|
Lila, Telehealth, and AI Misses the Mark on Critical Conditions
March 17, 2025
|
|
|
|
|
Together with
|
|
|
|
“I think the shift in tone from the administration gives a little bit more comfort to the stakeholders that if we are responsible on our own, with more self-governance, we might be able to move a little bit faster in a more responsible way. I’m sensing the gas pedal getting a bit more of a push towards adoption in healthcare.”
|
|
Arcadia CSO Aneesh Chopra
|
|
|
|
Most health systems have already begun turning to AI to predict if patient health conditions will deteriorate, but a new study in Nature Communications Medicine suggests that current models aren’t cut out for the task.
Virginia Tech researchers looked at several popular machine learning models cited in medical literature for predicting patient deterioration, then fed them datasets about the health of patients in ICUs or with cancer.
- They then created test cases for the models to predict potential health issues and risk scores in the event that patient metrics were changed from the initial dataset.
AI missed the mark. For in-hospital mortality prediction, the models tested using the synthesized cases failed to recognize a staggering 66% of relevant patient injuries.
- In some instances, the models failed to generate adequate mortality risk scores for every single test case.
- That’s clearly not great news, especially considering that algorithms that can’t recognize critical patient conditions obviously can’t alert doctors when urgent action is needed.
The study authors point out that it’s extremely important for technology being used in patient care decisions to incorporate medical knowledge, and that “purely data-driven training alone is not sufficient.”
- Not only did the study unearth “alarming deficiencies” in models being used for in-hospital mortality predictions, but it also turned up similar concerns with models predicting the prognosis of breast and lung cancer over five-year periods.
- The authors conclude that a significant gap exists between raw data and the complexities of medical reality, so models trained solely on patient data are “grossly insufficient and have many dangerous blind spots.”
The Takeaway
The promise of AI remains just as immense as ever, but studies like this provide constant reminders that we need a diligent approach to adoption – not just for the technology itself but for the lives of the patients it touches. Ensuring that medical knowledge gets incorporated into clinical AI models also seems like a theme that we’re about to start hearing more often.
|
|
|
2025 State of Payer Enrollment & Credentialing
With increasing costs and shifting regulations, outdated processes won’t cut it. Medallion’s new report breaks down the biggest challenges, emerging trends, and how automation is transforming the landscape. Get the insights you need – read the full report today.
|
|
New Abridge AI Infrastructure Powers Clinically Useful and Billable Notes
The new Abridge Contextual Reasoning Engine is a leap forward in AI architecture that enables clinically useful and billable notes at the point of care. Health systems are plagued by incomplete notes that delay billing processes. Generating comprehensive, billable notes that support appropriate claims at the point of care creates administrative efficiencies, reducing costs and freeing doctors to focus more on patient care. Learn more.
|
|
- Patients Prefer AI Messages: A study in JAMA Network Open found that patients prefer messages written by AI, but they like them less if they’re told that AI wrote them. The survey of 1,455 patients showed that AI-drafted responses were preferred to human-drafted responses with a mean difference in satisfaction of −0.30 points (on a 5-point scale), usefulness of −0.28, and perception they were cared for of −0.43. Participants tended to have higher satisfaction with responses they were told were written by humans (mean difference of 0.13), or that came with no disclosure, even though they preferred the content of the AI-drafted messages.
- Innovaccer Launches Gap Closure Solution: Innovaccer followed up its recent Agents of Care launch with the unveiling of a 360-degree gap closure solution for payors. The new solution is designed to streamline risk adjustment and quality gap closure by enabling health plans to boost coding accuracy and enhance member outcomes through improved engagement across care settings. Unlike the traditional approach of closing gaps retrospectively, the solution takes a proactive approach to combining prospective, concurrent, and retrospective reviews.
- Tia Rolls Out Nabla AI: Women’s health pioneer Tia is rolling out Nabla’s ambient AI assistant to its clinicians after a successful two-month pilot that cut clinical note submission time in half for participating providers. The implementation will help bolster Tia’s patient-provider experience at a time when its recent Women’s Integrated Primary Care 2024 Outcomes Report cited that nearly half of women ages 18-35 reported negative interactions with healthcare providers, contributing to higher rates of mental health issues and lack of midlife support.
