โก Quick Summary
This study examined the impact of AI-driven ambient scribes on psychiatric documentation and management in primary care, revealing that while AI scribes enhanced the documentation of neuropsychiatric symptoms, they were associated with a lower likelihood of psychiatric interventions compared to contemporaneous unscribed visits.
๐ Key Details
- ๐ Dataset: 20,302 primary care visit notes
- ๐งฉ Features analyzed: Neuropsychiatric symptom documentation, antidepressant prescriptions, diagnostic codes, and mental health referrals
- โ๏ธ Technology: AI ambient scribe (GPT-4o)
- ๐ฅ Study period: February 2023 to February 2025
๐ Key Takeaways
- ๐ AI scribes significantly improved documentation of neuropsychiatric symptoms across all six RDoC domains.
- ๐ Psychiatric interventions were less likely in AI-scribed visits (adjusted odds ratio 0.83) compared to unscribed visits.
- ๐ฉโโ๏ธ Human scribes did not show a significant difference in intervention likelihood compared to unscribed visits.
- ๐ง 5% of patients met criteria for moderate or greater depressive symptoms.
- ๐ Study conducted at Massachusetts General and Brigham and Women’s Hospital systems.
- ๐ Data analysis was performed in May 2025.
- ๐ก Further research is needed to explore the implications of these findings on patient outcomes.
๐ Background
The integration of artificial intelligence in healthcare has been rapidly evolving, particularly with the use of AI-driven ambient scribes. These technologies aim to streamline documentation processes, allowing clinicians to focus more on patient care. However, the effects of these tools on the management of psychiatric symptoms remain largely unexplored, prompting this study to investigate their impact in primary care settings.
๐๏ธ Study
This cohort study utilized a matched retrospective case-control design to analyze outpatient primary care notes from two major hospital systems. The researchers compared notes generated with AI ambient scribes to those created with human scribes and to notes from visits without scribes, ensuring that the groups were matched based on sociodemographic and clinical features.
๐ Results
The findings indicated that notes generated by AI scribes documented significantly higher levels of neuropsychiatric symptoms across all six domains of the Research Domain Criteria (RDoC). However, the likelihood of a documented psychiatric intervention was significantly lower in AI-scribed visits compared to contemporaneous unscribed visits, suggesting a potential gap in the management of identified symptoms.
๐ Impact and Implications
The results of this study highlight a critical paradox: while AI scribes enhance the documentation of psychiatric symptoms, they may inadvertently lead to a decrease in the management of these symptoms. This raises important questions about the role of AI in clinical practice and its implications for patient care. As AI technologies continue to evolve, understanding their impact on treatment outcomes will be essential for optimizing their use in healthcare settings.
๐ฎ Conclusion
This study underscores the dual-edged nature of AI integration in primary care. While AI ambient scribes improve documentation quality, they may also contribute to a decline in the management of psychiatric symptoms. Ongoing research is crucial to determine the long-term effects of these changes on patient outcomes and to ensure that AI tools are effectively supporting clinicians in delivering comprehensive care.
๐ฌ Your comments
What are your thoughts on the use of AI in psychiatric documentation? Do you believe it enhances or hinders patient care? ๐ฌ Join the conversation in the comments below or connect with us on social media:
Psychiatric Documentation and Management in Primary Care With Artificial Intelligence Scribe Use.
Abstract
IMPORTANCE: Despite increasingly widespread use of artificial intelligence (AI)-driven ambient scribes in medicine, the extent to which they are associated with clinician practice is not well studied.
OBJECTIVE: To characterize differences in documentation and treatment of psychiatric symptoms in primary care outpatient notes generated using ambient scribes compared with human or no scribes.
DESIGN, SETTING, AND PARTICIPANTS: This cohort study used a matched retrospective case-control design to evaluate primary care annual visit notes from the Massachusetts General and Brigham and Women’s Hospital systems between February 2023 and February 2025. A random sample of notes from 4 types of visits, matched 1:1 using sociodemographic and clinical features, was used: those using an ambient scribe, those using a human scribe, those occurring during the same period without a scribe (contemporaneous), and those occurring prior to scribe deployment. Data analysis was performed from April 25 to May 1, 2025.
EXPOSURE: Use of an AI ambient scribe.
MAIN OUTCOMES AND MEASURES: Neuropsychiatric symptom documentation, in terms of estimated Research Domain Criteria (RDoC), using a Health Insurance Portability and Accountability Act-compliant large language model (GPT-4o version gpt-4o-11-20; OpenAI); antidepressant prescriptions and diagnostic codes; and referral for mental health follow-up.
RESULTS: Among 20โฏ302 notes, the mean (SD) age of the patients was 48 (14) years and 11โฏ960 (59%) were for visits by female patients; 1026 (5%) met criteria for moderate or greater depressive symptoms by Patient Health Questionnaire-9 score. Estimated levels of RDoC symptoms in all 6 domains were significantly greater in the AI-scribed notes compared with other groups. In a multiple logistic regression model, likelihood of a psychiatric intervention (referral, new diagnosis, or antidepressant prescription) was significantly lower among AI-scribed visits compared with contemporaneous unscribed visits (adjusted odds ratio, 0.83; 95% CI, 0.72-0.95), but not for human-scribed visits compared with contemporaneous unscribed visits (adjusted odds ratio, 0.97; 95% CI, 0.85-1.11).
CONCLUSIONS AND RELEVANCE: In this retrospective cohort study using a matched case-control design examining outpatient primary care notes, incorporation of AI ambient scribes in primary care was associated with greater levels of neuropsychiatric symptom documentation but lesser likelihood of documented management of psychiatric symptoms. Further study will be required to determine whether these changes are associated with differential outcomes.
Author: [‘Castro VM’, ‘McCoy TH’, ‘Verhaak P’, ‘Ramachandiran A’, ‘Perlis RH’]
Journal: JAMA Psychiatry
Citation: Castro VM, et al. Psychiatric Documentation and Management in Primary Care With Artificial Intelligence Scribe Use. Psychiatric Documentation and Management in Primary Care With Artificial Intelligence Scribe Use. 2026; (unknown volume):(unknown pages). doi: 10.1001/jamapsychiatry.2025.4303