Artificial Intelligence-Based Chatbots in Chronic Disease Management: A Systematic Review of Applications and Challenges

• Published in: Curēus (Palo Alto, CA) Vol. 17; no. 3; p. e81001
• Main Authors: Altom, Dalia Saad, Awad Taha, Allaa Ibrahim, Mahmoud Hussein, Alaa Abu Agla, Ibrahim Elshiekh, Maisoon Ahmed, Alata Abdelmajed, Ashwag Hassan, Abdalla Ibrahim, Fatima Ibrahim, Abelgadir Mohammed, Sara Mohammed, Elamin Eltain Tifoor, Mosab Mohamed
• Format: Journal Article
• Language: English
• Published: United States Springer Nature B.V 22.03.2025; Cureus
• Subjects: Arthritis; Artificial intelligence; Bias; Chatbots; Chronic illnesses; Diabetes; Disease management; Internal Medicine; Intervention; Language; Medical diagnosis; Medical Subject Headings-MeSH; Natural language processing; Patient education; Professionals; Quasi-experimental methods; Systematic review; Telemedicine; User experience; Voice recognition; Canada; South Korea; United Kingdom > UK; Spain; conversational agents; chronic diseases; artificial intelligence; chatbots; healthcare
• ISSN: 2168-8184; 2168-8184
• DOI: 10.7759/cureus.81001

Artificial intelligence (AI) is being used by an increasing number of conversational agents, sometimes known as chatbots. In applications related to health care, such as those that educate and assist patients with chronic illnesses, which are among the main causes of mortality in the 21st century, they are becoming more and more common. Chatbots powered by AI allows for more frequent and efficient engagement with these patients. This systematic review aimed to examine the traits, medical conditions, and AI architectures of conversational agents that are based on artificial intelligence and are specifically made for chronic illnesses. We searched four databases (Scopus, Web of Science, PubMed, and Cumulative Index to Nursing and Allied Health Literature [CINAHL]) to search for relevant studies using specific inclusion and exclusion criteria. Among these databases, we found 386 studies that were screened for duplicates and then assessed by inclusion and exclusion criteria. We included the 10 most relevant studies in this systemic review. There is a dearth of research on AI-based interactive agents for chronic illnesses, and what little is available is primarily quasi-experimental studies, including chatbots in prototype stages that employ natural language processing (NLP) and enable multimodal user engagement. Future studies could benefit from comparing and evaluating AI-based conversational bots within and between various chronic health disorders using evidence-based methodology. In addition to improving comparability, more structured development and standardized evaluation procedures could improve the caliber of chatbots created for certain chronic diseases and their subsequent effects on the target patients.