Diagnosis and classification of arrhythmia, which is associated with abnormal electrical activities in the heart, are critical for clinical treatments. Previous studies focused on the diagnosis of atrial fibrillation, which is the most common arrhythmia in adults. The classification performance achieved by studies on other arrhythmia types is not satisfactory for clinical use owing to the small number of classes (minority classes). In this study, we propose a novel framework for automatic classification that combines a residual network with a squeeze-and-excitation block and a bidirectional long short-term memory. Eight-, four-, and two-class performances were evaluated on the MIT-BIH arrhythmia database (MITDB), the MIT-BIH atrial fibrillation database (AFDB), and the PhysioNet/Computing in the cardiology challenge 2017 database (CinC DB), respectively, and they were superior to the performance achieved by conventional methods. In addition, the classwise F1-score in the minority classes was higher than those of the methods adopted in existing studies. To measure the generalization ability of the proposed framework, AFDB and CinC DB were tested using an MITDB-trained model, and superior performance was achieved compared with ShallowConvNet and DeepConvNet. We performed a cross-subject experiment using AFDB and obtained a statistically higher performance using the proposed method compared with typical machine learning methods. The proposed framework can enable the direct diagnosis of arrhythmia types in clinical trials based on the accurate detection of the minority class.

Background: Cardiac arrest (CA) is one of the leading causes of death among patients in the intensive care unit (ICU). Although many CA prediction models with high sensitivity have been developed to anticipate CA, their practical application has been challenging due to a lack of generalization and validation. Additionally, the heterogeneity among patients in different ICU subtypes has not been adequately addressed. Objective: This study aims to propose a clinically interpretable ensemble approach for the timely and accurate prediction of CA within 24 hours, regardless of patient heterogeneity, including variations across different populations and ICU subtypes. Additionally, we conducted patient-independent evaluations to emphasize the model’s generalization performance and analyzed interpretable results that can be readily adopted by clinicians in real-time. Methods: Patients were retrospectively analyzed using data from the Medical Information Mart for Intensive Care-IV (MIMIC-IV) and the eICU-Collaborative Research Database (eICU-CRD). To address the problem of underperformance, we constructed our framework using feature sets based on vital signs, multiresolution statistical analysis, and the Gini index, with a 12-hour window to capture the unique characteristics of CA. We extracted 3 types of features from each database to compare the performance of CA prediction between high-risk patient groups from MIMIC-IV and patients without CA from eICU-CRD. After feature extraction, we developed a tabular network (TabNet) model using feature screening with cost-sensitive learning. To assess real-time CA prediction performance, we used 10-fold leave-one-patient-out cross-validation and a cross–data set method. We evaluated MIMIC-IV and eICU-CRD across different cohort populations and subtypes of ICU within each database. Finally, external validation using the eICU-CRD and MIMIC-IV databases was conducted to assess the model’s generalization ability. The decision mask of the proposed method was used to capture the interpretability of the model. Results: The proposed method outperformed conventional approaches across different cohort populations in both MIMIC-IV and eICU-CRD. Additionally, it achieved higher accuracy than baseline models for various ICU subtypes within both databases. The interpretable prediction results can enhance clinicians’ understanding of CA prediction by serving as a statistical comparison between non-CA and CA groups. Next, we tested the eICU-CRD and MIMIC-IV data sets using models trained on MIMIC-IV and eICU-CRD, respectively, to evaluate generalization ability. The results demonstrated superior performance compared with baseline models. Conclusions: Our novel framework for learning unique features provides stable predictive power across different ICU environments. Most of the interpretable global information reveals statistical differences between CA and non-CA groups, demonstrating its utility as an indicator for clinical decisions. Consequently, the proposed CA prediction system is a clinically validated algorithm that enables clinicians to intervene early based on CA prediction information and can be applied to clinical trials in digital health.

