M Guggenmos1, M Scheel2, M Sekutowicz1, M Garbusow1, M Sebold1, C Sommer3, K Charlet1, A Beck1, H-U Wittchen4,5, U S Zimmermann3, M N Smolka3,6, A Heinz1, P Sterzer1, K Schmack1. 1. Department of Psychiatry and Psychotherapy, Campus Charité Mitte, Charité Universitätsmedizin Berlin, Berlin, Germany. 2. Department of Radiology, Charité Universitätsmedizin Berlin, Berlin, Germany. 3. Department of Psychiatry and Psychotherapy, Technische Universität Dresden, Dresden, Germany. 4. Institute for Clinical Psychology and Psychotherapy, Technische Universität Dresden, Dresden, Germany. 5. Research Group Clinical Psychology and Psychotherapy, Department of Psychiatry and Psychotherapy, Ludwig Maximilans Universität Munich, Munich, Germany. 6. Neuroimaging Center, Technische Universität Dresden, Dresden, Germany.
Abstract
OBJECTIVE: We investigated the potential of computer-based models to decode diagnosis and lifetime consumption in alcohol dependence (AD) from grey-matter pattern information. As machine-learning approaches to psychiatric neuroimaging have recently come under scrutiny due to unclear generalization and the opacity of algorithms, our investigation aimed to address a number of methodological criticisms. METHOD: Participants were adult individuals diagnosed with AD (N = 119) and substance-naïve controls (N = 97) ages 20-65 who underwent structural MRI. Machine-learning models were applied to predict diagnosis and lifetime alcohol consumption. RESULTS: A classification scheme based on regional grey matter attained 74% diagnostic accuracy and predicted lifetime consumption with high accuracy (r = 0.56, P < 10-10 ). A key advantage of the classification scheme was its algorithmic transparency, revealing cingulate, insular and inferior frontal cortices as important brain areas underlying classification. Validation of the classification scheme on data of an independent trial was successful with nearly identical accuracy, addressing the concern of generalization. Finally, compared to a blinded radiologist, computer-based classification showed higher accuracy and sensitivity, reduced age and gender biases, but lower specificity. CONCLUSION: Computer-based models applied to whole-brain grey-matter predicted diagnosis and lifetime consumption in AD with good accuracy. Computer-based classification may be particularly suited as a screening tool with high sensitivity.
OBJECTIVE: We investigated the potential of computer-based models to decode diagnosis and lifetime consumption in alcohol dependence (AD) from grey-matter pattern information. As machine-learning approaches to psychiatric neuroimaging have recently come under scrutiny due to unclear generalization and the opacity of algorithms, our investigation aimed to address a number of methodological criticisms. METHOD:Participants were adult individuals diagnosed with AD (N = 119) and substance-naïve controls (N = 97) ages 20-65 who underwent structural MRI. Machine-learning models were applied to predict diagnosis and lifetime alcohol consumption. RESULTS: A classification scheme based on regional grey matter attained 74% diagnostic accuracy and predicted lifetime consumption with high accuracy (r = 0.56, P < 10-10 ). A key advantage of the classification scheme was its algorithmic transparency, revealing cingulate, insular and inferior frontal cortices as important brain areas underlying classification. Validation of the classification scheme on data of an independent trial was successful with nearly identical accuracy, addressing the concern of generalization. Finally, compared to a blinded radiologist, computer-based classification showed higher accuracy and sensitivity, reduced age and gender biases, but lower specificity. CONCLUSION: Computer-based models applied to whole-brain grey-matter predicted diagnosis and lifetime consumption in AD with good accuracy. Computer-based classification may be particularly suited as a screening tool with high sensitivity.
Authors: Matthias Guggenmos; Katharina Schmack; Ilya M Veer; Tristram Lett; Maria Sekutowicz; Miriam Sebold; Maria Garbusow; Christian Sommer; Hans-Ulrich Wittchen; Ulrich S Zimmermann; Michael N Smolka; Henrik Walter; Andreas Heinz; Philipp Sterzer Journal: Sci Rep Date: 2020-01-15 Impact factor: 4.379
Authors: Sage Hahn; Scott Mackey; Janna Cousijn; John J Foxe; Andreas Heinz; Robert Hester; Kent Hutchinson; Falk Kiefer; Ozlem Korucuoglu; Tristram Lett; Chiang-Shan R Li; Edythe London; Valentina Lorenzetti; Luijten Maartje; Reza Momenan; Catherine Orr; Martin Paulus; Lianne Schmaal; Rajita Sinha; Zsuzsika Sjoerds; Dan J Stein; Elliot Stein; Ruth J van Holst; Dick Veltman; Henrik Walter; Reinout W Wiers; Murat Yucel; Paul M Thompson; Patricia Conrod; Nicholas Allgaier; Hugh Garavan Journal: Hum Brain Mapp Date: 2020-10-16 Impact factor: 5.399