![\"Hilary](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/09\/SSBTBMDJ2KFQAEKVGHKJ3CGFHY.JPG\")
Hilary Eaton prompted ChatGPT with medical questions related to her daughter Olivia at home in Winchester.Meleck Eldahshoury for The Boston Globe<\/p>\nDoctors said Olivia\u2019s frequent bouts of illness were likely because she was isolated from other children during the coronavirus pandemic. But Eaton couldn\u2019t shake the feeling something else was going on. Her \u201cspidey sense,\u201d she said, was constantly tingling. <\/p>\n
\u201cI knew she was sick too much, too long,\u201d Eaton said.<\/p>\n
She hoped the lab tests, ordered by an immunologist, would offer new information. <\/p>\n
So on that January day in 2025, as chatter from the work meeting streamed from her computer, Eaton\u2019s attention was on her phone. She zoomed in on a PDF so she could read the test results.<\/p>\n
Several numbers stood out: They measured antibodies, the body\u2019s critical line of defense against foreign invaders. Olivia had far less than a healthy child should. <\/p>\n
Holy [expletive], Eaton thought. <\/p>\n
Hilary Eaton prompted ChatGPT with medical questions related to her daughter Olivia at home in Winchester.Meleck Eldahshoury for The Boston Globe<\/p>\n
She texted her husband as questions ran through her mind: What could cause this? Is it dangerous? <\/p>\n
Knowing she wouldn\u2019t be able to reach Olivia\u2019s doctor right away, she thought of another way to get information quickly. <\/p>\n
As scientists by training, Eaton and her husband, Matt, both used artificial intelligence in their jobs in the biotech industry. They had more recently started asking chatbots specific health questions at home. Now, Eaton wondered if AI could help if she gave it more information \u2014 feeding in Olivia\u2019s symptoms and her lab results. <\/p>\n
\u201cI\u2019m just going to shove everything into it,\u201d she recalled deciding.<\/p>\n
Eaton opened ChatGPT and started to type.<\/p>\n
\u201cWith the following test results,\u201d she wrote, \u201cwhat are possible diagnoses?\u201d<\/p>\n
The first piece of the puzzle <\/p>\n
Using large language models, or LLMs, for health questions has surged in popularity. A quarter of Americans now report using AI chatbots to diagnose symptoms, according to a Pew Research Center survey<\/a> from June. A similar share of respondents said they use AI to better understand information from their providers.<\/p>\n Yet AI can hallucinate and make mistakes \u2014 sometimes serious ones. In recent years, a cancer patient came to believe his treatment could be shortening his life<\/a>, based in part on conversations with AI. He refused options recommended by his doctor and eventually died. AI companies have also faced lawsuits alleging that<\/a> interactions with chatbots ended in people dying by suicide.<\/p>\n Experts say chatbots can be helpful tools for health-related questions, if used properly and with caution. They say patients should also understand the privacy policies of chatbots they plan to use with their medical information.<\/p>\n Platforms are also rapidly improving, and health care providers themselves are increasingly using the technology. Today, about 80 percent of physicians say they use AI for work, according to an American Medical Association survey<\/a> published in March.<\/p>\n Generative AI has \u201cgone from basically no one using it three years ago to being ubiquitous,\u201d said Dr. Adam Rodman, director of AI programs for the Carl J. Shapiro Institute for Education and Research at Beth Israel Deaconess Medical Center. \u201cIt\u2019s the fastest that I have ever seen technology proliferate in medicine.\u201d<\/p>\n Every week, more than 300 million people pepper ChatGPT with health queries, said Ashley Alexander, vice president of Health Products at OpenAI. She added that the company takes data privacy seriously and hundreds of physicians provide feedback on the model. <\/p>\n An OpenAI employee would eventually hear Eaton speak about her family\u2019s experience using ChatGPT, and the company has invited them to film a social media video; as compensation for their time, the company will make a donation to a rare-disease advocacy group. (The Eatons were not paid by OpenAI for participating in this story.)