Background: Cardiac arrest (CA) is the leading cause of death in critically ill patients. Clinical research has shown that early identification of CA reduces mortality. Algorithms capable of predicting CA with high sensitivity have been developed using multivariate time series data. However, these algorithms suffer from a high rate of false alarms, and their results are not clinically interpretable. Objective: We propose an ensemble approach using multiresolution statistical features and cosine similarity–based features for the timely prediction of CA. Furthermore, this approach provides clinically interpretable results that can be adopted by clinicians. Methods: Patients were retrospectively analyzed using data from the Medical Information Mart for Intensive Care-IV database and the eICU Collaborative Research Database. Based on the multivariate vital signs of a 24-hour time window for adults diagnosed with heart failure, we extracted multiresolution statistical and cosine similarity–based features. These features were used to construct and develop gradient boosting decision trees. Therefore, we adopted cost-sensitive learning as a solution. Then, 10-fold cross-validation was performed to check the consistency of the model performance, and the Shapley additive explanation algorithm was used to capture the overall interpretability of the proposed model. Next, external validation using the eICU Collaborative Research Database was performed to check the generalization ability. Results: The proposed method yielded an overall area under the receiver operating characteristic curve (AUROC) of 0.86 and area under the precision-recall curve (AUPRC) of 0.58. In terms of the timely prediction of CA, the proposed model achieved an AUROC above 0.80 for predicting CA events up to 6 hours in advance. The proposed method simultaneously improved precision and sensitivity to increase the AUPRC, which reduced the number of false alarms while maintaining high sensitivity. This result indicates that the predictive performance of the proposed model is superior to the performances of the models reported in previous studies. Next, we demonstrated the effect of feature importance on the clinical interpretability of the proposed method and inferred the effect between the non-CA and CA groups. Finally, external validation was performed using the eICU Collaborative Research Database, and an AUROC of 0.74 and AUPRC of 0.44 were obtained in a general intensive care unit population. Conclusions: The proposed framework can provide clinicians with more accurate CA prediction results and reduce false alarm rates through internal and external validation. In addition, clinically interpretable prediction results can facilitate clinician understanding. Furthermore, the similarity of vital sign changes can provide insights into temporal pattern changes in CA prediction in patients with heart failure–related diagnoses. Therefore, our system is sufficiently feasible for routine clinical use. In addition, regarding the proposed CA prediction system, a clinically mature application has been developed and verified in the future digital health field.

Background: The prediction of successful weaning from mechanical ventilation (MV) in advance of intubation can facilitate discussions regarding end-of-life care before unnecessary intubation. Objective: We aimed to develop a machine learning–based model that predicts successful weaning from ventilator support based on routine clinical and laboratory data taken before or immediately after intubation. Methods: We used the Medical Information Mart for Intensive Care IV database, which is an open-access database covering 524,740 admissions of 382,278 patients in Beth Israel Deaconess Medical Center, United States, from 2008 to 2019. We selected adult patients who underwent MV in the intensive care unit (ICU). Clinical and laboratory variables that are considered relevant to the prognosis of the patient in the ICU were selected. Data collected before or within 24 hours of intubation were used to develop machine learning models that predict the probability of successful weaning within 14 days of ventilator support. Developed models were integrated into an ensemble model. Performance metrics were calculated by 5-fold cross-validation for each model, and a permutation feature importance and Shapley additive explanations analysis was conducted to better understand the impacts of individual variables on outcome prediction. Results: Of the 23,242 patients, 19,025 (81.9%) patients were successfully weaned from MV within 14 days. Using the preselected 46 clinical and laboratory variables, the area under the receiver operating characteristic curve of CatBoost classifier, random forest classifier, and regularized logistic regression classifier models were 0.860 (95% CI 0.852-0.868), 0.855 (95% CI 0.848-0.863), and 0.823 (95% CI 0.813-0.832), respectively. Using the ensemble voting classifier using the 3 models above, the final model revealed the area under the receiver operating characteristic curve of 0.861 (95% CI 0.853-0.869), which was significantly better than that of Simplified Acute Physiology Score II (0.749, 95% CI 0.742-0.756) and Sequential Organ Failure Assessment (0.588, 95% CI 0.566-0.609). The top features included lactate and anion gap. The model’s performance achieved a plateau with approximately the top 21 variables. Conclusions: We developed machine learning algorithms that can predict successful weaning from MV in advance to intubation in the ICU. Our models can aid the appropriate management for patients who hesitate to decide on ventilator support or meaningless end-of-life care.

