|
AI Rivals Doctors, Scribes at TPMG, and Instant Results Anxiety April 14, 2025
|
|
|
|
Together with
|
|
|
“If you’re investing in healthcare AI, ask these two questions: (1) Does it reduce decision burden, or just redistribute it? (2) Would a clinician notice if it was turned off? If the answer is no, you’ve not got AI, you’ve got a glorified Clippy.”
|
Datalla Group CEO Kevin McDonnell
|
|
|
Real-world comparisons of AI recommendations and doctors’ clinical decisions have been few and far between, but a new study in the Annals of Internal Medicine gave us a great look at how performance stacks up with actual patients.
The early verdict? AI came out on top, but that doesn’t mean doctors should pack their bags quite yet.
Researchers from Cedars-Sinai and Tel Aviv University compared recommendations made by K Health’s AI Physician Mode to the final decisions made by physicians for 461 virtual urgent care visits. Here’s what they found:
- In 68% of cases, the AI and physician recommendations were rated as equal
- AI rated better on 21% of cases, versus just 11% for physicians
- AI recommendations were rated “optimal” in 77% of cases, versus 67% for physicians
Although AI takes the cake with the top line numbers, unpacking the data reveals some not-too-surprising strengths and weaknesses. AI was primarily rated better when physicians:
- Missed important lab tests (22.8%)
- Didn’t follow clinical guidelines (16.3%)
- Failed to refer patients to specialists or the ED if needed (15.2%)
- Overlooked risk factors and red flags (4.4%)
Physicians beat out AI when the human elements of care delivery came into play, such as adapting to new information or making nuanced decisions. Physicians were rated better when:
- AI made unnecessary ED referrals (8.0%)
- There was evolving or inconsistent information during consultations (6.2%)
- They made necessary referrals that the AI missed (5.9%)
- They correctly adjusted diagnoses based on visual examinations (4.4%)
While the study focused on the exact types of common conditions that AI excels at diagnosing (respiratory, urinary, vaginal, eye, and dental), it’s still impressive to see the outperformance in the messy trenches of a real clinical setting – a far cry from the static medical exams that have been the go-to for similar evaluations.
The Takeaway
For AI to truly transform healthcare, it’ll need to do a lot more than automate administrative work and back office operations. This study demonstrates AI’s potential to enhance decision-making in actual medical practice, and points toward a future where delivering high-quality patient care becomes genuinely scalable.
|
|
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.
|
|
Nabla’s Looking for an Events Manager!
Nabla is scaling up, and it’s looking for an Events Manager to help engage its audience through exceptional experiences. This role will manage events that create meaningful connections and amplify the brand of a company dedicated to bringing joy back to the practice of medicine. Learn more and apply here.
|
|
- Potential Path to AI Reimbursement: Reimbursement has been one of the major stumbling blocks holding back AI adoption, but new legislation introduced last week could help ease the path to broader usage. The Health Tech Investment Act would simplify the current patchwork reimbursement system by setting up a dedicated Medicare coverage pathway for AI-enabled medical devices approved by the FDA (called “algorithm-based healthcare services”). The Imaging Wire’s deep dive on the topic has you covered with all the details.
- Instant Result Anxiety: A study in JAMA Network Open revealed how giving patients instant access to test results can create new challenges for health systems. Using data on 290k patients at Vanderbilt University Medical Center who checked test results online, researchers found that 39% refreshed their portal while waiting for high-sensitivity results to appear (with some refreshing as many as 16 times). Even low-sensitivity results saw 25% of patients refresh their portal at least once, and the difficulty of interpreting results without a doctor runs the risk of compounding unnecessary anxiety and leading to more calls from worried patients.
- AI Scribe Use at TPMG: A stellar review of The Permanente Medical Group’s ambient AI scribe deployment estimates that 15,700 hours of documentation time were saved during the first year – equivalent to about 1,794 working days. Over 90% of physicians reported a positive experience using the scribe, and an accompanying patient survey showed that 47% felt their doctor spent less time than usual looking at a computer screen. Adoption was highest among mental health (42% of clinicians), primary care (32%), and emergency medicine (32%), followed by allergy (21%) and cardiology (20%).
