Antonino Uncini1, Graziano Aretusi2,3, Fiore Manganelli4, Yukari Sekiguchi5, Laurent Magy6, Stefano Tozza4, Atsuko Tsuneyama5, Sophie Lefour6, Satoshi Kuwabara5, Lucio Santoro4, Luigi Ippoliti3. 1. Department of Neuroscience, Imaging and Clinical Sciences, University "G. d'Annunzio", Via Luigi Polacchi 11, 66100, Chieti-Pescara, Italy. uncini@unich.it. 2. Department of Neuroscience, Imaging and Clinical Sciences, University "G. d'Annunzio", Via Luigi Polacchi 11, 66100, Chieti-Pescara, Italy. 3. Statistics Unit, Department of Economics, University "G. d'Annunzio", Chieti-Pescara, Italy. 4. Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples Federico II, Naples, Italy. 5. Department of Neurology, Graduate School of Medicine, Chiba University, Chiba, Japan. 6. National Reference Centre for Rare Peripheral Neuropathies and Department of Neurology, University of Limoges, Limoges, France.
Abstract
OBJECTIVE: The interpretation of electrophysiological findings may lead to misdiagnosis in polyneuropathies. We investigated the electrodiagnostic accuracy of three supervised learning algorithms (SLAs): shrinkage discriminant analysis, multinomial logistic regression, and support vector machine (SVM), and three expert and three trainee neurophysiologists. METHODS: We enrolled 434 subjects with the following diagnoses: chronic inflammatory demyelinating polyneuropathy (99), Charcot-Marie-Tooth disease type 1A (124), hereditary neuropathy with liability to pressure palsy (46), diabetic polyneuropathy (67), and controls (98). In each diagnostic class, 90% of subjects were used as training set for SLAs to establish the best performing SLA by tenfold cross validation procedure and 10% of subjects were employed as test set. Performance indicators were accuracy, precision, sensitivity, and specificity. RESULTS: SVM showed the highest overall diagnostic accuracy both in training and test sets (90.5 and 93.2%) and ranked first in a multidimensional comparison analysis. Overall accuracy of neurophysiologists ranged from 54.5 to 81.8%. CONCLUSIONS: This proof of principle study shows that SVM provides a high electrodiagnostic accuracy in polyneuropathies. We suggest that the use of SLAs in electrodiagnosis should be exploited to possibly provide a diagnostic support system especially helpful for the less experienced practitioners.
OBJECTIVE: The interpretation of electrophysiological findings may lead to misdiagnosis in polyneuropathies. We investigated the electrodiagnostic accuracy of three supervised learning algorithms (SLAs): shrinkage discriminant analysis, multinomial logistic regression, and support vector machine (SVM), and three expert and three trainee neurophysiologists. METHODS: We enrolled 434 subjects with the following diagnoses: chronic inflammatory demyelinating polyneuropathy (99), Charcot-Marie-Tooth disease type 1A (124), hereditary neuropathy with liability to pressure palsy (46), diabetic polyneuropathy (67), and controls (98). In each diagnostic class, 90% of subjects were used as training set for SLAs to establish the best performing SLA by tenfold cross validation procedure and 10% of subjects were employed as test set. Performance indicators were accuracy, precision, sensitivity, and specificity. RESULTS: SVM showed the highest overall diagnostic accuracy both in training and test sets (90.5 and 93.2%) and ranked first in a multidimensional comparison analysis. Overall accuracy of neurophysiologists ranged from 54.5 to 81.8%. CONCLUSIONS: This proof of principle study shows that SVM provides a high electrodiagnostic accuracy in polyneuropathies. We suggest that the use of SLAs in electrodiagnosis should be exploited to possibly provide a diagnostic support system especially helpful for the less experienced practitioners.