AI might come out on top when harvesting and analysing swathes of data but there\u2019s still a long way to go \u2014 it\u2019s doubtful the robots are ever going to put doctors out of a job.<\/p>\n
Is AI better than my doctor?<\/p>\n
An AI system developed by the boffins at Harvard University dubbed Dr CaBot has shown what is possible.<\/p>\n
In July, when was pitted head-to-head with an expert diagnostician in a demonstration that was likened to the 1997 chess match between chess Grand Master Garry Kasparov and IBM supercomputer Big Blue (which won), Dr CaBot was astonishingly quick and accurate.<\/p>\n
Dr Daniel Restrepo was given six weeks to prepare his diagnosis presentation. Dr CaBot got six minutes.<\/p>\n
Given a case study of a 41-year-old man who had come to the hospital with 10 days of fevers, body aches, swollen ankles, a patient rash and two instances of fainting, Dr Restrepo diagnosed the patient with Lofgren syndrome.<\/p>\n
Then it was Dr CaBot\u2019s turn. In a warm woman\u2019s voice, it talked through its diagnostic reasoning, generating a range of possibilities and noting their strengths and weaknesses.<\/p>\n
\u201cPutting it together, the single best fit is acute sarcoidosis manifesting as Lofgren syndrome,\u201d it concluded.<\/p>\n
In China, they are having equally incredible results.<\/p>\n
At a Shanghai medical AI skills competition on November 20, four masked physicians from top Shanghai hospitals split into two teams to face-off against two different AI systems \u2014 a gastrointestinal multimodal AI and an international AI system \u2014 to diagnose a real-life case.<\/p>\n
The AI produced diagnoses in under two seconds while the doctors took 13 minutes, China\u2019s state-run media reported.<\/p>\n
The international model reportedly fell slightly short on diagnostic accuracy, while the Shanghai-built gastrointestinal AI model, which was trained on 30,000 real cases and can read endoscopy and CT scans, matched the diagnosis of the doctors and their recommendations for treatment.<\/p>\n
So, what does that all mean for the future of medical diagnosis?<\/p>\n
Well, AI won\u2019t be replacing doctors anytime soon. But those doctors who embrace it will definitely replace those who don\u2019t and they will reap the benefits of improved diagnostic accuracy, reduced administrative load and better triaging of patients.<\/p>\n
Why shouldn\u2019t I use ChatGPT to diagnose myself?<\/p>\n
It might be slightly better than diagnosing yourself from a TikTok video or an Instagram reel, but Open AI\u2019s ChatGPT and large language models like it are not fool proof and in fact can get things just plain wrong.<\/p>\n
While people have been consulting \u201cDr Google\u201d for years, these tools bring something different to the table. A feeling that for some mimics a doctor\u2019s consultation.<\/p>\n
Overconfidence of some of these AI tools can mean that they take patients down the wrong path and down rabbit holes<\/p>\n
A patient lays out their symptoms and the chatbot gives its best answer, specific to what it is asked \u2014 not just a list of documents that might be helpful as with Google \u2014 to diagnose what ails them.<\/p>\n
\u201cIt\u2019s nothing new for us really in general practice that patients have sought their own information out before they come to see us . . . but obviously AI has changed the tools that patients are using and how they access information,\u201d GP and Australian Digital Health Agency chief clinical advisor Dr Amandeep Hansra told The Nightly.<\/p>\n
\u201cThey might go to ChatGPT or other large language model AI tools and try and work out what they think the doctor\u2019s going to say or what they might suggest as a diagnosis.<\/p>\n
\u201cThe core relationship hasn\u2019t changed. I still need to help them interpret the information that they\u2019ve brought to my consult, and I still need to continue contextualise and personalise that care.\u201d<\/p>\n
Depending on the information you feed into it: age, gender, past medical history. The answers you get back can feel like it\u2019s talking specifically about you, meaning patients are more likely to believe it is 100 per cent right.<\/p>\n
But that\u2019s not always the case.<\/p>\n
\u201cOverconfidence of some of these AI tools can mean that they take patients down the wrong path and down rabbit holes,\u201d Dr Hansra said.<\/p>\n
She recalled an experience with one patient who was convinced the diagnosis and recommended treatment that she gave for a common ailment was wrong because ChatGPT had told them otherwise.<\/p>\n
