Diagnostic agent keeps 49.4% of cases at 98.9% accuracy; House hears Medicare pay bills; 22 states fund remote monitoring as CMS moves to bar vendor staffing; Abridge adds pre-bill review

A diagnostic agent that scores its own consistency kept 49.4% of cases at 98.9% accuracy and routed the rest to a physician, a European group reported in Nature Medicine, dated Sept. 15. The group, led by Jakob Nikolas Kather, built an agent that takes a history, examines the patient, orders labs and imaging, and commits to a diagnosis, all on open-weight models running inside the hospital firewall. The agent reached about 90% on a seven-disease emergency task, close to a cloud GPT-5.2 baseline, the authors said. When the researchers ran the agent five times on each case, its agreement with itself predicted whether it was right better than any other measure they tested; the 49.4% of cases the agent kept were those that cleared a strict threshold on that score, and the other half went to a human. The paper appeared one week after the Advanced Research Projects Agency for Health funded heart-failure agents built on exception-based oversight, the design in which the machine keeps the cases it is sure of and hands the rest to a physician.

Chris Klomp, the deputy secretary nominee, appeared before the Senate Finance Committee on Tuesday and the Senate Health, Education, Labor and Pensions Committee on Wednesday morning, and coverage focused on vaccines and measles, not WISeR or AI. The House Energy and Commerce Health Subcommittee held a legislative hearing Tuesday on the Patients First Act and three other physician-payment bills. Sacramento has said nothing about AB 1979 with 14 days left on the clock. The Food and Drug Administration's only press release announced an expedited investigational new drug (IND) pilot. No major funding round or deal crossed the wire.

In other developments, states are putting rural transformation money into remote patient monitoring while the Centers for Medicare & Medicaid Services (CMS) proposes to bar the vendor-staffed version of the service; Abridge is selling a pre-bill review tool built on its ambient notes to coding departments; and 24 revenue cycle leaders told Becker's Hospital Review that their chief concern is payer automation that denies claims faster than they can answer, not autonomous coding.

  • Evidence Sept 15, 2026
    Kather's group tested a fully autonomous agent that interviews the patient, examines, orders tests and diagnoses on 551 MIMIC-IV cases across seven acute conditions (appendicitis, cholecystitis, diverticulitis, pancreatitis, pneumonia, pulmonary embolism and urinary infection), 2,400 abdominal cases and 990 published multispecialty cases. Open-weight models hosted on premises (Qwen, GLM and GPT-OSS), which keep patient data inside the hospital, reached 90.0% on the seven-disease task and 83.8% on the four-disease task, near a cloud GPT-5.2 baseline, the authors said. Agreement across five repeated runs separated right from wrong answers with an AUC of 0.86, and at a consistency threshold of 0.90 the agent retained 49.4% of cases at 98.9% accuracy; blinded physician review of 181 cases agreed with the automated grading 92.3% of the time. The authors listed the limitations: retrospective simulation only, text only, one institution's data, lower accuracy in older patients and roughly five times the compute. Under that design, the remaining cases, those on which the agent's repeated runs disagreed, are routed to a person.
  • Regulation Sept 15, 2026
    The Energy and Commerce Health Subcommittee took testimony Sept. 15 on 17 bills, including H.R. 9693, the Patients First Act, sponsored by three physician members of the House, John Joyce, Kim Schrier and Greg Murphy. The bill would tie the fee schedule to the Medicare Economic Index minus one point (minus half a point for alternative payment model participants), raise the budget-neutrality trigger from $20 million to $57.64 million in 2028 and replace the Merit-based Incentive Payment System (MIPS) over five years; the Provider Reimbursement Stability Act, H.R. 8163, addresses only the budget-neutrality change. Medicare physician payment has fallen about 33% against practice-cost inflation since 2001, according to the American Medical Association (AMA). A legislative hearing is not a markup, and no vote is scheduled. The conversion factor is set to drop another 1.19% on Jan. 1.
  • Regulation Sept 14, 2026
    The Alliance for Connected Care counts 22 states with roughly $240 million in remote patient monitoring (RPM) funding and 35 states with more than $2.4 billion in broader remote-care technology money, all drawn from the $50 billion Rural Health Transformation Program, Fierce Healthcare reported. The proposed 2027 fee schedule would limit remote physiologic and therapeutic monitoring to clinical staff employed by the billing practice, a change the American Telemedicine Association said would make the service unworkable for small practices; CMS received nearly 40,000 comments. Medicare RPM payments rose 31% to $536 million in 2024 and reached about 1 million beneficiaries. The final rule is expected around Nov. 1. Practices that bill the RPM codes 99454 and 99457 through a vendor would fall under the proposed staffing limit.
  • Deployment Sept 14, 2026
    The pre-bill review product compares coded diagnoses and diagnosis-related groups (DRGs) with the clinical documentation before a claim goes out and surfaces supporting evidence for clinical documentation integrity and coding teams, without changing the note or the codes, Fierce Healthcare reported. Reid Health in Indiana is the named early customer. Abridge said it works with 300 large health systems and handles more than 100 million conversations a year; both figures are the company's own. Shiv Rao said health systems "aren't reimbursed for the care they deliver. They're reimbursed for the care they document that they delivered." The tool draws on the same ambient recording that produces the clinical note.
  • Workforce Sept 15, 2026
    Becker's asked revenue cycle executives at Cleveland Clinic, Stanford, UC Davis, Rush, AdventHealth, Moffitt, the University of Kansas and 17 other organizations what worries them, and the consistent answer was payer AI. One said payers now review 100% of claims with automation while most health systems still manually sample a small fraction; another said payers can find reasons to challenge reimbursement far faster than providers can answer; several described payment being quietly reduced rather than denied. A companion piece the day before quoted UW Medicine and Springhill Medical Center leaders on restructuring teams, "replacing, say, 12 positions with four" at about the same total pay. A separate Becker's tally lists 10 health systems that cut IT and coding roles this year, from Stanford's 95 to Wellstar's 761, none of which named AI in its announcement.
  • Deployment Sept 15, 2026
    CareIntellect for Operations runs two proprietary models, Pressure Forecast and Estimated Day of Discharge, on bed, staffing and patient data to give capacity managers a three-day view, GE HealthCare said. The system is live at Duke and Queen's in Honolulu. Duke's patient-flow lead said it lets her team move faster from analysis to action. The company has published no accuracy or outcome figures.