Lin Yang

Background: Accurate short-term glucose forecasting is important for diabetes self-management, yet dietary information remains difficult to quantify and integrate into forecasting models in free-living settings, especially for complex Chinese meals. Methods: We investigated whether large language models (LLMs) can convert free-text Chinese dietary records into structured nutritional features for short-term continuous glucose forecasting. Five Chinese-capable LLMs were evaluated as nutrient estimators, and the resulting nutritional features were integrated with continuous glucose monitoring histories in a seasonal-patch transformer for glucose forecasting. Performance was assessed in 2 real-world cohorts (ShanghaiT1DM and ShanghaiT2DM) for both full-period and postprandial glucose forecasting. Results: LLM-derived nutrient estimates significantly outperformed semantic embeddings as dietary representations for glucose forecasting ( P < 0.001). In the primary comparison setting, the best-performing LLM-based model achieved a postprandial 3-h root mean square error (RMSE) of 34.668 mg/dl, reducing the error by 1.967 mg/dl compared to non-LLM settings. In the full-period setting, the optimal LLM-based model achieved an RMSE of 27.035 mg/dl, reducing the error by 0.42 mg/dl relative to non-LLM settings. Across both forecasting tasks, direct nutrient estimation by DeepSeek-v3.1 achieved the best average RMSE. Forecasting gains were positively associated with nutrient-estimation quality, particularly for carbohydrate, dietary fiber, and fat. Architecture ablations further showed that patch-based encoding was the most influential component, with additional contributions from temporal decomposition and side branch design. Conclusion: These findings show that LLM-based nutrient estimation provides a practical and physiologically interpretable way to convert free-text dietary records into structured meal-related inputs for glucose forecasting.

Objective: Gestational diabetes mellitus (GDM) is one of the most common pregnancy complications. Electronic health records (EHRs) promise GDM risk prediction, but missing data poses a challenge to developing reliable and generalizable risk prediction models. This study aims to address the problem of missing EHR data in GDM prediction before 12 weeks gestation. Methods: A total of 5066 women with singleton pregnancies, aged 18 to 50, were included in this retrospective study. This study evaluated 6 imputation methods, combined with 4 classification machine learning models. The evaluation encompassed downstream predictive performance, robustness to variable missingness, ability to restore original data distribution, and influence on feature selection based on 10-fold cross-validation. Results: Our findings revealed a significant improvement in model performance with imputation. When using the top 30 features, logistic regression (LR) with multivariate imputation by chained equations using classification and regression trees (mice) achieved the highest area under the receiver operating characteristic curve of 0.6899, compared to 0.6336 for the LR model without imputation. Mice also led to the best average performance across prediction models and yielded the most accurate restoration of the original data distribution. LR models trained on data imputed by mice remained the most robust across varying levels of missingness. The classification algorithm primarily accounted for differences in predictive performance. In addition, we identified 18 key features for early GDM prediction in the Chinese population. Conclusion: This study demonstrates the critical role of imputation in improving the performance and fairness of GDM prediction models. The findings provide practical guidance for integrating imputation into clinical machine learning pipelines.

Background: Nutrient needs vary over the lifespan. Improving knowledge of both population groups and care providers can help with healthier food choices, thereby promoting population health and preventing diseases. Providing evidence-based food knowledge online is credible, low cost, and easily accessible. Objective: This study aimed to develop an online multimodal food data exploration platform for easy access to evidence-based diet- and nutrition-related data. Methods: We developed an online platform named Food Atlas in collaboration with a multidisciplinary expert group from the National Institute for Nutrition and Health and Peking Union Medical College Hospital in China. To demonstrate its feasibility for Chinese food for pregnant women, a user-friendly and high-quality multimodal food knowledge graph was constructed, and various interactions with graph-structured data were developed for easy access, including graph-based interactive visualizations, natural language retrieval, and image-text retrieval. Subsequently, we evaluated Food Atlas from both the system perspective and the user perspective. Results: The constructed multimodal food knowledge graph contained a total of 2011 entities, 10,410 triplets, and 23,497 images. Its schema consisted of 11 entity types and 26 types of semantic relations. Compared with 5 other online dietary platforms (Foodwake, Boohee, Xiachufang, Allrecipes, and Yummly), Food Atlas offers a distinct and comprehensive set of data content and system functions desired by target populations. Meanwhile, a total of 28 participants representing 4 different user groups were recruited to evaluate its usability: preparing for pregnancy (n=8), pregnant (n=12), clinicians (n=5), and dietitians (n=3). The mean System Usability Scale index of our platform was 82.5 (SD 9.94; range 40.0-82.5). This above-average usability score and the use cases indicated that Food Atlas is tailored to the needs of the target users. Furthermore, 96% (27/28) of the participants stated that the platform had high consistency, illustrating the necessity and effectiveness of health professionals participating in online, evidence-based resource development. Conclusions: This study demonstrates the development of an online multimodal food data exploration platform and its ability to meet the rising demand for accessible, credible, and appropriate evidence-based online dietary resources. Further research and broader implementation of such platforms have the potential to popularize knowledge, thereby helping populations at different life stages make healthier food choices.

