OBJECTIVE: Real-world data encompass population diversity, enabling insights into chronic disease mortality risk among the elderly. Deep learning excels on large datasets, offering promise for real-world data. However, current models focus on single diseases, neglecting comorbidities prevalent in patients. Moreover, mortality is infrequent compared to illness, causing extreme class imbalance that impedes reliable prediction. We aim to develop a deep learning framework that accurately forecasts mortality risk from real-world data by addressing comorbidities and class imbalance.
METHODS: We integrated multi-task and cost-sensitive learning, developing an enhanced deep neural network architecture that extends multi-task learning to predict mortality risk across multiple chronic diseases. Each patient cohort with a chronic disease was assigned to a separate task, with shared lower-level parameters capturing inter-disease complexities through distinct top-level networks. Cost-sensitive functions were incorporated to ensure learning of positive class characteristics for each task and achieve accurate prediction of the risk of death from multiple chronic diseases.
RESULTS: Our study covers 15 prevalent chronic diseases and is experimented with real-world data from 482,145 patients (including 9,516 deaths) in Shenzhen, China. The proposed model is compared with six models including three machine learning models: logistic regression, XGBoost, and CatBoost, and three state-of-the-art deep learning models: 1D-CNN, TabNet, and Saint. The experimental results show that, compared with the other compared algorithms, MTL-CSDNN has better prediction results on the test set (ACC=0.99, REC=0.99, PRAUC=0.97, MCC=0.98, G-means = 0.98).
CONCLUSIONS: Our method provides valuable insights into leveraging real-world data for precise multi-disease mortality risk prediction, offering potential applications in optimizing chronic disease management, enhancing well-being, and reducing healthcare costs for the elderly population.

UNASSIGNED: The mortality rate from pulmonary tuberculosis (PTB) complicated by severe community-acquired pneumonia (SCAP) in the intensive care unit (ICU) remains high. We aimed to develop a rapid and simple model for the early assessment and stratification of prognosis in these patients.
UNASSIGNED: All adult patients with PTB complicated by SCAP admitted to the ICU of a tertiary hospital in Chengdu, Sichuan, China between 2019 and 2021 (development cohort) and 2022 (validation cohort) were retrospectively included. Data on demographics, comorbidities, laboratory values, and interventions were collected. The outcome was the 28-day mortality. Stepwise backward multivariate Cox analysis was used to develop a mortality risk prediction score model. Receiver operating characteristic (ROC) and calibration curves were used to evaluate the model\'s predictive efficiency. Decision curve analysis (DCA) was used to validate the model\'s clinical value and impact on decision making.
UNASSIGNED: Overall, 357 and 168 patients were included in the development and validation cohorts, respectively. The Pulmonary Tuberculosis Severity Index (PTSI) score included long-term use of glucocorticoid, body mass index (BMI) <18.5 kg/m2, diabetes, blood urea nitrogen (BUN) ≥7.14 mmol/L, PO2/FiO2 <150 mmHg, and vasopressor use. The area under the ROC curve (AUC) values were 0.817 (95% CI: 0.772-0.863) and 0.814 for the development and validation cohorts, respectively. The PTSI score had a higher AUC than the APACHE II, SOFA, and CURB-65 score. The calibration curves indicated good calibration in both cohorts. The DCA of the PTSI score indicated the high clinical application of the model compared with the APACHE II and SOFA scores.
UNASSIGNED: This prognostic tool was designed to rapidly evaluate the 28-day mortality risk in individuals with PTB complicated by SCAP. It can stratify this patient group into relevant risk categories, guide targeted interventions, and enhance clinical decision making, thereby optimizing patient care and improving outcomes.

Hemodialysis (HD) is the main treatment for end-stage renal disease with high mortality and heavy economic burdens. Predicting the mortality risk in patients undergoing maintenance HD and identifying high-risk patients are critical to enable early intervention and improve quality of life. In this study, we proposed a two-stage protocol based on electronic health record (EHR) data to predict mortality risk of maintenance HD patients. First, we developed a multilayer perceptron (MLP) model to predict mortality risk. Second, an Active Contrastive Learning (ACL) method was proposed to select sample pairs and optimize the representation space to improve the prediction performance of the MLP model. Our ACL method outperforms other methods and has an average F1-score of 0.820 and an average area under the receiver operating characteristic curve of 0.853. This work is generalizable to analyses of cross-sectional EHR data, while this two-stage approach can be applied to other diseases as well.

BACKGROUND: Mortality risk prediction is to predict whether a patient has the risk of death based on relevant diagnosis and treatment data. How to accurately predict patient mortality risk based on electronic health records (EHR) is currently a hot research topic in the healthcare field. In actual medical datasets, there are often many missing values, which can seriously interfere with the effect of model prediction. However, when missing values are interpolated, most existing methods do not take into account the fidelity or confidence of the interpolated values. Misestimation of missing variables can lead to modeling difficulties and performance degradation, while the reliability of the model may be compromised in clinical environments.
METHODS: We propose a model based on Missing Value Imputation and Reliability Assessment for mortality risk prediction (MVIRA). The model uses a combination of variational autoencoder and recurrent neural networks to complete the interpolation of missing values and enhance the characterization ability of EHR data, thus improving the performance of mortality risk prediction. In addition, we also introduce the Monte Carlo Dropout method to calculate the uncertainty of the model prediction results and thus achieve the reliability assessment of the model.
RESULTS: We perform performance validation of the model on the public datasets MIMIC-III and MIMIC-IV. The proposed model showed improved performance compared with competitive models in terms of overall specialties.
CONCLUSIONS: The proposed model can effectively improve the accuracy of mortality risk prediction, and can help medical institutions assess the condition of patients.

