked test set, random forest achieved an AUROC of 0.851 (95% CI 0.765-0.924), PR-AUC of 0.339, and Brier score of 0.051; XGBoost and logistic regression achieved AUROCs of 0.847 and 0.806. In a post hoc strictly nested analysis, adding temporal predictors increased discrimination across all three algorithms; random-forest AUROC increased from 0.815 with severity and static predictors to 0.870 with the full temporal representation. First-day temporal information therefore showed additional prognostic value, but external validation is required before clinical use.
Open AccessTemporal Clinical Features for 24-Hour Landmark Prediction of In-Hospital Mortality in ICU Patients With Diabetic Neuropathy: A MIMIC-IV Study
Diabetic neuropathy is associated with substantial systemic disease burden, but short-term mortality risk among affected intensive care unit (ICU) patients remains difficult to characterize. We evaluated whether temporal information from the first 24 hours of ICU care improves post-landmark mortality prediction beyond severity scores and static clinical summaries. Patients aged > 18 years with diabetic neuropathy were identified in MIMIC-IV v3.1. A 24-hour landmark was used: only patients alive and still hospitalized at 24 hours were included, and the outcome was subsequent in-hospital death. The final cohort included 1,347 patients, including 83 deaths (6.16%). Data were divided into an 80% development set and a locked 20% test set. Feature selection, hyperparameter tuning, calibration, and threshold selection were restricted to development data. Logistic regression, random forest, and XGBoost were evaluated. Random forest had the highest development cross-validated PR-AUC and was selected for interpretation. On the locked test set, random forest achieved an AUROC of 0.851 (95% CI 0.765-0.924), PR-AUC of 0.339, and Brier score of 0.051; XGBoost and logistic regression achieved AUROCs of 0.847 and 0.806. In a post hoc strictly nested analysis, adding temporal predictors increased discrimination across all three algorithms; random-forest AUROC increased from 0.815 with severity and static predictors to 0.870 with the full temporal representation. First-day temporal information therefore showed additional prognostic value, but external validation is required before clinical use.
- Open Access
Interpretable machine learning prediction of in-hospital mortality in ICU patients with cancer and sepsis using first-day data: Development using MIMIC-IV and external validation in eICU-CRD
Background: Critically ill patients with cancer and sepsis have high in-hospital mortality, but externally validated prediction models are limited. Objective: To develop and externally validate an interpretable machine learning framework using first-day intensive care data. Methods: We used MIMIC-IV version 3.1 for development and internal validation and eICU-CRD for external validation. Eligible adults had cancer, an intensive care unit stay of at least 24 hours, and met a prespecified operational sepsis definition. The prediction landmark was 24 hours after admission. The MIMIC-IV cohort included 3,729 stays (training, n = 2, 983; internal validation, n = 746). Same-admission diagnosis-derived variables were excluded, and 345 predictors were retained. Fourteen predictive models and a dummy baseline were evaluated. Frozen pipelines and training-derived thresholds were applied to eICU-CRD without refitting or recalibration. Results: Gradient boosting was selected as the primary model and achieved an internal AUROC of 0.8480 (95% CI, 0.8173-0.8755), AUPRC of 0.6984, and Brier score of 0.1346. Important predictors included Glasgow Coma Scale components, temperature, lactate dehydrogenase, age, respiratory rate, oxygen saturation, blood urea nitrogen, and serum lactate. In eICU-CRD (n = 611), gradient boosting achieved an AUROC of 0.7483 (95% CI, 0.7026-0.7919), AUPRC of 0.6243, and Brier score of 0.1709. Random forest had the highest external AUROC in secondary comparisons (0.7731). Conclusions: First-day data supported useful internal discrimination, but performance declined under locked external validation. Multicenter validation, recalibration, threshold assessment, and prospective evaluation are required before clinical implementation.
