Background: Generative AI, particularly large language models (LLMs), holds great potential for improving patient care and operational efficiency in healthcare. However, the use of LLMs is complicated by regulatory concerns around data security and patient privacy. This study aimed to develop and evaluate a secure infrastructure that allows researchers to safely leverage LLMs in healthcare while ensuring HIPAA compliance and promoting equitable AI.
Materials And Methods: We implemented a private Azure OpenAI Studio deployment with secure API-enabled endpoints for researchers. Two use cases were explored, detecting falls from electronic health records (EHR) notes and evaluating bias in mental health prediction using fairness-aware prompts.
Results: The framework provided secure, HIPAA-compliant API access to LLMs, allowing researchers to handle sensitive data safely. Both use cases highlighted the secure infrastructure's capacity to protect sensitive patient data while supporting innovation.
Discussion And Conclusion: This centralized platform presents a scalable, secure, and HIPAA-compliant solution for healthcare institutions aiming to integrate LLMs into clinical research.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1093/jamia/ocaf005 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Transforming healthcare: Saudi Arabia's vision 2030 healthcare model.
J Pharm Policy Pract
January 2025
School of Medical and Life Sciences, Sunway University, Sunway City, Malaysia.
Vision 2030 represents Saudi Arabia's strategic socio-economic plan aimed at promoting economic diversification and enhancing living standards. Launched in April 2016, this vision describes an innovative healthcare plan to improve services and outcomes. The merits and drawbacks of public hospitals' 'Model of Care' are examined in this study.
View Article and Find Full Text PDFU.S. State-Level Containment Policies Not Associated with Food Insecurity Changes During the Early COVID-19 Pandemic: A Multi-level Analysis.
Public Health Nutr
January 2025
Johns Hopkins Center for a Livable Future, Johns Hopkins University, Baltimore, MD, 21205, USA.
Objective: To investigate the relationship between United States (US) containment measures during the COVID-19 pandemic and household food insecurity.
Design: To investigate these relationships, we developed a framework linking COVID-related containment policies with different domains of food security, then used multilevel random effects models to examine associations between state-level containment policies and household food security. Our framework depicts theorized linkages between stringency policies and five domains of food security (availability, physical access, economic access, acceptability in meeting preferences, and agency, which includes both self-efficacy and infrastructure).
Home care program for high-risk pregnancies: a qualitative study of care providers perspectives from Iran.
BMC Pregnancy Childbirth
January 2025
Center for Health Related Social and Behavioral Sciences Research, Shahroud University of Medical Sciences, Shahroud, Iran.
Background: High-risk pregnancies are accompanied by significant complications for the mother, fetus, and baby if not controlled and received timely care. During home antenatal care, high-risk pregnant women can receive non-medical interventions by a home visitor.
Objective: This study's main aim was to explore care providers' perspectives regarding the home care program for high-risk pregnancies.
Harnessing Big Heterogeneous Data to Evaluate the Potential Impact of HIV Responses Among Key Populations in Sub-Saharan Africa: Protocol for the Boloka Data Repository Initiative.
JMIR Res Protoc
January 2025
Key Populations Program, Center for Public Health and Human Rights, Johns Hopkins Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD, United States.
Background: In South Africa, there is no centralized HIV surveillance system where key populations (KPs) data, including gay men and other men who have sex with men, female sex workers, transgender persons, people who use drugs, and incarcerated persons, are stored in South Africa despite being on higher risk of HIV acquisition and transmission than the general population. Data on KPs are being collected on a smaller scale by numerous stakeholders and managed in silos. There exists an opportunity to harness a variety of data, such as empirical, contextual, observational, and programmatic data, for evaluating the potential impact of HIV responses among KPs in South Africa.
View Article and Find Full Text PDFChallenges and opportunities of artificial intelligence in African health space.
Digit Health
January 2025
Department of Global Health and Development, Faculty of Public Health and Policy, London School of Hygiene and Tropical Medicine, London, UK.
The application of artificial intelligence (AI) to healthcare in Africa has the potential to transform productivity, diagnosis, disease surveillance, and resource allocation by improving accuracy and efficiency. However, to fully realize its benefits, it is necessary to consider issues concerning data privacy, equity, infrastructure integration, and ethical policy development. The use of these tools may improve the detection of diseases, the distribution of resources, and the continuity of care.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!