Transforming the Primary Care Journey with Generative AI: A Foundation Model to Boost Efficiency, Quality, and Engagement.

J Gen Intern Med

Stanford Healthcare AI Applied Research Team, Division of Primary Care and Population Health, Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA.

Published: August 2025


Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Primary care is the cornerstone of every patient's health journey. Given its central role in the delivery of medical care, primary care is crucial in the integration of artificial intelligence (AI) into healthcare. Generative AI has the potential to augment primary care workflows to achieve the quintuple aim. In this paper, we use a hypothetical case to outline a medical care experience for both a patient and provider. We highlight five common problems faced by primary care providers (PCPs): data overload, rapidly changing evidence, barriers to adequate patient education, clinical documentation burden, and increase in patient electronic messages. We propose a generative AI foundation model that can transform the primary care journey through chart summarization, clinical decision support, personalized patient instructions, clinical documentation, and asynchronous care delivery.

Download full-text PDF

Source
http://dx.doi.org/10.1007/s11606-025-09716-yDOI Listing

Publication Analysis

Top Keywords

primary care
24
care
9
care journey
8
generative foundation
8
foundation model
8
medical care
8
clinical documentation
8
primary
5
transforming primary
4
journey generative
4

Similar Publications

Background: The treatment of mandibular angle fractures remains controversial, particularly regarding the method of fixation. The primary aim of this study was to compare surgical outcomes following treatment with 1-plate versus 2-plate fixation across two oral and maxillofacial surgery clinics. The secondary aim was to evaluate associations between patient-, trauma-, and procedure-specific factors with postoperative complications and to identify high-risk patients for secondary osteosynthesis.

View Article and Find Full Text PDF

Background: Post-viral syndromes, including long- and post-COVID, often lead to persistent symptoms such as fatigue and dyspnoea, affecting patients' daily lives and ability to work. The COVI-Care M-V trial examines whether interprofessional, patient-centred teleconsultations, initiated by general practitioners in cooperation with specialists, can help reduce symptom burden and improve care for patients.

Methods: To evaluate the effectiveness of the intervention under routine care conditions, a cluster-randomised controlled trial is being conducted.

View Article and Find Full Text PDF

Background: Although current evidence supports the effectiveness of social norm feedback (SNF) interventions, their sustained integration into primary care remains limited. Drawing on the elements of the antimicrobial SNF intervention strategy identified through the Delphi-based evidence applicability evaluation, this study aims to explore the barriers and facilitators to its implementation in primary care institutions, thereby informing future optimization.

Methods: Based on the five domains of the Consolidated Framework for Implementation Research (CFIR), we developed semi-structured interview and focus group discussion guides.

View Article and Find Full Text PDF

Background: Maternal healthcare (MHC) in Cameroon reflects the persistent challenges in Sub-Saharan Africa, where high maternal mortality continues despite improved service utilization, stressing inequitable effective coverage (EC). This study applied EC cascade analysis-including service contact, continuity, and input-adjusted coverage-to quantify geographic and socioeconomic disparities, informing equity-focused strategies to dismantle structural barriers in the MHC continuum.

Methods: We combined population and health facility data (2018 Cameroon Demographic and Health Survey and 2015 Emergency Obstetric and Neonatal Care Assessment) to estimate the input-adjusted coverage of antenatal care (ANC) and intra-and postpartum care (IPC).

View Article and Find Full Text PDF

The Grams model, designed to predict adverse event risks in advanced chronic kidney disease (CKD) patients, was evaluated in a Chinese cohort of 1,333 patients with eGFR below 30 mL/min/1.73 m. The model demonstrated moderate to good discrimination across outcomes, performing well in predicting kidney replacement therapy (KRT) but overestimating the risks of cardiovascular disease (CVD) and mortality.

View Article and Find Full Text PDF