Background: Pregnancy is a pivotal phase in a woman’s life, demanding special attention to ensure maternal and fetal health. Prenatal education plays a vital role in promoting healthy pregnancies and reducing adverse outcomes for pregnant women. Mobile prenatal education programs have gained traction due to their accessibility and timeliness, especially in light of finite health care resources and the constraints imposed by the COVID-19 pandemic. Objective: This study aims to develop and evaluate the effectiveness of a mobile-based prenatal education program in improving pregnancy outcomes. Methods: We developed a mobile-based prenatal education curriculum in collaboration with a multidisciplinary maternal care team from Peking Union Medical College Hospital (PUMCH) in Beijing, China. Data were retrospectively collected from 1941 pregnant women who had registered for the PUMCH mobile prenatal education program and subsequently delivered at PUMCH between May 2021 and August 2022. The study compared pregnancy outcomes between the completing group, which were pregnant women who had completed at least 1 course, and the noncompleting group. We also analyzed differences among course topics within the completing group and assessed course topic popularity among pregnant women. Results: The PUMCH mobile prenatal education curriculum consists of 436 courses across 9 topics. Out of the participants, a total of 1521 did not complete any courses, while 420 completed at least 1 course. Compared with the noncompleting group, pregnant women who completed courses exhibited a significant reduction in the risk of gestational diabetes mellitus, induced abortion, postpartum infection, fetal intrauterine distress, and neonatal malformation. Among those in the completing group, a total of 86% (361/420) started course completion during the first and second trimesters. Furthermore, completing courses related to topics of pregnancy psychology and pregnancy nutrition was associated with reduced risks of premature rupture of membranes and small for gestational age infants, respectively. Pregnancy psychology and postpartum recovery were the preferred topics among pregnant women. Conclusions: The study demonstrates the potential of mobile-based prenatal education programs in improving pregnancy outcomes and supporting health care providers in delivering effective prenatal education. The rise of mobile prenatal education presents an opportunity to improve maternal and child health outcomes. Further research and broader implementation of such programs are warranted to continually improve maternal and child health.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Nutrient needs vary over the lifespan. Improving knowledge of both population groups and care providers can help with healthier food choices, thereby promoting population health and preventing diseases. Providing evidence-based food knowledge online is credible, low cost, and easily accessible. Objective: This study aimed to develop an online multimodal food data exploration platform for easy access to evidence-based diet- and nutrition-related data. Methods: We developed an online platform named Food Atlas in collaboration with a multidisciplinary expert group from the National Institute for Nutrition and Health and Peking Union Medical College Hospital in China. To demonstrate its feasibility for Chinese food for pregnant women, a user-friendly and high-quality multimodal food knowledge graph was constructed, and various interactions with graph-structured data were developed for easy access, including graph-based interactive visualizations, natural language retrieval, and image-text retrieval. Subsequently, we evaluated Food Atlas from both the system perspective and the user perspective. Results: The constructed multimodal food knowledge graph contained a total of 2011 entities, 10,410 triplets, and 23,497 images. Its schema consisted of 11 entity types and 26 types of semantic relations. Compared with 5 other online dietary platforms (Foodwake, Boohee, Xiachufang, Allrecipes, and Yummly), Food Atlas offers a distinct and comprehensive set of data content and system functions desired by target populations. Meanwhile, a total of 28 participants representing 4 different user groups were recruited to evaluate its usability: preparing for pregnancy (n=8), pregnant (n=12), clinicians (n=5), and dietitians (n=3). The mean System Usability Scale index of our platform was 82.5 (SD 9.94; range 40.0-82.5). This above-average usability score and the use cases indicated that Food Atlas is tailored to the needs of the target users. Furthermore, 96% (27/28) of the participants stated that the platform had high consistency, illustrating the necessity and effectiveness of health professionals participating in online, evidence-based resource development. Conclusions: This study demonstrates the development of an online multimodal food data exploration platform and its ability to meet the rising demand for accessible, credible, and appropriate evidence-based online dietary resources. Further research and broader implementation of such platforms have the potential to popularize knowledge, thereby helping populations at different life stages make healthier food choices.

