Jiaxiu Liu

Background: Obesity and related disorders are rising globally, especially in China, where they are linked to chronic diseases like diabetes and cardiovascular issues. As intermittent fasting (IF) gains popularity for weight management, the use of IF apps has increased, yet their quality varies significantly. A systematic evaluation of these apps is essential to assess their effectiveness and reliability. Objective: This study aimed to conduct a comprehensive evaluation of IF apps available in the Chinese mobile app market. We concentrated on evaluating their features, quality, and overall user experience to help users avoid low-quality options and direct app developers to enhance their offers. Methods: A systematic search was performed across 5 major app stores in China, including the Apple App Store, Huawei AppGallery, Oppo Software Store, Vivo App Store, and Xiaomi Market. “Fasting”, “Intermittent Fasting”, “Time-Restricted Feeding”, “Time-Restricted Fasting”, “Time-Restricted Eating” and “Meal Skipping” were used as keywords to identify relevant apps, which were then screened based on inclusion and exclusion criteria. The evaluation was conducted using the user version of the Mobile Application Rating Scale (uMARS). The uMARS assessment examined 4 key subscales: engagement, functionality, aesthetics, and information. Each app was independently evaluated by 2 raters who underwent uniform training to ensure consistency in scoring. Results: A total of 35 apps were assessed for the study. These apps mostly contain features such as fasting timer (100.0%), recording weight (97.14%), fasting reminder (85.71%), and recording water intake (85.71%). All of the apps have an obvious privacy protection. Most of the apps (79%) have tools for quantifying users’ health status. The results showed that the overall average uMARS score across the apps was 4.35 (SD 0.51). The subscale scores were as follows: engagement 4.42 (SD 0.47), functionality 4.65 (SD 0.31), aesthetics 4.19 (SD 0.64), and information 4.15 (SD 0.58). The functionality subscale had the highest mean score, while the aesthetic subscale showed the greatest range of scores, from 2.17 to 5.00. The overall uMARS score was significantly positively correlated with the subscale scores (r=0.786‐0.953, P<.001). The user ratings in the app stores did not significantly correlate with the uMARS overall scores (r=−0.290, P=.091). Strong inter-rater reliability was confirmed by intraclass correlation coefficients (ICC=0.809‐0.909 across subscales). Conclusions: All the apps reveal high overall quality but gaps in professional engagement and social features. Limited clinical input may undermine the evidence-based accuracy and long-term applicability of some apps. Developers are encouraged to collaborate with health care professionals to enhance content reliability and incorporate social features to boost user engagement, while ensuring robust privacy protections and reasonable use of artificial intelligence.

BACKGROUND Due to unique psychosocial stressors, men who have sex with men (MSM) are at a substantially higher risk of developing depressive symptoms compared with the general population. However, commonly used depression screening tools are primarily designed for the general population and fail to adequately account for MSM-specific stressors, limiting accurate risk identification in this group. In the Chinese context, the mental health of MSM is often underestimated, and there is a lack of precise assessment tools that integrate multidimensional psychosocial variables. This study aims to develop an interpretable machine learning framework to identify key risk factors for depression and enable risk stratification, thereby detecting MSM individuals at high risk for depressive symptoms and supporting timely early intervention. OBJECTIVE This study aimed to develop machine learning models and tools to identify MSM at high risk of depression and to assess their depression risk. METHODS Between November and December 2022, this study recruited 1,369 MSM using a non-probability sampling approach. Based on the Minority Stress Model, candidate risk factors were collected, encompassing sociodemographic characteristics, MSM-related stigma, psychological resilience, social support, and MSM sexual identity, with depressive symptoms as the primary outcome. 3 feature selection methods combined with ten machine learning algorithms were employed to construct predictive models, and model performance was evaluated to identify the optimal model. SHAP analysis was then applied to interpret the contributions of individual risk factors. To enhance clinical applicability, the risk probabilities of the optimal model were defined as risk scores (RS), which were subsequently used for risk stratification. RESULTS Following feature selection, 8 potential risk factors significantly associated with depressive symptoms were identified, which were then used to construct a depression risk identification model. Among all compared algorithms, the LightGBM model demonstrated the best performance, achieving an AUC of 0.945 and exhibiting superior overall performance across multiple evaluation metrics. Key risk factors included psychological resilience, identity superiority, experiences of stigma, and internalized homophobia. Risk stratification analysis revealed that individuals in the high-risk group had a significantly higher prevalence of depressive symptoms compared with those in the low-risk group (P < 0.001). Visualization tools were employed to intuitively illustrate the model’s classification threshold and its potential practical utility. CONCLUSIONS Machine learning models can effectively identify MSM individuals at high risk for depressive symptoms by integrating multidimensional features. Risk stratification based on model-derived probability scores facilitates early detection and targeted interventions, thereby supporting personalized mental health screening for this vulnerable population.

