Police departments across the U.S. are using technology to try to identify problem officers before their misbehavior harms innocent people, embarrasses their employer, or invites a costly lawsuit — from citizens or the federal government.

While such “early warning systems” are often treated as a cure-all, experts say, little research exists on their effectiveness or — more importantly — if they’re even being properly used.

Over the last decade, such systems have become the gold standard in accountability policing with a computerized system used by at least 39 percent of law enforcement agencies, according to the most recent data from the U.S. Bureau of Justice Statistics.

The issue of police-community relations was thrust into the spotlight after an officer fatally shot Michael Brown in Missouri. Since then, departments have held public forums to build trust with residents. Some are testing cameras mounted to officers to monitor their interactions with the public.

Experts say the early warning system can be another powerful tool to help officers do their jobs and improve relations, but it is only as good as the people and departments using it.

“It’s not a guarantee that you will catch all of those officers that are struggling,” said Jim Bueermann of the nonprofit Police Foundation, which is dedicated to better policing. “These systems are designed to give you a forewarning of problems and then you have to do something.”

The aim is to avoid cases where the first evidence of a troubled officer is a YouTube video showing them excessively beating a suspect. Such incidents stoke public fears about police and can result in huge monetary settlements.

The systems track factors such as how often officers are involved in shootings, get complaints, use sick days and get into car accidents. When officers hit a specific threshold, they’re supposed to be flagged and supervisors notified so appropriate training or counseling can be assigned.

Some law enforcement agencies adopted the systems under agreements they entered into with the federal government after officers were accused of abuse, including departments in Seattle, which is currently working to implement such a system, and Los Angeles.

The Los Angeles Police Department agreed to set up their $33 million early warning systems after the so-called Rampart scandal in which an elite anti-gang unit was found to have beaten and framed suspected gang members. The system was then implemented in 2007.

The LAPD’s inspector general found in a recent review that the system was seemingly ineffective in identifying officers who ultimately were fired. The report looked at 748 “alerts” over a four-month period and found the agency took little action in the majority of cases and only required training for 1.3 percent, or 10 alerts, of them.

Sam Walker, a University of Nebraska at Omaha professor emeritus and expert on such systems, said he was troubled by the department’s response to the report and concerned their follow-up study would be used to discredit the system a year after emerging from federal oversight.

“These are not predictive devices,” he said. “Is the failure in the system itself or is the failure in how the department managed the system. If they did such a small amount of retraining did they ignore lots of training needs and fail to do it?”

Maggie Goodrich, chief information officer for the LAPD, defended the technology before the department’s civilian oversight board but also said a deeper analysis of its impacts is necessary. “How do you prove a negative?” she asked. “What we can’t capture with this system is how many times have we stopped somebody from engaging in behavior?”

For rank-and-file officers, there’s concern someone could be flagged merely because, for example, they work in a high-crime area where they are more likely to use their weapon or physical force. Some systems attempt to correct for such factors by comparing officers with their direct peers, and managers are supposed to account for differences in assignments.

“Their concern is the concern that the public has about big brother,” said Tyler Izen, president of the union representing LAPD officers. “If you’re watching over me and there’s a setup matrix that is going to tell you that I’m bad, people are always skeptical of things like that.”

A 2011 Justice Department report found the New Orleans Police Department’s system, adopted roughly two decades ago, was “outdated and essentially exists in name only.” Investigators said information was included haphazardly and flagged officers were put into essentially “bad boy school,” a one-size-fits-all class seen by some as a badge of honor.

The system is being overhauled.

The Los Angeles County Sheriff’s Department is on the verge of entering into a federal consent decree for its mismanagement of jails. And a Justice Department investigation that concluded last year found deputies discriminated against blacks and Latinos by making unconstitutional stops, searches, seizures and using excessive force.

The sheriff’s department has an early warning system. “Our diagnostic systems were fine,” said the department’s Chief of Detectives, Bill McSweeney, who advised his agency on creation of the warning system. “Our managerial and supervision response was not fine. It’s that simple.”

(AP)