Assuta Develops Personal AI Medical Assistant
Assuta Medical Centers, in partnership with Microsoft, is developing an AI system to act as a personal assistant for doctors. The system will automate documentation and information retrieval during patient encounters.
A digital assistant to accompany the doctor: Assuta Medical Centers, as part of an agreement with Microsoft, is developing an artificial intelligence (AI) system that will effectively act as a personal assistant for doctors. It will collect relevant medical information, summarize test results and previous documents, document the encounter with the patient, and automatically draft a visit summary. The system is not intended to replace the doctor, but rather to free them from documentation and search tasks, leaving more time for examination, conversation, and medical decision-making.
At the heart of the initiative announced by Assuta and Microsoft is the development of a personal AI agent for every doctor. Unlike standard medical computing systems, where the doctor must navigate between screens, tests, hospitalization summaries, and referral letters, the agent is designed to read the material in the medical file and present important information ahead of the encounter.
Thus, before the patient enters the room, the doctor will receive a summary of previous diagnoses, medications, recent tests, treatments already tried, and changes in medical condition. The goal is to reduce the time dedicated to locating information within large quantities of documents and to decrease the risk of missing significant details.
During the visit, the system will be able to listen to the conversation between the doctor and the patient—after receiving necessary approvals and in accordance with privacy rules—and produce an organized transcript. Afterward, it will process the information and draft a full medical document, including patient complaints, medical background, examination findings, the doctor's impression, and follow-up recommendations.
The doctor will be required to review, correct, and approve the document before it enters the medical file. Assuta emphasizes that the system serves only as a decision-support tool and will not replace medical judgment. Responsibility for diagnosis, test selection, and treatment remains with the doctor.
The agent is also intended to assist in post-visit stages. According to the plan, it will be able to identify the need for further tests or meetings, find suitable times, and assist in coordinating follow-up appointments based on medical necessity and system availability. Future actions may be added throughout the care continuum, subject to medical oversight and information security rules.
One of the central problems in the healthcare system is the significant time doctors dedicate to administrative tasks. According to project goals, the use of the agent could cumulatively save hundreds of hours of doctor work each month. This could allow for shorter visit durations without reducing time spent talking to the patient, thereby increasing appointment availability and shortening waiting times.
Developing such a system requires a lengthy process of learning and training. Models of medical documents, visit summaries, and professional terms are fed into the systems, with identifying details removed to maintain patient privacy. The system is trained to distinguish between central information and marginal details, and to identify connections between diagnoses, medications, and tests.
One challenge is preventing errors characteristic of AI systems, such as omitting details or creating information not present in original documents. For this reason, outputs will not enter the medical file automatically without human review. Development and implementation will be carried out gradually.
The first pilot is expected to begin within a year. Alongside the personal agent, Assuta and Microsoft have agreed on a gradual transition to the company's cloud infrastructure and the creation of a platform for developing additional AI agents.
Sarit Sass, Director of Healthcare Organizations at Microsoft Israel, stated: "We believe that the future of the healthcare system relies on the combination of the human expertise of medical teams and the capabilities of artificial intelligence." Ofir Shani Shaharban, Head of the Information Systems and Technology Division at Assuta, added that the partnership is "a significant milestone in our journey," allowing the integration of AI into medical practice "responsibly, securely, and while strictly maintaining patient privacy."