BACKGROUND Pregnancy is a pivotal phase in a woman’s life, demanding special attention to ensure maternal and fetal health. Prenatal education plays a vital role in promoting healthy pregnancies and reducing adverse outcomes for pregnant women. Mobile prenatal education programs have gained traction due to their accessibility and timeliness, especially in light of finite health care resources and the constraints imposed by the COVID-19 pandemic. OBJECTIVE This study aims to develop and evaluate the effectiveness of a mobile-based prenatal education program in improving pregnancy outcomes. METHODS We developed a mobile-based prenatal education curriculum in collaboration with a multidisciplinary maternal care team from Peking Union Medical College Hospital (PUMCH) in Beijing, China. Data were retrospectively collected from 1941 pregnant women who had registered for the PUMCH mobile prenatal education program and subsequently delivered at PUMCH between May 2021 and August 2022. The study compared pregnancy outcomes between the completing group, which were pregnant women who had completed at least 1 course, and the noncompleting group. We also analyzed differences among course topics within the completing group and assessed course topic popularity among pregnant women. RESULTS The PUMCH mobile prenatal education curriculum consists of 436 courses across 9 topics. Out of the participants, a total of 1521 did not complete any courses, while 420 completed at least 1 course. Compared with the noncompleting group, pregnant women who completed courses exhibited a significant reduction in the risk of gestational diabetes mellitus, induced abortion, postpartum infection, fetal intrauterine distress, and neonatal malformation. Among those in the completing group, a total of 86% (361/420) started course completion during the first and second trimesters. Furthermore, completing courses related to topics of pregnancy psychology and pregnancy nutrition was associated with reduced risks of premature rupture of membranes and small for gestational age infants, respectively. Pregnancy psychology and postpartum recovery were the preferred topics among pregnant women. CONCLUSIONS The study demonstrates the potential of mobile-based prenatal education programs in improving pregnancy outcomes and supporting health care providers in delivering effective prenatal education. The rise of mobile prenatal education presents an opportunity to improve maternal and child health outcomes. Further research and broader implementation of such programs are warranted to continually improve maternal and child health.

Background: Medical postgraduates’ demand for data capabilities is growing, as biomedical research becomes more data driven, integrative, and computational. In the context of the application of big data in health and medicine, the integration of data mining skills into postgraduate medical education becomes important.Objective: This study aimed to demonstrate the design and implementation of a medical data mining course for medical postgraduates with diverse backgrounds in a medical school.Methods: We developed a medical data mining course called “Practical Techniques of Medical Data Mining” for postgraduate medical education and taught the course online at Peking Union Medical College (PUMC). To identify the background knowledge, programming skills, and expectations of targeted learners, we conducted a web-based questionnaire survey. After determining the instructional methods to be used in the course, three technical platforms—Rain Classroom, Tencent Meeting, and WeChat—were chosen for online teaching. A medical data mining platform called Medical Data Mining - R Programming Hub (MedHub) was developed for self-learning, which could support the development and comprehensive testing of data mining algorithms. Finally, we carried out a postcourse survey and a case study to demonstrate that our online course could accommodate a diverse group of medical students with a wide range of academic backgrounds and programming experience.Results: In total, 200 postgraduates from 30 disciplines participated in the precourse survey. Based on the analysis of students’ characteristics and expectations, we designed an optimized course structured into nine logical teaching units (one 4-hour unit per week for 9 weeks). The course covered basic knowledge of R programming, machine learning models, clinical data mining, and omics data mining, among other topics, as well as diversified health care analysis scenarios. Finally, this 9-week course was successfully implemented in an online format from May to July in the spring semester of 2020 at PUMC. A total of 6 faculty members and 317 students participated in the course. Postcourse survey data showed that our course was considered to be very practical (83/83, 100% indicated “very positive” or “positive”), and MedHub received the best feedback, both in function (80/83, 96% chose “satisfied”) and teaching effect (80/83, 96% chose “satisfied”). The case study showed that our course was able to fill the gap between student expectations and learning outcomes.Conclusions: We developed content for a data mining course, with online instructional methods to accommodate the diversified characteristics of students. Our optimized course could improve the data mining skills of medical students with a wide range of academic backgrounds and programming experience.