Background: Men who have sex with men (MSM) are at high risk for HIV infection and sexually transmitted diseases (STDs). However, there is a lack of accurate and convenient tools to assess this risk. Objective: This study aimed to develop machine learning models and tools to predict and assess the risk of HIV infection and STDs among MSM. Methods: We conducted a cross-sectional study that collected individual characteristics of 1999 MSM with negative or unknown HIV serostatus in Western China from 2013 to 2023. MSM self-reported their STD history and were tested for HIV. We compared the accuracy of 6 machine learning methods in predicting the risk of HIV infection and STDs using 7 parameters for a comprehensive assessment, ranking the methods according to their performance in each parameter. We selected data from the Sichuan MSM for external validation. Results: Of the 1999 MSM, 72 (3.6%) tested positive for HIV and 146 (7.3%) self-reported a history of previous STD infection. After taking the results of the intersection of the 3 feature screening methods, a total of 7 and 5 predictors were screened for predicting HIV infection and STDs, respectively, and multiple machine learning prediction models were constructed. Extreme gradient boost models performed optimally in predicting the risk of HIV infection and STDs, with area under the curve values of 0.777 (95% CI 0.639-0.915) and 0.637 (95% CI 0.541-0.732), respectively, demonstrating stable performance in both internal and external validation. The highest combined predictive performance scores of HIV and STD models were 33 and 39, respectively. Interpretability analysis showed that nonadherence to condom use, low HIV knowledge, multiple male partners, and internet dating were risk factors for HIV infection. Low degree of education, internet dating, and multiple male and female partners were risk factors for STDs. The risk stratification analysis showed that the optimal model effectively distinguished between high- and low-risk MSM. MSM were classified into HIV (predicted risk score <0.506 and ≥0.506) and STD (predicted risk score <0.479 and ≥0.479) risk groups. In total, 22.8% (114/500) were in the HIV high-risk group, and 43% (215/500) were in the STD high-risk group. HIV infection and STDs were significantly higher in the high-risk groups (P<.001 and P=.05, respectively), with higher predicted probabilities (P<.001 for both). The prediction results of the optimal model were displayed in web applications for probability estimation and interactive computation. Conclusions: Machine learning methods have demonstrated strengths in predicting the risk of HIV infection and STDs among MSM. Risk stratification models and web applications can facilitate clinicians in accurately assessing the risk of infection in individuals with high risk, especially MSM with concealed behaviors, and help them to self-monitor their risk for targeted, timely diagnosis and interventions to reduce new infections.

Background: Preexposure prophylaxis (PrEP) is an effective strategy to reduce the risk of HIV infection. However, the efficacy of PrEP is highly dependent on adherence. Meanwhile, adherence changes over time, making it difficult to manage effectively. Objective: Our study aimed to explore and predict the patterns of change in PrEP adherence among men who have sex with men (MSM) and evaluate the impact of the WeChat-based reminder intervention on adherence, thus providing more information for PrEP implementation strategies. Methods: From November 2019 to June 2023, in a randomized controlled longitudinal study of the PrEP demonstration project in Western China (Chongqing, Sichuan, and Xinjiang) based on a mobile health (mHealth) reminder intervention, participants were randomly divided into reminder and no-reminder groups, with those in the reminder group receiving daily reminders based on the WeChat app. Participants were followed up and self-reported their medication adherence every 12 weeks for a total of 5 follow-up visits. We used the growth mixture model (GMM) to explore potential categories and longitudinal trajectories of adherence among MSM, and patterns of change in PrEP adherence were predicted and evaluated based on the decision tree. Results: A total of 446 MSM were included in the analysis. The GMM identified 3 trajectories of adherence: intermediate adherence group (n=34, 7.62%), low adherence ascending group (n=126, 28.25%), and high adherence decline group (n=286, 64.13%). We included 8 variables that were significant in the univariate analysis in the decision tree prediction model. We found 4 factors and 8 prediction rules, and the results showed that HIV knowledge score, education attainment, mHealth intervention, and HIV testing were key nodes in the patterns of change in adherence. After 10-fold cross-validation, the final prediction model had an accuracy of 75%, and the classification accuracy of low and intermediate adherence was 78.12%. Conclusions: The WeChat-based reminder intervention was beneficial for adherence. A short set of questions and prediction rules, which can be applied in future large-scale validation studies, aimed at developing and validating a short adherence assessment tool and implementing it in PrEP practices among MSM.