<\/p>\n After uploading Olivia\u2019s lab results on that day early last year in her home office in Winchester, Eaton stared at her phone. ChatGPT responded to her query in a matter of seconds. <\/p>\n It was possible, the chatbot said, that her daughter had a primary immunodeficiency called CVID, an acronym for common variable immunodeficiency. Although low antibodies are a symptom of the manageable condition, CVID would turn out not to be the cause. <\/p>\n A mix of feelings swirled through Eaton. Validation and frustration. But also a sense of control.<\/p>\n Now she had something to go off. <\/p>\n \u201cI could go back to the doctor and say, \u2018I\u2019ve done my homework. I\u2019ve looked at a bunch of this stuff. Here\u2019s what I\u2019m thinking. Is that in any way aligned with what you\u2019re thinking?\u2019\u201d Eaton said. \u201cIt just felt like I could have some iota of agency or control back, that I could start having a conversation where I\u2019m not just sort of the passenger [on] a roller coaster that is totally off the rails.\u201d<\/p>\n Hilary and Matt Eaton met about two decades ago as graduate students at Duke University. At the time, Hilary said she was taking a break from dating. For how long? Matt asked. Maybe six months, she replied.<\/p>\n Matt set a calendar reminder. On the six-month anniversary of that conversation, he had a reservation at the nicest restaurant in Durham for the two of them. <\/p>\n Persistence and curiosity have defined the couple\u2019s relationship ever since, said Eaton, who is now 42. She graduated with a PhD in molecular cancer biology and completed a postdoctoral fellowship at Harvard Medical School. Matt, 44, also earned his PhD, did his postdoctoral research at MIT, and is a computational biologist.<\/p>\n The couple hoped for two children and in vitro fertilization resulted in two viable embryos. Their first daughter, Fiona, arrived in June 2017. Olivia followed less than two years later.<\/p>\n Soon, the parents grew concerned about Olivia. As a newborn, she failed her hearing test. At 9 months old, she couldn\u2019t sit up on her own. Tests from their doctors came back inconclusive. <\/p>\n Fiona, who has autism, had also hit milestones later than expected, but \u201cnot crazy late,\u201d Eaton said. Doctors tried to reassure the couple about Olivia\u2019s development. <\/p>\n \u201cDon\u2019t compare her to her sibling.\u201d<\/p>\n \u201cEvery kid\u2019s on a different trajectory.\u201d <\/p>\n Rationally, the explanations made sense. \u201cIt\u2019s easy to sort of justify it away,\u201d Eaton said. \u201cBut it just continued.\u201d <\/p>\n By the time Olivia was about a year and a half old, she still couldn\u2019t pull herself up or walk. During a 2020 orthopedics appointment for Olivia, the doctor asked her mother an unusual question: Did she have any \u201cparty tricks?\u201d Specifically, was Eaton especially bendy? <\/p>\n \u201cI\u2019m double-jointed everywhere,\u201d Eaton recalled saying. <\/p>\n Doctors suspected Olivia might have a connective tissue disorder passed down from her mother. Common symptoms typically include joint hypermobility and fragile tissues, which can lead to frequent bruising or poor wound healing.<\/p>\n But that still didn\u2019t explain why Olivia was getting sick so often. <\/p>\n The parents kept a calendar where they marked the days she didn\u2019t have symptoms of respiratory illness or skin infection. When they added them up, Eaton said, \u201cit was like seven days out of the year that she was healthy.\u201d <\/p>\n They needed more information. \u201cIn many ways, parenthood is the epitome of having to let go of control,\u201d Eaton said. \u201cBut as a scientist, you want data because that\u2019s how you make decisions, and feeling helpless is like the worst thing in the world.\u201d <\/p>\n In 2023, the Eatons spent about $4,500 to sequence the entire genomes of all four members of their family. Then they got down to work. <\/p>\n After they put the kids to bed, and continuing late into the night, they used ChatGPT to help them identify genes related to the connective tissue disorder. They also pored over the genome sequencing data looking for potential mutations that could help explain her low antibody count. They saved their research in an online folder they labeled \u201cGenome Detectives.\u201d<\/p>\n \u201cThis is us just amateur spelunking, basically, in our daughter\u2019s DNA,\u201d Eaton said.<\/p>\n Since the couple knew chatbots were prone to hallucinations and errors, they took steps to train the model. They explained their backgrounds in science, told the chatbot how they wanted it to interact with them, and instructed it to provide research citations for information. They emphasized that they would review the journal articles themselves.