Background And Aim: Access to quality health care is essential, particularly in remote areas where the availability of healthcare professionals may be limited. The advancement of artificial intelligence (AI) and natural language processing (NLP) has led to the development of large language models (LLMs) that exhibit capabilities in understanding and generating human-like text. This study aimed to evaluate the performance of a LLM, ChatGPT, in addressing primary healthcare issues.

Materials And Methods: This study was conducted in May 2023 with ChatGPT May 12 version. A total of 30 multiple-choice questions (MCQs) related to primary health care were selected to test the proficiency of ChatGPT. These MCQs covered various topics commonly encountered in primary healthcare practice. ChatGPT answered the questions in two segments-one is choosing the single best answer of MCQ and another is supporting text for the answer. The answers to MCQs were compared with the predefined answer keys. The justifications of the answers were checked by two primary healthcare professionals on a 5-point Likert-type scale. The data were presented as number and percentage.

Results: Among the 30 questions, ChatGPT provided correct responses for 28 yielding an accuracy of 93.33%. The mean score for explanation in supporting the answer was 4.58 ± 0.85. There was an inter-item correlation of 0.896, and the average measure intraclass correlation coefficient (ICC) was 0.94 (95% confidence interval 0.88-0.97) indicating a high level of interobserver agreement.

Conclusion: LLMs, such as ChatGPT, show promising potential in addressing primary healthcare issues. The high accuracy rate achieved by ChatGPT in answering primary healthcare-related MCQs underscores the value of these models as resources for patients and healthcare providers in remote healthcare settings. This can also help in self-directed learning by medical students.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11639534PMC
http://dx.doi.org/10.4103/jehp.jehp_688_23DOI Listing

Publication Analysis

Top Keywords

primary healthcare
20
healthcare
9
large language
8
healthcare issues
8
remote healthcare
8
health care
8
healthcare professionals
8
addressing primary
8
primary
7
chatgpt
7

Similar Publications

A Couple-Based Intervention for Chinese Older Adults With Type 2 Diabetes: A Randomized Clinical Trial.

JAMA Netw Open

January 2025

Department of Medical Statistics and Epidemiology, School of Public Health, Sun Yat-sen University, Guangzhou, China.

Importance: Spousal involvement in diabetes care is recommended theoretically, but effectiveness in clinical settings and among diverse populations is unclear.

Objective: To test the effect of a couple-based intervention among Chinese older patients with type 2 diabetes and their spouses.

Design, Setting, And Participants: This multicenter randomized clinical trial comprised 2 arms: a couple-based intervention arm and an individual-based control.

View Article and Find Full Text PDF

Importance: Influenza vaccination remains the most important intervention to prevent influenza morbidity and mortality among nursing home residents. The additional effectiveness of recombinant influenza vaccine vs standard dose vaccines was demonstrated in outpatient older adults but has not been evaluated in nursing home populations.

Objective: To compare hospitalization rates among residents in nursing homes immunized with a recombinant vs a standard dose egg-based influenza vaccine.

View Article and Find Full Text PDF

Background: Loss to follow-up to HIV care following delivery puts birthing parents with HIV at higher risk of loss of viral suppression, disease progression, and HIV partner transmission. This study assessed factors associated with retention in postpartum HIV care.

Methods: This is a retrospective cohort study at a single academic medical center and included patients followed from January 2014 to December 2022.

View Article and Find Full Text PDF

Importance: The current standard-of-care salvage therapy in relapsed/refractory classic Hodgkin lymphoma (cHL) includes consolidation high-dose chemotherapy (HDCT)/autologous stem cell transplant (aSCT).

Objective: To investigate whether presalvage risk factors and fludeoxyglucose-18 (FDG) positron emission tomography (PET) response to reinduction chemotherapy can guide escalation or de-escalation between HDCT/aSCT or transplant-free consolidation with radiotherapy to minimize toxic effects while maintaining high cure rates.

Design, Setting, And Participants: EuroNet-PHL-R1 was a nonrandomized clinical trial that enrolled patients younger than 18 years with first relapsed/refractory cHL across 68 sites in 13 countries in Europe between January 2007 and January 2013.

View Article and Find Full Text PDF

Chronic insomnia is one of the most common health problems among veterans and can significantly impact health, function, and quality of life. Brief behavioral treatment for insomnia (BBTI), an adaptation of cognitive behavioral therapy for insomnia (CBT-I), was developed to help increase access to care outside of specialty settings. However, training providers alone is rarely sufficient, and implementation strategies are needed for successful uptake, adoption, and sustainable delivery of care.

View Article and Find Full Text PDF

Want 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!