Healthcare
OpenAI Adds Over 20 Healthcare Plugins and Upgrades Clinical Search

Key PointsOpenAI's healthcare plugins consolidate records, evidence and operational tools into…
View more
- OpenAI's healthcare plugins consolidate records, evidence and operational tools into one governed ChatGPT conversation.
- Physicians rated the updated clinical search higher on all eight measured dimensions across more than 1,300 reviews.
- Deployment success hinges on operational governance defining access, review requirements and data protections for each connected system.
OpenAI announced on November 16, 2026 that more than 20 new healthcare plugins were available in ChatGPT for Healthcare, alongside improved clinical search designed to produce better-supported answers and connect them to work across hospital and payer systems.
The update spans ChatGPT for Healthcare and ChatGPT for Clinicians. It places medical evidence, patient information and everyday work tools in the same governed conversation instead of leaving users to move among an EHR, hospital policies, scheduling software and payer portals. The plugins cover clinical care, care coordination and business operations, with supported tasks ranging from reviewing records and preparing prescriptions for clinician review to checking insurance eligibility and analyzing costs and operational performance.
Plugins Link Records, Evidence and Operations
OpenAI’s examples show how the connectors can be chained together. After a patient is hospitalized elsewhere for heart failure, a primary care physician can retrieve the discharge summary through Metriport, have ChatGPT identify medication changes, and draw on UpToDate Expert AI for recommended follow-up monitoring, with links to both sources. An inpatient nurse admitting a patient who uses an insulin pump can combine Aiva’s hospital-policy information, including required nursing checks and documentation, with Amion’s on-call directory to find and contact the covering endocrinologist.
A care-navigation example extends the same approach to cost and access. IMO Health identifies the procedure code for a knee MRI without contrast, Stedi checks insurance eligibility and benefits, and Turquoise Health supplies the plan’s negotiated rate for that code at two hospitals. The workflow also identifies additional information needed to estimate what the patient would owe. Other examples use Luma Health and TriZetto to build a pre-visit confirmation list, or Assort Health and Ferry Health to combine referral trends with outstanding scheduling work.
The plugin expansion accompanied OpenAI’s separate computer-use announcement for healthcare teams. Those agents read screens, click, type and move between existing applications to help with referrals, prior authorizations, discharge planning and outreach. OpenAI described work with Abridge, Ambience, Cigna Healthcare and CVS Health. Organizations can configure application access and approvals and record audit logs.
Physicians Rate the Revised Answers
The clinical-search changes affect how ChatGPT finds, evaluates and cites medical evidence in both healthcare products. The answers are designed to connect relevant evidence to clinical questions and practical next steps, with citations clinicians can inspect. In a blind evaluation, physicians reviewed responses to real-world questions across multiple specialties, including multi-turn conversations, comparing the previous and updated ChatGPT for Clinicians experiences.
OpenAI reports that across more than 1,300 reviews, physicians rated the updated experience more highly on all eight measured dimensions: factual correctness, safety, actionability, calibration, source authoritativeness, locality alignment, temporal alignment and goal satisfaction. The evaluation therefore covers both the quality of an answer and whether its evidence is authoritative, current and appropriate to the local context. These are physician assessments of ChatGPT’s responses, rather than measured patient outcomes.
Availability and Data Controls
All of the new plugins are available in ChatGPT for Healthcare, although workspace administrators must enable them. Eligible, verified U.S. clinicians can sign up for a free ChatGPT for Clinicians account to review medical evidence and prepare clinical documentation; improved clinical search and select plugins are available to individual clinicians. The launch builds on OpenAI’s September 1, 2026 Epic integration, which brought authorized patient context into ChatGPT and, in supported deployments, placed ChatGPT within the EHR layout.
ChatGPT for Healthcare supports clinical, research and administrative teams in a governed workspace, and both healthcare products offer a Business Associate Agreement with OpenAI to support HIPAA-compliant workflows involving protected health information. Organizations must use eligible services covered by that agreement, apply required security and retention settings, and extend protections to connected systems. OpenAI states that content shared with ChatGPT for Healthcare is not used to train models. Deployment therefore depends on operational governance as well as answer quality: each connected system can expand the workflow, but its access, review requirements and data protections still have to be defined.












