Abstract
A modified neural network based on adaptive resonance theory (ART) was trained with the records of 211 psychiatric inpatients (74 schizophrenic, 50 unipolar depressed, 34 bipolar depressed, 20 bipolar manic, 33 other) who improved by at least 40 points of the GAFS during 8 weeks of treatment. Thereafter, a comparison was made between the clinical response of another 26 schizophrenic patients and 28 unipolar depressed inpatients, to treatment suggestd by the trained ART (N=21) and by the consensus of two senior psychiatrists (N=33). The patients were allocated blindly and randomly to the two treatment groups. The BPRS (for the schizophrenic patients) or the HDRS (for the unipolar depressed patients) was completed weekly for 5 weeks. Results showed no difference between decisions regarding treatment by the ART network and by the experts. Length of hospital stay was also similar. All ART suggestions included supportive psychotherapy. High potency antipsychotics were suggested for 7 schizophrenic inpatients, clozapine for one and the addition of community therapy for another. Depressed patients got a variety of treatment suggestions. No contraindicated treatment was suggested by ART; however, two incomplete treatment suggestions were dropped from the study. In conclusion, in a prospective study ART was successful in learning treatment strategies and performed under supervision similar to experts.
Similar content being viewed by others
References
Cross, S.C., Harrison, P.F., Kennedy, R.L., Introduction to neural networks.The Lancet 346: 1075–1179, 1995.
Baxt, W.G. Application of artificial neural networks to clinical medicine.The Lancet 1135–1138, 1995.
Dybowski, R., and Grant, V., Artificial neural networks in pathology and medical laboratories.The Lancet 346:1203–1207, 1995.
Eberhart, R.C., Dobbins, R.W., and Hutton, L.V., Neural network paradigm comparisons for appendicitis diagnosis. InProceedings of the fourth annual IEEE Symposium on Computer-based Medical Systems. 298–304, 1995.
Mann, N.H., and Brown, M.D., Artificial intelligence in the diagnosis of low back pain.Orthoped Clin. North Am. 22:304–314, 1991.
Mulsant, G.H., and Servan-Schrieber, E., A connectionist approach to the diagnosis of dementia. InProceedings of 12th annual symposium on Computer Applications in Medical Care (Washington, DC). 245–250, 1988.
Baxt, G., Use of artificial neural networks for the diagnosis of myocardial infarction.Ann. Int. Med. 115:843–848, 1991.
Somoza, E., and Somaza, J.R., A neural-network approach to predicting admission decisions in a psychiatric emergency room.Med. Decis. Making 13:273–280, 1993.
Patil, S., Henry, J.W., Rubenfire, M., and Stein, P.D. Neural network in the clinical diagnosis of acute pulmonary embolism.Chest 104:1685–1689, 1993.
Agyei-Mensah, S.O., and Lin, F.C. Application of neural network in medical diagnosis: The case of sexuality-transmitted diseases.Austr. Phys. Eng. Sci. Med. 15:186–192, 1992.
Reinus, W.R., Wilson, A.J., Kalman, B., and Kwasny, S., Diagnosis of focal bone lesions using neural networks,Invest. Radiol. 29:606–611, 1994.
Lo, S.C., Freedman, M.T., Lin, J.S., and Mun, S.K., Automatic lung nodule detection using profile matching and back-propagation neural network techniques.J. Digit. Imaging, 6:48–54, 1993.
Wu, Y., Giger, M.L., Doi, K., Vyborny, C.J., Schmidt, R.A., and Metz, C.E., Artificial neural networks in mammography: application to decision making in a diagnosis of breast cancer.Radiology 187:81–87, 1993.
Gross, G.W., Boone, J.M., Greco-Hunt, V., and Greenberg, B., Neural networks in radiologic diagnosis:II. Interpretation of neonatal chest radographs.Invest. Radiol. 25:1017–1023, 1990.
Kloppel, B., Application of neural networks for EEG analysis. Consideration and first results.Neuropsychobiology 29:39–46, 1994.
Ebell, M.H., Artificial neural networks for predicting failure to survive following cardiopulmonary resuscitation.J. Fam. Pract. 36:297–303, 1993.
Snow, P.B., Smith, D.S., and Catalona, W.J., Artificial neural networks in the diagnosis and prognosis of prostat cancer: a pilot study.J. Urol. 152(5 Pt 2), 1923–1926, 1994.
Narayanan, M.N., and Lucas, S.B., A genetic algorithm to improve a neural network to predict a patient's response to warfarin.Methods Inf. Med. 32:55–58, 1993.
Veng-Pedersen, P., and Modi, N.B., Application of neural networks to pharmacodynamics,J. Pharm. Sci. 82:918–926, 1993.
Engle, R.L., Jr., Attempts to use computers as a diagnostic aid in medical decision making. A thirty-year experience.Perspect. Biol. Med. 35:207–219, 1992.
McClelland, J.L., and Rumelhart, D.E., Training hidden units. InExploration in Parallel Disturbed Processing (J.L. McClelland and D.E. Rumelhart, eds.), MIT Press, Cambridge, MA, 1988, pp. 121–160.
Freeman, J.A., and Skapura, D.M., Neural networks-algorithms, applications and programming techniques.Addison Wesley Publishing Company, Inc. USA, 1992, pp. 291–336.
Modai, I., Inbar-Saban, N., Saban, N., and Stoler, M., Parametric profile of psychiatric disorders detected by a neural network in relation to 8 week outcome.Comput. Hum. Behav. 11:181–190 1995.
American Psychiatric Association,Diagnostic and Statistical Manual of Mental Disorders Revised (third edition), APA, Washington DC, 1987.
Modai, I., Stoler, M., Inbar-Saban, N., and Saban, N., Clinical decisions for psychiatric inpatients and their evaluation by a trained neural network.Methods Inf. Med. 32:396–399, 1993.
American Psychiatric Association.Diagnostic and Statistical Manual of Mental Disorders (tenth edition), APA, Washington DC, 1994.
First, M.B., Spitzer, R.L., Gibbon, M., and Williams, J.B.W.,Structured Clinical Interview for Axis I DSM-IV Disorders, Hebrew version, Shalevet al., Jackobson Inc. 1994.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Modai, I., Israel, A., Mendel, S. et al. Neural network based on adaptive resonance theory as compared to experts in suggesting treatment for schizophrenic and unipolar depressed in-patients. J Med Syst 20, 403–412 (1996). https://doi.org/10.1007/BF02257284
Issue Date:
DOI: https://doi.org/10.1007/BF02257284