Prediction of anxiety disorders using a feature ensemble based bayesian neural network

Anxiety disorders are common among youth, posing risks to physical and mental health development. Early screening can help identify such disorders and pave the way for preventative treatment. To this end, the Youth Online Diagnostic Assessment (YODA) tool was developed and deployed to predict youth disorders using online screening questionnaires filled by parents. YODA facilitated collection of several novel unique datasets of self-reported anxiety disorder symptoms. Since the data is self-reported and often noisy, feature selection needs to be performed on the raw data to improve accuracy. However, a single set of selected features may not be informative enough. Consequently, in this work we propose and evaluate a novel feature ensemble based Bayesian Neural Network (FE-BNN) that exploits an ensemble of features for improving the accuracy of disorder predictions. We evaluate the performance of FE-BNN on three disorder-specific datasets collected by YODA. Our method achieved the AUC of 0.8683, 0.8769, 0.9091 for the predictions of Separation Anxiety Disorder, Generalized Anxiety Disorder and Social Anxiety Disorder, respectively. These results provide initial evidence that our method outperforms the original diagnostic scoring function of YODA and several other baseline methods for three anxiety disorders, which can practically help prioritizing diagnostic interviews. Our promising results call for investigation of interpretable methods maintaining high predictive accuracy.

[1]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[2]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[3]  Radford M. Neal Bayesian Learning via Stochastic Dynamics , 1992, NIPS.

[4]  Roberto Cipolla,et al.  Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding , 2015, BMVC.

[5]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

[6]  Mark Olfson,et al.  Service utilization for lifetime mental disorders in U.S. adolescents: results of the National Comorbidity Survey-Adolescent Supplement (NCS-A). , 2011, Journal of the American Academy of Child and Adolescent Psychiatry.

[7]  Panayiotis E. Pintelas,et al.  A review of machine learning prediction methods for anxiety disorders , 2018, DSAI.

[8]  José Ignacio Orlando,et al.  U2-Net: A Bayesian U-Net Model With Epistemic Uncertainty Feedback For Photoreceptor Layer Segmentation In Pathological OCT Scans , 2019, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[9]  W. Silverman,et al.  The Anxiety Disorders Interview Schedule for Children. , 1988, Journal of the American Academy of Child and Adolescent Psychiatry.

[10]  Michael V Heinz,et al.  Predictive modeling of depression and anxiety using electronic health records and a novel machine learning approach with artificial intelligence , 2021, Scientific reports.

[11]  David Walter,et al.  Scales , 1981, Encyclopedia of Early Modern History Online.

[12]  A. Rothenberger,et al.  Mental health in children and adolescents , 2008, European Child & Adolescent Psychiatry.

[13]  H White,et al.  A randomized, controlled trial of child psychiatric assessments conducted using videoconferencing , 2000, Journal of telemedicine and telecare.

[14]  Masashi Sugiyama,et al.  Bayesian Dark Knowledge , 2015 .

[15]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[16]  R. Rapee,et al.  The Youth Online Diagnostic Assessment (YODA): Validity of a New Tool to Assess Anxiety Disorders in Youth , 2020, Child psychiatry and human development.

[17]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[18]  R. Rapee,et al.  Agreement between telephone and in-person delivery of a structured interview for anxiety disorders in children. , 2005, Journal of the American Academy of Child and Adolescent Psychiatry.

[19]  Alex Pentland,et al.  Daily Stress Recognition from Mobile Phone Data, Weather Conditions and Individual Traits , 2014, ACM Multimedia.

[20]  Lipo Wang,et al.  A Modified T-test Feature Selection Method and Its Application on the HapMap Genotype Data , 2008, Genom. Proteom. Bioinform..

[21]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[22]  J. Friedman Greedy function approximation: A gradient boosting machine. , 2001 .

[23]  C. Aliferis,et al.  Machine learning methods to predict child posttraumatic stress: a proof of concept study , 2017, BMC Psychiatry.

[24]  Leonardo Vanneschi,et al.  Multilayer Perceptrons , 2019, Encyclopedia of Bioinformatics and Computational Biology.

[25]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[26]  Gang Wang,et al.  The Kernel Path in Kernelized LASSO , 2007, AISTATS.

[27]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[28]  J. Hirsch,et al.  Reduced Anterior Temporal and Hippocampal Functional Connectivity During Face Processing Discriminates Individuals with Social Anxiety Disorder from Healthy Controls and Panic Disorder, and Increases Following Treatment , 2014, Neuropsychopharmacology.

[29]  R. Goodman Online child and adolescent mental health surveys can be good enough , 2013, Social Psychiatry and Psychiatric Epidemiology.

