Former NFL player convicted in $328M Medicare fraud; NIH builds AI ‘digital twin’ of eye cells; AI tool predicts bone removal in cochlear implant surgery – Morning Medical Update

Former NFL player convicted in $328M Medicare genetic testing fraud

A federal jury in Dallas has convicted former NFL player and Texas lab owner Keith J. Gray, 39, for orchestrating a $328 million Medicare fraud scheme involving medically unnecessary cardiovascular genetic tests. Prosecutors said Gray paid kickbacks to marketers who used telemarketing and “doctor chase” tactics to secure test orders, then disguised the payments through sham contracts. Medicare paid about $54 million on the claims, and Gray used some proceeds to buy luxury vehicles. He was convicted of conspiracy, Anti-Kickback Statute violations and money laundering, and faces up to 10 years in prison on each count.

Gray, a college football standout for the University of Connecticut Huskies, signed with the Carolina Panthers as an undrafted free agent after graduation, though he never appeared in an NFL game.

NIH creates ‘digital twin’ of eye cells to study macular degeneration

National Institutes of Health (NIH) researchers have built a highly detailed 3D “digital twin” of retinal pigment epithelial (RPE) cells — key support cells in the eye that are damaged in age-related macular degeneration (AMD), a leading cause of vision loss in people over 50. Using artificial intelligence (AI) trained on images from 1.3 million lab-grown cells, the team mapped how healthy cells organize themselves and how that structure breaks down in disease. The platform, called POLARIS, gives scientists a new way to study cell changes at the subcellular level and could help speed development of treatments for AMD and other conditions linked to disrupted cell organization.

AI tool predicts bone removal in cochlear implant surgery

Researchers report in the Journal of Medical Imaging that they’ve developed an AI-based imaging method that can predict how much bone will need to be removed during cochlear implant surgery using only preoperative CT scans. The system was trained on 751 pairs of before-and-after scans and achieved a mean Dice score of 0.72 when compared with surgeon-labeled cases, outperforming several existing models.