An exterior view of Parkland Hospital in Dallas. An AI model is helping to predict the risk of violent patient behavior to improve the safety of hospital staff.
Smiley N. Pool/Dallas Morning News
Once upon a time it would have sounded like science fiction, but North Texas scientists have developed an AI tool to help Parkland Health hospital staff identify patients at risk of becoming violent. This predictive model can help protect healthcare workers at a moment when violent incidents have become a major concern for hospitals all over the country.
In 2024, 8 out of 10 nurses reported experiencing violence at their workplace in the preceding year. This affects staff retention.
Needless to say, the cost for hospitals is significant, and exposure to violence is even fueling healthcare workers’ strikes in some states. A picketing nurse at a Michigan hospital told NPR this month that her colleagues were getting shoved, pushed, scratched and even bitten by their patients.
Article continues below this ad
Hospitals’ approach to this rising violence has been mostly reactive, relying on personal alarms and video surveillance. But Parkland Health is taking a step further by using this AI tool.
Developed by the Parkland Center for Clinical Innovation and first introduced in 2025, the Workplace Safety Model identifies patients unlikely to pose a risk — which is most of them — allowing the hospital staff to focus on the roughly 30% flagged as higher risk.
In validating the tool, the scientists found that among a group of patients identified as high risk, 77% were involved in a violent incident, PCCI staff told us.
Scientists are careful not to profile incoming patients, said Steve Miff, PCCI president and CEO. Race, ethnicity and religion are not considered. The AI risk assessment is a moment-in-time analysis.
“Every time a person comes in, [he or she] gets a new risk evaluation,” Miff said. “We build this in a way that it predicts an instance, not a person.”
Article continues below this ad
Factors PCCI uses in the model include severe infection, if the patient arrived by ambulance or on their own, or what medications they are receiving, for example.
One key factor is whether the patient has a smoking history, since Parkland is a tobacco-free campus. If a patient can’t smoke, that may lead them to be more irritable.
PCCI is also using information from its own data tool, the Community Vulnerability Compass, that pinpoints social and health vulnerabilities down to census tracts. The patient’s address provides information of life stressors like financial instability or food insecurity.
The model makes its prediction within about 15 minutes of admission, without a survey. Staff can then decide whether additional assessments or precautions are needed, said Jacqueline Naeem, vice president of clinical and social health at PCCI.
“It is designed to support, not replace good judgment,” she told us.
Article continues below this ad
Parkland is just the start. PCCI is about to apply its model at Northwestern Memorial Hospital in Chicago. It is also partnering with Vega Health, a healthcare technology company.
Since the pandemic, violence against healthcare workers has become so prevalent that it even became a plot point in HBO’s The Pitt, a medical drama praised for its realism. PCCI’s AI tool could alleviate this terrible trend. Talk about a plot twist.
Have thoughts about this? Send a letter to the editor using our letters form or email letters@dallasnews.com. Letters should be no more than 200 words and include the first and last name of the writer and city of residence.