Dr. Matthew Hitchcock, a family physician in Chattanooga, Tennessee, has an AI helper.
Record patient visits on your smartphone and organize them into treatment plans and bills. He easily edits his AI-generated content and records daily patient visits in about 20 minutes.
Dr. Hitchcock spent up to two hours typing these medical notes after his four children went to bed. “It’s in the past,” he said. “It’s pretty amazing.”
ChatGPT-style artificial intelligence is being introduced into healthcare, and the grand vision it can bring is exciting. Enthusiasts predict that every doctor will have a super-intelligent sidekick offering suggestions for improving their care.
But before that, more everyday applications of artificial intelligence will emerge. The primary goal is to alleviate the overwhelming digital paperwork burden that physicians have to enter and create long notes in electronic medical records for treatment, billing and administrative purposes.
For now, the new AI in medicine will be a tireless scribe rather than a genius partner.
From leaders of major medical centers to family physicians, there is optimism that healthcare will benefit from the latest advances in generative AI. Generative AI is a technology that can generate anything from poetry to computer programs with human-level fluency.
But doctors stress that medicine is not an area open to experimentation. The tendency of AI to create occasional fabrications, so-called hallucinations, may be interesting, but not in the high-stakes field of medicine.
As such, generative AI is very different from AI algorithms already approved by the Food and Drug Administration for specific uses, such as scanning medical images for cell clumps or subtle patterns that suggest the presence of lung or breast cancer. they say. Doctors are also using chatbots to communicate more effectively with some patients.
Physicians and medical researchers say regulatory uncertainty, patient safety and litigation concerns will slow the acceptance of generative AI in medicine, especially for its use in diagnosis and treatment planning.
“At this stage, we need to choose our use cases carefully,” said Dr. John Halamka, president of the Mayo Clinic Platform, which oversees the adoption of artificial intelligence in the health care system. “Reducing the burden of creating documentation would be a huge win in itself.”
Recent studies show that doctors and nurses report: high levels of burnout, prompt Many quit their jobs. High on the list of complaints, especially for primary care physicians, is the time spent documenting electronic medical records. The work often extends to hard work in the evenings after work hours, which doctors call “pajama time.”
Experts say generative AI looks like a promising weapon to combat the physician workload crisis.
“This technology is advancing rapidly at a time when healthcare needs help,” said Dr. Adam Landman, chief information officer for Massachusetts General Brigham, which includes Massachusetts General Hospital and Brigham and Women’s Hospital in Boston. There are,” he said.
Over the years, physicians have used various types of documentation aids, including speech recognition software and human transcription. But modern AI is doing more than that, summarizing, organizing, and tagging doctor-patient conversations.
Companies developing this type of technology include: Abridge, Ambience Healthcare, AugMedics, nuanceis part of Microsoft, and like.
Ten doctors at the University of Kansas Medical Center have been using generative AI software for the past two months, said Dr. Gregory Atholl, an otolaryngologist and chief medical informatics at the center. The medical center eventually plans to make the software available to 2,200 doctors.
However, the Kansas health system has avoided using generative AI for diagnosis, fearing that its recommendations may be unreliable and its inferences opaque. “In medicine, hallucinations are unacceptable,” says Dr. Atholl. “And we don’t like black boxes.”
The University of Pittsburgh Medical Center is a testbed for Abbridge, a startup led and co-founded by Dr. Shivdev Rao, a practicing cardiologist who is also an executive in the medical center’s venture arm.
Abridge was founded in 2018 with the advent of Large Language Models, the technology engine for generative AI. According to Dr. Rao, the technology has opened the door to automated solutions to medical overload. Dr. Rao said he saw the same situation in his own circle and in his own father.
“My father retired early,” said Dr. Rao. “He just couldn’t type fast enough.”
Today, Abridge software is used by more than 1,000 physicians in the University of Pittsburgh healthcare system.
Dr. Michelle Thompson, a Hermitage, Pennsylvania family physician who specializes in lifestyle and integrated care, said the software freed up nearly two hours of her day. Now she has time to attend yoga classes or sit down and have dinner with her family.
Another benefit, Dr. Thompson said, is an improved patient experience. No more typing, note-taking or other distractions. She simply asks the patient for permission to record the conversation over the phone.
“AI has made me 100% available as a doctor to my patients,” she said.
Thompson added that AI tools have also helped patients become more engaged with their treatments. Immediately following the consultation, patients will receive a summary that can be accessed through the University of Pittsburgh Health System online portal.
The software translates any medical terminology into plain English at a 4th grade reading level. It also provides a record of visits with ‘Medical Moments’ color-coded by medication, procedure and diagnosis. Patients can click on colored tags to listen to snippets of the conversation.
According to research, Patients forget up to 80% What the doctor or nurse said during the examination. Dr. Thompson said visit summaries recorded and generated by AI are a resource that patients can return to to remind them to schedule medications, exercise, or return visits.
After the examination, your doctor will receive and review a summary of your clinical records. There is a link to the recording of the doctor-patient conversation so you can see and validate the AI in action. “It helped us build trust in AI,” said Dr. Thompson.
In Tennessee, Dr. Hitchcock, who also uses Abridge software, read reports that ChatGPT scored high on standard medical tests and predicted that digital doctors would improve care and solve staffing shortages. I’m listening
Dr. Hitchcock tried ChatGPT and was impressed. But for legal, regulatory, and practical reasons, we would never have thought of loading patient records into a chatbot and asking for a diagnosis. For now, he’s grateful that his nights are free and he doesn’t have to bother with the tedious digital documents that America’s medical industry demands.
And he believes there is no technology solution to the medical staffing shortage. “AI isn’t going to solve this problem anytime soon,” said Dr. Hitchcock, who is hiring another doctor for a four-doctor practice.
