Computational methods for integrative evaluation of confidence, accuracy, and reaction time in facial affect recognition in schizophrenia

Varsha D Badal, Colin A Depp, Peter F Hitchcock, David L Penn, Philip D Harvey, Amy E Pinkham, Varsha D Badal, Colin A Depp, Peter F Hitchcock, David L Penn, Philip D Harvey, Amy E Pinkham

Abstract

People with schizophrenia (SZ) process emotions less accurately than do healthy comparators (HC), and emotion recognition have expanded beyond accuracy to performance variables like reaction time (RT) and confidence. These domains are typically evaluated independently, but complex inter-relationships can be evaluated through machine learning at an item-by-item level. Using a mix of ranking and machine learning tools, we investigated item-by-item discrimination of facial affect with two emotion recognition tests (BLERT and ER-40) between SZ and HC. The best performing multi-domain model for ER40 had a large effect size in differentiating SZ and HC (d = 1.24) compared to a standard comparison of accuracy alone (d = 0.48); smaller increments in effect sizes were evident for the BLERT (d = 0.87 vs. d = 0.58). Almost half of the selected items were confidence ratings. Within SZ, machine learning models with ER40 (generally accuracy and reaction time) items predicted severity of depression and overconfidence in social cognitive ability, but not psychotic symptoms. Pending independent replication, the results support machine learning, and the inclusion of confidence ratings, in characterizing the social cognitive deficits in SZ. This moderate-sized study (n = 372) included subjects with schizophrenia (SZ, n = 218) and healthy controls (HC, n = 154).

Keywords: Machine learning; Neural networks; Psychosis; Social cognition.

Conflict of interest statement

Dr. Harvey has received consulting fees or travel reimbursements from Allergan, Alkermes, Akili, Biogen, Boehringer Ingelheim, Forum Pharma, Genentech (Roche Pharma), Intra-Cellular Therapies, Jazz Pharma, Lundbeck Pharma, Minerva Pharma, Otsuka America (Otsuka Digital Health), Sanofi Pharma, Sunovion Pharma, Takeda Pharma, and Teva. He receives royalties from the Brief Assessment of Cognition in Schizophrenia and the MATRICS Consensus Battery. He is chief scientific officer of i-Function, Inc. He has a research grant from Takeda and from the Stanley Medical Research Foundation. None of the other authors have commercial interests to report.