BACKGROUND: A high mortality rate has always been observed in patients with severe community-acquired pneumonia (SCAP) admitted to the intensive care unit (ICU); however, there are few reported predictive models regarding the prognosis of this group of patients. This study aimed to screen for risk factors and assign a useful nomogram to predict mortality in these patients.
METHODS: As a developmental cohort, we used 455 patients with SCAP admitted to ICU. Logistic regression analyses were used to identify independent risk factors for death. A mortality prediction model was built based on statistically significant risk factors. Furthermore, the model was visualized using a nomogram. As a validation cohort, we used 88 patients with SCAP admitted to ICU of another hospital. The performance of the nomogram was evaluated by analysis of the area under the receiver operating characteristic (ROC) curve (AUC), calibration curve analysis, and decision curve analysis (DCA).
RESULTS: Lymphocytes, PaO2/FiO2, shock, and APACHE II score were independent risk factors for in-hospital mortality in the development cohort. External validation results showed a C-index of 0.903 (95% CI 0.838-0.968). The AUC of model for the development cohort was 0.85, which was better than APACHE II score 0.795 and SOFA score 0.69. The AUC for the validation cohort was 0.893, which was better than APACHE II score 0.746 and SOFA score 0.742. Calibration curves for both cohorts showed agreement between predicted and actual probabilities. The results of the DCA curves for both cohorts indicated that the model had a high clinical application in comparison to APACHE II and SOFA scoring systems.
CONCLUSIONS: We developed a predictive model based on lymphocytes, PaO2/FiO2, shock, and APACHE II scores to predict in-hospital mortality in patients with SCAP admitted to the ICU. The model has the potential to help physicians assess the prognosis of this group of patients.

UNASSIGNED: We attempted to establish a model for predicting the mortality risk of sepsis patients during hospitalization.
UNASSIGNED: Data on patients with sepsis were collected from a clinical record mining database, who were hospitalized at the Affiliated Dongyang Hospital of Wenzhou Medical University between January 2013 and August 2022. These included patients were divided into modeling and validation groups. In the modeling group, the independent risk factors of death during hospitalization were determined using univariate and multi-variate regression analyses. After stepwise regression analysis (both directions), a nomogram was drawn. The discrimination ability of the model was evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve, and the GiViTI calibration chart assessed the model calibration. The Decline Curve Analysis (DCA) was performed to evaluate the clinical effectiveness of the prediction model. Among the validation group, the logistic regression model was compared to the models established by the SOFA scoring system, random forest method, and stacking method.
UNASSIGNED: A total of 1740 subjects were included in this study, 1218 in the modeling population and 522 in the validation population. The results revealed that serum cholinesterase, total bilirubin, respiratory failure, lactic acid, creatinine, and pro-brain natriuretic peptide were the independent risk factors of death. The AUC values in the modeling group and validation group were 0.847 and 0.826. The P values of calibration charts in the two population sets were 0.838 and 0.771. The DCA curves were above the two extreme curves. Moreover, the AUC values of the models established by the SOFA scoring system, random forest method, and stacking method in the validation group were 0.777, 0.827, and 0.832, respectively.
UNASSIGNED: The nomogram model established by combining multiple risk factors could effectively predict the mortality risk of sepsis patients during hospitalization.

Risk prediction models are fundamental to effectively triage incoming COVID-19 patients. However, current triaging methods often have poor predictive performance, are based on variables that are expensive to measure, and often lead to hard-to-interpret decisions. We introduce two new classification methods that can predict COVID-19 mortality risk from the automatic analysis of routine clinical variables with high accuracy and interpretability. SVM22-GASS and Clinical-GASS classifiers leverage machine learning methods and clinical expertise, respectively. Both were developed using a derivation cohort of 499 patients from the first wave of the pandemic and were validated with an independent validation cohort of 250 patients from the second pandemic phase. The Clinical-GASS classifier is a threshold-based classifier that leverages the General Assessment of SARS-CoV-2 Severity (GASS) score, a COVID-19-specific clinical score that recently showed its effectiveness in predicting the COVID-19 mortality risk. The SVM22-GASS model is a binary classifier that non-linearly processes clinical data using a Support Vector Machine (SVM). In this study, we show that SMV22-GASS was able to predict the mortality risk of the validation cohort with an AUC of 0.87 and an accuracy of 0.88, better than most scores previously developed. Similarly, the Clinical-GASS classifier predicted the mortality risk of the validation cohort with an AUC of 0.77 and an accuracy of 0.78, on par with other established and emerging machine-learning-based methods. Our results demonstrate the feasibility of accurate COVID-19 mortality risk prediction using only routine clinical variables, readily collected in the early stages of hospital admission.

