Enhancing healthcare for patients with multiple chronic conditions using machine learning and medical specialist data

Abstract

Purpose: The aging population is leading to a rise in the number of patients with multiple chronic conditions (MCC), which is putting pressure on healthcare systems. Artificial Intelligence, including Machine Learning (ML) offers potential to enhance care for patients with MCC. This scoping review summarizes current ML applications, discusses shortcomings and identifies opportunities. Additionally, it aims to identify applications explored in practice. Methods: We searched PubMed, Embase, and Web of Science for studies published between 2015 and January 2025 that used ML techniques and specialist care data, focusing on adults with MCC. Screening was assisted by ASReview. Results: The search identified 13381 articles, of which 454 were reviewed full text, resulting in 21 included articles. ML was mainly used for clustering (n = 14), primarily focusing on cardiovasculair diseases, with eight studies focusing on chronic diseases and six studies on clinical features, like medical specialties involved and symptoms. Stated potential clinical use of the clusters varied, but primarily aimed to promote integrated, personalized care. Predictive modelling was employed to support clinical decision-making and enhance research (n = 7). No applications were clinically evaluated. Conclusion: Current research on ML for patients with MCC primarily focuses on cluster analysis and predictive modelling, mainly aiming to enable holistic care. Future efforts should explore clinical evaluation and implementation, Natural Language Processing and Large Language Models. These technologies could significantly enhance care by extracting valuable insights from the data-rich electronic patient records of MCC patients, potentially leading to more effective decision-making and tailored interventions.