Large Language Models have revolutionized information processing, yet their reliability is severely compromised by faithfulness hallucinations. While current approaches attempt to mitigate this issue through node-level adjustments or coarse suppression, they often overlook the distributed nature of neural information, leading to imprecise interventions. Recognizing that hallucinations propagate through specific forward transmission pathways like an infection, we aim to surgically block this flow using precise structural analysis. To leverage this, we propose Lancet, a novel framework that achieves precise neural intervention by leveraging structural entropy and hallucination difference ratios. Lancet first locates hallucination-prone neurons via gradient-driven contrastive analysis, then maps their propagation pathways by minimizing structural entropy, and finally implements a hierarchical intervention strategy that preserves general model capabilities. Comprehensive evaluations across hallucination benchmark datasets demonstrate that Lancet significantly outperforms state-of-the-art methods, validating the effectiveness of our surgical approach to neural intervention.
Chikungunya fever (CHIKV), a viral disease transmitted by mosquitoes, is currently affecting several territories in the Caribbean. The vector is found in the Americas from South Florida to Brazil and the Caribbean is a highly connected region. There is therefore a significant risk for the epidemic to quickly expand to a wide area in the Americas, and of introduction to Europe where competent vectors are present. Here, we describe the spread of CHIKV in the first three territories to report cases and between territories of the region. Local transmission of CHIKV in the Caribbean is found to be very effective (mean number of cases generated by a human case in the range 2 to 4). There is a strong spatial signature in the regional epidemic, with the risk of transmission between territories estimated to be inversely proportional to the distance rather than being driven by air transportation. So far, this simple model has successfully predicted observed patterns of spread. The spatial structure allows ranking territories according to their current risk of invasion. This characterization may help national and international agencies to optimize resource allocation for monitoring and contro
Health messages on social media are typically constructed through combinations of source cues, appeals, frames, and evidence, which jointly shape communication and persuasive effects. However, prior research has largely focused on single elements or simple pairwise interactions, offering insufficient insight into how multiple elements operate together in real-world digital environments. To address this gap, this study adopts a systems perspective to examine multi-element message combinations. Using 1.8 million health-related Weibo posts, we apply clustering analysis to identify recurring combinations and assess their relationships with communication effects. First, four recurring element combinations are identified: Institutional Authority, Narrative, Assertive Appeal, and Contextual Expression. These combinations function as core structures organized around two key elements. Second, stronger communication effects depend not only on core structures but also on peripheral elements aligned with these structures, with combinations of two to four peripheral elements generally showing greater advantages. Third, the optimal level of peripheral complexity varies with source influence, ind
The growing demand for home healthcare calls for tools that can support care delivery. In this study, we explore automatic health assessment from voice using real-world home care visit data, leveraging the diverse patient information it contains. First, we utilize Large Language Models (LLMs) to integrate Subjective, Objective, Assessment, and Plan (SOAP) notes derived from unstructured audio transcripts and structured vital signs into a holistic illness score that reflects a patient's overall health. This compact representation facilitates cross-visit health status comparisons and downstream analysis. Next, we design a multi-stage preprocessing pipeline to extract short speech segments from target speakers in home care recordings for acoustic analysis. We then employ an Audio Language Model (ALM) to produce plain-language descriptions of vocal biomarkers and examine their association with individuals' health status. Our experimental results benchmark both commercial and open-source LLMs in estimating illness scores, demonstrating their alignment with actual clinical outcomes, and revealing that SOAP notes are substantially more informative than vital signs. Building on the illness
Large language model-powered chatbots have transformed how people seek information, especially in high-stakes contexts like mental health. Despite their support capabilities, safe detection and response to crises such as suicidal ideation and self-harm are still unclear, hindered by the lack of unified crisis taxonomies and clinical evaluation standards. We address this by creating: (1) a taxonomy of six crisis categories; (2) a dataset of over 2,000 inputs from 12 mental health datasets, classified into these categories; and (3) a clinical response assessment protocol. We also use LLMs to identify crisis inputs and audit five models for response safety and appropriateness. First, we built a clinical-informed crisis taxonomy and evaluation protocol. Next, we curated 2,252 relevant examples from over 239,000 user inputs, then tested three LLMs for automatic classification. In addition, we evaluated five models for the appropriateness of their responses to a user's crisis, graded on a 5-point Likert scale from harmful (1) to appropriate (5). While some models respond reliably to explicit crises, risks still exist. Many outputs, especially in self-harm and suicidal categories, are ina
