Background Virtual reality exposure therapy (VRET) is currently being used to treat social anxiety disorder (SAD); however, VRET's magnitude of efficacy, duration of efficacy, and impact on treatment discontinuation are still unclear. Methods We conducted a meta-analysis of studies that investigated the efficacy of VRET for SAD. The search strategy and analysis method are registered at PROSPERO (#CRD42019121097). Inclusion criteria were: (1) studies that targeted patients with SAD or related phobias; (2) studies where VRET was conducted for at least three sessions; (3) studies that included at least 10 participants. The primary outcome was social anxiety evaluation score change. Hedges' g and its 95% confidence intervals were calculated using random-effect models. The secondary outcome was the risk ratio for treatment discontinuation. Results Twenty-two studies (n = 703) met the inclusion criteria and were analyzed. The efficacy of VRET for SAD was significant and continued over a long-term follow-up period: Hedges' g for effect size at post-intervention, −0.86 (−1.04 to −0.68); three months post-intervention, −1.03 (−1.35 to −0.72); 6 months post-intervention, −1.14 (−1.39 to −0.89); and 12 months post-intervention, −0.74 (−1.05 to −0.43). When compared to in vivo exposure, the efficacy of VRET was similar at post-intervention but became inferior at later follow-up points. Participant dropout rates showed no significant difference compared to in vivo exposure. Conclusion VRET is an acceptable treatment for SAD patients that has significant, long-lasting efficacy, although it is possible that during long-term follow-up, VRET efficacy lessens as compared to in vivo exposure.

We aimed to develop a machine learning algorithm to screen for depression and assess severity based on data from wearable devices. Methods: We used a wearable device that calculates steps, energy expenditure, body movement, sleep time, heart rate, skin temperature, and ultraviolet light exposure. Depressed patients and healthy volunteers wore the device continuously for the study period. The modalities were compared hourly between patients and healthy volunteers. XGBoost was used to build machine learning models and 10-fold cross-validation was applied for the validation. Results: Forty-five depressed patients and 41 healthy controls participated, creating a combined 5,250 days' worth of data. Heart rate, steps, and sleep were significantly different between patients and healthy volunteers in some comparisons. Similar differences were also observed longitudinally when patients' symptoms improved. Based on seven days' data, the model identified symptomatic patients with 0.76 accuracy and predicted Hamilton Depression Rating Scale-17 scores with a 0.61 correlation coefficient. Skin temperature, sleep time-related features, and the correlation of those modalities were the most significant features in machine learning. Limitations: The small number of subjects who participated in this study may have weakened the statistical significance of the study. There are differences in the demographic data among groups although we performed a correction for multiple comparisons. Validation in independent datasets was not performed, although 10-fold cross validation with the internal data was conducted. Conclusion:The results indicated that utilizing wearable devices and machine learning may be useful in identifying depression as well as assessing severity.

No abstract

No abstract

In recent years, studies on the use of natural language processing (NLP) approaches to identify dementia have been reported. Most of these studies used picture description tasks or other similar tasks to encourage spontaneous speech, but the use of free conversation without requiring a task might be easier to perform in a clinical setting. Moreover, free conversation is unlikely to induce a learning effect. Therefore, the purpose of this study was to develop a machine learning model to discriminate subjects with and without dementia by extracting features from unstructured free conversation data using NLP. We recruited patients who visited a specialized outpatient clinic for dementia and healthy volunteers. Participants’ conversation was transcribed and the text data was decomposed from natural sentences into morphemes by performing a morphological analysis using NLP, and then converted into real-valued vectors that were used as features for machine learning. A total of 432 datasets were used, and the resulting machine learning model classified the data for dementia and non-dementia subjects with an accuracy of 0.900, sensitivity of 0.881, and a specificity of 0.916. Using sentence vector information, it was possible to develop a machine-learning algorithm capable of discriminating dementia from non-dementia subjects with a high accuracy based on free conversation.