Background Heart failure (HF) is a common disease and a major public health problem. HF mortality prediction is critical for developing individualized prevention and treatment plans. However, due to their lack of interpretability, most HF mortality prediction models have not yet reached clinical practice. Objective We aimed to develop an interpretable model to predict the mortality risk for patients with HF in intensive care units (ICUs) and used the SHapley Additive exPlanation (SHAP) method to explain the extreme gradient boosting (XGBoost) model and explore prognostic factors for HF. Methods In this retrospective cohort study, we achieved model development and performance comparison on the eICU Collaborative Research Database (eICU-CRD). We extracted data during the first 24 hours of each ICU admission, and the data set was randomly divided, with 70% used for model training and 30% used for model validation. The prediction performance of the XGBoost model was compared with three other machine learning models by the area under the curve. We used the SHAP method to explain the XGBoost model. Results A total of 2798 eligible patients with HF were included in the final cohort for this study. The observed in-hospital mortality of patients with HF was 9.97%. Comparatively, the XGBoost model had the highest predictive performance among four models with an area under the curve (AUC) of 0.824 (95% CI 0.7766-0.8708), whereas support vector machine had the poorest generalization ability (AUC=0.701, 95% CI 0.6433-0.7582). The decision curve showed that the net benefit of the XGBoost model surpassed those of other machine learning models at 10%~28% threshold probabilities. The SHAP method reveals the top 20 predictors of HF according to the importance ranking, and the average of the blood urea nitrogen was recognized as the most important predictor variable. Conclusions The interpretable predictive model helps physicians more accurately predict the mortality risk in ICU patients with HF, and therefore, provides better treatment plans and optimal resource allocation for their patients. In addition, the interpretable framework can increase the transparency of the model and facilitate understanding the reliability of the predictive model for the physicians.

Background Heart failure (HF) is a common clinical syndrome associated with substantial morbidity, a heavy economic burden, and high risk of readmission. eHealth self-management interventions may be an effective way to improve HF clinical outcomes. Objective The aim of this study was to systematically review the evidence for the effectiveness of eHealth self-management in patients with HF. Methods This study included only randomized controlled trials (RCTs) that compared the effects of eHealth interventions with usual care in adult patients with HF using searches of the EMBASE, PubMed, CENTRAL (Cochrane Central Register of Controlled Trials), and CINAHL databases from January 1, 2011, to July 12, 2022. The Cochrane Risk of Bias tool (RoB 2) was used to assess the risk of bias for each study. The Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) criteria were used to rate the certainty of the evidence for each outcome of interest. Meta-analyses were performed using Review Manager (RevMan v.5.4) and R (v.4.1.0 x64) software. Results In total, 24 RCTs with 9634 participants met the inclusion criteria. Compared with the usual-care group, eHealth self-management interventions could significantly reduce all-cause mortality (odds ratio [OR] 0.83, 95% CI 0.71-0.98, P=.03; GRADE: low quality) and cardiovascular mortality (OR 0.74, 95% CI 0.59-0.92, P=.008; GRADE: moderate quality), as well as all-cause readmissions (OR 0.82, 95% CI 0.73-0.93, P=.002; GRADE: low quality) and HF-related readmissions (OR 0.77, 95% CI 0.66-0.90, P<.001; GRADE: moderate quality). The meta-analyses also showed that eHealth interventions could increase patients’ knowledge of HF and improve their quality of life, but there were no statistically significant effects. However, eHealth interventions could significantly increase medication adherence (OR 1.82, 95% CI 1.42-2.34, P<.001; GRADE: low quality) and improve self-care behaviors (standardized mean difference –1.34, 95% CI –2.46 to –0.22, P=.02; GRADE: very low quality). A subgroup analysis of primary outcomes regarding the enrolled population setting found that eHealth interventions were more effective in patients with HF after discharge compared with those in the ambulatory clinic setting. Conclusions eHealth self-management interventions could benefit the health of patients with HF in various ways. However, the clinical effects of eHealth interventions in patients with HF are affected by multiple aspects, and more high-quality studies are needed to demonstrate effectiveness.

