Dynamic decision support graph—Visualization of ANN-generated diagnostic indications of pathological conditions developing over time

• Published in: Artificial intelligence in medicine Vol. 42; no. 3; pp. 189 - 198
• Main Authors: Ellenius, Johan, Groth, Torgny
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.03.2008
• Subjects: Acute myocardial infarction; Algorithms; Angina Pectoris - blood; Angina Pectoris - etiology; Artificial Intelligence; Artificial neural network; Biomarkers - blood; Computer Graphics; Confidence Intervals; Decision Support Systems, Clinical; Decision Support Techniques; Diagnosis, Computer-Assisted; Disease Progression; Electrocardiography; Female; Humans; Internal Medicine; Male; MEDICIN; Medicin och hälsovetenskap; MEDICINE; Models, Biological; Myocardial Infarction - blood; Myocardial Infarction - complications; Myocardial Infarction - diagnosis; Myoglobin; Myoglobin - blood; Neural Networks (Computer); Other; Predictive Value of Tests; Sensitivity and Specificity; Time Factors; Troponin I - blood; troponin-1; Troponin-I; Visualization; Myoglobin; Visualization; Artificial neural network; Acute myocardial infarction; Troponin-I
• DOI: 10.1016/j.artmed.2007.10.002
• ISSN: 0933-3657; 1873-2860

Summary Objectives A common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic indications cannot be sufficiently well explained. This paper presents a method for visualizing diagnostic indications generated from an artificial neural network-based decision support algorithm (ANN-algorithm) in conditions developing over time. Methods The main idea behind the method is first to calculate and graphically present the decision regions corresponding to the diagnostic indications given as output from the ANN-algorithm, in the space of two selected, clinically established ‘display variables’. Secondly, the trajectory of time series measurement results of these, often biochemical markers, together with the respective 95% confidence intervals are superimposed on the decision regions. This will permit a nurse or clinician to grasp the diagnostic indication graphically at a glance. The indication is further presented in relation to clinical variables that the clinician is already familiar with, thus providing a sort of explanation. The predictive value of the indication is expressed by the proximity of the measurement result to the decision boundary, separating the decision regions, and by a numerically calculated individualized predictive value. Results The method is illustrated as applied to a previously published ANN-algorithm for the early ruling-in and ruling-out of acute myocardial infarction, using monitoring of measurement results of myoglobin and troponin-I in plasma. Conclusion The method is appropriate when there is a limited number of clinically established variables, i.e. variables which the clinician is used to taking into account in clinical reasoning.