\u201cI met the patient did my normal consult and the patient had already looked to ChatGPT and decided what treatment they wanted. They wanted a specific medication which I didn\u2019t prescribe for them.\u201d<\/p>\n
Dr Hansra had to explain why she was right and ChatGPT had it wrong.<\/p>\n
The difference, she said, was that she had examined the patient and the AI tool hadn\u2019t.<\/p>\n
\u201cPatients forget that when we\u2019re assessing them, we\u2019re taking a lot of different things into consideration and also our experience. I\u2019ve been a GP for 20 years, that experience counts for something versus what an AI tool can find on the internet.\u201d<\/p>\n
\u201cI think it\u2019s really important that people do check anything that they\u2019ve got from these AI tools with their regular treating practitioner because I have seen these tools be super confident at things that are very clearly wrong.\u201d<\/p>\n
![\"Sam](\"https:\/\/www.newsbeep.com\/il\/wp-content\/uploads\/2025\/12\/7727c12db7d08f2165a86ea507ab02127bad6437.jpg\")
Sam Altman, chief executive officer of OpenAI, agrees people shouldn\u2019t just rely on ChatGPT for a diagnosis. Credit: Kyle Grillot\/Bloomberg<\/p>\n
Even Open AI founder Sam Altman agrees. In August he told a conference in the US that ChatGPT was already surpassing human doctors in diagnostic accuracy.<\/p>\n
\u201cChatGPT today, by the way, most of the time, can give you better \u2013 it\u2019s like, a better diagnostician than most doctors in the world,\u201d he said.<\/p>\n
\u201cYet people still go to doctors, and I am not, like, maybe I\u2019m a dinosaur here, but I really do not want to, like, entrust my medical fate to ChatGPT with no human doctor in the loop.\u201d<\/p>\n
Australian e-Health Research Centre director Dr David Hansen said understanding exactly how large language models such as Chat GPT arrived at their answers was really important.<\/p>\n
\u201cIt\u2019s been trained on a lot of data and it will use a statistical method to form sentences based on the input, and that seems to work really well most of the time,\u201d Dr Hansen told The Nightly.<\/p>\n
\u201cBut also don\u2019t take it as gospel. It\u2019s just as important to make sure you do go through the normal process of talking to a real doctor, who may also be using AI tools but they\u2019re doing it in in educated way.\u201d<\/p>\n
Dr Hansen said the Health Department\u2019s Healthdirect symptom checker was probably a better tool. He said that had been trained on medical data and was continually revised and checked through rigorous testing.<\/p>\n
How is AI listening in on my consultation?<\/p>\n
Beyond diagnosis, for some doctors, other tools such as ambient medical scribes are helping keep them in the profession.<\/p>\n
Probably one of the most noticeable incursions of AI into a doctor\u2019s room, these tools free doctors from the need to take manual notes and allow them to look their patients in the eye during a consultation.<\/p>\n
Developmental paediatrician Kim Drever was on the brink of bowing out in mid-2022 because the COVID pandemic and a growing roster of patients who were struggling had piled on the pressure.<\/p>\n
Her job requires her to take extensive clinical notes and consult broadly with other professions, including GPs, schools and the justice system and she\u2019d become burnt out under an avalanche of paperwork and a system that was jammed.<\/p>\n
\u201cI just felt I couldn\u2019t be helpful anymore. . .(my job) is to help them get care in their community, the mental health or, you know, extra school help, or whatever it might be.<\/p>\n
\u201cI could not keep up and I just thought I can\u2019t be helpful, I\u2019m done, this is awful.\u201d<\/p>\n
But an AI scribe tool helped keep her in practice.<\/p>\n
The medical scribe \u201cgave me back my weekends and it also meant that I felt like I could be helpful because I could generate useful letters quickly and it could get things started for that family quickly\u201d.<\/p>\n
![\"Developmental](\"https:\/\/www.newsbeep.com\/il\/wp-content\/uploads\/2025\/12\/76f2b55c80dfa3ad10ffbfccf2647f2faa49cccf.jpg\")
Developmental Paediatrician Kim Dreve Credit: Supplied<\/p>\n
Up until recently, Dr Drever was an advisor to Lyrebird Health, one of about half a dozen AI scribe companies in Australia, working with the engineering team to help tailor it to the needs of those in her specialty, outlining the rules and scope of how it should work.<\/p>\n