- Telehealth’s Medicare Spending Impact: University of Michigan researchers published a pair of preprints shedding a favorable light on telehealth’s budget impact. The first study analyzed Medicare claims data for evaluation and management visits before and after the pandemic, finding that the rise in telehealth use didn’t lead to more E&M use. The second paper examined claims for Medicare FFS beneficiaries over the age of 65, which showed that telehealth visits were associated with lower 30-day spending ($260 vs. $342) than in-person visits, although return visit rates were slightly higher for telehealth (16.1% vs. 14.1%).
- CoachCare Acquires VitalTech: CoachCare acquired fellow remote patient monitoring startup VitalTech for an undisclosed amount, marking its eighth acquisition since 2023. VitalTech’s “AI-first virtual care platform” will reportedly allow CoachCare to further scale its solutions, expand payment models, and break into more large health systems. Our coverage of CoachCare’s $48M growth round from August has all the details on their M&A strategy and specialized RPM platform.
- Lila Sciences Debut: Lila Sciences emerged from stealth with $200M in seed funding and an AI platform that promises to transmute scientific data into physical results. A great New York Times article on the company said that the ultimate goal is to create a “scientific superintelligence,” and that Lila’s AI has already been able to generate novel antibodies to fight disease and produced new materials for carbon capture. Lila is also reportedly working on the “generation of optimal genetic medicine constructs that outperform commercially available therapeutics.”
- PE Impact on Physician Turnover: New research in Health Affairs looked into changes in physician employment and turnover after private equity acquisitions of 200 ophthalmology practices between 2014 and 2021. Relative to matched controls, PE-acquired practices increased the total number of clinicians by 46.8% through three years after acquisition, driven by both new ophthalmologists (up 30.7%) and optometrists (up 36.2%). PE acquisitions also increased physician turnover, with the share of physicians leaving PE-acquired practices from one year to another increasing by 13 percentage points, or 265%, after the acquisition.
- Monogram + Memorial Herman: Monogram Health and Memorial Hermann joined forces to deliver in-home care for commercial and MA members of the system’s health plan. The joint venture will initially focus on chronic kidney disease and its causes, combining Monogram’s expertise in multispecialty home care with Memorial Hermann’s physician network and 270+ care delivery sites across Houston. Monogram noted that it now covers 200k patients in 36 states.
- Talkspace Navy Pilot: Talkspace announced it will be supporting the U.S. Navy’s pilot program to provide access to therapy and mental health resources for approximately 25,000 sailors. The first-of-its-kind Navy pilot is already active across six bases, allowing members to easily get matched with one of Talkspace’s licensed providers and receive care through unlimited asynchronous messaging therapy or live video sessions.
- Welcome to Match Week 2025: March 17 marks the start of Match Week, when U.S. medical students will learn from the Main Residency Match the programs where they will train for their chosen specialty. Residency applicants will learn if they’ve matched on March 17, and will be notified of their specific programs on Friday March 21, an occasion marked by festivities at most medical schools.
|
|
Top Systems Scale Primary Care With K Health
Leading health systems are turning to K Health’s AI-driven primary care solution to give their patients access to high-quality care with wait times measured in hours, not months. Find out why K Health is the only clinical AI company partnering with top systems to scale fully integrated primary care experiences.
|
|
Lift MA Plan Performance by Impacting SDoH
Social factors and non-medical issues strongly influence health outcomes, and addressing these contributing determinants of health can not only improve the lives of patients, but also enhance Medicare Advantage plan success. Learn how Clear Arch Health’s remote monitoring services are helping MA plans deliver cost-effective care while enabling more seniors to age independently.
|
|
- BPM Pro 2 – Unparalleled Reliability: BPM Pro 2 increases data reliability with two new features that ensure patients are taking their reading properly and prompting them to rest and retake it if their first reading was abnormally high.
- The First 30 Days: What to Expect With AI: Implementing AI documentation tools promises significant benefits, but how do you ensure a smooth transition? Playback Health has you covered with this comprehensive 30-day roadmap outlining what to expect, industry best practices, and its own proven implementation approach.
- Nabla Health Workforce Well-Being Day: Nabla is teaming up with HealthLeaders to host a discussion on how to build a sustainable culture of clinician well-being in honor of this week’s Health Workforce Well-Being Day. Join Nabla on March 19 to learn practical strategies for long-term cultural change in healthcare organizations, as well as how AI can play a role in reducing administrative burdens.
|
|
|
|
|