Open AccessInterpretable machine learning prediction of in-hospital mortality in ICU patients with cancer and sepsis using first-day data: Development using MIMIC-IV and external validation in eICU-CRD
Background: Critically ill patients with cancer and sepsis have high in-hospital mortality, but externally validated prediction models are limited. Objective: To develop and externally validate an interpretable machine learning framework using first-day intensive care data. Methods: We used MIMIC-IV version 3.1 for development and internal validation and eICU-CRD for external validation. Eligible adults had cancer, an intensive care unit stay of at least 24 hours, and met a prespecified operational sepsis definition. The prediction landmark was 24 hours after admission. The MIMIC-IV cohort included 3,729 stays (training, n = 2, 983; internal validation, n = 746). Same-admission diagnosis-derived variables were excluded, and 345 predictors were retained. Fourteen predictive models and a dummy baseline were evaluated. Frozen pipelines and training-derived thresholds were applied to eICU-CRD without refitting or recalibration. Results: Gradient boosting was selected as the primary model and achieved an internal AUROC of 0.8480 (95% CI, 0.8173-0.8755), AUPRC of 0.6984, and Brier score of 0.1346. Important predictors included Glasgow Coma Scale components, temperature, lactate dehydrogenase, age, respiratory rate, oxygen saturation, blood urea nitrogen, and serum lactate. In eICU-CRD (n = 611), gradient boosting achieved an AUROC of 0.7483 (95% CI, 0.7026-0.7919), AUPRC of 0.6243, and Brier score of 0.1709. Random forest had the highest external AUROC in secondary comparisons (0.7731). Conclusions: First-day data supported useful internal discrimination, but performance declined under locked external validation. Multicenter validation, recalibration, threshold assessment, and prospective evaluation are required before clinical implementation.
- Open Access
First-24-hour machine learning for 30-day mortality prediction in ICU trauma patients: development in MIMIC-III and cross-database evaluation in MIMIC-IV
ICU trauma patients are clinically heterogeneous, and early mortality risk stratification may support monitoring and resource allocation. We developed machine learning models for 30-day mortality prediction using information recorded during the first 24 hours after ICU admission. In MIMIC-III, six feature configurations were trained using 3,411 patients and compared in a patient-level configuration-selection hold-out subset of 853 patients. The selected XGBoost configuration yielded an area under the precision–recall curve (AUPRC) of 0.556 and an area under the receiver operating characteristic curve (AUROC) of 0.863. For cross-database evaluation, a 228-predictor harmonized XGBoost model was refitted on the complete MIMIC-III cohort and evaluated in 13,747 MIMIC-IV ICU stays without using MIMIC-IV outcomes for model development or recalibration. It achieved an AUPRC of 0.495, an AUROC of 0.825, and a Brier score of 0.109. Calibration was monotonic but showed increasing overprediction at higher predicted risks. First-24-hour clinical information retained predictive value across MIMIC database versions, although internal configuration selection, model differences, same-center provenance, and incomplete feature-mapping documentation limit generalizability and deployment readiness.
Open AccessFirst-24-hour machine learning for 30-day mortality prediction in ICU trauma patients: development in MIMIC-III and cross-database evaluation in MIMIC-IV
ICU trauma patients are clinically heterogeneous, and early mortality risk stratification may support monitoring and resource allocation. We developed machine learning models for 30-day mortality prediction using information recorded during the first 24 hours after ICU admission. In MIMIC-III, six feature configurations were trained using 3,411 patients and compared in a patient-level configuration-selection hold-out subset of 853 patients. The selected XGBoost configuration yielded an area under the precision–recall curve (AUPRC) of 0.556 and an area under the receiver operating characteristic curve (AUROC) of 0.863. For cross-database evaluation, a 228-predictor harmonized XGBoost model was refitted on the complete MIMIC-III cohort and evaluated in 13,747 MIMIC-IV ICU stays without using MIMIC-IV outcomes for model development or recalibration. It achieved an AUPRC of 0.495, an AUROC of 0.825, and a Brier score of 0.109. Calibration was monotonic but showed increasing overprediction at higher predicted risks. First-24-hour clinical information retained predictive value across MIMIC database versions, although internal configuration selection, model differences, same-center provenance, and incomplete feature-mapping documentation limit generalizability and deployment readiness.