Clinical decision support systems (CDSSs) have been widely utilized to support the decisions made by cardiologists when detecting and classifying arrhythmia from electrocardiograms. However, forming a CDSS for the arrhythmia classification task is challenging due to the varying lengths of arrhythmias. Although the onset time of arrhythmia varies, previously developed methods have not considered such conditions. Thus, we propose a framework that consists of 1) local and global extraction and 2) local-global information fusion with attention to enable arrhythmia detection and classification within a constrained input length. The framework’s performance was evaluated in terms of 10-class and 4-class arrhythmia detection, focusing on identifying the onset and ending point of arrhythmia episodes and their duration using the MIT-BIH arrhythmia database (MITDB) and the MIT-BIH atrial fibrillation database (AFDB). Duration, episode, and Dice score performances resulted in overall F1-scores of 96.45%, 82.05%, and 96.31% on the MITDB and 97.57%, 98.31%, and 97.45% on the AFDB, respectively. The results demonstrated statistically superior performance compared to those of the benchmark models. To assess the generalization capability of the proposed method, an MITDB-trained model and MIT-BIH malignant ventricular arrhythmia database-trained model were tested AFDB and MITDB, respectively. Superior performance was attained compared with that of a state-of-the-art model. The proposed method effectively captures both local and global information and dynamics without significant information loss. Consequently, arrhythmias can be detected with greater accuracy, and their occurrence times can be precisely determined, enabling the clinical field to develop more accurate treatment plans based on the proposed method.

Cancer remains a leading cause of mortality worldwide. Chemotherapy is effective but can cause febrile neutropenia, deplete neutrophils, and increase infection risk. Although timely fever detection is critical to prevent complications, periodic temperature monitoring has inherent limitations. Wearable devices (WDs) for real-time body temperature (RBT) monitoring are emerging as tools for early fever detection, though their clinical feasibility and usability remain unverified. This study assessed the clinical feasibility of a novel WD by comparing its temperature concordance and fever detection capability against a standard reference in patients with cancer. The RBT system’s clinical maturity, including its capacity for early fever detection and monitoring treatment-related changes, was evaluated. Furthermore, satisfaction among clinicians and patients was analyzed in a hospital setting. In this prospective study, patients with hematologic malignancies at high infection risk admitted to the Chonnam National University in Hwasun Hospital, South Korea, were enrolled. Data from 47 patients were analyzed to compare MT100D as WD (SEERS Technology Co., Ltd., South Korea) readings with axillary thermometers. Temperature concordance was evaluated using the intraclass correlation coefficient (ICC), and diagnostic performance was compared with the reference thermometer. The early fever detection performance of the MT100D was analyzed to evaluate the clinical effectiveness of the early response system. Usability was evaluated through a five-point Likert scale survey completed by clinical nurses. The MT100D demonstrated good agreement with the reference thermometer (mean difference: −0.19 ± 0.35 °C; ICC: 0.78). The RBT system achieved sensitivity, specificity, and area under the receiver operating characteristic curve values of 81.50%, 96.32%, and 96.60%, respectively. The early fever detection rate was 77.1%, with the RBT system detecting fever an average of 1.13 ± 1.28 h earlier than the reference. Usability and satisfaction assessments showed high patient satisfaction (mean 4.69 ± 0.5; range 4.57–4.80) and moderate clinician satisfaction (mean 3.63 ± 0.75; range 2.89–4.11). Among patients with cancer, including those at risk of febrile neutropenia, the MT100D demonstrated strong concordance with standard thermometry, enabling early fever detection. The RBT system shows promise for the early identification of neutropenic risk during chemotherapy.