BACKGROUND: Accurate precision approaches have far not been developed for modeling mortality risk in intensive care unit (ICU) patients. Conventional mortality risk prediction methods can hardly extract the information in longitudinal electronic medical records (EHRs) effectively, since they simply aggregate the heterogeneous variables in EHRs, ignoring the complex relationship and interactions between variables and the time dependence in longitudinal records. Recently deep learning approaches have been widely used in modeling longitudinal EHR data. However, most existing deep learning-based risk prediction approaches only use the information of a single disease, neglecting the interactions between multiple diseases and different conditions.
RESULTS: In this paper, we address this unmet need by leveraging disease and treatment information in EHRs to develop a mortality risk prediction model based on deep learning (DeepMPM). DeepMPM utilizes a two-level attention mechanism, i.e. visit-level and variable-level attention, to derive the representation of patient risk status from patient\'s multiple longitudinal medical records. Benefiting from using EHR of patients with multiple diseases and different conditions, DeepMPM can achieve state-of-the-art performances in mortality risk prediction.
CONCLUSIONS: Experiment results on MIMIC III database demonstrates that with the disease and treatment information DeepMPM can achieve a good performance in terms of Area Under ROC Curve (0.85). Moreover, DeepMPM can successfully model the complex interactions between diseases to achieve better representation learning of disease and treatment than other deep learning approaches, so as to improve the accuracy of mortality prediction. A case study also shows that DeepMPM offers the potential to provide users with insights into feature correlation in data as well as model behavior for each prediction.

The widespread secondary use of electronic medical records (EMRs) promotes health care quality improvement. Representation learning that can automatically extract hidden information from EMR data has gained increasing attention.
We aimed to propose a patient representation with more feature associations and task-specific feature importance to improve the outcome prediction performance for inpatients with acute myocardial infarction (AMI).
Medical concepts, including patients\' age, gender, disease diagnoses, laboratory tests, structured radiological features, procedures, and medications, were first embedded into real-value vectors using the improved skip-gram algorithm, where concepts in the context windows were selected by feature association strengths measured by association rule confidence. Then, each patient was represented as the sum of the feature embeddings weighted by the task-specific feature importance, which was applied to facilitate predictive model prediction from global and local perspectives. We finally applied the proposed patient representation into mortality risk prediction for 3010 and 1671 AMI inpatients from a public data set and a private data set, respectively, and compared it with several reference representation methods in terms of the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), and F1-score.
Compared with the reference methods, the proposed embedding-based representation showed consistently superior predictive performance on the 2 data sets, achieving mean AUROCs of 0.878 and 0.973, AUPRCs of 0.220 and 0.505, and F1-scores of 0.376 and 0.674 for the public and private data sets, respectively, while the greatest AUROCs, AUPRCs, and F1-scores among the reference methods were 0.847 and 0.939, 0.196 and 0.283, and 0.344 and 0.361 for the public and private data sets, respectively. Feature importance integrated in patient representation reflected features that were also critical in prediction tasks and clinical practice.
The introduction of feature associations and feature importance facilitated an effective patient representation and contributed to prediction performance improvement and model interpretation.

The increase in coronavirus disease 2019 (COVID-19) infection caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has placed pressure on healthcare services worldwide. Therefore, it is crucial to identify critical factors for the assessment of the severity of COVID-19 infection and the optimization of an individual treatment strategy. In this regard, the present study leverages a dataset of blood samples from 485 COVID-19 individuals in the region of Wuhan, China to identify essential blood biomarkers that predict the mortality of COVID-19 individuals. For this purpose, a hybrid of filter, statistical, and heuristic-based feature selection approach was used to select the best subset of informative features. As a result, minimum redundancy maximum relevance (mRMR), a two-tailed unpaired t-test, and whale optimization algorithm (WOA) were eventually selected as the three most informative blood biomarkers: International normalized ratio (INR), platelet large cell ratio (P-LCR), and D-dimer. In addition, various machine learning (ML) algorithms (random forest (RF), support vector machine (SVM), extreme gradient boosting (EGB), naïve Bayes (NB), logistic regression (LR), and k-nearest neighbor (KNN)) were trained. The performance of the trained models was compared to determine the model that assist in predicting the mortality of COVID-19 individuals with higher accuracy, F1 score, and area under the curve (AUC) values. In this paper, the best performing RF-based model built using the three most informative blood parameters predicts the mortality of COVID-19 individuals with an accuracy of 0.96 ± 0.062, F1 score of 0.96 ± 0.099, and AUC value of 0.98 ± 0.024, respectively on the independent test data. Furthermore, the performance of our proposed RF-based model in terms of accuracy, F1 score, and AUC was significantly better than the known blood biomarkers-based ML models built using the Pre_Surv_COVID_19 data. Therefore, the present study provides a novel hybrid approach to screen the most informative blood biomarkers to develop an RF-based model, which accurately and reliably predicts in-hospital mortality of confirmed COVID-19 individuals, during surge periods. An application based on our proposed model was implemented and deployed at Heroku.