- Open Access
ICU Hour-24 Landmark Prediction of In-Hospital Mortality in Critically Ill Patients With Coronary Artery Disease: Development in MIMIC-IV and External Validation in eICU
Background: Retrospective intensive care unit prediction models are vulnerable to temporal leakage when predictors include information recorded after the intended prediction time. We developed and externally validated an ICU hour-24 landmark prediction pipeline for in-hospital mortality among critically ill patients with coronary artery disease using timestamp-restricted features from MIMIC-IV and eICU. Methods: Adults with coronary artery disease or coronary heart disease who were alive and remained under ICU observation at hour 24 were included. MIMIC-IV was used for model development, and eICU was reserved for external validation. Dynamic events were restricted to ICU admission through hour 24 in MIMIC-IV and offsets of 0–1440 minutes in eICU before aggregation. We evaluated an XGBoost model using baseline and respiratory-support predictors and a 102-predictor random forest using baseline, respiratory-support, and treatment predictors. Robustness was assessed across 30 repeated patient-grouped MIMIC-IV validation splits, and external uncertainty was estimated using 1,000 subject-clustered bootstrap resamples. Results: The MIMIC-IV cohort included 4,341 ICU stays with 993 deaths, and the eICU cohort included 19,464 stays with 2,237 deaths. In eICU, XGBoost achieved a ROC-AUC of 0.7973 (95% CI, 0.7878–0.8068), a PR-AUC (calculated as average precision) of 0.3627 (95% CI, 0.3423–0.3843), and a Brier score of 0.1189 (95% CI, 0.1164–0.1213). The random forest achieved a ROC-AUC of 0.8060 (95% CI, 0.7960–0.8154), a PR-AUC of 0.3687 (95% CI, 0.3471–0.3915), and a Brier score of 0.1032 (95% CI, 0.1012–0.1054). The random forest had a modestly higher ROC-AUC and lower Brier score than XGBoost. Mean validation ROC-AUCs across repeated MIMIC-IV splits were 0.7970 and 0.7954, respectively. Exploratory analyses suggested that narrower, consistently harmonized feature sets transported more reliably than broader expansions. Conclusions: Timestamp-restricted first-day models achieved external ROC-AUCs of approximately 0.80. However, external calibration remained imperfect, and local recalibration and prospective evaluation would be required before clinical use.
Open AccessICU Hour-24 Landmark Prediction of In-Hospital Mortality in Critically Ill Patients With Coronary Artery Disease: Development in MIMIC-IV and External Validation in eICU
Background: Retrospective intensive care unit prediction models are vulnerable to temporal leakage when predictors include information recorded after the intended prediction time. We developed and externally validated an ICU hour-24 landmark prediction pipeline for in-hospital mortality among critically ill patients with coronary artery disease using timestamp-restricted features from MIMIC-IV and eICU. Methods: Adults with coronary artery disease or coronary heart disease who were alive and remained under ICU observation at hour 24 were included. MIMIC-IV was used for model development, and eICU was reserved for external validation. Dynamic events were restricted to ICU admission through hour 24 in MIMIC-IV and offsets of 0–1440 minutes in eICU before aggregation. We evaluated an XGBoost model using baseline and respiratory-support predictors and a 102-predictor random forest using baseline, respiratory-support, and treatment predictors. Robustness was assessed across 30 repeated patient-grouped MIMIC-IV validation splits, and external uncertainty was estimated using 1,000 subject-clustered bootstrap resamples. Results: The MIMIC-IV cohort included 4,341 ICU stays with 993 deaths, and the eICU cohort included 19,464 stays with 2,237 deaths. In eICU, XGBoost achieved a ROC-AUC of 0.7973 (95% CI, 0.7878–0.8068), a PR-AUC (calculated as average precision) of 0.3627 (95% CI, 0.3423–0.3843), and a Brier score of 0.1189 (95% CI, 0.1164–0.1213). The random forest achieved a ROC-AUC of 0.8060 (95% CI, 0.7960–0.8154), a PR-AUC of 0.3687 (95% CI, 0.3471–0.3915), and a Brier score of 0.1032 (95% CI, 0.1012–0.1054). The random forest had a modestly higher ROC-AUC and lower Brier score than XGBoost. Mean validation ROC-AUCs across repeated MIMIC-IV splits were 0.7970 and 0.7954, respectively. Exploratory analyses suggested that narrower, consistently harmonized feature sets transported more reliably than broader expansions. Conclusions: Timestamp-restricted first-day models achieved external ROC-AUCs of approximately 0.80. However, external calibration remained imperfect, and local recalibration and prospective evaluation would be required before clinical use.
