This thesis by Panpan Hu explores the application of Artificial Neural Networks (ANNs) in identifying psychological patterns, particularly in the context of sociobehavioral functioning. The study focuses on six specific psychological cases: independent living skill deficits, disorder management deficits, occupational skill deficits, social skill deficits, dysregulation of anger/aggression, and substance abuse. Two models are developed: one based on the backpropagation algorithm and another based on the posteriori probability approach. These models are tested using data from 118 patients in a Community Transition Program (CTP). The models were evaluated using the DESIRE software and compared with results from the MATLAB Neural Network toolbox. The ANN models achieved varying degrees of accuracy, with the dysregulation of anger/aggression, substance abuse, and social skill deficits models correctly identifying 61.0%, 56.8%, and 56.1% of test cases, respectively. The combined network for dysregulation of anger/aggression and social skill deficits achieved 42.1% accuracy, while the combined network for dysregulation of anger/aggression and substance abuse achieved 36.0% accuracy. The thesis also discusses the limitations of the study, noting that more data is needed to confirm the increased predictability of the ANN approach. The results suggest that ANNs can be a valuable method for mining data in clinical assessment, particularly in identifying psychological patterns with high accuracy.This thesis by Panpan Hu explores the application of Artificial Neural Networks (ANNs) in identifying psychological patterns, particularly in the context of sociobehavioral functioning. The study focuses on six specific psychological cases: independent living skill deficits, disorder management deficits, occupational skill deficits, social skill deficits, dysregulation of anger/aggression, and substance abuse. Two models are developed: one based on the backpropagation algorithm and another based on the posteriori probability approach. These models are tested using data from 118 patients in a Community Transition Program (CTP). The models were evaluated using the DESIRE software and compared with results from the MATLAB Neural Network toolbox. The ANN models achieved varying degrees of accuracy, with the dysregulation of anger/aggression, substance abuse, and social skill deficits models correctly identifying 61.0%, 56.8%, and 56.1% of test cases, respectively. The combined network for dysregulation of anger/aggression and social skill deficits achieved 42.1% accuracy, while the combined network for dysregulation of anger/aggression and substance abuse achieved 36.0% accuracy. The thesis also discusses the limitations of the study, noting that more data is needed to confirm the increased predictability of the ANN approach. The results suggest that ANNs can be a valuable method for mining data in clinical assessment, particularly in identifying psychological patterns with high accuracy.