ARTIFICIAL NEURAL-NETWORK FOR DIAGNOSIS OF ACUTE PULMONARY-EMBOLISM -EFFECT OF CASE AND OBSERVER SELECTION

PURPOSE: To compare the diagnostic performance of an artificial neural network (ANN) with that of physicians in patients with suspected pulm onary embolism (PE). MATERIALS AND METHODS: An ANN was developed to pr edict PE by using findings from ventilation-perfusion lung scans and c hest radiographs. First, the network was evaluated on 1,064 cases from the Prospective Investigation of Pulmonary Embolism Diagnosis (PIOPED ) study that had a definitive angiographic outcome. An upper and lower bound of its diagnostic performance was provided depending on case di fficulty. Then, the network was tested on 104 patients with suspected PE in whom pulmonary angiography was essential for diagnosis. The diag nostic performance of the ANN was compared with that of(a) two nuclear medicine physicians who read the scans for the needs of this study an d (b) the nuclear medicine physicians who originally read the scans. T he effects of case and observer selection on performance were addresse d. RESULTS: The ANN outperformed the physicians when they used the PIO PED criteria for categoric assessment, and it performed as well as the two study physicians on the basis of their probability assessments. C ONCLUSION: The ANN can detect or exclude PE in a highly selected group of difficult cases with a consistency equivalent to that of very expe rienced physicians.