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.

Response to methylphenidate by adult and pediatric patients with attention-deficit/hyperactivity disorder: the Spanish multicenter DIHANA study.

BACKGROUND The purpose of this multicenter Spanish study was to evaluate the response to immediate-release methylphenidate by children and adults diagnosed with attention-deficit/hyperactivity disorder (ADHD), as well as to obtain information on current therapy patterns and safety characteristics. METHODS This multicenter, observational, retrospective, noninterventional study included 730 patients aged 4-65 years with a diagnosis of ADHD. Information was obtained based on a review of medical records for the years 2002-2006 in sequential order. RESULTS The ADHD predominantly inattentive subtype affected 29.7% of patients, ADHD predominantly hyperactive-impulsive was found in 5.2%, and the combined subtype in 65.1%. Overall, a significant lower Clinical Global Impression (CGI) score and mean number of DSM-IV TR (Diagnostic and Statistical Manual of Mental Disorders Fourth Edition, Text Revision) symptoms by subtype were found after one year of treatment with immediate-release methylphenidate; CGI decreased from 4.51 to 1.69, symptoms of inattention from 7.90 to 4.34, symptoms of hyperactivity from 6.73 to 3.39, and combined subtype symptoms from 14.62 to 7.7. Satisfaction with immediate-release methylphenidate after one year was evaluated as "very satisfied" or "satisfied" by 86.90% of the sample; 25.75% of all patients reported at least one adverse effect. At the end of the study, 41.47% of all the patients treated with immediate-release methylphenidate were still receiving it, with a mean time of 3.80 years on therapy. CONCLUSION Good efficacy and safety results were found for immediate-release methylphenidate in patients with ADHD.