A neural network approach to the outcome definition on first treatment with sertraline in a psychiatric population

Estimation of the Development of Depression and PTSD in Children Exposed to Sexual Abuse and Development of Decision Support Systems by Using Artificial Intelligence

The most common diagnoses after childhood sexual abuse are Post-Traumatic Stress Disorder and depression. The aim of this study is to design a decision support system to help psychiatry physicians in the treatment of childhood sexual abuse. Computer aided decision support system (CADSS) based on ANN, which predicts the development of PTSD and Major Depressive Disorder, using different parameters of the act of abuse and patients was designed. The data of 149 girls and 21 boys who were victims of sexual abuse were included in the study. In the designed CADDS, the gender of the victim, the type of sexual abuse, the age of exposure, the duration until reporting, the time of abuse, the proximity of the abuser to the victim, number of sexual abuse, whether the child is exposed to threats and violence during the abuse, the person who reported the event, and the intelligence level of the victim are used as input parameters. The average accuracy values for all three designed systems were calculated as 99.2%. It has been shown that the system designed by using these data can be used safely in the psychiatric assessment process, in order to differentiate psychiatric diagnoses in the early post-abuse period.

Artificial neural network prediction of clozapine response with combined pharmacogenetic and clinical data

Although one third to one half of refractory schizophrenic patients responds to clozapine, however, there are few evidences currently that could predict clozapine response before the use of the medication. The present study aimed to train and validate artificial neural networks (ANN), using clinical and pharmacogenetic data, to predict clozapine response in schizophrenic patients. Five pharmacogenetic variables and five clinical variables were collated from 93 schizophrenic patients taking clozapine, including 26 responders. ANN analysis was carried out by training the network with data from 75% of cases and subsequently testing with data from 25% of unseen cases to determine the optimal ANN architecture. Then the leave-one-out method was used to examine the generalization of the models. The optimal ANN architecture was found to be a standard feed-forward, fully-connected, back-propagation multilayer perceptron. The overall accuracy rate of ANN was 83.3%, which is higher than that of logistic regression (LR) (70.8%). By using the area under the receiver operating characteristics curve as a measure of performance, the ANN outperformed the LR (0.821+/-0.054 versus 0.579+/-0.068; p<0.001). The ANN with only genetic variables outperformed the ANN with only clinical variables (0.805+/-0.056 versus 0.647+/-0.066; p=0.046). The gene polymorphisms should play an important role in the prediction. Further validation of ANN analysis is likely to provide decision support for predicting individual response.

Clinical prediction of antidepressant response in mood disorders: linear multivariate vs. neural network models

Predicting the outcome of antidepressant treatment by pre-treatment features would be of great usefulness for clinicians as up to 50% of major depressives may not have a satisfactory response in spite of adequate trials of antidepressant drugs. In the present article we compared a linear multivariate model of predictors with a few artificial neural network (ANN) models differing from one another by outcome definition and validation procedure. The sample consisted of a reanalysis of 116 inpatients with a major depressive episode included in a 6-week open-label trial with fluvoxamine. With the original outcome definition (responders/non-responders), ANN performed better than logistic regression (90% of correct classifications in the training sample vs. 77%). However only 62% of new patients were correctly predicted by ANN for their outcome class. Length of the index episode, psychotic features and suicidal behavior emerged as outcome predictors in both models, while demographic characteristics, personality disorders and concomitant somatic morbidity were pointed to only by ANN analysis. Increase of classes in the outcome field resulted in a more elevated error: 46.4% for three classes, 60.4% for four classes and 70.3% for five classes. Overall, our findings suggest that antidepressant outcome prediction based on clinical variables is poor. The ANN approach is as valid as traditional multivariate techniques for the analysis of psychopharmacology studies. The complex interactions modelled through ANN may eventually be applied at the clinical level for individualized therapy. However, the accuracy of prediction is still far from satisfactory from a clinical point of view.