[30]  L. Yao,et al.  Diagnostic Prediction for Social Anxiety Disorder via Multivariate Pattern Analysis of the Regional Homogeneity , 2015, BioMed research international.

[31]  A. Field,et al.  A Meta-Analysis of Transdiagnostic Cognitive Behavioural Therapy in the Treatment of Child and Young Person Anxiety Disorders , 2013, Behavioural and Cognitive Psychotherapy.

[32]  A. Muhammad,et al.  Classification of Anxiety Disorders using Machine Learning Methods: A Literature Review , 2020 .

[33]  D. Feaster,et al.  Parent and Child Agreement on Anxiety Disorder Symptoms Using the DISC Predictive Scales , 2011, Assessment.

[34]  B. Penninx,et al.  A Randomized Controlled Trial of a Tailored Primary Care Program to Reverse Excessive Alcohol Consumption , 2012, The Journal of the American Board of Family Medicine.

[35]  Mats Fredrikson,et al.  Classifying social anxiety disorder using multivoxel pattern analyses of brain function and structure , 2014, Behavioural Brain Research.

[36]  Olivier Ledoit,et al.  Honey, I Shrunk the Sample Covariance Matrix , 2003 .

[37]  S. Lilienfeld,et al.  The Association between Anxiety and Psychopathy Dimensions in Children , 1999, Journal of abnormal child psychology.

[38]  Lawrence Carin,et al.  Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks , 2015, AAAI.

[39]  Ulrike Lueken,et al.  Separating generalized anxiety disorder from major depression using clinical, hormonal, and structural MRI data: A multimodal machine learning study , 2017, Brain and behavior.

[40]  P. Jensen,et al.  Scales, diagnoses, and child psychopathology: II. Comparing the CBCL and the DISC against external validators , 1996, Journal of abnormal child psychology.

[41]  R. Rapee,et al.  Anxiety disorders during childhood and adolescence: origins and treatment. , 2009, Annual review of clinical psychology.

[42]  C. Hartman,et al.  An Internet version of the Diagnostic Interview Schedule for Children (DISC-IV): correspondence of the ADHD section with the paper-and-pencil version. , 2009, Psychological assessment.

[43]  P. Alam ‘T’ , 2021, Composites Engineering: An A–Z Guide.

[44]  P. Fisher,et al.  The voice DISC-IV with incarcerated male youths: prevalence of disorder. , 2002, Journal of the American Academy of Child and Adolescent Psychiatry.

[45]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[46]  A. Statnikov,et al.  Bridging a translational gap: using machine learning to improve the prediction of PTSD , 2015, BMC Psychiatry.

[47]  H. Meltzer,et al.  The Development and Well-Being Assessment: description and initial validation of an integrated assessment of child and adolescent psychopathology. , 2000, Journal of child psychology and psychiatry, and allied disciplines.

[48]  A. James,et al.  Cognitive behavioural therapy for anxiety disorders in children and adolescents. , 2013, The Cochrane database of systematic reviews.

[49]  Ekin Ekinci,et al.  An alternative evaluation of post traumatic stress disorder with machine learning methods , 2015, 2015 International Symposium on Innovations in Intelligent SysTems and Applications (INISTA).

[50]  B. Chorpita,et al.  Evidence Base Update: 50 Years of Research on Treatment for Child and Adolescent Anxiety , 2016, Journal of clinical child and adolescent psychology : the official journal for the Society of Clinical Child and Adolescent Psychology, American Psychological Association, Division 53.

[51]  Harry Zhang,et al.  The Optimality of Naive Bayes , 2004, FLAIRS.

[52]  Louis-Philippe Morency,et al.  Context-based signal descriptors of heart-rate variability for anxiety assessment , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[53]  Zoubin Ghahramani,et al.  Deep Bayesian Active Learning with Image Data , 2017, ICML.

[54]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[55]  P. West,et al.  Voice-DISC identified DSM-IV disorders among 15-year-olds in the west of Scotland. , 2003, Journal of the American Academy of Child and Adolescent Psychiatry.

[56]  Jiawei Han,et al.  Generalized Fisher Score for Feature Selection , 2011, UAI.

[57]  N. Ryan,et al.  Schedule for Affective Disorders and Schizophrenia for School-Age Children-Present and Lifetime Version (K-SADS-PL): initial reliability and validity data. , 1997, Journal of the American Academy of Child and Adolescent Psychiatry.

[58]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[59]  G. Wasserman,et al.  Contribution of parent report to voice DISC-IV diagnosis among incarcerated youths. , 2004, Journal of the American Academy of Child and Adolescent Psychiatry.

[60]  H. Robbins A Stochastic Approximation Method , 1951 .