- Open Access
Optimally Predicting Mortality in Patients with Abdominal Aortic Aneurysms
Abdominal aortic aneurysm (AAA) patients in the intensive care unit (ICU) form a high-risk population whose mortality risk evolves across clinical phases. Existing tools rely largely on Cox proportional hazards nomograms with narrow predictor sets and single horizons, leaving the value of machine learning, extended features, and external generalizability uncharacterized. We extracted an ICD-coded AAA ICU cohort from MIMIC-IV v2.2 (858 patients with complete six-predictor admission data) using a 24-hour window. An extended set added hemodynamic, laboratory, and comorbidity variables via LASSO and support vector machine recursive feature elimination. Six models (Cox proportional hazards, logistic regression, random forest, gradient boosting, XGBoost, multilayer perceptron) were trained on a 70% split and evaluated at 7, 14, and 28 days by discrimination, calibration, and Shapley additive explanations, with external validation on a harmonized eICU-CRD cohort. In-hospital mortality was 11.8%. Logistic regression led on the six-predictor set (7-day area under the curve 0.866; 14-day 0.872); random forest achieved the best 28-day extended-set value (0.892). The multilayer perceptron underperformed throughout; external validation attenuated as expected (best 7-day 0.771). Anion gap, blood urea nitrogen, and age were the leading contributors. Regularized models excel under data scarcity, while tree ensembles gain advantage as features and horizons expand.
Open AccessOptimally Predicting Mortality in Patients with Abdominal Aortic Aneurysms
Abdominal aortic aneurysm (AAA) patients in the intensive care unit (ICU) form a high-risk population whose mortality risk evolves across clinical phases. Existing tools rely largely on Cox proportional hazards nomograms with narrow predictor sets and single horizons, leaving the value of machine learning, extended features, and external generalizability uncharacterized. We extracted an ICD-coded AAA ICU cohort from MIMIC-IV v2.2 (858 patients with complete six-predictor admission data) using a 24-hour window. An extended set added hemodynamic, laboratory, and comorbidity variables via LASSO and support vector machine recursive feature elimination. Six models (Cox proportional hazards, logistic regression, random forest, gradient boosting, XGBoost, multilayer perceptron) were trained on a 70% split and evaluated at 7, 14, and 28 days by discrimination, calibration, and Shapley additive explanations, with external validation on a harmonized eICU-CRD cohort. In-hospital mortality was 11.8%. Logistic regression led on the six-predictor set (7-day area under the curve 0.866; 14-day 0.872); random forest achieved the best 28-day extended-set value (0.892). The multilayer perceptron underperformed throughout; external validation attenuated as expected (best 7-day 0.771). Anion gap, blood urea nitrogen, and age were the leading contributors. Regularized models excel under data scarcity, while tree ensembles gain advantage as features and horizons expand.
- Open Access
- 6 July 2026
- Published by Elsevier in Informatics in Medicine Unlocked
- Vol. 64
Retrospective machine learning approach for forecasting in-hospital death in ICU patients after cardiac arrest
- 6 July 2026
- Published by Elsevier in Informatics in Medicine Unlocked
- Vol. 64
Open AccessRetrospective machine learning approach for forecasting in-hospital death in ICU patients after cardiac arrest
- Open Access
Temporal Feature Engineering and Ensemble Learning for Predicting 28-Day Mortality in ICU Patients with Alcoholic Cirrhosis
Background: Predicting 28-day mortality in ICU patients with alcoholic cirrhosis is challenging because clinical deterioration is dynamic and heterogeneous. Methods: Using MIMIC-IV (v3.1), this study included 1,907 patients (training n = 1,334; validation n = 573), engineering 208 temporal and static predictors from 64 base variables and reducing them to 40 through multi-stage selection. Seven classifiers and a weighted gradient-boosting ensemble (XGBoost, CatBoost, LightGBM) were compared with Optuna tuning. Results: The ensemble achieved the highest internal validation AUC (0.9276; 95% CI: 0.9011-0.9507) and lowest Brier score (0.0870), with strong discrimination on eICU-CRD (AUC 0.9347) and related MIMIC-III (AUC 0.9071). Ablation indicated that temporal features, especially deltas, were major contributors (∆AUC ≈ 0.17 when removed). SHAP highlighted APS III score, anion gap, oxygen saturation (delta), lactate, and INR as leading predictors. Conclusions: The framework supports interpretable, trajectory-informed risk stratification in critically ill cirrhotic patients; prospective validation is needed before clinical use.
