Person washing his or her hands

Hand hygiene is always important, but there are few (if any) settings where clean palms and fingers are as vital as in hospitals. Nurse, doctor or patient — all three could potentially pass on something bad by neglecting to wash their hands well and often. Fortunately, the monitoring of hand washing compliance by hospitals can be made more successful through the use of artificial intelligence (AI).

A recent study from Saint Louis University concluded that by using AI to analyze the data hospitals gather on the hand washing compliance of their employees, healthcare facilities are more likely to receive feedback that they can use to improve this compliance, reports AI in Healthcare.

The study involved a special algorithm which was tested by researchers appointing trained observers to monitor hand-hygiene habits in a 356-bed academic medical center over the course of just under three years. At the end of the study, it was discovered that, on average, 1,561 hand washing sessions were monitored per month and that only 58 percent of the hand washing sessions were sufficient. But that wasn’t the whole story. Because of the AI empowered-algorithm, researchers were able to determine that 18 percent of the hand washing sessions were anomalous. In other words, the compliance rate wasn’t indicative of regular hand washing practices.

“Even in times when all the rates are normal, it is possible that the rates are too low overall (with hand hygiene compliance) or too high (for infection rates), the researchers wrote, according to AI in Healthcare. “Therefore, care must always be taken to evaluate the data statistically as well through a clinical lens.”