조현병 감별진단에 대한 머신 러닝 기법의 적용 : WAIS-IV의 진단 예측 역량
A Case Study of a Machine-Learning Approach in Differential Diagnosis of Schizophrenia : The Predictive Capacity of WAIS-IV
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
Objectives Machine learning (ML) encompasses a body of statistical approaches that can detect complex interaction patterns from multi-dimensional data. ML is gradually being adopted in medical science, for example, in treatment response prediction and diagnostic classification. Cognitive impairment is a prominent feature of schizophrenia, but is not routinely used in differential diagnosis. In this study, we investigated the predictive capacity of the Wechsler Adult Intelligence Scale IV (WAIS-IV) in differentiating schizophrenia from non-psychotic illnesses using the ML methodology. The purpose of this study was to illustrate the possibility of using ML as an aid in differential diagnosis. Methods The WAIS-IV test data for 434 psychiatric patients were curated from archived medical records. Using the final diagnoses based on DSM-IV as the target and the WAIS-IV scores as predictor variables, predictive diagnostic models were built using 1) linear 2) non-linear/non-parametric ML algorithms. The accuracy obtained was compared to that of the baseline model built without the WAIS-IV information. Results The performances of the various ML models were compared. The accuracy of the baseline model was 71.5%, but the best non-linear model showed an accuracy of 84.6%, which was significantly higher than that of non-informative random guessing (p=0.002). Overall, the models using the non‑linear algorithms showed better accuracy than the linear ones. Conclusion The high performance of the developed models demonstrated the predictive capacity of the WAIS-IV and justified the application of ML in psychiatric diagnosis. However, the practical application of ML models may need refinement and larger-scale data collection.
Abstract
Objectives Machine learning (ML) encompasses a body of statistical approaches that can detect complex interaction patterns from multi-dimensional data. ML is gradually being adopted in medical science, for example, in treatment response prediction and diagnostic classification. Cognitive impairment is a prominent feature of schizophrenia, but is not routinely used in differential diagnosis. In this study, we investigated the predictive capacity of the Wechsler Adult Intelligence Scale IV (WAIS-IV) in differentiating schizophrenia from non-psychotic illnesses using the ML methodology. The purpose of this study was to illustrate the possibility of using ML as an aid in differential diagnosis. Methods The WAIS-IV test data for 434 psychiatric patients were curated from archived medical records. Using the final diagnoses based on DSM-IV as the target and the WAIS-IV scores as predictor variables, predictive diagnostic models were built using 1) linear 2) non-linear/non-parametric ML algorithms. The accuracy obtained was compared to that of the baseline model built without the WAIS-IV information. Results The performances of the various ML models were compared. The accuracy of the baseline model was 71.5%, but the best non-linear model showed an accuracy of 84.6%, which was significantly higher than that of non-informative random guessing (p=0.002). Overall, the models using the non‑linear algorithms showed better accuracy than the linear ones. Conclusion The high performance of the developed models demonstrated the predictive capacity of the WAIS-IV and justified the application of ML in psychiatric diagnosis. However, the practical application of ML models may need refinement and larger-scale data collection.
참고문헌 (44)
- Hastie T, "The elements of statistical learning:data mining, inference, and prediction" (2009), Springer Science & Business Media
- Clarke B, "Principles and theory for data mining and machine learning" (2009), Springer Science & Business Media
- Zhou ZH, "Ensemble methods: foundations and algorithms" (2012), CRC Press
- Mikolas P, "Connectivity of the anterior insula differentiates participants with first-episode schizophrenia spectrum disorders from controls: a machine-learning study", Psychol Med, 46, pp.2695~2704 (2016)
- Deo RC, "Machine learning in medicine", Circulation, 132, pp.1920~1930 (2015)
- Ravan M, "A machine learning approach using auditory odd-ball responses to investigate the effect of Clozapine therapy", Clin Neurophysiol, 126, pp.721~730 (2015)
- Shim M, "Machine-learningbased diagnosis of schizophrenia using combined sensor-level and source-level EEG features", Schizophr Res, 176, pp.314~319 (2016)
- Johannesen JK, "Machine learning identification of EEG features predicting working memory performance in schizophrenia and healthy adults", Neuropsychiatr Electrophysiol, 2, pp.3~ (2016)
