ACUTE PULMONARY-EMBOLISM - COST-EFFECTIVENESS ANALYSIS OF THE EFFECT OF ARTIFICIAL NEURAL NETWORKS ON PATIENT-CARE

PURPOSE: To evaluate the cost-effectiveness of artificial neural netwo rks for diagnosis inpatients suspected of having acute pulmonary embol ism who are typically referred for pulmonary angiography. MATERIALS AN D METHODS: Four diagnostic strategies were explored to help define the diagnostic role of neural networks in patients suspected of having pu lmonary embolism in whom nondiagnostic ventilation-perfusion lung scan s were obtained. First, a network was used to determine which patients could be directly referred for treatment without angiography. Second, the network was applied,to determine in which patients treatment coul d be withheld. Third, the network was used:to distinguish patients in whom the network gave indeterminate responses and who should proceed t o angiography. Each strategy was compared with use of angiography in t erms of morbidity, mortality, and cost per life saved. RESULTS-The use of the neural network reduced the average cost per patient by more th an one-half relative to the cost of angiography. Morbidity and mortali ty rates were also comparable to or lower than those associated with a ngiography. The results were consistent regardless of the prevalence o f disease, CONCLUSION: The use of neural networks in the diagnosis:of pulmonary embolism is a promising way to improve cost-effectiveness in :the care of patients with nondiagnostic lung scans.