References

    1. Alloy L.B., Abramson L.Y. Judgment of contingency in depressed and nondepressed students: sadder but wiser? J. Exp. Psychol. Gen. 1979;108:441.
    1. Beck A.T., Steer R.A., Brown G.K. Vol. 78. 1996. Beck Depression Inventory-II. San Antonio; pp. 490–498.
    1. Bell M., Bryson G., Lysaker P. Positive and negative affect recognition in schizophrenia: a comparison with substance abuse and normal control subjects. Psychiatry Res. 1997;73:73–82.
    1. Bommert A., Sun X., Bischl B., Rahnenführer J., Lang M. Benchmark for filter methods for feature selection in high-dimensional classification data. Comput. Stat. Data Anal. 2020;143:106839.
    1. Bortolotti L., Antrobus M. Costs and benefits of realism and optimism. Curr. Opin. Psychiatry. 2015;28:194.
    1. Chemerinski E., Bowie C., Anderson H., Harvey P.D. Depression in schizophrenia: methodological artifact or distinct feature of the illness? J. Neuropsychiatry Clin. Neurosci. 2008;20:431–440.
    1. Claesen M., De Moor B. Hyperparameter search in machine learning. arXiv preprint. 2015 arXiv:1502.02127.
    1. Cornacchio D., Pinkham A.E., Penn D.L., Harvey P.D. Self-assessment of social cognitive ability in individuals with schizophrenia: appraising task difficulty and allocation of effort. Schizophr. Res. 2017;179:85–90.
    1. Demsar J.C.T., Erjavec A., Gorup C., Hocevar T., Milutinovic M., Mozina M., Polajnar M., Toplak M., Staric A., Stajdohar M., Umek L., Zagar L., Zbontar J., Zitnik M., Zupan B. Orange: data mining toolbox in python. J. Mach. Learn. Res. 2013;14(Aug):2349–2353.
    1. Dubey R., Zhou J., Wang Y., Thompson P.M., Ye J., Initiative A.S.D.N. Analysis of sampling techniques for imbalanced data: an n= 648 ADNI study. NeuroImage. 2014;87:220–241.
    1. Gur R.C., Sara R., Hagendoorn M., Marom O., Hughett P., Macy L., Turner T., Bajcsy R., Posner A., Gur R.E. A method for obtaining 3-dimensional facial expressions and its standardization for use in neurocognitive studies. J. Neurosci. Methods. 2002;115:137–143.
    1. Gur R.E., Calkins M.E., Gur R.C., Horan W.P., Nuechterlein K.H., Seidman L.J., Stone W.S. The consortium on the genetics of schizophrenia: neurocognitive endophenotypes. Schizophr. Bull. 2007;33:49–68.
    1. Harvey P.D., Khan A., Keefe R.S.E. Using the positive and negative syndrome scale (PANSS) to define different domains of negative symptoms: prediction of everyday functioning by impairments in emotional expression and emotional experience. Innov Clin Neurosci. 2017;14:18–22.
    1. Harvey P.D., Deckler E., Jones M.T., Jarskog L.F., Penn D.L., Pinkham A.E. Autism symptoms, depression, and active social avoidance in schizophrenia: association with self-reports and informant assessments of everyday functioning. J. Psychiatr. Res. 2019;115:36–42.
    1. Healey K.M., Combs D.R., Gibson C.M., Keefe R.S., Roberts D.L., Penn D.L. Observable Social Cognition—a Rating Scale: an interview-based assessment for schizophrenia. Cogn. Neuropsychiatry. 2015;20:198–221.
    1. Hooker C., Park S. Emotion processing and its relationship to social functioning in schizophrenia patients. Psychiatry Res. 2002;112:41–50.
    1. Hoven M., Lebreton M., Engelmann J.B., Denys D., Luigjes J., VAN Holst R.J. Abnormalities of confidence in psychiatry: an overview and future perspectives. Transl. Psychiatry. 2019;9:1–18.
    1. Jones M.T., Deckler E., Laurrari C., Jarskog L.F., Penn D.L., Pinkham A.E., Harvey P.D. Schizophrenia Research: Cognition. 2019. Confidence, performance, and accuracy of self-assessment of social cognition: a comparison of schizophrenia patients and healthy controls.
    1. Kalin M., Kaplan S., Gould F., Pinkham A.E., Penn D.L., Harvey P.D. Social cognition, social competence, negative symptoms and social outcomes: inter-relationships in people with schizophrenia. J. Psychiatr. Res. 2015;68:254–260.
    1. Kantardzic M. John Wiley & Sons; 2011. Data Mining: Concepts, Models, Methods, and Algorithms.
    1. Kay S.R., Fiszbein A., Opler L.A. The positive and negative syndrome scale (PANSS) for schizophrenia. Schizophr. Bull. 1987;13:261–276.
    1. Kerr S.L., Neale J.M. Emotion perception in schizophrenia: specific deficit or further evidence of generalized poor performance? J. Abnorm. Psychol. 1993;102:312.
    1. Maatz A., Hoff P., Angst J. Eugen Bleuler’s schizophrenia—a modern perspective. Dialogues Clin. Neurosci. 2015;17:43.
    1. Mandal M.K., Pandey R., Prasad A.B. Facial expressions of emotions and schizophrenia: a review. Schizophr. Bull. 1998;24:399–412.
    1. Noordewier M.K., Breugelmans S.M. On the valence of surprise. Cognit. Emot. 2013;27:1326–1334.
    1. Oliveri L.N., Awerbuch A.W., Jarskog L.F., Penn D.L., Pinkham A., Harvey P.D. Depression predicts self assessment of social function in both patients with schizophrenia and healthy people. Psychiatry Res. 2019;112681
    1. Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V. Scikit-learn: machine learning in python. J. Mach. Learn. Res. 2011;12:2825–2830.
    1. Pinkham A.E., Harvey P.D., Penn D.L. Social cognition psychometric evaluation: results of the final validation study. Schizophr. Bull. 2017;44:737–748.
    1. Pinkham A.E., Harvey P.D., Penn D.L. Social cognition psychometric evaluation: results of the final validation study. Schizophr. Bull. 2018;44:737–748.
    1. Pinkham A.E., Klein H.S., Hardaway G.B., Kemp K.C., Harvey P.D. Neural correlates of social cognitive introspective accuracy in schizophrenia. Schizophr. Res. 2018;202:166–172.
    1. Pinkham A.E., Morrison K.E., Penn D.L., Harvey P.D., Kelsven S., Ludwig K., Sasson N.J. Comprehensive comparison of social cognitive performance in autism spectrum disorder and schizophrenia. Psychol. Med. 2019:1–9.
    1. Salgado J.F. Transforming the area under the normal curve (AUC) into Cohen’sd, Pearson’s rpb, odds-ratio, and natural log odds-ratio: two conversion tables. J. Exp. Psychol. Gen. 2018;10:35–47.
    1. Sasson N.J., Pinkham A.E., Richard J., Hughett P., Gur R.E., Gur R.C. Controlling for response biases clarifies sex and age differences in facial affect recognition. J. Nonverbal Behav. 2010;34:207–221.
    1. Schneider F., Gur R.C., Gur R.E., Shtasel D.L. Emotional processing in schizophrenia: neurobehavioral probes in relation to psychopathology. Schizophr. Res. 1995;17:67–75.
    1. Scikit-Learn. [Online]. [Accessed December 2019].
    1. Silberstein J.M., Pinkham A.E., Penn D.L., Harvey P.D. Self-assessment of social cognitive ability in schizophrenia: association with social cognitive test performance, informant assessments of social cognitive ability, and everyday outcomes. Schizophr. Res. 2018;199:75–82.
    1. Strassnig M., Bowie C., Pinkham A.E., Penn D., Twamley E.W., Patterson T.L., Harvey P.D. Which levels of cognitive impairments and negative symptoms are related to functional deficits in schizophrenia? J. Psychiatr. Res. 2018;104:124–129.

Source: PubMed

Patrocinadores e Colaboradores

Condições médicas

Intervenções de drogas

3
Se inscrever