- Koutsouleris N, "Multisite prediction of 4-week and 52-week treatment outcomes in patients with first-episode psychosis: a machine learning approach", Lancet Psychiatry, 3, pp.935~946 (2016)
- Weickert CS, "Biomarkers in schizophrenia:a brief conceptual consideration", Dis Markers, 35, pp.3~9 (2013)
- Tomasik J, "Blood test for schizophrenia", Eur Arch Psychiatry Clin Neurosci, 262(Suppl 2), pp.S79~S83 (2012)
- Michel NM, "WAIS-IV profile of cognition in schizophrenia", Assessment, 20, pp.462~473 (2013)
- Schaefer J, "The global cognitive impairment in schizophrenia: consistent over decades and around the world", Schizophr Res, 150, pp.42~50 (2013)
- Kahn RS, "Schizophrenia is a cognitive illness: time for a change in focus", JAMA Psychiatry, 70, pp.1107~1112 (2013)
- Bora E, "Cognitive impairment in euthymic major depressive disorder: a meta-analysis", Psychol Med, 43, pp.2017~2026 (2013)
- Seaton BE, "Sources of heterogeneity in schizophrenia:the role of neuropsychological functioning", Neuropsychol Rev, 11, pp.45~67 (2001)
- Keefe RS, "How should DSM-V criteria for schizophrenia include cognitive impairment?", Schizophr Bull, 33, pp.912~920 (2007)
- Dickinson D, "General and specific cognitive deficits in schizophrenia", Biol Psychiatry, 55, pp.826~833 (2004)
- Dickinson D, "General and specific cognitive deficits in schizophrenia: Goliath defeats David?", Biol Psychiatry, 64, pp.823~827 (2008)
- Trivedi MH, "Cognitive dysfunction in unipolar depression:implications for treatment", J Affect Disord, 152-154, pp.19~27 (2014)
- Iwabuchi SJ, "Clinical utility of machinelearning approaches in schizophrenia: improving diagnostic confidence for translational neuroimaging", Front Psychiatry, 4, pp.95~ (2013)
- Jordan MI, "Machine learning: trends, perspectives, and prospects", Science, 349, pp.255~260 (2015)
- Wechsler D, "The psychometric tradition: developing the wechsler adult intelligence scale", Contemp Educ Psychol, 6, pp.82~85 (1981)
- Sumiyoshi C, "Development of brief versions of the Wechsler Intelligence Scale for schizophrenia:considerations of the structure and predictability of intelligence", Psychiatry Res, 210, pp.773~779 (2013)
- Fujino H, "Performance on the Wechsler Adult Intelligence Scale-III in Japanese patients with schizophrenia", Psychiatry Clin Neurosci, 68, pp.534~541 (2014)
- Heinrichs RW, "Neurocognitive deficit in schizophrenia:a quantitative review of the evidence", Neuropsychology, 12, pp.426~445 (1998)
- Hwang ST, "Standardization of the K-WAIS-IV", Proceedings of Korean Psychological Association Annual Conference (2012), Korean Psychological Association
- McHugh ML, "Interrater reliability: the kappa statistic", Biochem Med (Zagreb), 22, pp.276~282 (2012)
- R Development Core Team, "R: a language and environment for statistical computing. 3.2.4 ed", R Foundation for Statistical Computing, ~ (2016)
- Kuhn M, "Caret: classification and regression training. R package version 6.0-68 ed", ~ (2016)
- Harrison-Read P, "IQ tests as aids to diagnosis and management in early schizophrenia", Adv Psychiatr Treat, 14, pp.235~240 (2008)
- Bora E, "Cognitive functioning in schizophrenia, schizoaffective disorder and affective psychoses: meta-analytic study", Br J Psychiatry, 195, pp.475~482 (2009)
- Keefe RS, "A longitudinal study of neurocognitive function in individuals at-risk for psychosis", Schizophr Res, 88, pp.26~35 (2006)
- Kitchen H, "Cognitive impairment associated with schizophrenia: a review of the humanistic burden", Adv Ther, 29, pp.148~162 (2012)
- Dickinson D, "Overlooking the obvious: a meta-analytic comparison of digit symbol coding tasks and other cognitive measures in schizophrenia", Arch Gen Psychiatry, 64, pp.532~542 (2007)
- Chekroud AM, "Cross-trial prediction of treatment outcome in depression:a machine learning approach", Lancet Psychiatry, 3, pp.243~250 (2016)
- Chekroud AM, "Reevaluating the efficacy and predictability of antidepressant treatments: a symptom clustering approach", JAMA Psychiatry, 74, pp.370~378 (2017)
- Manove E, "Cognitive impairment in bipolar disorder: an overview", Postgrad Med, 122, pp.7~16 (2010)
- Vieta E, "The clinical implications of cognitive impairment and allostatic load in bipolar disorder", Eur Psychiatry, 28, pp.21~29 (2013)
- Zielesny A, "From curve fitting to machine learning: an illustrative guide to scientific data analysis and computational intelligence" (2016), Springer International Publishing
- Han H, "Overcome support vector machine diagnosis overfitting", Cancer Inform, 13(Suppl 1), pp.145~158 (2014)
- Holthausen EA, "Schizophrenic patients without neuropsychological deficits: subgroup, disease severity or cognitive compensation?", Psychiatry Res, 112, pp.1~11 (2002)
- Allen DN, "A consideration of neuropsychologically normal schizophrenia", J Int Neuropsychol Soc, 9, pp.56~63 (2003)
- Reichenberg A, "Neuropsychological function and dysfunction in schizophrenia and psychotic affective disorders", Schizophr Bull, 35, pp.1022~1029 (2009)