#medicalai

waynerad@diasp.org

"Xaira, an AI drug discovery startup, launches with a massive $1B, says it's 'ready' to start developing drugs."

$1 billion, holy moly, that's a lot.

"The advances in foundational models come from the University of Washington's Institute of Protein Design, run by David Baker, one of Xaira's co-founders. These models are similar to diffusion models that power image generators like OpenAI's DALL-E and Midjourney. But rather than creating art, Baker's models aim to design molecular structures that can be made in a three-dimensional, physical world."

Xaira, an AI drug discovery startup, launches with a massive $1B, says it's 'ready' to start developing drugs

#solidstatelife #ai #medicalai #drugdiscovery #chemistry

waynerad@diasp.org

"Will AI save physicians and clinicians time and from burnout?"

"Copilots for clinicians are also becoming more common. Ambient clinical documentation is a booming business. The technology allows doctors to record conversations with patients to automatically turn them into clinical notes and summaries using AI and is a major topic at Healthcare conferences like HIMSS conference this year, where more than 30,000 health and tech professionals gathered in Orlando, Florida."

"Earlier in March, Salesforce announced Einstein Copilot: Health Actions will allow doctors to book appointments, summarize patient information and send referrals by prompting AI with conversational language."

"Administrative workloads are a major problem for clinicians across the US health-care system. A survey published (via CNBC) by Athenahealth in February found that more than 90% of physicians report feeling burned out on a regular basis, largely because of the paperwork they are expected to complete."

"I used to be part of an admissions committee for a medical school. When I interviewed idealistic young people applying to medical school, 'typing' and 'filling out forms' was never once mentioned as a reason for becoming a physician."

She goes on to describe using AI for prior authorization letters that have to be written to insurance companies. These require a letter to be written to justify the use of a drug or therapy for a specific patient and to contain details of that specific patient and why that patient needs that therapy. These are frequently rejected by the insurance companies and have to be re-written over and over to eventually get approval. "A third of medical offices employ full-time staff to take care of the average 30 prior authorizations per physician per week."

On the flip side, "the insurers have started to use AI to deny claims more quickly."

Another use is referral letters from one physician to another. "Like prior authorization letters, these are pretty formulaic."

But the thing she has the most enthusiasm for is what she calls "ambient scribes". "Ambient scribes" are AI systems that listen in to the conversation between the patient and the physician and create a templated note for the medical record. "This technology allows physicians to avoid looking at a screen and typing while they're trying to connect with a patient."

"I've tried versions from multiple AI scribe companies (including TORTUS AI, which - full disclosure - I consult for) and they do an amazing job of filtering out irrelevant information and putting the information in the right spot."

"Think of the technological challenge inherent in this process: patient visits are often interrupted by clinic staff or phone calls, meander off into conversations about kids and dogs, and use abbreviations and technical jargon. They're often circular, meaning a patient will mention a symptom and the physician won't ask a follow up question about it until several minutes later. These tools produce a full transcript that uses generative AI to find the important information and put it into a form that's indistinguishable from what a physician would actually type. Many of my friends have reported that ambient scribes actually do a better job of including important details than they would have included themselves."

Will AI save physicians and clinicians time and from burnout?

#solidstatelife #ai #voicetotext #nlp #genai #llms #medicalai

waynerad@diasp.org

"Each day, around 350 people in the United States die from lung cancer. Many of those deaths could be prevented by screening with low-dose computed tomography (CT) scans. But scanning millions of people would produce millions of images, and there aren't enough radiologists to do the work. Even if there were, specialists regularly disagree about whether images show cancer or not. The 2017 Kaggle Data Science Bowl set out to test whether machine-learning algorithms could fill the gap."

"The Data Science Bowl provided chest CT scans from 1,397 patients to hundreds of teams, for the teams to develop and test their algorithms. At least five of the winning models demonstrated accuracy exceeding 90% at detecting lung nodules. But to be clinically useful, those algorithms would have to perform equally well on multiple data sets."

"To test that, Kun-Hsing Yu, a data scientist at Harvard Medical School in Boston, Massachusetts, acquired the ten best-performing algorithms and challenged them on a subset of the data used in the original competition. On these data, the algorithms topped out at 60-70% accuracy. In some cases, they were effectively coin tosses." "Almost all of these award-winning models failed miserably."

The reproducibility issues that haunt health-care AI

#solidstatelife #ai #medicalai #reproducibility

waynerad@pluspora.com

"How a largely untested AI algorithm crept into hundreds of hospitals". "The use of algorithms to support clinical decision-making isn't new. But historically, these tools have been put into use only after a rigorous peer review of the raw data and statistical analyses used to develop them. Epic's Deterioration Index, on the other hand, remains proprietary despite its widespread deployment. Although physicians are provided with a list of the variables used to calculate the index and a rough estimate of each variable's impact on the score, we aren't allowed under the hood to evaluate the raw data and calculations.

"Furthermore, the Deterioration Index was not independently validated or peer-reviewed before the tool was rapidly deployed to America's largest healthcare systems."

How a largely untested AI algorithm crept into hundreds of hospitals

#solidstatelife #ai #medicalai #deteriorationindex