RESPONSE OF GENERAL-PRACTITIONERS TO COMPUTER-GENERATED CRITIQUES OF HYPERTENSION THERAPY

We recently have shown that a computer system, known as HyperCritic, c an successfully audit general practitioners' treatment of hypertension by analyzing computer-based patient records. HyperCritic reviews the electronic medical records and offers unsolicited advice. To determine which unsolicited advice might be perceived as inappropriate, builder s of programs such as HyperCritic need insight into providers' respons es to computer-generated critique of their patient care. Twenty medica l charts, describing in total 243 visits of patients with hypertension , were audited by 8 human reviewers and by the critiquing-system Hyper Critic. A panel of 14 general practitioners subsequently judged the re levance of those critiques on a five-point scale ranging from relevant critique to erroneous or harmful critique. The panel judged reviewers ' comments to be either relevant or somewhat relevant in 61 to 68% of cases, and either erroneous or possibly erroneous in 15 to 18%; the pa nel judged HyperCritic's comments to be either relevant or somewhat re levant in 65% of cases, and either erroneous or possibly erroneous in 16%. Comparison of individual members of the panel showed large differ ences; for example, the portion of HyperCritic's comments judged relev ant ranged from 0 to 82%. We conclude that, from the perspective of ge neral practitioners, critiques generated by the critiquing system Hype rCritic are perceived equally beneficial as critiques generated by hum an reviewers. Different general practitioners, however, judge the crit iques differently. Before auditing systems based on computer-based pat ient records that are acceptable to practitioners can be introduced, a dditional studies are needed to evaluate the reasons a physician may h ave for judging critiques to be irrelevant, and to evaluate the effect of critiques on physician behavior.