Finna E. Indriany

Background: The risk of rehospitalization in patients with heart failure (HF) has initiated various efforts to prevent and simultaneously improve quality of life. Self-monitoring at home is one option, and technology is increasingly being used for this purpose. Objective: This pilot study aimed to evaluate the feasibility and preliminary effects of a digital home monitoring intervention on patient-reported outcomes and 30-day readmissions among patients with HF in Indonesia. Methods: A mixed methods pilot study was conducted, combining qualitative system development and quantitative evaluation. Patients were assigned to an intervention group (digital monitoring) or control group (standard care). Readmission rates were compared using chi-square tests and odds ratios. Changes in Kansas City Cardiomyopathy Questionnaire scores were analyzed using linear mixed-effects models. Results: A total of 60 patients were included (n=30, 50% in the intervention group; n=30, 50% in the control group). Readmission occurred in 20% (6/30) of patients in the intervention group and 43.3% (13/30) of patients in the control group (odds ratio 0.33, 95% CI 0.10‐1.09; P =.10). Linear mixed-effects analysis showed greater improvement in Kansas City Cardiomyopathy Questionnaire overall summary score in the intervention group ( P =.02). Improvements were observed in the physical limitation, symptom frequency, symptom burden, quality of life, and social limitation domains. During follow-up, 3.3% (1/30) of the patients in the intervention group died of non–HF-related causes, and 10% (3/30) of the patients in the control group died due to HF. Conclusions: This pilot study suggests that digital home monitoring is feasible and associated with improvements in patient-reported outcomes, with a potential signal toward reduced readmission. Larger studies are needed to confirm effectiveness.

BACKGROUND The risk of rehospitalization in heart failure (HF) patients has initiated various preventive efforts and to simultaneously improve the quality of life (QoL) of the patients. Self-monitoring at home is one option, and technology is increasingly being used for this purpose. OBJECTIVE To reduce the risk of hospital readmission and maintain the QoL of HF patients through self-monitoring with the assistance of a digital application. METHODS Starting with determining the need for HF services in National Cardiovascular Center Jakarta in 2024, an application called FineHeart was built and tested on HF patients in a quasi-experimental pilot study. After the User Acceptance Test was completed, HF patients were recruited as intervention group and control group participants. Quality of Life was measured with the Kansas City Cardiomyopathy Questionnaire (KCCQ) before and after the test. The readmission rate and 4 of the KCCQ parameters were analysed between the 2 groups. RESULTS Of the 72 patients who met the inclusion criteria, thirty participated in the intervention group and thirty in the control group who had signed the consent form. In the intervention group, after 30 days, 22 people complied using the FineHeart application prototype (73.3%), six were readmitted (20%), and one died not because of HF (3.3%). In the control group, 10 were readmitted (33.3%), and three died because of HF (10%). There was a significant relationship between adherence to application usage and an increase in Quality-of-Life scores (p<0.029) and Overall Summary Score (p<0.001)), but not in Self-efficacy and Social Limitation Scores. CONCLUSIONS The findings of this study provide a potential benefit for HF patients to perform self-monitoring at home in collaboration with the hospital team by using FineHeart app. Patient adherence may reduce the risk of readmission and improve QoL. Multicenter studies on larger groups of patients are needed to confirm these preliminary results.

Objectives: In Indonesia, the poor prognosis and high hospital readmission rates of patients with heart failure (HF) have yet to receive focused attention. However, machine learning (ML) approaches can help to mitigate these problems. We aimed to determine which ML models best predicted HF severity and hospital readmissions and could be used in a patient self-monitoring mobile application.Methods: In a retrospective cohort study, we collected the data of patients admitted with HF to the Siloam Diagram Heart Center in 2020, 2021, and 2022. Data was analyzed using the Orange data mining classification method. ML support algorithms, including artificial neural network (ANN), random forest, gradient boosting, Naïve Bayes, tree-based models, and logistic regression were used to predict HF severity and hospital readmissions. The performance of these models was evaluated using the area under the curve (AUC), accuracy, and F1-scores.Results: Of the 543 patients with HF, 3 (0.56%) were excluded due to death on admission. Hospital readmission occurred in 138 patients (25.6%). Of the six algorithms tested, ANN showed the best performance in predicting both HF severity (AUC = 1.000, accuracy = 0.998, F1-score = 0.998) and readmission for HF (AUC = 0.998, accuracy = 0.975, F1-score = 0.972). Other studies have shown variable results for the best algorithm to predict hospital readmission in patients with HF.Conclusions: The ANN algorithm performed best in predicting HF severity and hospital readmissions and will be integrated into a mobile application for patient self-monitoring to prevent readmissions.