Individualized treatment response prediction of dialectical behavior therapy for borderline personality disorder using multimodal magnetic resonance imaging

Mike M Schmitgen, Inga Niedtfeld, Ruth Schmitt, Falk Mancke, Dorina Winter, Christian Schmahl, Sabine C Herpertz, Mike M Schmitgen, Inga Niedtfeld, Ruth Schmitt, Falk Mancke, Dorina Winter, Christian Schmahl, Sabine C Herpertz

Abstract

Introduction: Individualized treatment prediction is crucial for the development and selection of personalized psychiatric interventions. Here, we use random forest classification via pretreatment clinical and demographical (CD), functional, and structural magnetic resonance imaging (MRI) data from patients with borderline personality disorder (BPD) to predict individual treatment response.

Methods: Before dialectical behavior therapy (DBT), 31 female patients underwent functional (three different emotion regulation tasks) and structural MRI. DBT response was predicted using CD and MRI data in previously identified anatomical regions, which have been reported to be multimodally affected in BPD.

Results: Amygdala and parahippocampus activation during a cognitive reappraisal task (in contrasts displaying neural activation for emotional challenge and for regulation), along with severity measures of BPD psychopathology and gray matter volume of the amygdala, provided best predictive power with neuronal hyperractivities in nonresponders. All models, except one model using CD data solely, achieved significantly better accuracy (>70.25%) than a simple all-respond model, with sensitivity and specificity of >0.7 and >0.7, as well as positive and negative likelihood ratios of >2.74 and <0.36 each. Surprisingly, a model combining all data modalities only reached rank five of seven. Among the functional tasks, only the activation elicited by a cognitive reappraisal paradigm yielded sufficient predictive power to enter the final models.

Conclusion: This proof of principle study shows that it is possible to achieve good predictions of psychotherapy outcome to find the most valid predictors among numerous variables via using a random forest classification approach.

Keywords: functional MRI; machine learning; multimodal data analysis; prediction of treatment response; random forest; structural MRI.

Conflict of interest statement

None declared.

© 2019 The Authors. Brain and Behavior published by Wiley Periodicals, Inc.

Figures

Figure 1
Figure 1
Flowchart of the 10‐repeated 10‐fold cross‐validation procedure. Green round‐edged boxes show start and stop of the procedure, blue boxes show operations, yellow parallelograms show output, and orange diamonds show branches
Figure 2
Figure 2
Comparison of positive and negative likelihood ratios (middle vertical line each) for the three models performing better than response rate. (a) CD and sMRI, (b) CD and fMRI and sMRI, (c) CD and fMRI (d) fMRI, (e) sMRI, and (f) fMRI and sMRI. Blue lines indicate positive, red lines negative test result (i.e., predicted responders and nonresponders, respectively)
Figure 3
Figure 3
Localization of the brain areas included in the final models. Left amygdala, (red, reap emotional challenge and regulation, GMV); right parahippocampus (green, reap regulation) provided sufficient predictive power to be included in any of the final models. L: left view, R: right view, Sup: superior view, Inf: inferior view, Ant: anterior view, Pos: posterior view. This figure was created using MRIcroGL (https://www.mccauslandcenter.sc.edu/mricrogl/home)
Figure 4
Figure 4
Mean fMRI activation in responders (shaded) and nonresponders (white) in regions selected for the final models comprising fMRI data for emotional challenge (negative watch vs. neutral watch) and regulation (negative regulate vs. negative watch). Error bars show standard error of the mean. l.Amy.reap.ec: left amygdala in the reappraisal task for emotional challenge, l.Amy.reap.reg: left amygdala in the reappraisal task for regulation, r.Par.Hip.reap.reg: right parahippocampus in the reappraisal task for regulation
Figure 5
Figure 5
Mean GMV in responders (shaded) and nonresponders (white) in regions selected for the final models. Error bars show standard error of the mean. l.Amy.GMV: gray matter volume of the left amygdala
Figure 6
Figure 6
Correlations (Spearman) between all variables used in the final models. Positive correlations are displayed in red, and negative correlations are displayed in blue. Black fillings indicate significant (p < .0018, Bonferroni corrected) results, gray fillings indicate statistical trends (p < .05, not surviving Bonferroni correction). BDI, BDI total score; BSL, BSL total score; Education, education in years; l.Amy.GMV, gray matter volume of the left amygdala; l.Amy.reap.ec, left amygdala in the reappraisal task for emotional challenge; l.Amy.reap.reg, left amygdala in the reappraisal task for regulation; r.ParHip.reap.reg, right parahippocampus in the reappraisal task for regulation; ZAN, ZAN‐BPD total score