BACKGROUND Men who have sex with men (MSM) are at high risk for HIV infection and sexually transmitted diseases (STDs). However, there is a lack of accurate and convenient tools to assess this risk. OBJECTIVE This study aimed to develop machine learning models and tools to predict and assess the risk of HIV infection and STDs among MSM. METHODS We conducted a cross-sectional study that collected individual characteristics of 1999 MSM with negative or unknown HIV serostatus in Western China from 2013 to 2023. MSM self-reported their STD history and were tested for HIV. We compared the accuracy of 6 machine learning methods in predicting the risk of HIV infection and STDs using 7 parameters for a comprehensive assessment, ranking the methods according to their performance in each parameter. We selected data from the Sichuan MSM for external validation. RESULTS Of the 1999 MSM, 72 (3.6%) tested positive for HIV and 146 (7.3%) self-reported a history of previous STD infection. After taking the results of the intersection of the 3 feature screening methods, a total of 7 and 5 predictors were screened for predicting HIV infection and STDs, respectively, and multiple machine learning prediction models were constructed. Extreme gradient boost models performed optimally in predicting the risk of HIV infection and STDs, with area under the curve values of 0.777 (95% CI 0.639-0.915) and 0.637 (95% CI 0.541-0.732), respectively, demonstrating stable performance in both internal and external validation. The highest combined predictive performance scores of HIV and STD models were 33 and 39, respectively. Interpretability analysis showed that nonadherence to condom use, low HIV knowledge, multiple male partners, and internet dating were risk factors for HIV infection. Low degree of education, internet dating, and multiple male and female partners were risk factors for STDs. The risk stratification analysis showed that the optimal model effectively distinguished between high- and low-risk MSM. MSM were classified into HIV (predicted risk score <0.506 and ≥0.506) and STD (predicted risk score <0.479 and ≥0.479) risk groups. In total, 22.8% (114/500) were in the HIV high-risk group, and 43% (215/500) were in the STD high-risk group. HIV infection and STDs were significantly higher in the high-risk groups (P<.001 and P=.05, respectively), with higher predicted probabilities (P<.001 for both). The prediction results of the optimal model were displayed in web applications for probability estimation and interactive computation. CONCLUSIONS Machine learning methods have demonstrated strengths in predicting the risk of HIV infection and STDs among MSM. Risk stratification models and web applications can facilitate clinicians in accurately assessing the risk of infection in individuals with high risk, especially MSM with concealed behaviors, and help them to self-monitor their risk for targeted, timely diagnosis and interventions to reduce new infections.

Background: Students are a priority population in mental health research. This study aimed to explore the risk factors of anxiety and depression symptoms among college students in Chongqing, a megacity under the impact of COVID-19, and to provide a basis for determining the priorities of public health policies and implementing effective educational health care interventions. Methods: In this cross-sectional study conducted in Chongqing, China, the data came from web-based stratified random sampling. Anxiety and depression symptoms were measured by the Self-Rating Anxiety Scale (SAS) and the Center for Epidemiological Studies Depression Scale (CES-D), respectively, and risk factors were analyzed by logistic regression. Results: Data were obtained from 915 college students (34.75% were male, and 65.25% were female) with age (20.29 ± 1.51) in Chongqing, China. The prevalence rates of anxiety and depression were 19.78% and 22.62%, respectively. Logistic regression analysis revealed that the risk factors of anxiety symptoms were associated with junior years, sleep time of less than 6 h a day, influence on career planning, and depression symptoms. Comprehensive, science and engineering, and medicine disciplines, having siblings, poorer mastery of study, and anxiety symptoms were risk factors for developing depression symptoms. Conclusions: During the pandemic, college students experienced varying degrees of anxiety and depression. Our research findings highlight the necessity of universities and relevant departments providing precise mental health education for college students under major public health emergencies.

