Teacher pleads guilty in $51M Medicare fraud scheme; CMS to ask states to revalidate “high-risk” Medicaid providers; AI model predicts cancer survival from single-cell tumor model – Morning Medical Update

Teacher pleads guilty in $51M Medicare fraud scheme

Jeanett Valenzuela pleaded guilty to money laundering conspiracy.

A former California teacher has pleaded guilty to money laundering conspiracy for her role in a $51 million Medicare fraud scheme involving fraudulent durable medical equipment (DME) claims for orthotic braces that beneficiaries never requested or used, many of which were found still in their original unopened packaging. Jeanett Valenzuela Ayub, 51, of Chula Vista, admitted that she and her co-conspirators billed Medicare nearly $51 million, were paid approximately $20 million, laundered at least $14 million in proceeds, and paid $3.7 million in kickbacks to sham marketing companies that provided bogus prescriptions signed by physicians with no real patient relationships. When her brother and co-conspirator Fernando Valenzuela Ayub was arrested in December 2024, Valenzuela fled to Tijuana. She was detained in August 2025 in the Dominican Republic while on a family vacation and returned to the United States by U.S. Marshals. She is scheduled for sentencing July 24, 2026, and faces a maximum of 20 years in prison.

CMS to ask states to revalidate Medicaid providers in high-risk areas

States will have 30 days to submit a revalidation plan to CMS under the fraud-reduction effort.

The Trump administration plans to ask all 50 states to revalidate Medicaid providers in what CMS Administrator Mehmet Oz, M.D., MBA, described as "high-risk" areas, as part of a broader push to reduce fraud in the program. Oz announced the audit at Politico's Health Care Summit in Washington, D.C., on Tuesday, saying states will be asked to submit a revalidation plan to CMS within 30 days. He did not define what constitutes a high-risk area.

"These are non-licensed individuals — often in unsupervised settings," Oz said. "You have to provide some additional level of audit to make sure that this is legitimately a valuable effort." The announcement follows the administration's decision earlier this year to pause $259 million in deferred Medicaid payments to Minnesota after an audit found the state had allowed the theft of federal funds intended for social welfare programs. Reuters has more.

AI model predicts cancer survival by analyzing individual tumor cells

The tool identifies which specific cell populations drive patient risk.

National Institutes of Health (NIH)-funded researchers at Oregon Health & Science University (OHSU) have developed a machine learning model that predicts cancer survival outcomes by analyzing single-cell tumor data — pinpointing the specific cell populations linked to higher or lower risk rather than averaging data across entire tumors, which the authors say erases potentially critical detail. Tested on clinical data from more than 150 patients with melanoma or liver cancer, the model, called scSurvival, outperformed traditional survival prediction methods and traced its predictions back to specific immune and tumor cell groups, including cell populations associated with immunotherapy responses in melanoma.

"A risk assessment tool that not only tells you who may be at higher risk, but also provides clues as to why, could really help in these difficult cancers," said Anthony Letai, M.D., Ph.D., director of NIH's National Cancer Institute. The findings were published in Cancer Discovery.