References

    1. Ball, T. M. , Stein, M. B. , Ramsawh, H. J. , Campbell‐Sills, L. , & Paulus, M. P. (2014). Single‐subject anxiety treatment outcome prediction using functional neuroimaging. Neuropsychopharmacology, 39(5), 1254–1261. 10.1038/npp.2013.328
    1. Beck, A. T. , Ward, C. H. , Mendelson, M. , Mock, J. , & Erbaugh, J. (1961). An inventory for measuring depression. Archives of General Psychiatry, 4, 561–571. 10.1001/archpsyc.1961.01710120031004
    1. Bohus, M. , Haaf, B. , Simms, T. , Limberger, M. F. , Schmahl, C. , Unckel, C. , … Linehan, M. M. (2004). Effectiveness of inpatient dialectical behavioral therapy for borderline personality disorder: A controlled trial. Behavior Research and Therapy, 42(5), 487–499. 10.1016/S0005-7967(03)00174-8
    1. Bohus, M. , Limberger, M. F. , Frank, U. , Chapman, A. L. , Kuhler, T. , & Stieglitz, R. D. (2007). Psychometric properties of the Borderline Symptom List (BSL). Psychopathology, 40(2), 126–132. 10.1159/000098493
    1. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. 10.1023/A:1010933404324
    1. Brett, M. , Anton, J.‐L. , Valabregue, R. , & Poline, J.‐B. (2002). Region of interest analysis using an SPM toolbox [abstract]. Sendai, Japan: 8th International Conference on Functional Mapping of the Human Brain.
    1. Bureau, A. , Dupuis, J. , Falls, K. , Lunetta, K. L. , Hayward, B. , Keith, T. P. , & Van Eerdewegh, P. (2005). Identifying SNPs predictive of phenotype using random forests. Genetic Epidemiology, 28(2), 171–182. 10.1002/gepi.20041
    1. Bzdok, D. , & Meyer‐Lindenberg, A. (2018). Machine learning for precision psychiatry: Opportunities and challenges. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, 3(3), 223–230. 10.1016/j.bpsc.2017.11.007
    1. Cristea, I. A. , Gentili, C. , Cotet, C. D. , Palomba, D. , Barbui, C. , & Cuijpers, P. (2017). Efficacy of psychotherapies for borderline personality disorder: A systematic review and meta‐analysis. JAMA Psychiatry, 74(4), 319–328. 10.1001/jamapsychiatry.2016.4287
    1. Cuthbert, B. N. , & Insel, T. R. (2013). Toward the future of psychiatric diagnosis: The seven pillars of RDoC. BMC Medicine, 11, 126 10.1186/1741-7015-11-126
    1. Cuthbert, B. N. , & Kozak, M. J. (2013). Constructing constructs for psychopathology: The NIMH research domain criteria. Journal of Abnormal Psychology, 122(3), 928–937. 10.1037/a0034028
    1. Frank, D. W. , Dewitt, M. , Hudgens‐Haney, M. , Schaeffer, D. J. , Ball, B. H. , Schwarz, N. F. , … Sabatinelli, D. (2014). Emotion regulation: Quantitative meta‐analysis of functional activation and deactivation. Neuroscience and Biobehavioral Reviews, 45, 202–211. 10.1016/j.neubiorev.2014.06.010
    1. Genuer, R. , Poggi, J. M. , & Tuleau‐Malot, C. (2010). Variable selection using random forests. Pattern Recognition Letters, 31(14), 2225–2236. 10.1016/j.patrec.2010.03.014
    1. Gratz, K. L. , Dixon‐Gordon, K. L. , & Tull, M. T. (2014). Predictors of treatment response to an adjunctive emotion regulation group therapy for deliberate self‐harm among women with borderline personality disorder. Personality Disorders: Theory, Research, and Treatment, 5(1), 97–107. 10.1037/per0000062
    1. Gratz, K. L. , & Roemer, L. (2004). Multidimensional assessment of emotion regulation and dysregulation: Development, factor structure, and initial validation of the difficulties in emotion regulation scale. Journal of Psychopathology and Behavioral Assessment, 26(1), 41–54. 10.1023/B:Joba.0000007455.08539.94
