Colorado funds rural tele-ICU with $169.6 million; coding vendors dispute insurers on AI costs; AI score predicts heart failure deaths; robot data flags surgical skill
Listen to this post
all episodesTHE SHORT READ
Colorado awarded $169.6 million on Monday to 91 rural health care providers for about 250 projects, including tele-ICU, telehospitalist and remote patient monitoring services, under the federal Rural Health Transformation Program, the state said.
The awards cover 52 rural or frontier counties and three rural census tract counties and were chosen from 112 eligible applications seeking more than $250 million, according to the state's Department of Health Care Policy and Financing. The same day, the Centers for Medicare and Medicaid Services announced $51 million for chronic disease prevention through 68 rural hospital districts and authorities in Texas. Neither announcement names an artificial intelligence project.
Makers of hospital coding software disputed insurers' finding that AI-assisted billing added $942 million in costs, Healthcare Dive reported. New papers in npj Digital Medicine describe an Oxford heart failure mortality score, a University of Pennsylvania CT model and a Japanese analysis of robot motion during prostate surgery. It was otherwise a quiet day for new developments.
THE DETAILS
- Money Sept 28, 2026Colorado's Department of Health Care Policy and Financing, the state Medicaid agency, announced $169,587,181 in Rural Health Transformation Program grants on Sept. 28 for about 250 projects in 52 rural or frontier counties and three rural census tract counties. The program is the $50 billion federal fund for rural health that CMS is distributing to all 50 states, and Colorado's first-year federal allotment is $200.1 million, the state said. The state listed tele-ICU, telehospitalist services, remote patient monitoring, regional telehealth networks, electronic health record updates, shared technology platforms and digital health tools among the funded work, and CMS's release added telemedicine in ICUs and inpatient settings, mobile clinics and prehospital whole-blood transfusion training for EMS in 39 counties. The state received 112 eligible applications seeking more than $250 million for 368 projects. "These RHTP awards are a direct investment in rural resiliency," said Michelle Mills, chief executive of the Colorado Rural Health Center. Neither release names an AI project, and the state said the full awardee list is on its program page.
- Money Sept 28, 2026Vendors of hospital coding software rejected the Blue Cross Blue Shield Association's conclusion, reported in this site's Sept. 25 post, that AI-assisted billing raised inpatient costs without a matching rise in treatment, according to Healthcare Dive. "If patients are truly sicker, we'd expect to see more treatment," Luke Chalker, the association's senior vice president of product and data science, said, citing more anemia diagnoses without more transfusions. Dr. Travis Bias of Solventum, whose coding products Healthcare Dive said are used by more than 80% of U.S. hospitals, said the cause is fee-for-service payment: "we pay for volume, not for value." Hamid Tabatabaie, chief executive of CodaMetrix, which serves more than 500 hospitals, said hospitals not using such systems had been missing billable services. TechCrunch reported that Abridge founder Dr. Shiv Rao described competing automated systems on both sides of claims as a possible "horrible dystopic future."
- Evidence Sept 26, 2026University of Oxford researchers distilled a transformer neural network into SIMPLE-HF, an 11-variable score built from age, body mass index, comorbidities and medications, using UK primary care records for 373,389 adults with heart failure, according to the paper published Sept. 26 in npj Digital Medicine. For 12-month all-cause mortality the score reached a C-index of 0.801, compared with 0.735 for an electronic record version of the MAGGIC score, the authors reported. At a set risk threshold it identified 177 true events per 1,000 people screened, compared with 89 for MAGGIC. The score uses point-of-care variables and does not require echocardiography, the authors said, and they called for external validation and prospective clinical evaluation before use.Source: npj Digital Medicine
- Evidence Sept 29, 2026Researchers in the University of Pennsylvania's radiology department described Percival, a model trained on paired CT images and radiology reports, in npj Digital Medicine on Sept. 29. The model learned from more than 400,000 CT-report pairs and was evaluated on more than 20,000 held-out participants, the authors reported. Its internal representations tracked demographic, physiological and laboratory differences, and training on reports as well as images captured clinical information that image-only comparison models did not, in disease classification and longitudinal risk assessment, according to the paper.Source: npj Digital Medicine
- Evidence Sept 29, 2026Kobe University urologists analyzed instrument motion recorded by the hinotori surgical robot during the bladder-urethra reconnection step of 98 robot-assisted radical prostatectomies by 16 surgeons, according to a study published Sept. 29 in npj Digital Medicine. A random forest classifier distinguished certified proctors from other surgeons with an area under the curve of 0.892, and a three-feature model generalized to surgeons it had not seen, the authors reported. Proctors finished the step in 45.5 minutes on average, compared with 67.8 minutes. The authors described the work as exploratory, citing a single platform, a single surgical step, a 1-hertz sampling rate and only five anastomotic leaks for outcome analysis.Source: npj Digital Medicine
- Evidence Sept 26, 2026University of Alabama at Birmingham researchers reviewed health record data for 5,280 patients with hypertension and 88 primary care clinicians at a large academic health system in the Deep South, according to a paper published Sept. 26 in npj Digital Medicine. Remote patient monitoring reached 5.2% of eligible patients, and 62.5% of primary care clinicians made at least one referral, the authors reported. Referrals were concentrated among a small number of clinicians, and the authors said more research is needed on how clinicians and patients decide to use the service.Source: npj Digital Medicine
- Workforce Sept 28, 2026Optum Health, UnitedHealth Group's care delivery arm, named Wes Donohoe chief executive for AI and product innovation, effective Sept. 21, Becker's Hospital Review reported Sept. 28. Donohoe most recently led VisitRecall, an ambient AI scribe company that Becker's said is closing, and has been a general partner at the venture fund BullVC since 2020. He visited Optum teams in Minnesota and Texas and its Atrius Health medical group in Massachusetts in his first week, and said he plans to pilot tools with individual care teams, evaluate them and scale what works to millions of patients, according to the report. Becker's corrected an earlier version that gave his title as chief product officer.Source: Becker's Hospital Review