Background: Intensive lifestyle modifications have proved effective in preventing type 2 diabetes mellitus (T2DM), yet the efficiency and effectiveness of these modifications need to be improved. Emerging social media interventions are considered useful in promoting these lifestyles; nevertheless, few studies have investigated the effectiveness of combining them with behavior theory. Objective: This study aims to examine the effectiveness of a 6-month mobile-based intervention (DHealthBar, a WeChat applet) combined with behavioral theory compared with a printed intervention in improving dietary behaviors, physical activity, and intention to change these behaviors among populations at high risk for T2DM. Methods: Participants aged 23 to 67 years were recruited offline in Beijing, China, and were randomized into the intervention group or the control group, which received educational content via DHealthBar or a printed handbook, respectively. Educational materials were culturally tailored recommendations on improving dietary behaviors, physical activity, and intention to change based on the transtheoretical model. Participants in the intervention arm received push notifications twice per week on WeChat and had access to the educational content for the 6-month study period. Participants in the control arm received the same intervention content through printed materials. The outcomes of participants’ behavior change, intention to change behavior, and anthropometric characteristics were collected via online measuring tools at baseline, 3 months, and 6 months. Results: In this study, 79 enrolled individuals completed baseline information collection (control: n=38 vs intervention: n=41), and 96% (76/79) completed the 6-month follow-up visit. Attrition rates did not differ significantly between the 2 groups (χ21=0.0, P=.61). Baseline equivalence was found. Participants in both groups reported a statistically significant decrease in energy intake at the 2 follow-up assessments compared with baseline (3 months, control: exp[β]=0.83, 95% CI 0.74-0.92 vs intervention: exp[β]=0.76, 95% CI 0.68-0.85; 6 months, control: exp[β]=0.87, 95% CI 0.78-0.96 vs intervention: exp[β]=0.57, 95% CI 0.51-0.64). At 6 months, a significantly larger decrease was observed in the intervention group in energy, fat, and carbohydrate intake, accompanied with a significantly larger increase in moderate-intensity physical activity compared with the control group (energy: exp[β]=0.66, 95% CI 0.56-0.77; fat: exp[β]=0.71, 95% CI 0.54-0.95; carbohydrates: exp[β]=0.83, 95% CI 0.66-1.03; moderate-intensity physical activity: exp[β]=2.05, 95% CI 1.23-3.44). After 6 months of the intervention, participants in the intervention group were more likely to be at higher stages of dietary behaviors (exp[β]=26.80, 95% CI 3.51-204.91) and physical activity (exp[β]=15.60, 95% CI 2.67-91.04) than the control group. Conclusions: DHealthBar was initially effective in improving dietary behavior, physical activity, and intention to change these behaviors among populations who were at high risk of developing T2DM, with significant differences in the changes of outcomes over the 6-month intervention period. Trial Registration: Chinese Clinical Trial Registry ChiCTR2000032323; https://tinyurl.com/y4h8q4uf

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Medical postgraduates’ demand for data capabilities is growing, as biomedical research becomes more data driven, integrative, and computational. In the context of the application of big data in health and medicine, the integration of data mining skills into postgraduate medical education becomes important. Objective: This study aimed to demonstrate the design and implementation of a medical data mining course for medical postgraduates with diverse backgrounds in a medical school. Methods: We developed a medical data mining course called “Practical Techniques of Medical Data Mining” for postgraduate medical education and taught the course online at Peking Union Medical College (PUMC). To identify the background knowledge, programming skills, and expectations of targeted learners, we conducted a web-based questionnaire survey. After determining the instructional methods to be used in the course, three technical platforms—Rain Classroom, Tencent Meeting, and WeChat—were chosen for online teaching. A medical data mining platform called Medical Data Mining - R Programming Hub (MedHub) was developed for self-learning, which could support the development and comprehensive testing of data mining algorithms. Finally, we carried out a postcourse survey and a case study to demonstrate that our online course could accommodate a diverse group of medical students with a wide range of academic backgrounds and programming experience. Results: In total, 200 postgraduates from 30 disciplines participated in the precourse survey. Based on the analysis of students’ characteristics and expectations, we designed an optimized course structured into nine logical teaching units (one 4-hour unit per week for 9 weeks). The course covered basic knowledge of R programming, machine learning models, clinical data mining, and omics data mining, among other topics, as well as diversified health care analysis scenarios. Finally, this 9-week course was successfully implemented in an online format from May to July in the spring semester of 2020 at PUMC. A total of 6 faculty members and 317 students participated in the course. Postcourse survey data showed that our course was considered to be very practical (83/83, 100% indicated “very positive” or “positive”), and MedHub received the best feedback, both in function (80/83, 96% chose “satisfied”) and teaching effect (80/83, 96% chose “satisfied”). The case study showed that our course was able to fill the gap between student expectations and learning outcomes. Conclusions: We developed content for a data mining course, with online instructional methods to accommodate the diversified characteristics of students. Our optimized course could improve the data mining skills of medical students with a wide range of academic backgrounds and programming experience.