Artificial intelligence moves into the MS exam room. But should it?
Despite many positive features, questions remain about the use of AI diagnoses
Is artificial intelligence (AI) intelligent enough to help make a diagnosis of multiple sclerosis (MS)? Apparently so, and more.
In the United Kingdom, a project named AssistMS is studying whether AI can be used to detect and highlight changes on brain MRIs. An algorithm software called icobrain MS is said to be able to detect lesions in the brain, measure brain volume, and report on how each of these changes over time.
“Neurologists will be able to get a much more accurate idea of how each patient’s disease course is progressing and, in turn, to recommend the best possible treatment for that person,” said Rachel Horne, an MS patient and the patient and public involvement lead for AssistMS.
A study review published in February 2022 in the journal Multiple Sclerosis and Related Disorders predicts that “with advances made in AI, the way we monitor and diagnose our MS patients can change drastically.”
These researchers reviewed 38 studies covering 5,433 people. Of these, 2,924 were people with MS; the rest were healthy controls. Diagnostic tools such as MRI, OCT, spinal fluid examinations, and simple observations of patients’ movements were compared with AI. Many of the studies reported that AI was 100% correct in detecting signs of MS, and many others reported at least 75% accuracy.
Proceed with caution
It seems as if we can use artificial intelligence in the process of diagnosing, and possibly treating, MS, but does that mean we should use it? In an article published on March 27 in JAMA Network, a trio of researchers suggest we look carefully before we leap.
These doctors caution that AI has “great potential, but early implementations have demonstrated the potential for harm, failure to perform, and furtherance of inequity.” They worry about reviews that, they say, show nearly all algorithms still fail to achieve substantial gains over what a human can do. They worry, too, that in complex AI systems, a lot of investigation is needed to confirm how the AI model arrived at its results.
A headline on an April 15 Bloomberg article puts it more bluntly: “We’re Not Ready to Be Diagnosed by ChatGPT.” Opinion columnist Faye Flam writes that some doctors are already experimenting to see if artificial intelligence can diagnose patients and choose treatments, and she worries about it, writing, “Whether this is good or bad hinges on how doctors use it.”
“It may act like it cares about you, but it probably doesn’t. ChatGPT and its ilk are tools that will take great skill to use well — but exactly which skills aren’t yet well understood,” Flam writes.
Ethics and standards for AI
The JAMA Network article cautions that healthcare ethics, oaths, and standards need to be followed. To accomplish this, the authors propose a code of conduct for AI in healthcare. Such a code would outline rules, norms, and expected behaviors for people who develop, test, and use algorithms. They also suggest that the code be comprehensive, easy to understand, and include a way of putting core values into practice in every stage of the algorithmic life cycle.
But an AI code of conduct is a pretty tall order to fill. I wonder if anyone has asked ChatGPT to write one.
Let us know how you feel about AI in the exam room by leaving a comment below. And you’re invited to visit my personal blog at www.themswire.com.
Note: Multiple Sclerosis News Today is strictly a news and information website about the disease. It does not provide medical advice, diagnosis, or treatment. This content is not intended to be a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition. Never disregard professional medical advice or delay in seeking it because of something you have read on this website. The opinions expressed in this column are not those of Multiple Sclerosis News Today or its parent company, BioNews, and are intended to spark discussion about issues pertaining to multiple sclerosis.
Gerardo L. Morales
I personally think as a SPMS progressively deteriorating patient, that all the studies, research, information, etc. be populated in. Ie. Watson and request cure, instead of wasting valuable time on known things. I’m just a suffering patient.
Useful but should only be used as a tool by a neurologiist (a human). Its information, could you call it knowledge, is probably based on the usual or norm. As we know, it is a snowflake disease. We do not all follow the same or usual patterns. Therefore we need the knowledge and adaptations of a neurologist.
Good points, Leanne. Thanks,
Have you heard of MS14, a supplement that could help MS symptoms?
I get flu symptoms often when I exert myself, have you experienced people that get the same?
Thanks for your time:))))
Hi Sherri -
It's a natural supplement made up of king prawns, celery, and St. John's wart. At least one study has shown it to improve physical activity. I've not heard of activity resulting in flu symptoms in people with MS. I've pretty active, exercising and swimming, and it's never happened to me. Here's an article we published about MS14. Ed
I expect 40 yrs from now, it’ll be commonplace. As to wether the money/medical world will accept it, who knows.
I suspect it will be a lot fewer than 40 years, Paula. Probably no more than ten...but guidelines (guardrails?) are needed.
Faye Flam's comments presume all doctors care and empathise with their patients. She must have been very lucky in her interactions with the medical profession. I am sad to say I would trust AI more than a doctor. As long as a patient is given accurate results, and a plan of treatment discussed in good time, most patients would be satisfied. Not all doctors are proficient or knowledgeable. The frightening part is they are too proud to admit it. My faith in the medical profession has been diminished greatly. I write as a very disappointed ex midwife.
Hi Eve -
You make a good point about a lack of empathy and a lack of knowledge about MS among some doctors. And, AI seems to be very good about helping with a diagnosis and proposed treatment. I think partnership is needed between human and the machine. It might help some of those doctors who are lacking.
If AI can determine the cause of MS it may be possible to treat the disease. It could be a toxin, a pesticide, vaccines, germ warfare, chemicals, artificial sweetener, anything man made. There may be a common thread in all the levels of MS. I have seen a rise in MS in the past 20 years. More and more children are being diagnosed with MS.
I'm not sure whether the rise in MS diagnoses is due to an increase in the illness or just better diagnostic techniques...including realizing that children aren't exempt. That aside, if AI can serve as another diagnostic tool to help neurologists make that DX, and even suggest a treatment course, go for it.