Brain, Vol. 119, No. 3, 831-839, 1996
© 1996 Guarantors of Brain
research-article |
What can artificial neural networks teach us about neurodegenerative disorders with extrapyramidal features?
1Neuroepidemiology Branch, National Institute of Neurological Disorders and Stroke Bethesda 2Division of Computer Research and Technology, National Institutes of Health Bethesda 3Department of Neuropathology, Massachusetts General Hospital Boston 4Department of Neuropathology, Albert Einstein College of Medicine New York 5Department of Pathology (Neuropathology), Stanford School of Medicine Stanford 6Division of Neuropathology, Case Western Reserve University Cleveland, USA 7Raymond Escourolle Neuropathology Laboratory, INSERM U 360, Hôpital de la Salpêtrière, Association Claude Bernard Paris, France 8Ludwig Boltzmann Institute of Clinical Neurobiology Vienna, Austria 9Parkinson's Disease Society Brain Tissue Bank and Department of Neuropathology Institute of Neurology London, UK 10Department of Neuropathology, Institute of Psychiatry London, UK
Correspondence to:
Correspondence to: I. Litvan, Federal Building, Room 714, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892-9130, USA
Artificial neural networks (ANNs), computer paradigms that can learn, excel in pattern recognition tasks such as disease diagnosis. Artificial neural networks operate in two different learning modes: supervised, in which a known diagnostic outcome is presented to the ANN, and unsupervised, in which the diagnostic outcome is not presented. A supervised learning ANN could emulate human expert diagnostic performance and identify relevant predictive markers in the diagnostic task, while an unsupervised learning ANN could suggest reasonable alternative diagnostic classification criteria. In the present study, we used ANN methodology to try to overcome the neuropathological difficulties in differentiating the subtypes of progressive supranuclear palsy (PSP), and in differentiating PSP from postencephalitic parkinsonism (PEP) and corticobasal degeneration, or Pick's disease from corticobasal degeneration. First, we applied supervised learning ANN to classify 62 cases of these disorders and to identify diagnostic markers that distinguish them. In a second experiment, we used unsupervised learning ANN to investigate possible alternative nosological classifications. Artificial neural networks input data for each case consisted of values representing histological features, including neurofibrillary tangles, neuronal loss and gliosis found in multiple brain sampling areas. The supervised learning ANN achieved excellent accuracy in classifying PSP but had difficulty classifying the other disorders. This method identified a few features that might help to differentiate PEP, supported currently proposed criteria for Pick's disease, corticobasal degeneration and typical PSP, but detected no features to characterize the atypical subtype of PSP. In general, unsupervised learning ANN supported the present nosological classification for PSP, PEP, Pick's disease and corticobasal degeneration, although it overlapped some groups. Artificial neural networks methodology appears promising for studying neurodegenerative disorders
artificial neural networks; dystal; neurodegenerative disorders; neuropathology; progressive supranuclear palsy
Received December 1, 1995. Accepted January 12, 1996.