This is a topic I have often discussed with friends so I was very interested to read the following.
AI can reinvent clinical decision support, but obstacles remain
January 06, 2020, 12:03 a.m. EST
While artificial intelligence has the potential to address the epidemic of diagnostic errors in healthcare, the industry must overcome the challenges and limitations of these new digital tools.
That’s the contention of a new book on clinical decision support co-authored by John Halamka, MD, president of the Mayo Clinic Platform, and healthcare writer Paul Cerrato.
“Algorithms that take advantage of machine learning, neural networks and a variety of other types of artificial intelligence (AI) can help address many of the shortcomings of human intelligence,” explain Halamka and Cerrato, who make the point that the complexity of medicine now exceeds the capacity of the human mind.
The book’s authors contend that such complexity “requires humility for clinicians with years of experience successfully diagnosing patients’ ills to admit that they may be missing as many disorders as they catch.”
Nonetheless, while AI has the potential to address many of the shortcomings of human intelligence, the authors also outline in the book the criticisms, obstacles and limitations of this technology—including the fact that the evidence to show that it is having an impact on patient outcomes is mixed.
“Among the criticisms discussed is the relative lack of hard scientific evidence supporting some of the latest algorithms and the ‘explainability’ dilemma,” write Halamka and Cerrato. “Most machine learning systems are based on advanced statistics and mind-bending mathematical equations, which have made many clinicians skeptical about their worth.”
Much more here:
At the same time we read this:
From Google to the iPhone: How technology in healthcare has evolved
As we enter a new decade, Haidar Samiei, consultant in emergency medicine and clinical director at EMIS Health, takes us back to New Year’s Eve 1999 to reflect on how technology in healthcare has evolved.
DHI News Team – January 7, 2020
Who remembers New Year’s Eve 1999?
For most it was a night of partying, for others a period of reflection, and for a few it was a time of uncertainty. We weren’t sure what the new millennium would bring, with crazy stories circulating that the world was going to end. Even if the apocalypse didn’t happen at midnight, the Millennium Bug might strike and we wouldn’t be able to turn on a computer.
As a junior doctor, I was working in A&E that night. I will have been an SHO 1 (FY2 in current terminology). It’s actually difficult to explain the intricate circumstances/interactions that show just how information poor life as a junior doctor was back then.
Not only was Google in its infancy, but the thought of using the internet to inform a decision on how to treat a patient was unthinkable.
We didn’t have an intranet brimming with up to date content either. Any specialist pathway or treatment regime had to be designed, photocopied, laminated, distributed and lord forbid should a pathway change, the whole process restarted.
Mobiles were not allowed in hospitals because, I don’t actually remember why. Wi-Fi wasn’t around then, so it can’t have been interference, but there was some way in which mobiles would almost certainly cause hospitals to blow up. I remember that, and the big posters everywhere.
When it comes to getting expert advice, we had the pager system. Our consultants left at 5pm, and our registrars at 10pm. After that, there was no one to ask for advice other than two fellow junior doctors. Specialists didn’t even carry phones. Imagine replacing your consultant, registrar, intranet, Google, mobile etc with a pager and some textbooks on a night shift, in a tertiary emergency department.
21st Century toys
When the iPhone was launched in 2007, I realised that the mobile phone, and more over mobile communication, would change the world, and that medicine couldn’t remain immune.
Using mobiles in a clinical setting came up against a lot of resistance, at first because of hospitals potentially blowing up, but after that just about any reason anyone could think of: battery life, infection control, wireless reception.
More here:
The first article points out – as clearly as one might need to read it “the complexity of medicine now exceeds the capacity of the human mind”
The second makes it clear mobile technology is evolving and clinical decision support can go part way to helping, but that the changes and transitions to have all this effective are really only beginning.
What is clear is that there is a lot of work to integrate technology into clinical work flows in such a way that the knowledge support is both fully trustworthy and safe.
I suspect this area will become increasingly important going forward. Watch this space!
David.
No comments:
Post a Comment