Dr. Matthew Hitchcock, a family physician in Chattanooga, Tennessee, has an AI assistant.
It records patient visits on his smartphone and summarizes them for treatment plans and billing. He does some light editing of what the AI produces, and completes his daily patient visit documentation in about 20 minutes.
Dr. Hitchcock would spend up to two hours typing these medical notes after his four children had gone to sleep. “It is a thing of the past,” he said. “It is quite wonderful.”
ChatGPT-style artificial intelligence is coming to health care, and the grand vision of what it could bring is inspiring. Enthusiasts predict that every doctor will have a superintelligent sidekick, who will make suggestions to improve care.
But first will come more mundane applications of artificial intelligence. A major goal will be to reduce the burden of digital paperwork that physicians must create by typing long notes into electronic medical records needed for treatment, billing and administrative purposes.
For now, the new AI in health care is going to be a genius partner rather than a tireless author.
From leaders of major medical centers to family physicians, there is optimism that health care will benefit from the latest advances in generative AI – technology that can craft everything from poetry to computer programs, often with human-level fluency .
But doctors stress that medicine is not a wide open field of experimentation. AI’s tendency to produce occasional concoctions or so-called hallucinations can be amusing, but not in the high-risk area of health care.
This, he says, makes generative AI very different from AI algorithms already approved by the Food and Drug Administration for specific applications, such as scanning medical images for cell clusters or subtle patterns that may indicate the presence of lung or breast cancer. make suggestions. Doctors are also using chatbots to communicate more effectively with some patients.
Physicians and medical researchers say regulatory uncertainty, and concerns about patient safety and litigation, will slow the acceptance of generic AI in health care, particularly its use in diagnosis and treatment planning.
Physicians who have tried the new technology say its performance has improved markedly in the past year. and medical note software designed so doctors can check AI-generated Summarizing the words spoken during a patient visit, making it verifiable and fostering trust.
“At this stage, we have to choose our use cases carefully,” said Dr. John Halamka, president of the Mayo Clinic Platform, which oversees the adoption of artificial intelligence in health systems. “Reducing the burden of documentation would be a big win in itself.”
Recent studies show that doctors and nurses report high level of burnout, Excitement Many people will leave this profession. At the top of the list of complaints, especially for primary care physicians, is the time spent on documentation of electronic health records. That work often lasts into the evening, after the drudgery of office hours, which doctors call “pajama time.”
Generative AI looks like a promising weapon to combat the physician workload crisis, experts say.
“At a time when health care needs help, this technology is improving rapidly,” said Dr. Adam Landman, chief information officer at Mass General Brigham, which includes Massachusetts General Hospital and Brigham and Women’s Hospital in Boston. “
Over the years, doctors have used a variety of documentation aids, including speech recognition software and human transcribers. But the latest AI is doing far more: summarizing, organizing and tagging interactions between doctor and patient.
Ten physicians at the University of Kansas Medical Center have been using the generative AI software for the past two months, said Dr. Gregory Ettore, an ear, nose and throat specialist and the center’s chief medical informatics officer. The medical center plans to eventually make the software available to its 2,200 physicians.
But the Kansas health system is shying away from using generic AI in diagnosis, worried that its recommendations could be unreliable and its reasoning not transparent. Dr. Ator said, “In medicine, we cannot tolerate hallucinations.” “And we don’t like black boxes.”
The University of Pittsburgh Medical Center has been a testing ground for Abridge, a start-up led and co-founded by Dr. Shivdev Rao, a practicing cardiologist who is part of the medical center’s venture arm. He was also an executive.
Abridge was founded in 2018, when the technology engine for large language models, Generative AI, emerged. Technology, Dr. Rao said, opened the door to an automated solution to the clerical overload in health care that he saw around him, even for his own father.
Dr. Rao said, “My father retired early.” “He couldn’t type fast enough.”
Today, Abridge software is used by more than 1,000 physicians in the University of Pittsburgh Medical System.
Dr. Michelle Thompson, a family physician in Hermitage, PA, who specializes in lifestyle and integrative care, said the software freed up about two hours of her day. Now, she has time to take a yoga class, or sit down and have dinner with the family.
Another benefit, Dr. Thompson said, is to improve the patient visit experience. No more typing, note taking or other distractions. She simply asks permission from patients to record their conversations on her phone.
“As a physician, AI has allowed me to be 100 percent present for my patients,” he said.
The AI tool has also helped patients become more engaged in their care, Dr. Thompson said. Immediately following the visit, the patient receives a summary, which can be accessed through the University of Pittsburgh Medical System’s online portal.
The software translates any medical terminology into general English at approximately the fourth grade reading level. It also provides recording of visits with color-coded “medical moments” for medications, procedures, and diagnoses. The patient can click on a colored tag and hear part of the conversation.
studies show that Patients forget up to 80 percent What doctors and nurses say during visits. The recorded and AI-generated summaries of visits are a resource that their patients can return to for reminders to take medications, exercise, or schedule follow-up visits, Dr. Thompson said.
After the appointment, physicians receive a clinical note summary for review. There are also links to transcripts of doctor-patient interactions, so that the AI’s work can be checked and verified. “It’s really helped me build my confidence in AI,” Dr. Thompson said.
In Tennessee, Dr. Hitchcock, who also uses Abridge software, has read reports of ChatGPT getting higher scores on standard medical tests and heard predictions that digital doctors will improve care and solve staffing shortages.
Dr. Hitchcock has tried ChatGPT and is impressed. But for legal, regulatory and practical reasons, they would never have thought of loading a patient’s record into a chatbot and asking for a diagnosis. For now, he’s grateful to have his evenings free, no longer bogged down in the tedious digital documentation required of the American health care industry.
And they see no technology solution to the health care staff shortage. “AI isn’t going to fix it anytime soon,” said Dr. Hitchcock, who is looking to hire one more doctor for his four-physician practice.