1. A. Khodayari-R., J.P. Reilly, G.M. Hasey, H. de Bruin and D.J. MacCrimmon, “A Machine Learning Approach Using EEG Data to Predict Response to SSRI Treatment for Major Depressive Disorder”, Clinical Neurophysiology, vol. 124, pp. 1975-1985, Oct. 2013.
2. A. Khodayari-R., J.P. Reilly and G.M. Hasey, “Latent variable dimensionality reduction using a Kullback-Leibler criterion and its application to predict antidepressant treatment response”, in Proceedings Int. Workshop on Pattern Recognition in Neuroimaging (PRNI), pp. 148-151, June 2013, Philadelphia.
3. A.Khodayari-R., J.P. Reilly, G.M. Hasey, H.de Bruin and D.J. MacCrimmon, “Using Pre-treatment Electroencephalography Data to Predict Response to Transcranial Magnetic Stimulation Therapy for Major Depression”, Proceedings 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), pp. 6418-6421, Aug.-Sept. 2011, Boston.
4. A.Khodayari-R., G.M. Hasey, D.J. MacCrimmon, J.P. Reilly and H. de Bruin, “A pilot study to determine whether machine learning methodologies using pre-treatment electroencephalography can predict the symptomatic response to clozapine therapy”, Clinical Neurophysiology, vol. 121, pp. 1998–2006, 2010.
5. A.Khodayari-R., J.P. Reilly, G.M. Hasey, H. de Bruin and D.J. MacCrimmon, “Using Pre-treatment EEG Data to Predict Response to SSRI Treatment for MDD”, in Proceedings 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), pp. 6103–6106, Aug.-Sept. 2010, Buenos Aires.
6. A.Khodayari-R., J.P. Reilly, G.M. Hasey, H. de Bruin and D.J. MacCrimmon, “Diagnosis of Psychiatric Disorders Using EEG Data and Employing a Statistical Decision Model”, in Proceedings 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), pp. 4006–4009, Aug.-Sept. 2010, Buenos Aires.
7. A.Khodayari-R., G.M. Hasey, J.P. Reilly, H. de Bruin and D.J. MacCrimmon, “Predicting Response to SSRI Treatment for MDD: A Pilot Study Using Machine Learning Analysis of EEG Data”, Society of Biological Psychiatry 65th Annual Meeting, May 2010.
8. G.M. Hasey, A.Khodayari-R., J.P. Reilly, H. de Bruin and D.J. MacCrimmon, “A Personalized Approach Using Machine Learning Methods to Predict Response to rTMS Treatment for Major Depression”, Society of Biological Psychiatry 66th Annual Meeting, May 2011.
9. G.M. Hasey, A.Khodayari-R., J.P. Reilly, H. de Bruin and D.J. MacCrimmon, “A Pilot Study Employing Machine Learning Analysis of EEG Data to Build an Automated Diagnosis System for Psychiatric Disorders”, Society of Biological Psychiatry 66th Annual Meeting, May 2011.
Physicians make life-altering decisions primarily on the basis of a subjective assessment of a set of symptoms. The symptoms of different psychiatric conditions can overlap and diagnosis may be inaccurate. Only 20% of bipolar depression (BD) individuals during a depressive episode receive the correct diagnosis of BD within the first year of seeking treatment [1,2], and latency from onset to diagnosis and appropriate treatment averages 5 to 10 years [2,3]. Close to 60% of BD individuals are initially diagnosed as having unipolar depression (UD) [1,4]. Incorrect diagnostic classification results in delayed recovery, increased medical costs and prolonged disability and patient suffering. Treatment often assumes the form of serial trials of different psychotropics and psychotherapies.
We can eliminate the "trial and error" process of finding the best treatment for a given patient with major depression by determining, in advance, the probability of response to several commonly used antidepressant medications and cognitive behaviour therapy. Our algorithms have also been successfully used to predict response to clozapine in patients with treatment-resistant schizophrenia and to predict the response of depressed patients to transcranial magnetic stimulation. We are currently developing algorithms to predict the response to cognitive behaviour therapy, electroconvulsive therapy and four medications.
We can reduce the clinician's reliance on the patient's highly subjective and impressionistic report of clinical symptoms. Our technology uses quantitative analysis of objective laboratory markers to render a diagnosis and to guide management. Machine learning algorithms can differentiate schizophrenia from severe major depressive disorder and accurately detect underlying bipolarity in a depressed patient using electroencephalography data alone.
. Hirschfeld RM, Lewis L, Vornik LA. Perceptions and impact of bipolar disorder:How far have we really come? Results of the national depressive and manic-depressive association 2000 survey of individuals with bipolar disorder. J Clin Psychiatry, 2003; 64:161-174.
. Baethge C, Tondo L, I.M. Bratti, T. Bschor, M. Bauer, A.C. Viguera, R.J. Baldessarini. Prophylaxis latency and outcome in bipolar disorders. Can J Psychiatry, 2003; 48:449-457.
. Baldessarini RJ, Tondo L, Baethge CJ, Lepri B, Bratti IM. Effects of treatment latency on response to maintenance treatment in manic-depressive disorders. Bipolar Disord, 2007; 9:386-393.
. Goodwin FK, Jamison KR. Manic-Depressive Illness: Bipolar Disorders and Recurrent Depression, 2nd ed., Oxford University Press, New York, 2007.