A while back my wife saw her doctor for an ongoing health concern. After one or two visits her primary care physician recommended that she see a specialist. She made repeated visits to the specialist, who ordered multiple tests. The specialist ordered an X-ray, then a CT scan and a subsequent MRI. Along the way there was a urinalysis and other lab work. Hindsight is 20/20 as they say, but my wife’s health issue should have been easily diagnosed and resolved in one visit with a follow-up visit or two to confirm the treatment was working. Years later we still wonder why an obvious diagnosis was missed and what could have been done to avoid unnecessary care.
Why do I say the diagnosis was obvious? I recently entered a one-sentence description of the problem into Google, and it told me the exact cause and listed a variety of websites discussing treatments. I also entered the one-sentence description into Microsoft’s AI platform, Copilot, and it also spelled out the problem and a treatment that ultimately worked. If you are wondering why my wife did not try Dr. Google years ago, it is because these physicians’ visits occurred before AI was a thing, although Google probably would have helped.
The root cause of the problem is our dysfunctional health care system. Due to the convoluted way most medical care is reimbursed, about two-thirds to three-fourths of physician revenue goes to cover the overhead. That is why doctors are so rushed. In addition, there are an estimated 300,000 official medical guidelines originating from tens of millions of research papers. Physicians need to understand the various guidelines and treatment protocols for their area of practice and refer patients to specialists when specialized care is needed. Doctors are under a lot of pressure to observe and discuss a health problem with a patient during a 10-minute office visit and spit out a solution like a Pez candy dispenser in the remaining 5-minutes of the visit. It is a lot to expect, but there is hope on the horizon.
Artificial intelligence (AI) has the potential to revolutionize medical care and diagnosis, assisting doctors but not replacing them. AI is already used to assist reading mammograms and documenting physician visits into medical records. Patients themselves now have access to powerful AI tools well beyond platforms like Copilot and Google. The following is from Kaiser Family Foundation (KFF) Health News:
When Judith Miller had routine blood work done in July, she got a phone alert the same day that her lab results were posted online. So, when her doctor messaged her the next day that her overall tests were fine, Miller wrote back to ask about the elevated carbon dioxide and low anion gap listed in the report.
While the 76-year-old Milwaukee resident waited to hear back, Miller did something patients increasingly do when they can’t reach their health care team. She put her test results into Claude and asked the AI assistant to evaluate the data.
“Claude helped give me a clear understanding of the abnormalities,” Miller said. The generative AI model didn’t report anything alarming, so she wasn’t anxious while waiting to hear back from her doctor, she said.
I wrote about the power of the Internet to boost medical information about diseases and conditions more than 20 years ago in my dissertation. At that time, I could not have envisioned what lay ahead. You too can experiment with Claude AI. If you want a dedicated, top-of-the-line medical AI chatbot, Dr. Oracle claims to be the World’s most powerful medical artificial intelligence platform. It also claims the highest score on the U.S. medical licensing exams of any of the medical AI platforms. Dr. Oracle Basic starts out at $5.99 a month for a limited number of questions per day. More robust plans, such as Dr. Oracle Pro offer unlimited access for higher monthly fees (~$25 I believe). As you would expect, some experts that KFF Health News talked to worried that patients are too uneducated to effectively benefit from access to these types of diagnostic tools. That is similar to attitudes when I began researching medical information on the Internet 25 years ago.
Dr. Oracle was designed for medical professionals, researchers, and medical students. Dr Oracle claims 53,000 medical professionals use the platform. A sample question on the website:
Can a nasogastric (NG) feeding tube cause bacterial pneumonia in a patient with severe Herpes Simplex Virus-1 (HSV-1) Encephalitis during the final days of a 21-day treatment cycle with Acyclovir (antiviral medication)?
Here is the answer, along with medical guidelines, links to research papers and related questions and answers. You can also ask follow-up questions.
Many physicians use clinical documentation software, such as Pabau Practice Management, Scribe Create, Carepatron, Raintree Systems, DeepCura AI and numerous others. While capturing symptoms and patient complaints for the medical record, that is an ideal time to link to potential diagnoses.
Read more at KFF Heath News: An AI Assistant Can Interpret Those Lab Results for You