Human and Computer-aided Diagnosis of Abdominal Pain: Further Report with Emphasis on Performance of Clinicians

Abstract

This paper reports a controlled trial of human and computer-aided diagnosis in a series of 552 patients with acute abdominal pain. The overall diagnostic accuracy of the computer-aided system was 91.5% and that of the senior clinician to see each case was 81.2%. However, the clinician's diagnostic performance improved markedly during the period of the trial. The proportion of appendices which perforated before operation fell from 36% to 4% during the trial, and the negative laparotomy rate dropped sharply. After the trial closed in August 1972 these figures reverted towards their pretrial levels.It is suggested that while computer-aided diagnosis is a valuable direct adjunct to the clinician dealing with the "acute abdomen," he may also benefit in the short-term from the constant feedback he receives and from the disciplines and constraints involved in communicating with the computer.

Knowledge engineering for medical decision making: A review of computer-based clinical decision aids

“…Another Leeds study of note was an analysis of the effect of the system on the performance of clinicians (13]. The trial we have mentioned that involved 304 patients was eventually extended to 552 before termination .…”

Quality Assessment and Quality Assurance in Medical Care

“…Stapleton (118) reported a higher level of performance by staff physicians caring for patients in a teaching service than when the same physicians cared for comparable patients in a nonteaching service of the same hospital. De Dombal et al (93) observed that surgeons, required as part of a study to provide critical data upon which they based their diagnosis and decision to operate, substantially reduced the incidence of ruptured appendices and of non indicated operations during the study. After the study ended, performance of the same surgeons promptly reverted toward previous less satisfactory levels.…”

“…Gonnella et al (123) more definitively documented the lack of association between low actual performance in diagnosing urinary tract infection and high scores on tests of knowledge on diagnosis of urinary tract infection. McDonald (120) noted that physicians did not sustain their higher level of performance when they no longer received reminders, just as surgeons' accuracy of diagnoses and judgments decreased promptly after termination of a study (93).…”

The Need for Assessing the Outcome of Common Medical Practices

“…In the equivocal case, the judgment of the physician will be infl uenced by the subjective weight he gives to (0) missing the early false negative case and delaying intervention (with the possible complication of an abscess or perforation) and (b) operating on the false positive patient. deDombal and his associates (48) and Graham (49) have shown that computer-assisted diagnosis can improve clinical judgment, helping the physician to reduce the number of false positive cases that receive appendectomy.…”