<\/p>\n But even with their scientific training, and the safeguards they put in place, the Eatons weren\u2019t immune to scares. <\/p>\n As they searched for mutations that might explain Olivia\u2019s immunodeficiency, ChatGPT flagged several possible genes. When the parents looked up one of the mutations in medical literature, they were horrified. <\/p>\n \u201cYou find that these kids are dead by the time they\u2019re like 7 to 10,\u201d Eaton said. \u201cOlivia at the time was 6, so we freaked out. We spent two hours thinking that she was close to death.\u201d<\/p>\n It turned out, however, that the genome sequencing data itself contained errors. Olivia didn\u2019t have that deadly mutation. The chatbot had been working off bad source material.<\/p>\n The Eatons cleaned up the genome data and learned to approach what they were finding with greater caution. But the experience didn\u2019t deter them. <\/p>\n \u2018Are you sitting down?\u2019<\/p>\n The Eatons and their doctors were beginning to understand Olivia\u2019s condition was more complex than a single disorder. They didn\u2019t always know which symptoms aligned with a particular diagnosis and the chatbot was helping them connect the dots. <\/p>\n It was difficult, Matt Eaton recalled, but the couple was grateful to have their scientific training and experience using AI. \u201cWe were obviously having a tough time just with the realities of the diagnosis,\u201d he said. \u201cBut at least we can wrap our heads around it.\u201d<\/p>\n The Eatons\u2019 backgrounds make them ideal users of a large language model, several experts said. And rare diseases can be an excellent use case for the technology, said Arjun Manrai, an associate professor of biomedical informatics at Harvard Medical School.<\/p>\n \u201cThese are cases where there\u2019s a lot of information, but oftentimes an elusive missing diagnosis,\u201d said Manrai, who researches AI in health care. \u201cA lot of context can be given to these models to help us think through a second opinion or another differential diagnosis, which can then be taken back to physicians.\u201d<\/p>\n AI is now a fixture in the Eatons\u2019 lives. They rely on ChatGPT for helping them research and prepare for doctor appointments, using the chatbot to come up with questions they should ask.<\/p>\n And they\u2019ve seen results. <\/p>\n Olivia\u2019s low antibody levels had been worrying them ever since Eaton received the alarming test results on her phone last January. The chatbot helped them make sense of the results and offered possible treatments to ask about. One of the suggestions, a monthly IV treatment that pumps her full of healthy antibodies, ended up being what doctors recommended. <\/p>\n But that was still just a treatment \u2014 it didn\u2019t explain the root cause of Olivia\u2019s low antibodies. More sleuthing with ChatGPT around Olivia\u2019s other conditions would also help solve that mystery. <\/p>\n Eaton discovered another mutation that could explain why Olivia\u2019s scrapes took so long to heal, and why removing a Band-Aid could take off some of her skin. The finding, Eaton said, prompted doctors to order additional genetic testing, which in turn pointed them to a possible answer. <\/p>\n Olivia had Okur-Chung neurodevelopmental syndrome<\/a>, a rare genetic disorder that is estimated to affect only 1 in 100,000 people. The severity of symptoms can vary, but those with the disorder typically have some degree of developmental delay and differences in brain function. Symptoms can be treated, such as using physical therapy for motor delays. Doctors believed that the genetic mutation could also be affecting Olivia\u2019s ability to make antibodies.<\/p>\n Olivia started the IV treatment last fall, and her parents have seen a significant boost to her immune system.<\/p>\n \u201cShe\u2019s missed three days of school,\u201d Eaton said. \u201cThat\u2019s it.\u201d<\/p>\n Dr. Wendy Chung, one of Olivia\u2019s doctors and the co-discoverer of Okur-Chung syndrome, said the key for parents using alternative sources of information, like chatbots, is for it to be a partnership with medical providers.<\/p>\n \u201cThe more that each of us can do, powered by whatever tools we can do it [with], the better we get to answers, and the faster we get to the right path,\u201d said Chung, chief of the department of pediatrics at Boston Children\u2019s Hospital.<\/p>\n The couple partnered with doctors again this winter, when they noticed Olivia began displaying unusual motor tics, such as grimacing uncontrollably. In preparation for a medical appointment, Eaton once again fired up ChatGPT. <\/p>\n \u201dWe are going to see a neurologist for a new patient intake \u2014 what should we expect, what tests should we ask for?