YouTube has rapidly emerged as a predominant platform for content consumption, effectively displacing conventional media such as television and news outlets. A part of the enormous video stream uploaded to this platform includes health-related content, both from official public health organizations, and from any individual or group that can make an account. The quality of information available on YouTube is a critical point of public health safety, especially when concerning major interventions, such as vaccination. This study differentiates itself from previous efforts of auditing YouTube videos on this topic by conducting a systematic daily collection of posted videos mentioning vaccination for the duration of 3 months. We show that the competition for the public's attention is between public health messaging by institutions and individual educators on one side, and commentators on society and politics on the other, the latest contributing the most to the videos expressing stances against vaccination. Videos opposing vaccination are more likely to mention politicians and publication media such as podcasts, reports, and news analysis, on the other hand, videos in favor are more li
Social Determinants of Health correlate with patient outcomes but are rarely captured in structured data. Recent attention has been given to automatically extracting these markers from clinical text to supplement diagnostic systems with knowledge of patients' social circumstances. Large language models demonstrate strong performance in identifying Social Determinants of Health labels from sentences. However, prediction in large admissions or longitudinal notes is challenging given long distance dependencies. In this paper, we explore hospital admission multi-label Social Determinants of Health ICD-9 code classification on the MIMIC-III dataset using reasoning models and traditional large language models. We exploit existing ICD-9 codes for prediction on admissions, which achieved an 89% F1. Our contributions include our findings, missing SDoH codes in 139 admissions, and code to reproduce the results.
Although serious games have been increasingly used for mental health applications, few explicitly address coping with grief as a core mechanic and narrative experience for patients. Existing grief-related digital games often focus on clinical training for medical professionals rather than immersive storytelling and agency in emotional processing for the patient. In response, we designed Road to Acceptance, a VR game that presents grief through first-person narrative and gameplay. As the next phase of evaluation, we propose a workshop-based study with 12 licensed mental health professionals to assess the therapeutic impacts of the game and the alignment with best practices in grief education and interventions. This will inform iterative game design and patient evaluation methods, ensuring that the experience is clinically appropriate. Potential findings can contribute to the design principles of grief-related virtual reality experiences, bridging the gap between interactive media, mental health interventions, and immersive storytelling.
The Oregon Health Insurance Experiment (OHIE) offers a unique opportunity to examine the causal relationship between Medicaid coverage and happiness among low-income adults, using an experimental design. This study leverages data from comprehensive surveys conducted at 0 and 12 months post-treatment. Previous studies based on OHIE have shown that individuals receiving Medicaid exhibited a significant improvement in mental health compared to those who did not receive coverage. The primary objective is to explore how Medicaid coverage impacts happiness, specifically analyzing in which direction variations in healthcare spending significantly improve mental health: higher spending or lower spending after Medicaid. Utilizing instrumental variable (IV) regression, I conducted six separate regressions across subgroups categorized by expenditure levels and happiness ratings, and the results reveal distinct patterns. Enrolling in OHP has significantly decreased the probability of experiencing unhappiness, regardless of whether individuals had high or low medical spending. Additionally, it decreased the probability of being pretty happy and having high medical expenses, while increasing the
Selecting the right monitoring level in Remote Patient Monitoring (RPM) systems for e-healthcare is crucial for balancing patient outcomes, various resources, and patient's quality of life. A prior work has used one-dimensional health representations, but patient health is inherently multidimensional and typically consists of many measurable physiological factors. In this paper, we introduce a multidimensional health state model within the RPM framework and use dynamic programming to study optimal monitoring strategies. Our analysis reveals that the optimal control is characterized by switching curves (for two-dimensional health states) or switching hyper-surfaces (in general): patients switch to intensive monitoring when health measurements cross a specific multidimensional surface. We further study how the optimal switching curve varies for different medical conditions and model parameters. This finding of the optimal control structure provides actionable insights for clinicians and aids in resource planning. The tunable modeling framework enhances the applicability and effectiveness of RPM services across various medical conditions.