    1. Hamann, S. (2001). Cognitive and neural mechanisms of emotional memory. Trends in Cognitive Sciences, 5(9), 394–400. 10.1016/S1364-6613(00)01707-1
    1. Jacobson, N. S. , & Truax, P. (1991). Clinical‐Significance – A statistical approach to defining meaningful change in psychotherapy‐research. Journal of Consulting and Clinical Psychology, 59(1), 12–19. 10.1037//0022-006x.59.1.12
    1. Kliem, S. , Kroger, C. , & Kosfelder, J. (2010). Dialectical behavior therapy for borderline personality disorder: A meta‐analysis using mixed‐effects modeling. Journal of Consulting and Clinical Psychology, 78(6), 936–951. 10.1037/a0021015
    1. Koenigsberg, H. W. , Fan, J. , Ochsner, K. N. , Liu, X. , Guise, K. G. , Pizzarello, S. , … Siever, L. J. (2009). Neural correlates of the use of psychological distancing to regulate responses to negative social cues: A study of patients with borderline personality disorder. Biological Psychiatry, 66(9), 854–863. 10.1016/j.biopsych.2009.06.010
    1. Lang, P. J. , Bradley, M. M. , & Cuthbert, B. N. (1997). International Affective Picture System (IAPS): Technical manual and affective ratings. Paper presented at The Center for Research in Psychology, University of Florida, Gainesville.
    1. Linehan, M. (1993). Cognitive‐behavioral treatment of borderline presonality disorder. New York, NY: Guilford Press.
    1. Loranger, A. (1999). International Personality Disorder Examination (IPDE): DSM‐IV and ICD‐10 modules. Odessa, FL: Psychological Assessment Resources.
    1. Lueken, U. , Zierhut, K. C. , Hahn, T. , Straube, B. , Kircher, T. , Reif, A. , … Domschke, K. (2016). Neurobiological markers predicting treatment response in anxiety disorders: A systematic review and implications for clinical application. Neuroscience and Biobehavioral Reviews, 66, 143–162. 10.1016/j.neubiorev.2016.04.005
    1. Maldjian, J. A. , Laurienti, P. J. , Kraft, R. A. , & Burdette, J. H. (2003). An automated method for neuroanatomic and cytoarchitectonic atlas‐based interrogation of fMRI data sets. NeuroImage, 19(3), 1233–1239. 10.1016/S1053-8119(03)00169-1
    1. Niedtfeld, I. , Schmitt, R. , Winter, D. , Bohus, M. , Schmahl, C. , & Herpertz, S. C. (2017). Pain‐mediated affect regulation is reduced after dialectical behavior therapy in borderline personality disorder: A longitudinal fMRI study. Social Cognitive and Affective Neuroscience, 12(5), 739–747. 10.1093/scan/nsw183
    1. Phelps, E. A. (2004). Human emotion and memory: Interactions of the amygdala and hippocampal complex. Current Opinion in Neurobiology, 14(2), 198–202. 10.1016/j.conb.2004.03.015
    1. Qi, Y. J. , Bar‐Joseph, Z. , & Klein‐Seetharaman, J. (2006). Evaluation of different biological data and computational classification methods for use in protein interaction prediction. Proteins: Structure, Function, and Bioinformatics, 63(3), 490–500. 10.1002/prot.20865
    1. Schmitt, R. , Winter, D. , Niedtfeld, I. , Herpertz, S. C. , & Schmahl, C. (2016). Effects of psychotherapy on neuronal correlates of reappraisal in female patients with borderline personality disorder. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, 1(6), 548–557. 10.1016/j.bpsc.2016.07.003
