health app developers

Abstract: Large language models hold promise for delivering safe, scientifically grounded, and personalized exercise guidance at scale, yet the sports-and-health domain still lacks curated training corpora and rigorous evaluation benchmarks. Keepace.ai is a domain-specialized LLM built on Qwen3.5-27B through post-training, currently optimized for Chinese-language exercise guidance across three tasks: workout plan generation, sports-and-health knowledge QA, and personal sports data analysis. In internal rubric-based evaluations designed with domain experts, Keepace.ai outperforms its base model and larger general-purpose baselines, with the most pronounced improvements in exercise safety, boundary compliance, structured output completeness, and scientific accuracy. This report summarizes the current design, data pipeline, safety-first evaluation framework, and evaluation results of Keepace.ai.

Abstract: Social media text offers new opportunities for tracking psychological constructs over time, but such measurement requires methods that are interpretable and stable in longitudinal settings. Grounded in Conceptual Space Theory and semantic projection, this study develops the Word Embedding Projection Approach (WEPA), which represents psychological constructs as semantic axes defined by theory-driven anchor words in a domain-specific word embedding space. WEPA scores are interpreted as indicators of expressed psychological salience in user-generated text. Using panel data from Keep, a Chinese fitness-oriented social media platform (177,829 users; 2,668,298 weekly observations), we evaluate WEPA across four studies. Study I examines the measurement foundation through anchor-word validation, human-coded benchmarks, and cross-temporal semantic-axis stability checks. Studies II and III show theoretically interpretable predictive associations between WEPA-derived scores and subsequent exercise duration for goal-setting constructs and the four source dimensions of self-efficacy. Study IV provides exploratory relative-week trajectories of aggregate construct dynamics. Overall, WEPA shows strong agreement with human-coded benchmarks for goal specificity and physiological states and achieves broader text coverage than a dictionary-based baseline. These findings suggest that WEPA offers a promising approach to theory-driven psychological measurement from domain-specific social media text.

Abstract: As wearable and digital health systems increasingly generate longitudinal physiological records, communicating these observations in patient-accessible language remains a significant challenge. Large Language Models (LLMs) offer a promising mechanism for translating structured clinical information into readable narratives, but this process may introduce semantic drift, where clinically precise meaning is distorted during simplification. We investigate evidence-grounded health summarization for menstrual health monitoring using a constrained generation framework that combines structured evidence conditioning with Retrieval-Augmented Generation (RAG) using a prompt-based constrained generation framework. We evaluate semantic alignment using Natural Language Inference (NLI), atomic factuality metrics, and readability measures. Across three LLMs and 4,500 generated summaries, explicit grounding constraints consistently improve clinical alignment, particularly by improving uncertainty preservation and, once faithfulness is evaluated against retrieved evidence, generally preserving or improving faithfulness, while effects on omission remain model-dependent. We also find that improved clinical alignment comes at the cost of increased reading difficulty and medical terminology. These findings highlight the need to jointly evaluate faithfulness, uncertainty preservation, and readability when developing patient-facing medical LLM systems.

Abstract: Photo-based estimation of food energy could ease dietary assessment, and general-purpose multimodal large language models (LLMs) make such estimates easy to obtain. Most evaluations use one photo taken before eating and compare with energy served, while dietary assessment needs energy eaten. We evaluated six models from two vendors (Claude Haiku, Sonnet and Opus 5.5; GPT-6 luna, 6.1 sol and 6 astra) on 802 meals from ACETADA, a controlled feeding trial with weighed intake, with the before photo only, before and after photos in separate calls (subtraction), or both photos in one request. Three results ran against intuition. Subtraction under-estimated intake for five of six models, because the models still report hundreds of kilocalories for a nearly empty tray. Scaling the before-only estimate by the average share eaten (0.87) matched much of the gain from the after photo; beyond that constant, the second photo lowered meal-level error by only 2.2 to 3.4 points, mainly in meals with food left. With one photo, two models had a near-zero intake bias only because they under-estimated the served energy and ignored uneaten food. In ablations, adding the after photo improved accuracy under both prompt formats for five models, while prompt effects varied across models. Over 148 feeding days, three models kept the 90% confidence interval of their mean error within a pre-set 10% margin, but no model reached the pre-set 30% limits of agreement. Protein was under-estimated by every model, most in protein-dense meals; repeated calls changed error by at most 1.4 points; a high reasoning effort helped only the smallest model (4.2 points) and changed the others by less than 1 point. A low average bias is not evidence of accurate individual intake estimation; such estimates should support, not replace, assessment by a dietitian.

