Estimating Body Mass Index (BMI) from camera images with machine learning models enables rapid weight assessment when traditional methods are unavailable or impractical, such as in telehealth or emergency scenarios. Existing computer vision approaches have been limited to datasets of up to 14,500 images. In this study, we present a deep learning-based BMI estimation method trained on our WayBED dataset, a large proprietary collection of 84,963 smartphone images from 25,353 individuals. We introduce an automatic filtering method that uses posture clustering and person detection to curate the dataset by removing low-quality images, such as those with atypical postures or incomplete views. This process retained 71,322 high-quality images suitable for training. We achieve a Mean Absolute Percentage Error (MAPE) of 7.9% on our hold-out test set (WayBED data) using full-body images, the lowest value in the published literature to the best of our knowledge. Further, we achieve a MAPE of 13% on the completely unseen (during training) VisualBodyToBMI dataset, comparable with state-of-the-art approaches trained on it, demonstrating robust generalization. Lastly, we fine-tune our model on VisualBodyToBMI and achieve a MAPE of 8.56%, the lowest reported value on this dataset so far. We deploy the full pipeline, including image filtering and BMI estimation, on Android devices using the CLAID framework. We release our complete code for model training, filtering, and the CLAID package for mobile deployment as open-source contributions.

Digital health interventions (DHIs) offer promising solutions to the rising global challenges of noncommunicable diseases by promoting behavior change, improving health outcomes, and reducing healthcare costs. However, high churn rates are a concern with DHIs, with many users disengaging before achieving desired outcomes. Churn prediction can help DHI providers identify and retain at-risk users, enhancing the efficacy of DHIs. We analyzed churn prediction models for a weight loss app using various machine learning algorithms on data from 1,283 users and 310,845 event logs. The best-performing model, a random forest model that only used daily login counts, achieved an F1 score of 0.87 on day 7 and identified an average of 93% of churned users during the week-long trial. Notably, higher-dimensional models performed better at low false positive rate thresholds. Our findings suggest that user churn can be forecasted using engagement data, aiding in timely personalized strategies and better health results.

OBJECTIVE: The aim of this study was to disseminate insights from a nationwide pilot of the International Classification of Diseases-11th revision (ICD-11). MATERIALS AND METHODS: The strategies and methodologies employed to implement the ICD-11 morbidity coding in 59 hospitals in China are described. The key considerations for the ICD-11 implementation were summarized based on feedback obtained from the pilot hospitals. Coding accuracy and Krippendorff's alpha reliability were computed based on the coding results in the ICD-11 exam. RESULTS: Among the 59 pilot hospitals, 58 integrated ICD-11 Coding Software into their health information management systems and 56 implemented the ICD-11 in morbidity coding, resulting in 3 723 959 diagnoses for 873 425 patients being coded over a 2-month pilot coding phase. The key considerations in the transition to the ICD-11 in morbidity coding encompassed the enrichment of ICD-11 content, refinement of tools, provision of systematic and tailored training, improvement of clinical documentation, promotion of downstream data utilization, and the establishment of a national process and mechanism for implementation. The overall coding accuracy was 82.9% when considering the entire coding field (including postcoordination) and 92.2% when only one stem code was considered. Krippendorff's alpha was 0.792 (95% CI, 0.788-0.796) and 0.799 (95% CI, 0.795-0.803) with and without consideration of the code sequence, respectively. CONCLUSION: This nationwide pilot study has enhanced national technical readiness for the ICD-11 implementation in morbidity, elucidating key factors warranting careful consideration in future endeavors. The good accuracy and intercoder reliability of the ICD-11 coding achieved following a brief training program underscore the potential for the ICD-11 to reduce training costs and provide high-quality health data. Experiences and lessons learned from this study have contributed to WHO's work on the ICD-11 and can inform other countries when formulating their transition plan.