An artificial intelligence tool to assess the risk of severe mental distress among college students in terms of demographics, eating habits, lifestyles, and sport habits: an externally validated study using machine learning.

BACKGROUND: Precisely estimating the probability of mental health challenges among college students is pivotal for facilitating timely intervention and preventative measures. However, to date, no specific artificial intelligence (AI) models have been reported to effectively forecast severe mental distress. This study aimed to develop and validate an advanced AI tool for predicting the likelihood of severe mental distress in college students. METHODS: A total of 2088 college students from five universities were enrolled in this study. Participants were randomly divided into a training group (80%) and a validation group (20%). Various machine learning models, including logistic regression (LR), extreme gradient boosting machine (eXGBM), decision tree (DT), k-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM), were employed and trained in this study. Model performance was evaluated using 11 metrics, and the highest scoring model was selected. In addition, external validation was conducted on 751 participants from three universities. The AI tool was then deployed as a web-based AI application. RESULTS: Among the models developed, the eXGBM model achieved the highest area under the curve (AUC) value of 0.932 (95% CI: 0.911-0.949), closely followed by RF with an AUC of 0.927 (95% CI: 0.905-0.943). The eXGBM model demonstrated superior performance in accuracy (0.850), precision (0.824), recall (0.890), specificity (0.810), F1 score (0.856), Brier score (0.103), log loss (0.326), and discrimination slope (0.598). The eXGBM model also received the highest score of 60 based on the evaluation scoring system, while RF achieved a score of 49. The scores of LR, DT, and SVM were only 19, 32, and 36, respectively. External validation yielded an impressive AUC value of 0.918. CONCLUSIONS: The AI tool demonstrates promising predictive performance for identifying college students at risk of severe mental distress. It has the potential to guide intervention strategies and support early identification and preventive measures.

An Artificial Intelligence Platform to Stratify the Risk of Experiencing Sleep Disturbance in University Students After Analyzing Psychological Health, Lifestyle, and Sports: A Multicenter Externally Validated Study.

Background: Sleep problems are prevalent among university students, yet there is a lack of effective models to assess the risk of sleep disturbance. Artificial intelligence (AI) provides an opportunity to develop a platform for evaluating the risk. This study aims to develop and validate an AI platform to stratify the risk of experiencing sleep disturbance for university students. Methods: A total of 2243 university students were included, with 1882 students from five universities comprising the model derivation group and 361 students from two additional universities forming the external validation group. Six machine learning techniques, including extreme gradient boosting machine (eXGBM), decision tree (DT), k-nearest neighbor (KNN), random forest (RF), neural network (NN), and support vector machine (SVM), were employed to train models using the same set of features. The models' prediction performance was assessed based on discrimination and calibration, and feature importance was determined using Shapley Additive exPlanations (SHAP) analysis. Results: The prevalence of sleep disturbance was 44.69% in the model derivation group and 49.58% in the external validation group. Among the developed models, eXGBM exhibited superior performance, surpassing other models in metrics such as area under the curve (0.779, 95% CI: 0.728-0.830), accuracy (0.710), precision (0.737), F1 score (0.692), Brier score (0.193), and log loss (0.569). Calibration and decision curve analyses demonstrated favorable calibration ability and clinical net benefits, respectively. SHAP analysis identified five key features: stress score, severity of depression, vegetable consumption, age, and sedentary time. The AI platform was made available online at https://sleepdisturbancestudents-xakgzwectsw85cagdgkax9.streamlit.app/, enabling users to calculate individualized risk of sleep disturbance. Conclusion: Sleep disturbance is prevalent among university students. This study presents an AI model capable of identifying students at high risk for sleep disturbance. The AI platform offers a valuable resource to guide interventions and improve sleep outcomes for university students.

Performance Study of Portable Semiconductor Refrigeration Device Based on CFD Simulation.