    1. Schulze, L. , Domes, G. , Krüger, A. , Berger, C. , Fleischer, M. , Prehn, K. , … Herpertz, S. C. (2011). Neuronal correlates of cognitive reappraisal in borderline patients with affective instability. Biological Psychiatry, 69(6), 564–573. 10.1016/j.biopsych.2010.10.025
    1. Schulze, L. , Schmahl, C. , & Niedtfeld, I. (2016). Neural correlates of disturbed emotion processing in borderline personality disorder: A multimodal meta‐analysis. Biological Psychiatry, 79(2), 97–106. 10.1016/j.biopsych.2015.03.027
    1. Spielberger, C. D. , Gorusch, R. L. , & Lushene, R. E. (1970). Manual for the State‐Trait Anxiety inventory. Retrieved from
    1. Spitzer, C. , Freyberger, H. J. , Stieglitz, R. D. , Carlson, E. B. , Kuhn, G. , Magdeburg, N. , & Kessler, C. (1998). Adaptation and psychometric properties of the German version of the Dissociative Experience Scale. Journal of Traumatic Stress, 11(4), 799–809. 10.1023/A:1024457819547
    1. Stoffers, J. M. , Vollm, B. A. , Rucker, G. , Timmer, A. , Huband, N. , & Lieb, K. (2012). Psychological therapies for people with borderline personality disorder. Cochrane Database of Systematic Reviews, (8), CD005652 10.1002/14651858.CD005652.pub2
    1. Strobl, C. , Malley, J. , & Tutz, G. (2009). An introduction to recursive partitioning: Rationale, application, and characteristics of classification and regression trees, bagging, and random forests. Psychological Methods, 14(4), 323–348. 10.1037/a0016973
    1. Tewes, U. (1991, Revision 1991). Hamburg‐Wechsler intelligenztest für Erwachsene. Retrieved from
    1. Tzourio‐Mazoyer, N. , Landeau, B. , Papathanassiou, D. , Crivello, F. , Etard, O. , Delcroix, N. , … Joliot, M. (2002). Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single‐subject brain. NeuroImage, 15(1), 273–289. 10.1006/nimg.2001.0978
    1. Wade, B. S. , Joshi, S. H. , Pirnia, T. , Leaver, A. M. , Woods, R. P. , Thompson, P. M. , … Narr, K. L. (2015). Random forest classification of depression status based on subcortical brain morphometry following electroconvulsive therapy In Proc IEEE Int Symp Biomed Imaging (pp. 92–96).
    1. Wessa, M. , Kanske, P. , Neumeister, P. , Bode, K. , Heissler, J. , & Schönfelder, S. (2010). EmoPics: Subjektive und psychophysiologische Evaluationen neuen Bildmaterials für die klinisch‐bio‐psychologische Forschung. Zeitschrift Für Klinische Psychologie Und Psychotherapie Supplement, 1(11), 77.
    1. Winter, D. , Niedtfeld, I. , Schmitt, R. , Bohus, M. , Schmahl, C. , & Herpertz, S. C. (2017). Neural correlates of distraction in borderline personality disorder before and after dialectical behavior therapy. European Archives of Psychiatry and Clinical Neuroscience, 267(1), 51–62. 10.1007/s00406-016-0689-2
    1. Wittchen, H. U. , Wunderlich, U. , Gruschwitz, S. , & Zaudig, M. (1997). SKID I. Strukturiertes Klinisches Interview für DSM‐IV. Achse I. Göttingen, Germany: Hogrefe.
    1. Zanarini, M. C. , Vujanovic, A. A. , Parachini, E. A. , Boulanger, J. L. , Frankenburg, F. R. , & Hennen, J. (2003). Zanarini Rating Scale for Borderline Personality Disorder (ZAN‐BPD): A continuous measure of DSM‐IV borderline psychopathology. Journal of Personality Disorders, 17(3), 233–242. 10.1521/pedi.17.3.233.22147

Source: PubMed

Sponsors and Collaborators

Medical Conditions

Drug Interventions

3
Subscribe