Utah launches world’s first autonomous prescription system without human doctors

Utah has cleared a healthcare system to begin issuing initial acne prescriptions without a doctor approving each prescription beforehand, marking a significant test of autonomous medical decision-making in the U.S.

The system, developed by New York-based health technology company Nolla Health, uses patient information and facial scans to select treatments from a limited set of physician-approved options. It cannot create its own treatment regimens, according to the company, and must hand a case to a licensed physician when it cannot confidently choose a treatment.

The autonomy will be introduced gradually. A physician will approve every prescription for the first 100 patients. During the next stage, covering the first 500 patients, the system will issue prescriptions autonomously while a physician reviews them afterwards each day. In the third stage, doctors will retrospectively review a sample of prescriptions once a week.

The pilot is available through the Nolla Derm app to Utah residents ages 18 and older. Patients complete a 10- to 15-minute questionnaire and a facial scan before the system assesses their skin and selects an acne treatment. Nolla says the process can produce a treatment plan and prescription within minutes.

Prescribing autonomy expands gradually

The program was developed with Utah’s Office of Artificial Intelligence Policy under the state’s regulatory framework for testing new AI applications. Utah regulators have described the arrangement as a controlled pilot for evaluating technology that can assess acne and write new prescriptions without prior human review.

Today, Nolla Health became the first organization in the U.S. (and possibly the world) to receive regulatory approval for an AI to issue initial prescriptions.

This makes Nolla the first ever actual end-to-end AI doctor. pic.twitter.com/xn6rvb8IyW

— Luis Wenus (@luiswenus) October 5, 2026

The distinction from conventional telehealth is important. Many digital health services use software to collect symptoms or assist clinicians, but a medical professional ultimately makes the prescribing decision. Nolla’s system is designed to eventually make that decision itself within predefined limits.

The technology combines structured information from the patient’s intake with analysis of facial images. Nolla says its healthcare platform uses multimodal machine-learning systems, including vision transformers, which can identify patterns across images and other patient data. The company says its broader systems have been trained on more than 3 million labeled clinical cases.

For the acne pilot, however, the system cannot freely choose among all prescription drugs. It is restricted to a short list of physician-approved topical treatments and predefined treatment pathways.

“The AI can’t improvise. It can only choose from a short list of physician-approved topical treatments,” said Dr. Zaid Fadul, Nolla Health’s chief medical advisor. “The moment a patient falls outside those limits, it stops and hands them to a doctor.”

Doctors audit automated decisions

Nolla says licensed clinicians agree with the system’s treatment recommendations in more than 96 percent of real-world cases. The company says disagreements have involved adjustments such as changing the strength of a topical medication rather than fundamentally different treatments. That performance figure was provided by Nolla and was not independently established in the announcement.

After receiving a prescription, patients can choose home delivery or pharmacy pickup. The app also uses daily skin scans to track changes, with treatment plans reviewed monthly based on the patient’s response. Patients can contact a licensed physician directly when they need additional support.

The service starts at $4.99 per month under the Utah pilot. Nolla says its dermatology app has already been downloaded more than 175,000 times across 44 states, although autonomous initial prescribing is currently limited to eligible adults in Utah.