(1) Background: Few studies have explored the heterogeneity of trajectories of stress, anxiety, and depressive symptoms during pregnancy. This study aimed to explore the trajectory groups of stress, anxiety, and depressive symptoms in women during pregnancy and the risk factors associated with those groups. (2) Methods: Data came from pregnant women recruited from January to September 2018 in four hospitals in Chongqing Province, China. A structured questionnaire was given to pregnant women, which collected basic information, including personal, family, and social information. The growth mixture model was applied to identify potential trajectory groups, and multinomial logistic regression was applied to analyze factors of trajectory groups. (3) Results: We identified three stress trajectory groups, three anxiety trajectory groups, and four depression trajectory groups. Less developed regions, inadequate family care, and inadequate social support were associated with a high risk of stress; residence, use of potentially teratogenic drugs, owning pets, family care, and social support were strongly associated with the anxiety trajectory group; family care and social support were the most critical factors for the depression trajectory group. (4) Conclusions: The trajectories of prenatal stress, anxiety, and depressive symptoms are dynamic and heterogeneous. This study may provide some critical insights into the characteristics of women in the high-risk trajectory groups for early intervention to mitigate worsening symptoms.

Background: The psychological status of men who have sex with men (MSM) as a vulnerable population during COVID-19 is worthy of attention. However, studies of Chinese MSM are limited. The aim of this study was to investigate the psychological status and influencing factors of MSM population and to provide a scientific basis for this group to actively respond to public health emergencies. Methods: From June to September 2020, we conducted an online survey. MSMs were recruited through collaboration with non-governmental organizations (NGOs) and peer recommendations. The variables we collected included four aspects: demographic and HIV-related characteristics; COVID-19-related knowledge, attitudes, and behaviors; COVID-19-related risk perception; epidemic exposure. The psychological status was assessed by the Psychological Questionnaire for Emergent Events of Public Health (PQEEPH), which defined the psychological status as five primary disorders: depression, neurasthenia, fear, anxiety, and hypochondria. Multivariate logistic regression was used to explore the influences of COVID-19-related factors on the psychological status. Results: We surveyed 412 MSM online during COVID-19. The five psychological status of high-risk states accounted for 16.99% (depression), 14.08% (neurasthenia), 16.75% (fear), 16.50% (anxiety), and 18.20% (hypochondria), respectively. Not being well-informed about the causes of COVID-19 (p = 0.020) and having experienced epidemic exposure (p = 0.006) were able to promote the occurrence of depression. Lack of knowledge of the curative effect of COVID-19 has a higher risk of occurrence neurasthenia (p < 0.001). Being afraid of the novel coronavirus (p < 0.001) promoted fear. The perceived prevalence of the epidemic (p = 0.003), being more susceptible to COVID-19 (p < 0.001), and not being well-informed about the causes of COVID-19 (p = 0.005) had a positive effect on anxiety. Considering that the epidemic was not effectively controlled (p = 0.017), being more susceptible to COVID-19 (p < 0.001) was a contributing factor to the hypochondria. Conclusions: The incidence of psychological disorders in Chinese MSM was higher than that in other groups during COVID-19. Factors associated with COVID-19 may cause a range of mental health problems in this population. Greater attention should be paid to the mental health status of special populations during the epidemic, and effective preventive education and intervention measures should be taken.

Background: It can be considered that pre-exposure prophylaxis (PrEP) risk perception is the negative experiences or concerns about taking PrEP. The aim of this study is to explore the longitudinal trajectory of PrEP risk perception among men who have sex with men (MSM) and its impact on adherence. Methods: Data related to PrEP risk perception and adherence were derived from a prospective cohort study in Western China from 2013 to 2015. Subjects were categorized into the time-driven, event-driven and blank control groups. Tenofovir disoproxil fumarate (TDF) was administered to subjects in the time-driven and event-driven groups, and all subjects were followed up every 12 weeks. The PrEP risk perception scale was constructed, and the growth mixture model (GMM) was used to classify longitudinal PrEP risk perception. The effect of different levels of PrEP risk perception on drug adherence was explored using generalized estimating equations (GEE) with relative risk (RR) and 95% confidence interval (CI). Results: The PrEP risk perception scale consists of 4 dimensions and 16 items with Cronbach's alpha = 0.828 and a good model fit. According to the GMM analysis, the subjects' PrEP risk perceptions were separated into two groups: a "high-risk perception group" (n = 133) and a "low-risk perception group" (n = 493), where the proportion of high levels of drug adherence were 57.89% and 68.35%, respectively (p = 0.024). High levels of PrEP risk perception in the MSM population hinder drug adherence (RR = 0.71, 95% CI 0.50 to 0.99, p = 0.046). The results of this study were validated in the subsequent PrEP projects conducted in 2019 to 2021. Conclusion: This study demonstrates that high levels of PrEP risk perception in the MSM population are an obstacle to drug adherence, emphasizing the necessity of focusing on PrEP risk perception in this population and the value of its application in the current context.