\u201d she typed.<\/p>\n One suggestion was to talk to the doctor about doing an EEG, a test that measures electrical activity in the brain. In February, during Olivia\u2019s first appointment with Dr. John McLaren, a neurologist at Children\u2019s Hospital, Eaton brought up the test.<\/p>\n \u201cEEGs are not necessarily done in kids that do not have clinical suspicion or clinical manifestations of seizure,\u201d McLaren recalled explaining. But in Olivia\u2019s case, they both agreed an EEG could still be worth trying. It would be a way of \u201csort of \u2018peeking under the hood,\u2019\u201d McLaren said. <\/p>\n Less than an hour after getting the EEG, Olivia and her mother were shopping for fuzzy pajama pants \u2014 a reward for enduring the test \u2014 when Eaton\u2019s phone rang. It was Dr. McLaren. He had the results. <\/p>\n \u201cHey, are you sitting down?\u201d he asked. <\/p>\n \u201cI was like, \u2018No, I\u2019m standing up in a fuzzy pajama pants shop,\u2019\u201d Eaton recalled responding.<\/p>\n The results showed Olivia had abnormal brain activity, which might indicate she was prone to having seizures. He was getting the pharmacy to fill a prescription for an anti-seizure medicine. Olivia should start taking it in the next hour. <\/p>\n Once on medication, Olivia finally began sleeping through the night. \u201cThis kid has not slept through the night since she was born,\u201d Eaton said. <\/p>\n On a Saturday in August, Olivia, now 7, raced around her house in Winchester. Her father trailed behind her. <\/p>\n They needed to leave for Children\u2019s, but Hospital Moose was missing. The stuffed animal with a blood pressure cuff on one leg wasn\u2019t inside the duffel bag full of games, snacks, and other toys that Matt Eaton regularly lugged to the hospital. It was time for another monthly IV infusion of antibodies, a procedure that could take hours. <\/p>\n \u201cIs this going to be her last one?\u201d Fiona asked her mother.<\/p>\n It unfortunately wasn\u2019t, Eaton responded. Although Olivia isn\u2019t sick all the time anymore and gets enough sleep during the night, her health journey isn\u2019t over. There\u2019s no growing out of genetic mutations, but the Eatons said they feel a measure of relief knowing they\u2019ve been able to get some answers and manage the symptoms.<\/p>\n They\u2019ve also been diving deeper into Fiona\u2019s genome. The bespectacled 9-year-old\u2019s data revealed two mutations related to metabolic processing. From some initial research, Eaton learned that one of the mutations might be affecting how Fiona\u2019s body processes creatine, which supplies energy to muscles.<\/p>\n Or, at least that\u2019s what she thought for now. <\/p>\n \u201cI\u2019m not an expert yet,\u201d Eaton said, \u201cbecause I haven\u2019t spent enough time with ChatGPT.\u201d <\/p>\n Allyson Chiu can be reached at allyson.chiu@globe.com<\/a>. Follow her on X @_allysonchiu<\/a>.<\/p>\n![\"Olivia](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/09\/GFKVTIIRJ2JXHQKHKC24CV6LMM.JPG\")
Olivia prepared to go out to the garden with her mother. Meleck Eldahshoury for The Boston Globe<\/p>\n![\"Olivia](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/09\/P32VLI74WUZCQGITVDU4RRSPVU.JPG\")
Olivia (left) and big sister Fiona made crafts with their father, as their mom looked at a family medications chart on her laptop.Meleck Eldahshoury for The Boston Globe<\/p>\n![\"Hilary](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/09\/2KMHUPRG6WEMTSWQ4L4HDIP22E.JPG\")
Hilary Eaton keeps notes on a calendar, tracking Olivia’s symptoms.Meleck Eldahshoury for The Boston Globe![\"Olivia](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/09\/CSFC4FMNUGS574MMMNWESKCBCI.JPG\")
Olivia and her mother harvested peppers in their vegetable garden at home. Meleck Eldahshoury for The Boston Globe<\/p>\n![\"“Olivia,](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/09\/HROSA55Y7V6ATHEZIAEN3IYXYU.JPG\")
\u201cOlivia, are you going to remind me where to turn?\u201d her father asked on the way to an August appointment at Boston Children’s Hospital. Focused on a workbook, she promptly responded, \u201cI might be looking at this.\u201dMeleck Eldahshoury for The Boston Globe<\/p>\n![\"A](\"https:\/\/www.newsbeep.com\/us\/wp-content\/uploads\/2026\/09\/5V262I3DME44QJRAYYLPJJUHFI.JPG\")
A nurse measured Olivia\u2019s height.Meleck Eldahshoury for The Boston Globe<\/p>\n