Southeast Asia is a geopolitically and socio-economically significant region with unique challenges and opportunities. Intensifying progress in generative AI against a backdrop of existing health security threats makes applications of AI to mitigate such threats attractive but also risky if done without due caution. This paper provides a brief sketch of some of the applications of AI for health security and the regional policy and governance landscape. I focus on policy and governance activities of the Association of Southeast Asian Nations (ASEAN), an international body whose member states represent 691 million people. I conclude by identifying sustainability as an area of opportunity for policymakers and recommend priority areas for generative AI researchers to make the most impact with their work.
Global rates of mental health concerns are rising, and there is increasing realization that existing models of mental health care will not adequately expand to meet the demand. With the emergence of large language models (LLMs) has come great optimism regarding their promise to create novel, large-scale solutions to support mental health. Despite their nascence, LLMs have already been applied to mental health related tasks. In this paper, we summarize the extant literature on efforts to use LLMs to provide mental health education, assessment, and intervention and highlight key opportunities for positive impact in each area. We then highlight risks associated with LLMs' application to mental health and encourage the adoption of strategies to mitigate these risks. The urgent need for mental health support must be balanced with responsible development, testing, and deployment of mental health LLMs. It is especially critical to ensure that mental health LLMs are fine-tuned for mental health, enhance mental health equity, and adhere to ethical standards and that people, including those with lived experience with mental health concerns, are involved in all stages from development through
Growth of the older adult population has led to an increasing interest in technology-supported aged care. However, the area has some challenges such as a lack of caregivers and limitations in understanding the emotional, social, physical, and mental well-being needs of seniors. Furthermore, there is a gap in the understanding between developers and ageing people of their requirements. Digital health can be important in supporting older adults wellbeing, emotional requirements, and social needs. Requirements Engineering (RE) is a major software engineering field, which can help to identify, elicit and prioritize the requirements of stakeholders and ensure that the systems meet standards for performance, reliability, and usability. We carried out a systematic review of the literature on RE for older adult digital health software. This was necessary to show the representatives of the current stage of understanding the needs of older adults in aged care digital health. Using established guidelines outlined by the Kitchenham method, the PRISMA and the PICO guideline, we developed a protocol, followed by the systematic exploration of eight databases. This resulted in 69 primary studies o
The rapid spread of health misinformation on online social networks (OSNs) during global crises such as the COVID-19 pandemic poses challenges to public health, social stability, and institutional trust. Centrality metrics have long been pivotal in understanding the dynamics of information flow, particularly in the context of health misinformation. However, the increasing complexity and dynamism of online networks, especially during crises, highlight the limitations of these traditional approaches. This study introduces and compares three novel centrality metrics: dynamic influence centrality (DIC), health misinformation vulnerability centrality (MVC), and propagation centrality (PC). These metrics incorporate temporal dynamics, susceptibility, and multilayered network interactions. Using the FibVID dataset, we compared traditional and novel metrics to identify influential nodes, propagation pathways, and misinformation influencers. Traditional metrics identified 29 influential nodes, while the new metrics uncovered 24 unique nodes, resulting in 42 combined nodes, an increase of 44.83%. Baseline interventions reduced health misinformation by 50%, while incorporating the new metrics
Electronic health record (EHR) data is an essential data source for machine learning for health, but researchers and clinicians face steep barriers in extracting and validating EHR data for modeling. Existing tools incur trade-offs between expressivity and usability and are typically specialized to a single data standard, making it difficult to write temporal queries that are ready for modern model-building pipelines and adaptable to new datasets. This paper introduces TempoQL, a Python-based toolkit designed to lower these barriers. TempoQL provides a simple, human-readable language for temporal queries; support for multiple EHR data standards, including OMOP, MEDS, and others; and an interactive notebook-based query interface with optional large language model (LLM) authoring assistance. Through a performance evaluation and two use cases on different datasets, we demonstrate that TempoQL simplifies the creation of cohorts for machine learning while maintaining precision, speed, and reproducibility.
