IBM’s Jeopardy-champion computer, Watson, has huge potential for helping physicians and other clinicians work with patients.
The leap from TV game show to physicians’ offices will probably take at least two years. But Watson’s understanding of natural language, vast storehouse of information and ability to keep up with rapidly changing medical research could significantly improve medical care.
The medical faculty at Columbia University and University of Maryland are helping program a Watson-type computer to assist clinicians.
A few years from now, consulting Watson could become a routine part of a clinician’s practice. Caregivers have traditionally resisted computerized assistance in diagnosis and treatment because the technology has been awkward to use and questionnaire-based systems have been too rigid. But Watson can “understand” descriptions of a patient’s symptoms in natural language, and it can even scan years of medical records and doctors’ notes to determine what diagnostic and therapeutic options it might suggest. Doctors can ask it questions using the same terms they would use in an e-mail to a colleague.
The amount of medical knowledge is doubling every five to seven years, according to various estimates. It’s impossible for anyone to keep up, but Watson could. It could also review the medical histories that patients accumulate as they age. In the next few years when genetic tests for all become commonplace, Watson would be able to analyze them, too. That will be challenging for most primary care physicians.
One quarter of all medical errors involve misdiagnosis or delayed diagnosis. For example, it often takes over 10 years before a patient is correctly diagnosed with celiac disease, which can cause malnutrition, stomach pain and constant diarrhea because the patient can’t digest gluten. It takes an average of four years to diagnose multiple sclerosis. Doctors fail to suspect these diseases because they have many symptoms that suggest more common problems.
Watson, by using the same capability it used on Jeopardy, can search its vast memory for a likely diagnosis. Then it may say that the evidence it has points with 88% confidence to the patient having dermatitis, but that there’s also a 6% likelihood she has celiac disease, something the doctor might not have even considered.
As is demonstrated weekly on TV shows like “House,” correctly reaching a rare diagnosis may be an exciting, glamorous aspect of medicine. But in practice, figuring out even common diagnoses with increased confidence, accurately and quickly, can keep scores of patients more healthy, getting them on treatment paths sooner.
Prescribing treatment is difficult because “one size doesn’t fit all”. A clinician doesn’t need Watson to treat high blood pressure. But Watson might help if the patient is an 80-year-old diabetic with prostate problems, because he may not be able to take certain medications. Watson could backstop a doctor with suggestions and warnings.
Most clinicians believe in practicing evidence-based medicine, which is a central theme of recent changes to U.S. health care laws. But it’s very difficult for a caregiver to extrapolate the results of medical research to the special case of an individual. Watson could go through FDA records of adverse reactions to drugs to see if there were reasons a patient shouldn’t get a common prescription.
Because Watson understands what people mean when they write in ordinary English, it could be trained to be an omnivorous reader of all sorts of both standard and unorthodox medical literature. The information to inform a clinician’s choices is out there somewhere.
Watson’s ability to hit all those sources of information could one day make it an indispensable aid to caregivers.
This year marks IBM’s Centennial – and Watson is another example of a long history of healthcare innovations, including the 1981 invention of an excimer laser technique that made photorefractive (LASIK) eye surgery possible. IBM also played a major role in developing the heart lung machine in the 1950s, and invented the first continuous blood separator in the 1960s, used to treat critically ill leukemia patients.
Dan Pelino is general manager for the IBM Healthcare and Life Sciences business. He leads the corporation in helping clients create smarter, more connected health care systems, working closely with public and private health care providers and payers, biotech and pharmaceutical companies, and medical device and instrument companies. He is an expert in the areas of health care transformation and health IT. He has advised numerous countries and states on health care IT-related issues. Under his leadership, IBM has been involved in helping transform and digitize health systems worldwide.
Categories: Uncategorized
This section also has a website checker; submit the URL of the website that is selling the GHD flat iron, and it will tell you whether the website is authentic.
Wholesale Ray Ban http://natsumi-smile.com/a/ray-ban-china.php
http://journals.lww.com/journalpatientsafety/Abstract/2010/03000/Meaningful_Use_of_Computerized_Prescriber_Order.3.aspx
” This paper has presented an update to the National Quality Forum Safe Practice on CPOE for 2010. Although the practice itself has not changed, the scientific evidence of the impact of CPOE on medication safety and quality of care continues to accumulate.”
You are rather naive to make such vapid statements, or giving you the benefit of the doubt, you know nothing about patients and clinical care.
You said: “Most clinicians believe in practicing evidence-based medicine, which is a central theme of recent changes to U.S. health care laws. But it’s very difficult for a caregiver to extrapolate the results of medical research to the special case of an individual. Watson could go through FDA records of adverse reactions to drugs to see if there were reasons a patient shouldn’t get a common prescription.”
Thanks for bringing up matters of evidence. There is not any evidence that CPOE or decision support devices are safe, efficacious, or usable for clinical care. The adverse events have been covered up. There is not any vetting for such safety and efficacy nor is there any evidence for improved outcomes. Watson is merely another patient.
As the grande clinician and professor, Abe Verghese, of Stanford, recently stated in a NY Times Op-Ed, have Watson provide the question to the following answer: “An emergency treatment that is administered by ear”.
All the recent studies have shown an increase in doctor usage of Google, they even made a long video showing how to use Google to help your medical practice. If you can trust Google results I don’t see why a “superpowerful” computer shouldn’t help. Of course as long as this is being used as an additional resource and not as a doctor replacement…
“Caregivers have traditionally resisted computerized assistance in diagnosis and treatment because the technology has been awkward to use and questionnaire-based systems have been too rigid.”
This may be true but I think a bigger obstacle is that physicians don’t trust the computer and that they think they are smarter than the computer. They don’t think that a computer could be much use since each patient is special and each doctor is also special.
Doctors also don’t like “evidence based medicine”. They regularly brand it as “cookbook” medicine and they think they know better because they are special and their patients are special.
The computer could be of great benefit to patients but it will be difficult to get past the gatekeeper doctor.
Indeed, this type of algorithm-driven pattern recognition combined with huge amounts of clinical data is an ideal application of AI programs such as Watson. Additionally, the lack of learned bias in a piece of software is another major advantage. The problem with human experience is that it while it learns to filter for relevant information, it isn’t always so good at determining the relevance of and accuracy of those filters. Software has no such problems, and will apply the algorithm consistently in each case.