BACKGROUND Heart failure (HF) is a common disease and a major public health problem. The HF mortality prediction is critical for developing individualized prevention and treatment plans. However, due to their lack of interpretability, most HF mortality prediction models have not yet reached clinical practice. OBJECTIVE We aimed to develop an interpretable model to predict the risk mortality for HF patients in intensive care unit (ICU) and use the Shapley additive explanation (SHAP) method to explain the extreme gradient boosting (XGBoost) model and explore prognostic factors for HF. METHODS In this retrospective cohort study, we achieved model development and performance comparison on the eICU Collaborative Research Database (eICU-CRD). We extracted data during the first 24 hours of each ICU admission and the data set was randomly divided, with 70% used for model training and 30% for model validation. The prediction performance of the XGBoost model was compared with three other machine learning models by the areas under the receiver operating characteristic curve (AUROC). Moreover, we used the Shapley additive explanation SHAP method to explain the XGBoost model. RESULTS A total of 2,798 eligible patients with HF were included in the final cohort for this study. The observed in-hospital mortality of patients with HF was 9.97%. Comparatively, the XGBoost model had the highest predictive performance among four models (AUC 0.824, 95% Confidence Interval (CI) 0.7766 to 0.8708), while support vector machine (SVM) had the poorest generalization ability (AUC 0.701, 95% CI 0.6433 to 0.7582). The decision curve showed that the net benefit of the XGBoost model surpassed those of other machine learning models at 10%~28% threshold probabilities. The SHAP method reveals the top 20 predictors of HF according to the importance ranking and the average of the blood urea nitrogen was recognized as the most important predictor variable. CONCLUSIONS The interpretable predictive model helps physicians more accurately predict the mortality risk in ICU Patients with HF. This will help physicians to provide better treatment plan and optimal resource allocation for their patients. In addition, the interpretable framework can increase the transparency of the model and facilitates physicians to understand the reliability of the predictive model.

BACKGROUND The COVID-19 vaccine is considered to be the most promising approach to alleviate the pandemic. However, in recent surveys, acceptance of the COVID-19 vaccine has been low. To design more effective outreach interventions, there is an urgent need to understand public perceptions of COVID-19 vaccines. OBJECTIVE Our objective was to analyze the potential of leveraging transfer learning to detect tweets containing opinions, attitudes, and behavioral intentions toward COVID-19 vaccines, and to explore temporal trends as well as automatically extract topics across a large number of tweets. METHODS We developed machine learning and transfer learning models to classify tweets, followed by temporal analysis and topic modeling on a dataset of COVID-19 vaccine–related tweets posted from November 1, 2020 to January 31, 2021. We used the F1 values as the primary outcome to compare the performance of machine learning and transfer learning models. The statistical values and <i>P</i> values from the Augmented Dickey-Fuller test were used to assess whether users’ perceptions changed over time. The main topics in tweets were extracted by latent Dirichlet allocation analysis. RESULTS We collected 2,678,372 tweets related to COVID-19 vaccines from 841,978 unique users and annotated 5000 tweets. The F1 values of transfer learning models were 0.792 (95% CI 0.789-0.795), 0.578 (95% CI 0.572-0.584), and 0.614 (95% CI 0.606-0.622) for these three tasks, which significantly outperformed the machine learning models (logistic regression, random forest, and support vector machine). The prevalence of tweets containing attitudes and behavioral intentions varied significantly over time. Specifically, tweets containing positive behavioral intentions increased significantly in December 2020. In addition, we selected tweets in the following categories: positive attitudes, negative attitudes, positive behavioral intentions, and negative behavioral intentions. We then identified 10 main topics and relevant terms for each category. CONCLUSIONS Overall, we provided a method to automatically analyze the public understanding of COVID-19 vaccines from real-time data in social media, which can be used to tailor educational programs and other interventions to effectively promote the public acceptance of COVID-19 vaccines.