I’m sure other health journalists, like me, have received pitches from PR professionals since OpenAI announced a new tool called ChatGPT Health a few days ago. Many of these speeches essentially said that the generative AI company missed the mark with the announcement.
For example, one speech promoted the opinion of a CEO of an AI-based healthcare navigation company. The speech said: Americans don’t need AI to help them burn more calories in 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. This last 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 it themselves?
Actually, I’m not just thinking about companies like Epic Systems, but also companies like Microsoft. Why Microsoft? Because a few years ago Microsoft demonstrated a tool that seemed to get to the heart of what ChatGPT Health aims to do: provide information about an individual’s medical history.
It was the fall of 2023, and Microsoft was promoting various AI capabilities to a group of journalists, including me, at an industry event. I volunteered for a live demonstration of the company’s ambient AI capabilities that came courtesy of its acquisition of Nuance. But the most notable moment of that afternoon was a less brilliant capability highlighted by Linishya Vaz, senior project manager for Health and Life Sciences at Microsoft. I paste verbatim what I wrote in that story below:
Imagine that you have had some blood tests or radiological images done. The language of the radiologist’s report is replete with scientific terminology; It is almost deliberately designed to keep patients in the dark or guessing what the reports say. I’ve resorted to Google searching to guess what the images and other lab reports mean, as I’m sure countless people have done over the years.
Microsoft aims to make this easier for patients, assuming, of course, that your imaging provider/health system is a Microsoft customer and has implemented these capabilities.
In the hypothetical example Vaz shared, a patient with chest pain had a chest x-ray. The report says this:
“Double-lead pacemaker of the left anterior chest wall stable since before
exam. Hyperinflated lungs to clear up. No pneumothorax or pleural.
eltusion. Normal pulmonary vasculature. Normal heart size. Osseous
demineralized structures, although intact.
Impression: Hyperinflated lungs corresponding to emphysema. Osteopenia.”
Now Microsoft’s generative AI capability can simplify scientific jargon into 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 pacemaker) is stable on the left front of your chest, as seen in the previous exam.
* Your lungs are overinflated, which is consistent with a condition called emphysema.
* There is no air (pneumothorax) or fluid (pleural effusion) around the lungs.
* The blood vessels in the lungs appear normal.
*Your heart size is normal.
* Your bones show a decrease in density (demineralization), but are intact. This is called osteopenia.In conclusion:
His lungs are overinflated, which is consistent with emphysema, and he has osteopenia (decreased bone density).
The patient would also see this important disclaimer at the end of the report: This simplified version was generated by an assistant of Al.
The power of this technology in helping patients decipher a radiology or lab report cannot be overestimated (assuming, of course, that generative AI is accurately simplifying). It will completely eliminate the need for patients to perform time-consuming web searches to understand what is happening to them. And make them feel empowered.
That’s what I wrote in October 2023.
Now, let’s move on to the recent OpenAI announcement and specifically a couple of sentences from it: People have shared countless stories about turning to ChatGPT to help make sense of it all. In fact, health is one of the most common ways people use ChatGPT today: according to our anonymous conversation analysis, more than 230 million people around the world ask health and wellness-related questions on ChatGPT every year. week. (emphasis added)
“…helps make sense of everything.” Hence the genesis of ChatGPT Health, which is currently open to only a few users.
Now, how will ChatGPT Health make money for OpenAI? I don’t know. Can you trust the fact that ChatGPT Health is HIPAA compliant? They are saying it. But are average ChatGPT users worried about their healthcare in relation to HIPAA, assuming they even know about this standard? I’m willing to bet “no.” And while that’s no excuse for having lax privacy standards, the bottom line is simple: There’s a need for a well-designed, consumer-oriented tool that sheds more light on a person’s medical history and health trends over time. There is a demand for a centralized location of health data, including medical records and wearable devices, and the ability to query that collective, disparate data and get actionable, easily understandable answers in plain language. OpenAI saw the need and seized the opportunity. Microsoft saw it but never scaled it enough – at least that’s what it seems to be.
When asked if this was a missed opportunity, an outside Microsoft MP sent me a blog post that Microsoft AI CEO Mustafa Suleyman wrote in the fall of 2025, which included this paragraph about the Washington company’s consumer-facing healthcare capabilities.
Copilot for Health addresses one of the most common user needs: health-related questions. We’ve improved how we base answers on credible sources like Harvard Health to provide users with reliable information. Copilot also helps you find the right doctors quickly and securely, matching them based on specialty, location, language, and other preferences. The goal is simple: help you take control of your health by providing you with high-quality information and quickly connecting you to the right care.
Except Copilot for Health isn’t actually a dedicated health tool at all. It is simply Copilot and you can ask health-related questions to the generative AI tool. It does not have the functionality or privacy standards to handle an individual’s medical records or data from wearable devices.
In other words, a huge missed opportunity for Microsoft, as well as traditional healthcare companies that claim to be patient-centric.
Two Epic executives, including the EHR firm’s chief medical officer, contradict this conclusion. Stay tuned for that story and what you think about ChatGPT Health.
Photo: Wong Yu Liang, Getty Images