This thesis explores the use of artificial neural networks (ANNs) to identify psychological patterns in patients from the Nebraska Community Transition Program (CTP). The study focuses on six psychological cases related to sociobehavioral functioning: independent living skill deficits, disorder management deficits, occupational skill deficits, social skill deficits, dysregulation of anger/aggression, and substance abuse. Two models were developed: one based on a backpropagation algorithm and another based on a posteriori probability approach. The models were tested using data from 118 patients in the CTP. For each case, a portion of the data was used for training, and the remaining data was used for testing. The models were evaluated using the DESIRE software and compared with results from the MATLAB Neural Network Toolbox. The backpropagation model achieved 61.0%, 56.8%, and 56.1% accuracy for the dysregulation of anger/aggression, substance abuse, and social skill deficits models, respectively. The posteriori probability model achieved 42.1% accuracy for the dysregulation of anger/aggression and social skill deficits combined. The results showed that ANNs can be a valuable method for mining data for clinical assessment. However, more data is needed to confirm their increased predictability. The study also evaluated the performance of ANN models for two problem cases, including social skill deficits and dysregulation of anger/aggression, and substance abuse and dysregulation of anger/aggression. The results demonstrated that ANNs can effectively identify psychological patterns with high accuracy. The study concludes that ANNs have potential for use in clinical assessment and decision support systems.This thesis explores the use of artificial neural networks (ANNs) to identify psychological patterns in patients from the Nebraska Community Transition Program (CTP). The study focuses on six psychological cases related to sociobehavioral functioning: independent living skill deficits, disorder management deficits, occupational skill deficits, social skill deficits, dysregulation of anger/aggression, and substance abuse. Two models were developed: one based on a backpropagation algorithm and another based on a posteriori probability approach. The models were tested using data from 118 patients in the CTP. For each case, a portion of the data was used for training, and the remaining data was used for testing. The models were evaluated using the DESIRE software and compared with results from the MATLAB Neural Network Toolbox. The backpropagation model achieved 61.0%, 56.8%, and 56.1% accuracy for the dysregulation of anger/aggression, substance abuse, and social skill deficits models, respectively. The posteriori probability model achieved 42.1% accuracy for the dysregulation of anger/aggression and social skill deficits combined. The results showed that ANNs can be a valuable method for mining data for clinical assessment. However, more data is needed to confirm their increased predictability. The study also evaluated the performance of ANN models for two problem cases, including social skill deficits and dysregulation of anger/aggression, and substance abuse and dysregulation of anger/aggression. The results demonstrated that ANNs can effectively identify psychological patterns with high accuracy. The study concludes that ANNs have potential for use in clinical assessment and decision support systems.