\u201cFrom the very get-go, the potential of it was amazing, but it is no good to anyone if the design of it and the intent of it is not informed by people who are using it,\u201d she told The Nightly.<\/p>\n
\u201cScribes or anything that is kind of partnering with a doctor needs to act like us, but not think for us.\u201d<\/p>\n
She also noted it was important patients be made aware when AI was being used and to what degree doctors were relying on it.<\/p>\n
Why is it risky diagnosing yourself with ChatGPT?<\/p>\n
What the humans need to do, Dr Drever said, was to bring context to the huge amounts of data being taken in by AI tools.<\/p>\n
There are lots of different ways AI can be inaccurate, including hallucinations, where it completely makes something up. AI omissions, too, can be just as damaging.<\/p>\n
Dr Drever gave an example where she was using an ambient scribe during a consultation when a child made disclosures about being sexually abused.<\/p>\n
Relying on the scribe to take accurate notes that may one day be used in court proceedings, Dr Drever was alarmed to find it wasn\u2019t taking down the sensitive remarks because of restrictions imposed by Open AI and Amazon.<\/p>\n
This has since been resolved but could have been disastrous if Dr Drever hadn\u2019t resorted to transcribing by hand.<\/p>\n
\u201cFor me that omission could have been harmful to that child, right? Because then you\u2019d have to rely on my memory and maybe I didn\u2019t remember properly because you\u2019re relying on another tool that failed you.\u201d<\/p>\n
There are also inaccuracies where the AI tool can \u201chear\u201d things wrong, such as a blood pressure reading or a person\u2019s name.<\/p>\n
And if the AI gets it wrong and that has an impact for the patient, then it\u2019s the doctor that could be held legally liable.<\/p>\n
What is AI\u2019s potential for good?<\/p>\n
That aside, Dr Hansen is excited for what the future holds when it comes to AI in medicine, especially around genomics, imaging and precision medicine \u2014 finding the right treatments for individuals for everything from cancer to rare diseases.<\/p>\n
\u201cThat\u2019s an area where clinicians. . . really need to be leveraging what AI can offer to make sure that we\u2019re getting the best diagnosis as fast as we can.\u201d<\/p>\n
Dr Hansen said he expects AI tools will also be doing more triaging of patients.<\/p>\n
\u201cYou could do an AI consult beforehand and they could give you the blood test order and you go get your blood test before you go to the doctor so you can discuss the result,\u201d he said.<\/p>\n
\u201cSo there\u2019s lots of efficiencies that we can think of like triaging people and making sure they\u2019re going to the right place.\u201d<\/p>\n
But Dr Hansra is sceptical that AI will ever make doctors redundant, because to do so would be high risk.<\/p>\n
\u201cAI is really great at automating tasks and helping us sift through large amounts of information but I think health care itself relies on clinical judgment, ethical decision-making, empathy, understanding of the complexity of people\u2019s lives. . .all of those factors that come into our decision-making.<\/p>\n
\u201cI think the AI will help augment what we do, but I don\u2019t think it can replace what we do.\u201d<\/p>\n","protected":false},"excerpt":{"rendered":"If AI models can diagnose patients in seconds and large language tools such as ChatGPT are offering patients…\n","protected":false},"author":2,"featured_media":202296,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[34],"tags":[163,521,85,46,5087,125],"class_list":{"0":"post-202295","1":"post","2":"type-post","3":"status-publish","4":"format-standard","5":"has-post-thumbnail","7":"category-healthcare","8":"tag-health","9":"tag-healthcare","10":"tag-il","11":"tag-israel","12":"tag-society","13":"tag-technology"},"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/202295","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/comments?post=202295"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/posts\/202295\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media\/202296"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/media?parent=202295"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/categories?post=202295"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/il\/wp-json\/wp\/v2\/tags?post=202295"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}