Patient-specific, eye catching alerts less likely to be ignored

Want doctors to read the alerts they receive in their electronic health records systems? Then make them more patient-specific and interesting to read.

That's the skinny from a recent study published in the Journal of the American Medical Informatics Association. The study focused on the use of computerized drug alerts for psychotropic drugs prescribed to 5,628 senior citizens by 81 physicians. The researchers expected computerized alerts to reduce the number of falls by these seniors, which is a leading cause of injuries. However, physicians overrode most drug alerts because they believed that the benefit of the drugs outweigh the risks involved. Physicians also expressed a concern that too many drug alerts were "nuisance alerts" of little clinical value.

The researchers created more patient-specific alerts for seniors on these drugs, estimating the risk of injury from falling using factors such as the patient's injury history, type and dose of psychotropic drug, presence of cognitive impairment, gait and balance. The improved alert showed both numerically and graphically on a "risk thermometer" how much risk the patient may be of falling; changes in the patient's risk from therapy changes--say, from a reduction in dosage--was reflected on the thermometer.

The "new generation" of drug alert worked: the physicians opened more than 83 percent of the alerts and the physicians modified the therapy in nearly one-fourth of them, reducing the risk of injury by 1.7 injuries per 1,000 patients.

"Individual risk estimates displayed graphically and numerically are a more effective method of eliciting response to drug alerts and reducing the risk of medicine-related injuries in higher-risk seniors," the authors noted.

To learn more:
- here's the abstract of the JAMIA study

Suggested Articles

Roche, which already owned a 12.6% stake in Flatiron Health, has agreed to buy the health IT company for $1.9 billion.

Allscripts managed to acquire two EHR platforms for just $50 million by selling off a portion of McKesson's portfolio for as much as $235 million.

Artificial intelligence could help physicians predict a patient's risk of developing a deadly infection.