Artificial Intelligence in Healthcare: A Multidisciplinary Approach to Patient-Centered Care
Abstract
Background:
Artificial intelligence (AI) is rapidly transforming healthcare, offering unprecedented potential to enhance diagnostics, personalize treatments, and optimize workflows. However, the ethical and effective implementation of AI hinges on multidisciplinary collaboration and patient-centered care. This systematic review aims to synthesize existing research on AI applications in healthcare, focusing on how multidisciplinary approaches influence its impact on patient-centered care.
Methods:
A systematic review was conducted following PRISMA guidelines. Electronic databases (PubMed, Scopus, Web of Science, Embase, IEEE Xplore) were searched using predefined keywords related to AI, healthcare settings, and patient-centered care. Studies published in English from January 2010 to August 2024 were included. Two reviewers independently screened titles, abstracts, and full texts, extracted data, and assessed methodological quality. Disagreements were resolved through consensus or a third reviewer.
Results:
From over 1500 initial citations, 12 studies (5 clinical trials, 7 cohort studies) met the inclusion criteria. These studies, conducted primarily in North American and European tertiary care hospitals, explored AI applications in diverse areas, including predicting adverse drug reactions, detecting cardiovascular events, managing diabetes, and predicting renal side effects. Significant heterogeneity was observed in the findings, with some studies reporting statistically significant improvements in diagnostic accuracy and patient outcomes, while others focused on risk stratification and personalized interventions. AI models demonstrated high sensitivity and specificity in predicting adverse events and improving clinical decision-making.
Conclusions:
AI holds significant promise for enhancing patient-centered care, particularly in predicting and managing complex medical conditions. Effective implementation necessitates robust multidisciplinary collaboration to ensure ethical, equitable, and clinically valid AI solutions. Future research should focus on standardizing evaluation methods and addressing challenges related to data privacy, algorithmic bias, and clinical integration.
