The robot doctor will see you now

Most doctors agree that taking a medical history is fundamental to accurate diagnosis and establishing a trusting relationship with patients. However, it seems that AI systems can learn it, too.

The rapid rise in artificial intelligence has created intense discussions in many industries over what kind of role these tools can and should play – and healthcare has been no exception. The medical community largely anticipated that combining the abilities of doctors and AI would be the best of both worlds, leading to more accurate diagnoses and more efficient care.

That assumption might prove to be incorrect. A growing body of research suggests that AI is outperforming doctors, even when they use it as a tool.

A recent MIT-Harvard study examined how radiologists diagnose potential diseases from chest x-rays. The study found that when radiologists were shown AI predictions about the likelihood of disease, they often undervalued the AI input compared to their own judgment. The doctors stuck to their initial impressions even when the AI was correct, which led them to make less accurate diagnoses. Another trial yielded a similar result: When AI worked independently to diagnose patients, it achieved 92 percent accuracy, while physicians using AI assistance were only 76 percent accurate – barely better than the 74 percent they achieved without AI.

This research is early and may evolve. But the findings more broadly indicate that right now, simply giving physicians AI tools and expecting automatic improvements doesn’t work. Physicians aren’t completely comfortable with AI and still doubt its utility, even if it could demonstrably improve patient care.

But AI will forge ahead, and the best thing for medicine to do is to find a role for it that doctors can trust. The solution, we believe, is a deliberate division of labor. Instead of forcing both human doctors and AI to review every case side by side and trying to turn AI into a kind of shadow physician, a more effective approach is to let AI operate independently on suitable tasks so that physicians can focus their expertise where it matters most.

What might this division of labor look like? Research points to three distinct approaches. In the first model, physicians start by interviewing patients and conducting physical examinations to gather medical information. A Harvard-Stanford study that Dr. Rajpurkar helped write demonstrates why this sequence matters – when AI systems attempted to gather patient information through direct interviews, their diagnostic accuracy plummeted – in one case from 82 percent to 63 percent. The study revealed that AI still struggles with guiding natural conversations and knowing which follow-up questions will yield crucial diagnostic information. By having doctors gather this clinical data first, AI can then apply pattern recognition to analyze that information and suggest potential diagnoses.

In another approach, AI begins with analyzing medical data and suggesting possible diagnoses and treatment plans. AI seems to have a natural penchant for such tasks: A 2024 study showed that OpenAI’s latest models perform well at complex critical thinking tasks like generating diagnoses and managing health conditions when tested on case studies, medical literature and patient scenarios. The physician’s role is to then apply his clinical judgment to turn AI ’s suggestions into a treatment plan, adjusting the recommendations based on a patient’s physical limitations, insurance coverage and health care resources.

The most radical model might be complete separation: having AI handle certain routine cases independently (like normal chest x-rays or low-risk mammograms), while doctors focus on more complex disorders or rare conditions with atypical features.

Early evidence suggests this approach can work well in specific contexts. A Danish study published last year found that an AI system could reliably identify about half of all normal chest X-rays, freeing up radiologists to devote more time to studying images that were deemed suspicious. In a landmark Swedish trial involving mammograms for more than 80,000 women, half the scans were assessed by two radiologists, as is usual. The other half were evaluated by AI -supported screening first, followed by additional review by one radiologist (and in rarer instances where the AI determined an elevated risk, by two radiologists). The AI -assisted approach led to the identification of 20 percent more breast cancers while reducing the overall radiologist workload almost in half.

This might be the clearest path to dealing with the shortage of healthcare workers hurting medicine. This model is particularly promising for underserved areas, where AI systems could provide initial screening and triage, so limited specialist resources can be redirected to more pressing issues.

All these approaches raise questions about liability, regulation and the need for ongoing clinician education. Medical training will need to adapt to help doctors understand not just how to use AI , but when to rely on it and when to trust their own judgment. Perhaps most important, we still lack definitive proof that these approaches, tested in research studies or pilot programs, will achieve the same success in the messy realities of everyday care.

But the promise for patients is obvious: fewer bottlenecks, shorter waits and potentially better outcomes. For doctors, there’s potential for AI to alleviate the routine burdens so that health care might become more accurate, efficient and – paradoxically – more human.

Authored by Pranav Rajpurkar, assistant professor, Harvard Medical School and founder, a2z Radiology AI and Eric J. Topol, professor and executive vice president, Scripps Research in La Jolla, Californina, USA for The New York Times.