Abstract: People increasingly bring their health questions to ChatGPT, yet safety evaluations of LLM health advice rest almost entirely on clinician-authored vignettes, synthetic prompts, or simulated user profiles. The gap is widest for the Global South, where concerns about demographic bias and unsafe recommendations are well documented but have never been tested on real usage. We present, to our knowledge, the first demographically grounded safety evaluation of real-world health conversations with ChatGPT. From a consent-based data-donation corpus of 202,590 conversations from 1,252 users in India, Nigeria, Brazil, and Pakistan (December 2022 to February 2026), each linked to self-reported age and gender, we identify 15,555 health conversations, classify their health intent using an LLM classifier adapted from an established taxonomy, and score response safety under both a context-blind and a user-context-aware rubric. Roughly one in five health conversations receives a high-risk rating. Risk concentrates in symptom and condition queries and recurs through identifiable failure modes: unsafe medication or dosage guidance, harmful self-diagnosis, missing safety warnings, encouraging over-reliance on the model, and failure to refer users to professionals. Supplying the user's own accumulated context raises the high-risk share by 13-17 percentage points, and about one in four conversations rated safe in isolation turns out to be unsafe for the specific person asking. Safety evaluations built on synthetic cases are likely to miss these harms.

Abstract: Machine learning risk models are increasingly being used in patient-facing health tools, but it remains unclear how well users understand the information these systems present. In this work, we study how people interpret an interactive Type 2 Diabetes (T2D) risk interface and whether interacting with it influences their attitudes toward behavioural change. Through an exploratory mixed-methods study with 15 participants, we compare participants' perceived understanding with their actual understanding and identify key themes from qualitative interviews. We find that participants often understood the interface better than they initially believed, but still faced important barriers related to unclear terminology, ambiguous risk framing, and limited explanations of model inputs. Finally, we propose relevant design guidelines and discuss broader issues surrounding trust and fairness. Our findings highlight the importance of intuitive visual design, familiar presentation, and clear explanations in patient-facing ML interfaces.

Abstract: Impaired glucose regulation is a major contributor to metabolic dysfunction and type 2 diabetes. This study developed an interpretable machine-learning framework to predict log-transformed fasting blood glucose using metabolic, hormonal, lifestyle, demographic, nutritional, and circadian variables from the National Health and Nutrition Examination Survey 2017--2020 pre-pandemic dataset. After merging multiple NHANES sub-datasets, data processing used a leakage-resistant pipeline in which imputation, scaling, and one-hot encoding were performed only after dataset splitting and within training folds. Elastic Net, LASSO, and XGBoost models were evaluated using 94 candidate predictors and engineered circadian interaction terms. Performance was assessed using mean absolute error, root mean squared error, coefficient of determination, calibration, and Shapley Additive Explanations. The final interaction-augmented XGBoost model achieved strong performance on the independent test set, with a mean absolute error of 0.0804, a root mean squared error of 0.1148, and a coefficient of determination of 0.7761, using 10 predictors. Glycohemoglobin was the dominant predictor, followed by insulin, diabetes diagnosis, gamma-glutamyl transferase, age, race, and gender. Among the engineered interaction terms, sleep midpoint multiplied by age was consistently retained in repeated random-split analyses, although its contribution remained modest relative to dominant glycaemic predictors. These findings support further investigation of circadian-age interactions in metabolic health.

Abstract: Medical Named Entity Recognition (NER) for low-resource languages remains a challenging task due to high linguistic variability and a scarcity of domain-specific annotated corpora. This work presents a comprehensive empirical benchmark evaluating three fine-tuned transformer encoders-BanglaBERT, multilingual BERT (mBERT), and XLM-RoBERTa-against GPT-4o mini under zero-shot and few-shot prompting configurations for Bangla medical NER. In contrast to prior studies that evaluated large language models on limited subsets of only 50 samples, we conduct a large-scale evaluation across the full test set of 3,179 samples, providing statistically robust and reproducible baselines. Our fine-tuned XLM-RoBERTa model achieves an F1- score of 0.5959, establishing a new state-of-the-art and surpassing the previously reported best result of 0.5848. Crucially, we demonstrate that the language-specific BanglaBERT model consistently underperforms its multilingual counterparts with an F1-score of 0.4937, indicating that pretraining domain diversity can outweigh language specificity in highly specialized clinical settings. Furthermore, we present a detailed per-entity-type analysis for this task, revealing that Medicine and Specialist categories are recognized with high reliability, achieving F1- scores above 0.83, while the Symptom category remains the most challenging with an F1-score of 0.4367 despite being the most frequent training class. Finally, fine-tuned transformer models outperform the optimal prompting configuration by a factor of 3.76, confirming that prompt-only pipelines remain inadequate for structured clinical entity extraction in low-resource language environments.