A neural network model for combining clinical predictors of antidepressant response in mood disorders

Artificial neural networks (ANN) represent a promising tool for combining multiple predictors in complex diseases. Antidepressant response in mood disorders is a typical complex phenomenon were a number of predictors influence outcome under non-linear interactions. In the present study we tested a neural network strategy for antidepressant outcome in subjects affected by major depression. One hundred and forty-five never reported depressed inpatients were included in this study (major depressives/bipolars: 111/34). A multi layer perceptron network composed of 1 hidden layer with 13 nodes was chosen. The network was performed on the sample of 145 cases divided as follows: train 73+verify 36+test 36. Correlation of predicted versus observed response was 0.46 in the test (independent) sample that corresponds to 21% of variance explained. Number of episodes, side effects, delusional features, baseline HAM-D, length of current episode, lithium augmentation, current medical condition and personality disorders were the main factors identified by the model. Sex, age at onset, polarity, plasma level and baseline VAS score were part of the model but with a lower rank. Overall, our findings suggest that neural networks could be a valid technique for the analysis of psychopharmacology studies. The complex interactions modelled through ANN may be eventually applied at the clinical level for the individualized therapy.

Supporting tools in psychiatric treatment decision-making: sertraline outcome investigation with artificial neural network method

Controlled trials in clinical psychopharmacology may fail to provide reliable information about the benefit of treatment for the patient when considered in a real-life setting rather than as a part of a well-defined sampling procedure. Previously, we applied the mathematical model of an artificial neural network (ANN) to a pool of clinical information gathered through case descriptions provided by senior psychiatrists in clinical charts of patients receiving their first exposure to sertraline. In the present study, we applied the same mathematical model to a larger sample. The performance of the ANN model in forecasting successful and unsuccessful treatment showed an overall accuracy of classification of 97.12%. This result supports our previous finding about the potential application of this method as a reliable predictor of a given psychiatric patient's outcome during a specific psychopharmacological therapy.

Clinicians' predictions of patient response to psychotropic medications

Clinicians prescribe a medication when they assume that there is a reasonable probability of its success. There are many studies on the predictive value of social or clinical information, but these studies do not include the prognosis made by psychiatrists before treatment. These studies indicate that a small to moderate proportion of the total variance of outcome can be predicted from social or clinical information. It is peculiar that there are very few studies on the accuracy of psychiatrists’ “bets” about the effects of psychotropic drugs when they use the clinical characteristics of patients as predictors, considering the practical relevance of predicting the outcome of a psychiatric treatment. The absence of studies on the accuracy of clinicians’ bets or predictions in psychiatry is unfortunate.

A preliminary evaluation of neural network analysis for pharmacodynamic modeling of the dosing of the hydroxymethylglutaryl coenzyme A-reductase inhibitors simvastatin and atorvastatin

BACKGROUND

Neural networks have been used in diagnosing and treating many diseases, including the diagnosis of myocardial infarction and insulin dosing in diabetes mellitus.

OBJECTIVE

The goal of this study was to develop a preliminary pharmacodynamic model for dosing of the hydroxymethylglutaryl coenzyme A (HMG-CoA)-reductase inhibitors simvastatin and atorvastatin using neural network analysis.

METHODS

Using NeuralSIM neural network software (NeuralWare, Carnegie, Pa), lipid panels from patients at a hospital lipid clinic were entered as inputs for the model, and the doses of simvastatin or atorvastatin that achieved those lipid results were used as outputs. The network was trained using 2 different data sets and was run using a subset of the data as inputs. The results of the neural network run (predictions) were compared with the actual doses used as directed by the hospital pharmacist in accordance with the lipid clinic protocol.

RESULTS

Complete data sets were available for 17 patients (11 men, 6 women). The mean age of these patients was 56.7 years (range, 40-67 years). The neural network model based on data set 1 predicted a dose that was within 95% of the actual dose 7 of 12 times and predicted use of the drug actually used 13 of 19 (68.4%) times. The neural network based on data set 2 predicted use of the drug actually used 10 of 17 (58.8%) times, but the predicted doses never approximated the actual doses by > or = 90%.

CONCLUSIONS

A neural network model for the dosing of the HMG-CoA-reductase inhibitors simvastatin and atorvastatin demonstrated an ability to predict appropriate dosing, but inclusion of other factors (eg, age, body weight, sex) and a larger sample size may be necessary for development of a more accurate model.