Objective:To investigate the predictive value of multimodal magnetic resonance imaging (MRI) techniques in assessing symptom remission of post-traumatic stress disorder (PTSD) of bereaved parents who lost their only child.Methods:In this prospective study, 34 parents with PTSD resulting from the loss of the only child were followed-up for 2 years. Based on the PTSD diagnostic status at the end of the follow-up, participants were divided into the remission group and the persistent group.R 3.6.1 and SPSS 20.0 software were used for statistical analysis.Baseline clinical data and neuroimaging findings were compared between the two groups. Logistic regression and LASSO regression analyses were used to identify independent predictors of PTSD symptom remission. The predictive performance of these factors was evaluated by receiver operating characteristic (ROC) curve analysis.Results:Initial screening with univariate Logistic regression and LASSO regression revealed that regional homogeneity (ReHo) in the left middle temporal gyrus, the combined predictive value based on ReHo, and the integrated predictive value combining gray matter volume (GMV) and ReHo (GMV-ReHo predictor) were significant factors influencing symptom remission (all P<0.05). Multivariate Logistic regression further demonstrated that the GMV-ReHo predictor retained independent predictive significance ( P<0.05), with ROC curve analysis showing an area under the curve (AUC) of 0.979 (95% CI=0.935-0.996, P<0.001) for its ability to predict PTSD remission. Notably, a combined model incorporating both the scores of the clinician administered PTSD scale (CAPS) and the GMV-ReHo predictor achieved an enhanced predictive performance, yielding an AUC of 0.984 (95% CI=0.952-0.998, P<0.001). Conclusion:The GMV-ReHo predictor effectively identifies symptom remission in PTSD resulting from the loss of the only child.

Objective:To investigate the predictive value of multimodal magnetic resonance imaging (MRI) techniques in assessing symptom remission of post-traumatic stress disorder (PTSD) of bereaved parents who lost their only child.Methods:In this prospective study, 34 parents with PTSD resulting from the loss of the only child were followed-up for 2 years. Based on the PTSD diagnostic status at the end of the follow-up, participants were divided into the remission group and the persistent group.R 3.6.1 and SPSS 20.0 software were used for statistical analysis.Baseline clinical data and neuroimaging findings were compared between the two groups. Logistic regression and LASSO regression analyses were used to identify independent predictors of PTSD symptom remission. The predictive performance of these factors was evaluated by receiver operating characteristic (ROC) curve analysis.Results:Initial screening with univariate Logistic regression and LASSO regression revealed that regional homogeneity (ReHo) in the left middle temporal gyrus, the combined predictive value based on ReHo, and the integrated predictive value combining gray matter volume (GMV) and ReHo (GMV-ReHo predictor) were significant factors influencing symptom remission (all P<0.05). Multivariate Logistic regression further demonstrated that the GMV-ReHo predictor retained independent predictive significance ( P<0.05), with ROC curve analysis showing an area under the curve (AUC) of 0.979 (95% CI=0.935-0.996, P<0.001) for its ability to predict PTSD remission. Notably, a combined model incorporating both the scores of the clinician administered PTSD scale (CAPS) and the GMV-ReHo predictor achieved an enhanced predictive performance, yielding an AUC of 0.984 (95% CI=0.952-0.998, P<0.001). Conclusion:The GMV-ReHo predictor effectively identifies symptom remission in PTSD resulting from the loss of the only child.

Advances in biological and medical technologies have been providing us explosive volumes of biological and physiological data, such as medical images, electroencephalography, genomic and protein sequences. Learning from these data facilitates the understanding of human health and disease. Developed from artificial neural networks, deep learning-based algorithms show great promise in extracting features and learning patterns from complex data. The aim of this paper is to provide an overview of deep learning techniques and some of the state-of-the-art applications in the biomedical field. We first introduce the development of artificial neural network and deep learning. We then describe two main components of deep learning, i.e., deep learning architectures and model optimization. Subsequently, some examples are demonstrated for deep learning applications, including medical image classification, genomic sequence analysis, as well as protein structure classification and prediction. Finally, we offer our perspectives for the future directions in the field of deep learning.
Algorithms ; Computational Biology ; methods ; Diagnostic Imaging ; Genomics ; methods ; Humans ; Image Interpretation, Computer-Assisted ; methods ; Machine Learning ; Neural Networks (Computer) ; Protein Structure, Secondary ; Proteins ; metabolism