AI Software Failed to Detect Nurse’s Fentanyl Theft at Chattanooga Hospital
Artificial intelligence software failed for months to detect a nurse stealing fentanyl at Chattanooga’s largest hospital, raising questions about AI monitoring systems.

CHATTANOOGA, TENNESSEE β A nurse at Erlanger Baroness Hospital stole fentanyl for months while artificial intelligence software designed to detect drug diversion failed to raise alarms, according to a Tennessee Board of Nursing consent order.
About a year ago, anesthesia staff noticed the nurse slurring his words and struggling to stay awake while on duty in the surgery center at Chattanooga‘s largest hospital. The nurse failed a drug test in the days that followed and was terminated, the order states.
The nurse later admitted to pilfering and abusing fentanyl left over after surgeries, sometimes daily, for months according to the nursing board order. He took the controlled substances from the healthcare facility and used them himself.
AI Monitoring System Missed Red Flags
The case stands out because Erlanger Baroness uses Sentri7, medication-monitoring software powered by artificial intelligence that is designed to detect missing drugs faster than humans can. The system is marketed as the newest line of defense against drug diversion, the unlawful taking of controlled substances from healthcare facilities.
For months at Erlanger, Sentri7 failed to flag missing drugs and other inconsistencies that “should have been flagged,” according to the nursing board’s order. The software overlooks what should have been obvious warning signs of drug theft.
Drug diversion is believed to be so widespread that it occurs at just about every U.S. hospital. Healthcare facilities are not required to disclose their implementation of AI monitoring software or report malfunctions to regulators.
Limited Oversight of AI Systems
The Erlanger case offers a rare glimpse at an apparent failure of AI drug diversion software used in hundreds of U.S. hospitals with little transparency or oversight. There is no full account of how widely these programs are used or how often they fail to detect theft.
Erlanger Baroness, also referred to as Erlanger Medical Center, declined to comment on its use of Sentri7 or on the diverted drugs. AndrΓ© Rebelo, a spokesperson for the health division at Wolters Kluwer, the Dutch technology company behind Sentri7, declined to answer questions about what happened at Erlanger.
“We remained confident in our software,” Rebelo said according to the report.
David Rastall, a Johns Hopkins Medicine neurologist and AI researcher, noted the lack of transparency around AI technology failures in healthcare settings. The case has not been previously reported publicly.


