RESUMO
[This corrects the article DOI: 10.2196/52782.].
RESUMO
Background: The health care system is undergoing a shift toward a more patient-centered approach for individuals with chronic and complex conditions, which presents a series of challenges, such as predicting hospital needs and optimizing resources. At the same time, the exponential increase in health data availability has made it possible to apply advanced statistics and artificial intelligence techniques to develop decision-support systems and improve resource planning, diagnosis, and patient screening. These methods are key to automating the analysis of large volumes of medical data and reducing professional workloads. Objective: This article aims to present a machine learning model and a case study in a cohort of patients with highly complex conditions. The object was to predict mortality within the following 4 years and early mortality over 6 months following diagnosis. The method used easily accessible variables and health care resource utilization information. Methods: A classification algorithm was selected among 6 models implemented and evaluated using a stratified cross-validation strategy with k=10 and a 70/30 train-test split. The evaluation metrics used included accuracy, recall, precision, F1-score, and area under the receiver operating characteristic (AUROC) curve. Results: The model predicted patient death with an 87% accuracy, recall of 87%, precision of 82%, F1-score of 84%, and area under the curve (AUC) of 0.88 using the best model, the Extreme Gradient Boosting (XGBoost) classifier. The results were worse when predicting premature deaths (following 6 months) with an 83% accuracy (recall=55%, precision=64% F1-score=57%, and AUC=0.88) using the Gradient Boosting (GRBoost) classifier. Conclusions: This study showcases encouraging outcomes in forecasting mortality among patients with intricate and persistent health conditions. The employed variables are conveniently accessible, and the incorporation of health care resource utilization information of the patient, which has not been employed by current state-of-the-art approaches, displays promising predictive power. The proposed prediction model is designed to efficiently identify cases that need customized care and proactively anticipate the demand for critical resources by health care providers.
RESUMO
Introduction: The evaluation of integrated care programmes for high-need high-cost older people is a challenge. We aim to share the early implementation results of the ProPCC programme in the North-Barcelona metropolitan area, in Catalonia, Spain. Methods: We analysed the intervention with retrospective data from May 2018 to December 2021 by describing the cohort complexity and by showing its 6-months pre-post impact on time spent at home and resources used: primary care visits, emergency department visits, hospital admissions and hospital stay. Findings: 264 cases were included (91% at home; 9% in nursing homes). 6-month pre vs. 6-months post results were (mean, p-value): primary care visits 8.2 vs. 11.5 (p < 0.05); emergency department visits 1.4 vs. 0.9 (p < 0.05); hospital admissions 0.7 vs. 0.5 (p < 0.05); hospital stay 12.8 vs. 7.9 days (p < 0.05). Time spent at home was 169.2 vs.174.2 days (p < 0.05). Conclusion: Early implementation of the ProPCC programme results in an increase in time spent at home (up to 3%) and significant reductions in emergency department attendance (-37.2%) and hospital stays (-38.3%). The increased use of primary care resources is compensated by the hospital resources savings, with a result in the average total cost of -46.3%.