Open AccessTemporal Feature Engineering and Ensemble Learning for Predicting 28-Day Mortality in ICU Patients with Alcoholic Cirrhosis
Background: Predicting 28-day mortality in ICU patients with alcoholic cirrhosis is challenging because clinical deterioration is dynamic and heterogeneous. Methods: Using MIMIC-IV (v3.1), this study included 1,907 patients (training n = 1,334; validation n = 573), engineering 208 temporal and static predictors from 64 base variables and reducing them to 40 through multi-stage selection. Seven classifiers and a weighted gradient-boosting ensemble (XGBoost, CatBoost, LightGBM) were compared with Optuna tuning. Results: The ensemble achieved the highest internal validation AUC (0.9276; 95% CI: 0.9011-0.9507) and lowest Brier score (0.0870), with strong discrimination on eICU-CRD (AUC 0.9347) and related MIMIC-III (AUC 0.9071). Ablation indicated that temporal features, especially deltas, were major contributors (∆AUC ≈ 0.17 when removed). SHAP highlighted APS III score, anion gap, oxygen saturation (delta), lactate, and INR as leading predictors. Conclusions: The framework supports interpretable, trajectory-informed risk stratification in critically ill cirrhotic patients; prospective validation is needed before clinical use.
- Open Access
- 30 March 2026
- Published by MDPI AG in BioMedInformatics
- Vol. 6 (2) , 17
Machine Learning-Based Prediction of Mortality in Geriatric Traumatic Brain Injury Patients
Traumatic Brain Injury (TBI) is a major contributor to mortality among older adults, with geriatric patients facing disproportionately high risk due to age-related physiological vulnerability and comorbidities. Early and accurate prediction of mortality is essential for guiding clinical decision-making and optimizing ICU resource allocation. In this study, we utilized the MIMIC-III database and identified a final analytic cohort of 667 geriatric TBI patients, on which we developed a machine learning framework for 30-day mortality prediction. A rigorous preprocessing pipeline—including Random Forest-based imputation, feature engineering, and hybrid selection—was implemented to refine predictors from 69 to 9 clinically meaningful variables. CatBoost emerged as the top-performing model, achieving an AUROC of 0.867 (95% CI: 0.809–0.922), with a sensitivity of 0.752 and a specificity of 0.888 on the independent test set. SHAP analysis confirmed the importance of the GCS score, oxygen saturation, and prothrombin time as dominant predictors. These findings highlight the potential value of interpretable machine learning tools for early mortality risk stratification in elderly TBI patients and support further validation for future clinical use.
- 30 March 2026
- Published by MDPI AG in BioMedInformatics
- Vol. 6 (2) , 17
Open AccessMachine Learning-Based Prediction of Mortality in Geriatric Traumatic Brain Injury Patients
Traumatic Brain Injury (TBI) is a major contributor to mortality among older adults, with geriatric patients facing disproportionately high risk due to age-related physiological vulnerability and comorbidities. Early and accurate prediction of mortality is essential for guiding clinical decision-making and optimizing ICU resource allocation. In this study, we utilized the MIMIC-III database and identified a final analytic cohort of 667 geriatric TBI patients, on which we developed a machine learning framework for 30-day mortality prediction. A rigorous preprocessing pipeline—including Random Forest-based imputation, feature engineering, and hybrid selection—was implemented to refine predictors from 69 to 9 clinically meaningful variables. CatBoost emerged as the top-performing model, achieving an AUROC of 0.867 (95% CI: 0.809–0.922), with a sensitivity of 0.752 and a specificity of 0.888 on the independent test set. SHAP analysis confirmed the importance of the GCS score, oxygen saturation, and prothrombin time as dominant predictors. These findings highlight the potential value of interpretable machine learning tools for early mortality risk stratification in elderly TBI patients and support further validation for future clinical use.