Cadet, a computer based decision support system for early cancer detection: a performance evaluation

I Heller MD, M Topilsky, MD, Y Villa, PhD, H Natour, MD, M Inbar 1, MD, J Fuchs, MD, S Blinder-Vayner, MD, I Shapira, MD, A Isakov, MD

Tel Aviv Sourasky Medical Center and Sackler School of Medicine, Tel Aviv University, Israel

AIM: The CaDet computer program is designed to help primary care physicians detect cancer earlier. It analyzes the epidemiologic and clinical attributes of individual patients and then identifies in this information and presents to physicians patterns that may require further attention. This study was conducted to evaluate the performance of the CaDet program as a tool in early cancer detection. METHODS: Personal epidemiologic and clinical data was obtained by a detailed questionnaire (357 items) from 160 healthy volunteers. Scored cancer alerts generated by the computer program in response to this data were evaluated in comparison to alerts provided by five expert internists who reviewed the same information in blinded fashion. RESULTS: The patient profiles generated by the computer were highly correlated to those provided by the clinicians. The computer's alert rate increased with the number of physicians who raised corresponding alerts (20%, 32%, 54%, 73% and 91% respectively for 1, 2, 3, 4 and 5 physicians, p < 0.0001) and with the scores assigned by the physicians to these alerts (22%, 56%, 84% and 90% for cumulative scores of 1-4, 5-8, 9-12 and 13 or more points, respectively, p < 0.0001). CONCLUSIONS: Qualitatively and quantitatively the five physicians and the computer operated in comparable fashion. The CaDet computer program seems well adapted to the system's task of aiding physicians to improve early detection. Clinical testing of the system is needed.

KEY WORDS: Early cancer detection, decision support.

For more information, contact

Paper presented at the International Symposium on Predictive Oncology and Intervention Strategies; Paris, France; February 9 - 12, 2002; in the section on Diagnostic Markers.