- Solace Lands $60M for Care Advocacy: Solace landed $60M in Series B funding to connect more patients and families to expert healthcare advocates. With $81M raised since launching in 2022, Solace now plans to enhance its personalized care navigation platform and expand its advocate network across the U.S. to accelerate its move beyond Medicare into Medicaid and commercial coverage.
- Analytics for Community Systems: Health Catalyst debuted its Ignite Spark data and analytics solution purpose-built for community health systems, regional hospitals, and multi-site practices. Ignite Spark is designed to complement existing systems and provide enterprise-grade analytics for teams with lean resources, delivering insights through intuitive self-service tools, smart data pathways, and fewer vendor handoffs.
- AI Assistants, Not AI Replacements: Innovaccer’s AI Trends in Healthcare report consolidated insights from 73 U.S. healthcare organizations to shed light on current perceptions of AI, finding that most view it as an assistant rather than a replacement. Key findings included that 82% of physicians are eager to adopt AI tools to combat burnout and administrative inefficiencies, and 65% of the overall respondents now see AI as a vital tool for reducing existing workloads across all levels. A far smaller share (37%) see AI as key to decision-making, such as enhancing diagnostics or treatment planning.
- UiPath Medical Records Summarization: UiPath launched a generative AI-based Medical Record Summarization agent powered by Google Cloud Vertex AI and Gemini models. The new agent benefits both payors and providers by providing clinician-level medical summaries in minutes, streamlining downstream processes such as utilization management, appeals, referrals, and clinical trial eligibility checks. It’s reportedly already been deployed by a major payor and improved “the speed and accuracy of document processing to achieve results 23% faster.”
- RapidClaims Raises $11M: Revenue cycle and claims management startup RapidClaims raised $11M of Series A funding to help providers leverage AI to improve coding accuracy and contain costs. RapidClaims offers autonomous coding, clinical documentation improvement for medical imaging, and a solution that analyzes claims presubmissions to identify and fix errors.
- Artera Agent Momentum: Artera announced that its Staff and Insights AI Co-Pilot Agents have been adopted by 100+ healthcare organizations and generated strong satisfaction scores after six months of real-world use. The Staff Co-Pilot is designed to assist administrative staff in managing patient communications with three core skills (real-time translation, message shortening, conversation summaries), while the Insights Co-Pilot analyzes patient engagement data to serve up next steps and timely recommendations.
- Nudging Cardiologists: Electronic provider notifications (EPNs) could help increase aortic valve replacement in patients found to have symptomatic severe aortic stenosis in echo exams. A recent AHA study randomized 285 healthcare providers to receive EPNs or usual care for each of their patients with AS, finding that aortic valve replacement rates at one year were 48.2% with EPNs versus 37.2% with usual care. This EPN-driven valve replacement increase led to a longer mean survival in all patients (+12 days), especially among those that were symptomatic (+23 days).
|
|
Transforming Remote Blood Pressure Monitoring
BPM Pro 2 integrates effortlessly into health programs, streamlines care delivery, and boosts patient adherence and engagement. Discover a better experience for your patients and care teams.
|
|
Create Efficient Primary Care Access With K Health’s Clinical AI
Keeping up with patient access feels like a losing battle? Hartford HealthCare, Cedars-Sinai, and Hackensack Meridian Health found a new approach. K Health partners with health systems to scale high-quality 24/7 primary care access without sacrificing quality. Learn how K Health’s peer-reviewed clinical AI and Virtualist model are transforming how leading systems deliver care.
|
|
- How Abridge Scales for Diverse Health Systems: From the largest urban health institutions to sprawling rural systems that spread across several states and serve a diverse array of communities with varying levels of resources, Abridge is impacting the lives of clinicians and patients. Read why Hurley Medical Center in Flint, Mich., Saint Francis Medical Center in Cape Girardeau, Mo., and Deaconess Health System in Evansville, Ind., all chose Abridge. Learn more.
- Transform Value-Based Outcomes With Navina: Navina’s AI copilot brings clinical intelligence directly to care teams, turning fragmented data into a concise patient profile with actionable insights to transform value-based outcomes. Designed for and loved by physicians, Navina’s Best in KLAS AI reduces missed diagnoses, improves quality metrics and risk adjustment accuracy, and alleviates the administrative burden—allowing providers to focus on what matters most: their patients. Learn more.
- 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.
|
|
|
|
|