Prediction of Postpartum Depression Using Multilayer Perceptrons and Pruning

OBJECTIVE The main goal of this paper is to obtain a classification model based on feed-forward multilayer perceptrons in order to improve postpartum depression prediction during the 32 weeks after childbirth with a high sensitivity and specificity and to develop a tool to be integrated in a decision support system for clinicians. MATERIALS AND METHODS Multilayer perceptrons were trained on data from 1397 women who had just given birth, from seven Spanish general hospitals, including clinical, environmental and genetic variables. A prospective cohort study was made just after delivery, at 8 weeks and at 32 weeks after delivery. The models were evaluated with the geometric mean of accuracies using a hold-out strategy. RESULTS Multilayer perceptrons showed good performance (high sensitivity and specificity) as predictive models for postpartum depression. CONCLUSIONS The use of these models in a decision support system can be clinically evaluated in future work. The analysis of the models by pruning leads to a qualitative interpretation of the influence of each variable in the interest of clinical protocols.

[1]  M. Gratacós,et al.  Mood changes after delivery: role of the serotonin transporter gene , 2008, British Journal of Psychiatry.

[2]  Ayse Canan Yazici,et al.  Comparison of logistic regression model and classification tree: An application to postpartum depression data , 2007, Expert Syst. Appl..

[3]  M. Gili,et al.  Diagnostic Interview for Genetic Studies (DIGS): Inter-rater and test-retest reliability and validity in a Spanish population , 2007, European Psychiatry.

[4]  Donald C. Wunsch,et al.  Neural network explanation using inversion , 2007, Neural Networks.

[5]  K Akazawa,et al.  Accuracy in the Diagnostic Prediction of Acute Appendicitis Based on the Bayesian Network Model , 2007, Methods of Information in Medicine.

[6]  David Goldman,et al.  Association of a triallelic serotonin transporter gene promoter region (5-HTTLPR) polymorphism with stressful life events and severity of depression. , 2006, The American journal of psychiatry.

[7]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[8]  Paulo J. G. Lisboa,et al.  The Use of Artificial Neural Networks in Decision Support in Cancer: a Systematic Review , 2005 .

[9]  Reeti Tandon,et al.  Neural networks for longitudinal studies in Alzheimer's disease , 2006, Artif. Intell. Medicine.

[10]  C. Dennis.  Psychosocial and psychological interventions for prevention of postnatal depression: systematic review , 2005, BMJ : British Medical Journal.

[11]  E. Balas,et al.  Improving clinical practice using clinical decision support systems: a systematic review of trials to identify features critical to success , 2005, BMJ : British Medical Journal.

[12]  Juan Miguel García-Gómez,et al.  SOC: A Distributed Decision Support Architecture for Clinical Diagnosis , 2004, ISBMDA.

[13]  Margot Albus,et al.  Serotonin transporter promoter and intron 2 polymorphisms: relationship between allelic variants and gene expression , 2004, Biological Psychiatry.

[14]  M. Romach,et al.  Mood changes during pregnancy and the postpartum period: development of a biopsychosocial model , 2004, Acta psychiatrica Scandinavica.

[15]  K. Kendler,et al.  The interrelationship of neuroticism, sex, and stressful life events in the prediction of episodes of major depression. , 2004, The American journal of psychiatry.

[16]  C. Klier,et al.  Postnatal depression across countries and cultures: a qualitative study , 2004, British Journal of Psychiatry.

[17]  Paul S. Heckerling,et al.  Entering the Black Box of Neural Networks , 2003, Methods of Information in Medicine.

[18]  A. Caspi,et al.  Influence of Life Stress on Depression: Moderation by a Polymorphism in the 5-HTT Gene , 2003, Science.

[19]  L. F. García,et al.  A psychometric analysis of the revised Eysenck Personality Questionnaire short scale , 2003 .

[20]  C. Ascaso,et al.  Validation of the Edinburgh Postnatal Depression Scale (EPDS) in Spanish mothers. , 2003, Journal of affective disorders.

[21]  D. Rubinow,et al.  Endocrine factors in the etiology of postpartum depression. , 2003, Comprehensive psychiatry.

[22]  M Fieschi,et al.  Medical Decision Support Systems: Old Dilemmas and new Paradigms? , 2003, Methods of Information in Medicine.

[23]  A. Caspi,et al.  Influence of Life Stress on Depression: Moderation by a Polymorphism in the 5-HTT Gene , 2003, Science.

[24]  Nathalie Japkowicz,et al.  The class imbalance problem: A systematic study , 2002, Intell. Data Anal..

[25]  Antanas Verikas,et al.  Feature selection with neural networks , 2002, Pattern Recognit. Lett..

[26]  Enrico Smeraldi,et al.  A neural network approach to the outcome definition on first treatment with sertraline in a psychiatric population , 2001, Artif. Intell. Medicine.

[27]  C T Beck,et al.  Predictors of Postpartum Depression: An Update , 2001, Nursing research.

[28]  N. Martin,et al.  Genetic influences on post-natal depressive symptoms: findings from an Australian twin sample , 1999, Psychological Medicine.

[29]  M F Jefferson,et al.  Evolution of Artificial Neural Network Architecture: Prediction of Depression after Mania , 1998, Methods of Information in Medicine.

[30]  S Berdia,et al.  An artificial neural network stimulating performance of normal subjects and schizophrenics on the Wisconsin card sorting test , 1998, Artif. Intell. Medicine.

[31]  P. Cooper,et al.  Prediction, detection, and treatment of postnatal depression , 1997, Archives of disease in childhood.

[32]  Stan Matwin,et al.  Addressing the Curse of Imbalanced Training Sets: One-Sided Selection , 1997, ICML.

[33]  J. D. L. D. Castillo,et al.  Validez y fiabilidad del cuestionario de apoyo social funcional Duke-UNC-11 , 1996 .

[34]  K. Kendler.  Major Depression and Generalised Anxiety Disorder , 1996, British Journal of Psychiatry.

[35]  M. O’Hara,et al.  Rates and risk of postpartum depression—a meta-analysis , 1996 .

[36]  J. L. D. Luna del Castillo,et al.  [Validity and reliability of the Duke-UNC-11 questionnaire of functional social support]. , 1996, Atencion primaria.

[37]  Anil K. Jain,et al.  Artificial neural networks for feature extraction and multivariate data projection , 1995, IEEE Trans. Neural Networks.

[38]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[39]  J. Nurnberger,et al.  Diagnostic interview for genetic studies. Rationale, unique features, and training. NIMH Genetics Initiative. , 1994, Archives of general psychiatry.

[40]  Gregory J. Wolff,et al.  Optimal Brain Surgeon and general network pruning , 1993, IEEE International Conference on Neural Networks.

[41]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

[42]  Yann LeCun,et al.  Optimal Brain Damage , 1989, NIPS.

[43]  Emile Servan-Schreiber,et al.  A Connectionist Approach to the Diagnosis of Dementia , 1988 .

[44]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[45]  E. Paykel.  Methodological aspects of life events research. , 1983, Journal of psychosomatic research.

[46]  David G. Stork,et al.  Pattern Classification , 1973 .

[47]  Hans J. Eysenck,et al.  The Eysenck Personality Inventory , 1965 .

[48]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.