Since the summer of 2022, the whole world has suffered the abnormal weather phenomena of high ambient temperature. Equipment for refrigeration, particularly portable refrigeration equipment, is crucial for personal protection in high-temperature environments, but cooling performance and miniaturization have been challenging issues. A portable air conditioner based on a semiconductor refrigeration device for human body cooling was developed. The total weight of the device is 450 g. The overall power consumption of the device is 82 W and the energy consumption ratio of semiconductor cooling plate is 0.85. The semiconductor refrigeration technology is based on the Peltier effect, supplemented by a DC fan to send the cooling air out to a specified position or zone. The structural parts are manufactured by 3D printing technology to make the overall size of the device more compact. The air volume and cooling performance of the device were analyzed by computational fluid dynamics simulation and the temperature distribution was measured by an infrared thermal imager and other instruments, and the measured results agreed with the CFD simulation results. The test ambient temperature was 20 °C. The measurement results showed that the wind speed of the hot air outlet was 6.92 m/s and that of the cold air outlet was 8.24 m/s. The cold air surface temperature reached a stable state of 13.9 °C in about 4 min, while the hot air surface temperature reached a stable state of 47.2 °C.

Algorithms to Predict Anxiety and Depression Among University Students in China After Analyzing Lifestyles and Sport Habits.

PURPOSE: This study aims to identify potential risk factors associated with anxiety or depression and propose algorithms to predict anxiety and depression especially among university students. METHODS: We included and analyzed 881 university students from eight colleges in China in November 2020. Student's basic information, lifestyles, sport habits, comorbidities, and mental health conditions were collected. Anxiety and depression were measured using the generalized anxiety disorder 7 (GAD-7) and the patient health questionnaire 9 (PHQ-9), respectively. A multiple linear regression analysis was used to assess the ability of 25 potential risk factors for predicting anxiety and depression, and significant risk factors were included in the algorithms. RESULTS: Of all the included students, 44.27% lived with mild or above anxious symptoms and 50.62% had mild or above depressive symptoms. According to the multiple linear regression model, grade levels (P<0.01), member of college sports dance team (P=0.05), sedentary time (P=0.02), exercise frequency (P<0.01), only child status (P=0.05), addiction of drinking (P<0.01), and prefer eating vegetable (P<0.01) were significantly associated with anxiety; grade levels (P<0.01), member of college sports dance team (P<0.01), sedentary time (P<0.01), exercise frequency (P<0.01), academic study period during free time (P=0.03), only child status (P<0.01), addiction of drinking (P<0.01), prefer eating vegetables (P<0.01), and main types of drinking water (P<0.01) were significantly associated with depression. Based on these significant factors, two algorithms were successfully developed, and two risk groups were created according to the algorithms. CONCLUSION: The study proposed two algorithms to calculate anxiety and depression, respectively, which can be useful tools to identify students with different risk of anxiety or depression. Effective measures are warranted to improve student's sport habits and healthy lifestyles in order to mitigate anxiety and depression, especially among students in the high risk group.

Frequent Sports Dance May Serve as a Protective Factor for Depression Among College Students: A Real-World Data Analysis in China.

PURPOSE: This study aims to investigate the role of frequent sports dance in preventing mental disorders, including anxiety and depression, among college students using real-world data, and to further analyze potential risk factors associated with anxiety and depression. METHODS: We investigated 921 college students from eight universities in China. A survey was completed by 901 students and they were included in the analysis. The anxiety score was evaluated by the Generalized Anxiety Disorder 7-item (GAD-7) scale and the depression score was evaluated by the Patient Health Questionnaire-9 (PHQ-9). Subgroup comparisons were performed among frequent sports dance students and non-frequent sports dance students. RESULTS: Of all the students, 9.98% had moderate-to-severe anxiety and 14.65% students suffered from moderate-to-severe depression. Compared with non-frequent sports dance students, frequent sports dance students had significantly lower depression scores (P=0.04). According to the multiple logistic regression models, when potential confounding factors were all adjusted, frequent sports dance was also significantly associated with less depression (OR=0.55, 95% CI: 0.36-0.84, P<0.01). We also found that higher college grade levels (P<0.01), non-physical education students (P=0.02), higher body mass index (P=0.02), lower exercise frequency per week (P<0.01), addiction to drinking (P=0.02), and previous diagnosis of anxiety or depression in hospital (P<0.01) were significantly associated with more anxiety; higher college grade levels (P<0.01), addiction to drinking (P<0.01), preference for eating fried food (P=0.02), soda as the main source of drinking water (P=0.01), and previous diagnosis of anxiety or depression (P=0.03) were significantly associated with more depression, while higher exercise frequency per week (P<0.01), only-child status (P<0.01), and preference for eating vegetables (P=0.02) were significantly associated with less depression. CONCLUSION: Anxiety and depression are common among college students. Frequent sports dance may serve as a protective factor for preventing depression and it can be recommended for college students.