Abstract: Wearable health questions often combine data retrieval, longitudinal analysis, and health advice over structured records. Prompting a single large language model with a complete record and a composite query obscures whether every request is executed and which evidence supports the answer. We propose a task-oriented multi-agent framework that represents a composite query as distinct intents and typed tasks with explicit intra-intent dependencies. Specialized agents execute retrieval, analysis, and advice tasks; isolated intent states preserve request boundaries and evidence relationships before aggregation. We evaluate the framework on a synthetic dataset of $10{,}000$ virtual users with one month of longitudinal wearable records, covering structured data retrieval, multi-intent recognition, and overall response quality. Across $1{,}500$ retrieval questions, the Query Agent achieves $98.3\%$ accuracy, compared with $97.9\%$ for the Direct LLM baseline, while reducing average query-stage token consumption from $6{,}869$ to $3{,}136$. On $180$ multi-intent questions, the Manager Agent achieves $100.0\%$ Multi-Intent Coverage and $94.4\%$ Multiset Jaccard Similarity. Under the current synthetic evaluation setting, our method receives higher mean Trustworthiness and Transparency scores on both question categories, whereas Actionability does not improve consistently. These results provide preliminary evidence that explicit task organization can support task-relevant data access and data-grounded longitudinal analysis, while leaving health advice generation and validation on real wearable data as open challenges.

Abstract: Sleep monitoring using wearable data has shown promise for personal health, yet large language model (LLM)-based summarization and question answering remain insufficient for personalized sleep guidance. Training specialized models, however, often requires costly expert annotation. Moreover, privacy and accessibility concerns motivate lightweight, local deployment for end users. We present a two-stage framework to address these challenges. Specifically, in Stage~1, a multi-agent LLM pipeline reasons structured sleep guidance from unannotated wearable records, enabling scalable dataset construction. Stage~2 distills guidance reasoning trajectories into small language models (SLMs) through supervised fine-tuning and integrates a training-free Best-of-$N$ selection strategy to enhance inference. Experimental results demonstrate our method outperforms commercial general and medical LLMs and open-source models. Human evaluation further supports the quality of the generated guidance and the feasibility of personalized sleep guidance with SLMs.

Abstract: As conversational LLMs become deeply embedded in daily life, users frequently disclose sensitive personal health information during routine interactions. We present a large-scale computational audit analyzing 179,057 conversations across India, Nigeria, Brazil, and Pakistan (N = 1,057) to evaluate personal health disclosures and background memory synthesis in ChatGPT. We find that 21.31% of audited conversations contain personal health data, with 3.62% posing high-to-extreme privacy risks involving stigmatized conditions, direct identifiers, and precise locations. When evaluating the memory entries of ChatGPT, we uncover a stark disconnect between corporate framing and system behavior: over 95% of profile entries are implicitly extracted without explicit user prompts or consent. Furthermore, background memory synthesis selectively condenses temporary, symptom-level disclosures into permanent diagnostic traits, stripping contextual integrity and amplifying re-identification risks. We conclude with sociotechnical design guidelines to restore user agency and consent-driven boundaries in stateful AI systems.

Abstract: Overeating and emotional eating are common health issues that affect people even without an eating disorder. The vagus nerve plays a critical role in the gut-brain axis, and implanted vagus nerve stimulators have been associated with reduced appetite. In this paper, we propose transcutaneous cervical vagus nerve stimulation (tcVNS) as a ubiquitous system to provide immediate, low-effort intervention during an eating episode. In a study with 24 participants, we evaluated a mobile, handheld tcVNS device during a single episode of distracted snacking. We found that participants ate 9.6% less and 23.6% more slowly during vagus nerve stimulation than during sham stimulation. Post-snacking satiety was the same in both conditions, while heart rate was lower during vagus nerve stimulation. The stimulation was described as subtle and barely noticeable. Overall, these results provide evidence for the feasibility of non-invasive vagus nerve stimulation as a low-attention intervention for managing eating behavior -- one that can be packaged inside ubiquitous interactive systems. As such, we extend the design space of implicit interfaces toward physiological intervention, motivating future ubiquitous systems that pair eating-related sensing with low-attention interventions.