I am sure that other healthcare journalists, like myself, have received pitches from public relations professionals since OpenAI announced a new tool called ChatGPT Health a few days ago. Many of these pitches essentially said the generative AI company missed the mark with the announcement.
For instance, one pitch touted the opinion of a CEO of an AI-driven health navigation company. The pitch stated: Americans don’t need AI to help them burn more calories on their Peleton (sic). They need AI to help them find care at the lowest price.
The reality is that both statements are true. People are worried about rising healthcare costs and they also want to be healthy and understand their own health data. The latter reality is undoubtedly the catalyst that led to the genesis of ChatGPT Health.
But the question is, why didn’t traditional EHR companies or companies that have been innovating with AI in healthcare do this themselves?
I am actually not just thinking of companies like Epic Systems, but also companies like Microsoft. Why Microsoft? Because a few years ago Microsoft demoed a tool that seemed to get to the heart of what ChatGPT Health is aiming to do – provide insights about an individual’s own medical record.
This was the fall of 2023 and Microsoft was touting several AI capabilities to a group of journalists, including me, at an industry event. I volunteered for a live demo of the company’s ambient AI capabilities that came courtesy of its Nuance acquisition. But the most notable moment of that afternoon was a less shiny capability highlighted by Linishya Vaz, principal project manager, Health and Life Sciences at Microsoft. I am pasting verbatim what I wrote in that story below:
Imagine you’ve had some bloodwork or radiological images done. The language of the radiologists’s report is replete with scientific terminology — it’s almost deliberately designed to keep patients in the dark or guessing about what the reports say. I’ve taken to Google search to divine the meaning of imaging and other lab reports as I am sure countless people have over the years.
Microsoft is aiming to make this easier for patients, assuming of course that their imaging provider/health system is a Microsoft customer and has deployed these capabilities.
In the hypothetical example that Vaz shared, a patient with chest pain has undergone a chest X-Ray. The report reads like this:
“Left anterior chest wall dual-lead pacer stable from prior
examination. Lungs hyperinflated to clear. No pneumothorax or pleural
eltusion. Pulmonary vasculature normal. Heart size normal. Osseous
structures demineralized, however intact.
Impression: Hyperinflated lungs in keeping with emphysema. Osteopenia.”
Now Microsoft’s generative AI capability can simplify the scientific jargon in plain English. And, per Vaz’s presentation, create a report that the patient can view in the patient portal.
* A device with two leads (dual-lead pacer) is stable in the left front part of your chest, as seen in the previous examination.
* Your lungs are overinflated, which is consistent with a condition called emphysema
* There is no air (pneumothorax) or fluid (pleural effusion) around your lungs
* The blood vessels in your lungs appear normal.
* The size of your heart is normal
* Your bones show a decrease in density (demineralization), but they are intact. This is called osteopeniaIn conclusion:
Your lungs are overinflated, which is consistent with emphysema, and you have osteopenia (decreased bone density).
The patient would also see this all-important disclaimer at the bottom of the report: This simplified version was generated by an Al assistant.
The power of this technology in helping patients decipher a radiology or lab report – assuming of course that the generative AI is simplifying accurately – cannot be overestimated. It will utterly eliminate the need for patients to conduct time-consuming web searches to understand what is happening to them. And make them feel empowered.
That’s what I wrote back in October, 2023
Now, let’s turn to the recent OpenAI announcement and specifically a couple of sentences from it: People have shared countless stories of turning to ChatGPT to help make sense of it all. In fact, health is one of the most common ways people use ChatGPT today: based on our de-identified analysis of conversations, over 230 million people globally ask health and wellness related questions on ChatGPT every week. (emphasis added)
“… help make sense of it all.” Hence, the genesis of ChatGPT Health, which is currently open to only a few users.
Now, how will ChatGPT Health make OpenAI money? I don’t know. Can you trust the fact that ChatGPT Health is HIPAA compliant? They are saying so. But do average ChatGPT users worried about their health care about HIPAA, assuming they even know about this standard? I am willing to bet “no.” And while that is no excuse for having lax privacy standards, the takeaway is simple: there is a hunger for a well-designed, consumer-facing tool that sheds more light on a person’s medical record and health trends over time. There is a demand for a centralized location of health data, including medical records and wearables and the ability to query that collective and disparate data and get easily understandable, actionable responses in plain English. OpenAI saw the need and jumped on the opportunity. Microsoft saw it but never scaled it enough – at least that’s what it appears to be.
When asked if this was a missed opportunity, an external Microsoft spokeswoman forwarded me a blog post that Microsoft AI CEO Mustafa Suleyman wrote in the fall of 2025, which included this paragraph on the Washington company’s capabilities in consumer-facing health.
Copilot for health addresses one of the most common user needs: health-related questions. We’ve improved how we ground responses in credible sources like Harvard Health to empower users with reliable information. Copilot also helps you find the right doctors quickly and confidently, matching based on specialty, location, language, and other preferences. The goal is simple: to help you take control of your health by empowering you with high-quality information and connecting you to the right care fast.
Except Copilot for health is not really a dedicated health tool at all. It’s simply Copilot and you can ask the generative AI tool health-related questions. It doesn’t have the functionality or the privacy standards to handle an individual’s medical records or data from wearables.
In other words, a big missed opportunity for Microsoft, as well as traditional health companies that claim to be patient-centric.
Two Epic executives, including the EHR firm’s chief medical officer, counter this conclusion. Stay tuned for that story and what they think of ChatGPT Health.
Photo: Wong Yu Liang, Getty Images
