Forskning
Udskriv Udskriv
Switch language
Region Hovedstaden - en del af Københavns Universitetshospital
Udgivet

Accuracy of diagnostic classification algorithms using cognitive-, electrophysiological-, and neuroanatomical data in antipsychotic-naïve schizophrenia patients

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Harvard

APA

CBE

MLA

Vancouver

Author

Bibtex

@article{b6cfdae12f1145d785f5405c8c323abb,
title = "Accuracy of diagnostic classification algorithms using cognitive-, electrophysiological-, and neuroanatomical data in antipsychotic-na{\"i}ve schizophrenia patients",
abstract = "BACKGROUND: A wealth of clinical studies have identified objective biomarkers, which separate schizophrenia patients from healthy controls on a group level, but current diagnostic systems solely include clinical symptoms. In this study, we investigate if machine learning algorithms on multimodal data can serve as a framework for clinical translation.METHODS: Forty-six antipsychotic-na{\"i}ve, first-episode schizophrenia patients and 58 controls underwent neurocognitive tests, electrophysiology, and magnetic resonance imaging (MRI). Patients underwent clinical assessments before and after 6 weeks of antipsychotic monotherapy with amisulpride. Nine configurations of different supervised machine learning algorithms were applied to first estimate the unimodal diagnostic accuracy, and next to estimate the multimodal diagnostic accuracy. Finally, we explored the predictability of symptom remission.RESULTS: Cognitive data significantly classified patients from controls (accuracies = 60-69{\%}; p values = 0.0001-0.009). Accuracies of electrophysiology, structural MRI, and diffusion tensor imaging did not exceed chance level. Multimodal analyses with cognition plus any combination of one or more of the remaining three modalities did not outperform cognition alone. None of the modalities predicted symptom remission.CONCLUSIONS: In this multivariate and multimodal study in antipsychotic-na{\"i}ve patients, only cognition significantly discriminated patients from controls, and no modality appeared to predict short-term symptom remission. Overall, these findings add to the increasing call for cognition to be included in the definition of schizophrenia. To bring about the full potential of machine learning algorithms in first-episode, antipsychotic-na{\"i}ve schizophrenia patients, careful a priori variable selection based on independent data as well as inclusion of other modalities may be required.",
keywords = "Antipsychotic-na{\"i}ve first-episode schizophrenia, cognition, diffusion tensor imaging, electrophysiology, machine learning, structural magnetic resonance imaging",
author = "Ebdrup, {Bj{\o}rn H} and Axelsen, {Martin C} and Nikolaj Bak and Birgitte Fagerlund and Bob Oranje and Raghava, {Jayachandra M} and Nielsen, {Mette {\O}} and Egill Rostrup and Hansen, {Lars K} and Glenth{\o}j, {Birte Y}",
year = "2019",
month = "12",
doi = "10.1017/S0033291718003781",
language = "English",
volume = "49",
pages = "2754--2763",
journal = "Psychological Medicine",
issn = "0033-2917",
publisher = "Cambridge University Press",
number = "16",

}

RIS

TY - JOUR

T1 - Accuracy of diagnostic classification algorithms using cognitive-, electrophysiological-, and neuroanatomical data in antipsychotic-naïve schizophrenia patients

AU - Ebdrup, Bjørn H

AU - Axelsen, Martin C

AU - Bak, Nikolaj

AU - Fagerlund, Birgitte

AU - Oranje, Bob

AU - Raghava, Jayachandra M

AU - Nielsen, Mette Ø

AU - Rostrup, Egill

AU - Hansen, Lars K

AU - Glenthøj, Birte Y

PY - 2019/12

Y1 - 2019/12

N2 - BACKGROUND: A wealth of clinical studies have identified objective biomarkers, which separate schizophrenia patients from healthy controls on a group level, but current diagnostic systems solely include clinical symptoms. In this study, we investigate if machine learning algorithms on multimodal data can serve as a framework for clinical translation.METHODS: Forty-six antipsychotic-naïve, first-episode schizophrenia patients and 58 controls underwent neurocognitive tests, electrophysiology, and magnetic resonance imaging (MRI). Patients underwent clinical assessments before and after 6 weeks of antipsychotic monotherapy with amisulpride. Nine configurations of different supervised machine learning algorithms were applied to first estimate the unimodal diagnostic accuracy, and next to estimate the multimodal diagnostic accuracy. Finally, we explored the predictability of symptom remission.RESULTS: Cognitive data significantly classified patients from controls (accuracies = 60-69%; p values = 0.0001-0.009). Accuracies of electrophysiology, structural MRI, and diffusion tensor imaging did not exceed chance level. Multimodal analyses with cognition plus any combination of one or more of the remaining three modalities did not outperform cognition alone. None of the modalities predicted symptom remission.CONCLUSIONS: In this multivariate and multimodal study in antipsychotic-naïve patients, only cognition significantly discriminated patients from controls, and no modality appeared to predict short-term symptom remission. Overall, these findings add to the increasing call for cognition to be included in the definition of schizophrenia. To bring about the full potential of machine learning algorithms in first-episode, antipsychotic-naïve schizophrenia patients, careful a priori variable selection based on independent data as well as inclusion of other modalities may be required.

AB - BACKGROUND: A wealth of clinical studies have identified objective biomarkers, which separate schizophrenia patients from healthy controls on a group level, but current diagnostic systems solely include clinical symptoms. In this study, we investigate if machine learning algorithms on multimodal data can serve as a framework for clinical translation.METHODS: Forty-six antipsychotic-naïve, first-episode schizophrenia patients and 58 controls underwent neurocognitive tests, electrophysiology, and magnetic resonance imaging (MRI). Patients underwent clinical assessments before and after 6 weeks of antipsychotic monotherapy with amisulpride. Nine configurations of different supervised machine learning algorithms were applied to first estimate the unimodal diagnostic accuracy, and next to estimate the multimodal diagnostic accuracy. Finally, we explored the predictability of symptom remission.RESULTS: Cognitive data significantly classified patients from controls (accuracies = 60-69%; p values = 0.0001-0.009). Accuracies of electrophysiology, structural MRI, and diffusion tensor imaging did not exceed chance level. Multimodal analyses with cognition plus any combination of one or more of the remaining three modalities did not outperform cognition alone. None of the modalities predicted symptom remission.CONCLUSIONS: In this multivariate and multimodal study in antipsychotic-naïve patients, only cognition significantly discriminated patients from controls, and no modality appeared to predict short-term symptom remission. Overall, these findings add to the increasing call for cognition to be included in the definition of schizophrenia. To bring about the full potential of machine learning algorithms in first-episode, antipsychotic-naïve schizophrenia patients, careful a priori variable selection based on independent data as well as inclusion of other modalities may be required.

KW - Antipsychotic-naïve first-episode schizophrenia

KW - cognition

KW - diffusion tensor imaging

KW - electrophysiology

KW - machine learning

KW - structural magnetic resonance imaging

UR - http://www.scopus.com/inward/record.url?scp=85075494697&partnerID=8YFLogxK

U2 - 10.1017/S0033291718003781

DO - 10.1017/S0033291718003781

M3 - Journal article

VL - 49

SP - 2754

EP - 2763

JO - Psychological Medicine

JF - Psychological Medicine

SN - 0033-2917

IS - 16

ER -

ID: 56303102