Large Language Models (LLMs) hold promise in addressing complex medical problems. However, while most prior studies focus on improving accuracy and reasoning abilities, a significant bottleneck in developing effective healthcare agents lies in the readability of LLM-generated responses, specifically, their ability to answer public health problems clearly and simply to people without medical backgrounds. In this work, we introduce RephQA, a benchmark for evaluating the readability of LLMs in public health question answering (QA). It contains 533 expert-reviewed QA pairs from 27 sources across 13 topics, and includes a proxy multiple-choice task to assess informativeness, along with two readability metrics: Flesch-Kincaid grade level and professional score. Evaluation of 25 LLMs reveals that most fail to meet readability standards, highlighting a gap between reasoning and effective communication. To address this, we explore four readability-enhancing strategies-standard prompting, chain-of-thought prompting, Group Relative Policy Optimization (GRPO), and a token-adapted variant. Token-adapted GRPO achieves the best results, advancing the development of more practical and user-friendl
Sonification can provide valuable insights about data but most existing approaches are not designed to be controlled by the user in an interactive fashion. Interactions enable the designer of the sonification to more rapidly experiment with sound design and allow the sonification to be modified in real-time by interacting with various control parameters. In this paper, we describe two case studies of interactive sonification that utilize publicly available datasets that have been described recently in the International Conference on Auditory Display (ICAD). They are from the health and energy domains: electroencephalogram (EEG) alpha wave data and air pollutant data consisting of nitrogen dioxide, sulfur dioxide, carbon monoxide, and ozone. We show how these sonfications can be recreated to support interaction utilizing a general interactive sonification framework built using ChucK, Unity, and Chunity. In addition to supporting typical sonification methods that are common in existing sonification toolkits, our framework introduces novel methods such as supporting discrete events, interleaved playback of multiple data streams for comparison, and using frequency modulation (FM) synth
Wearable movement data is collected by nearly all commercially available smartwatches and is a valuable resource for mental health research, reflecting fine-grained temporal behavioral trends. Despite its promise, the development of foundation models for health wearable modeling remains limited when compared to clinical image and text analysis. We designed transformers with patch embeddings and used self-supervised masked autoencoder pretraining on minute-level week-long actigraphy (physical activity intensity measurement) sequences to develop and evaluate the Pretrained Actigraphy Transformer (PAT). PAT is an open-source foundation model for wearable movement time series that combines week-long temporal modeling, psychiatric outcome evaluation, and reproducibility on public data. Pretrained on data from 21,538 U.S. participants in a nationally representative cohort from the National Health and Nutrition Examination Survey (NHANES), PAT consistently outperformed non-foundation-model baselines across mental health prediction tasks-including benzodiazepine and SSRI use, depression, and sleep abnormalities. During the benzodiazepine medication usage prediction task, PAT demonstrated t
Mobile health has the potential to revolutionize health care delivery and patient engagement. In this work, we discuss how integrating Artificial Intelligence into digital health applications-focused on supply chain, patient management, and capacity building, among other use cases-can improve the health system and public health performance. We present an Artificial Intelligence and Reinforcement Learning platform that allows the delivery of adaptive interventions whose impact can be optimized through experimentation and real-time monitoring. The system can integrate multiple data sources and digital health applications. The flexibility of this platform to connect to various mobile health applications and digital devices and send personalized recommendations based on past data and predictions can significantly improve the impact of digital tools on health system outcomes. The potential for resource-poor settings, where the impact of this approach on health outcomes could be more decisive, is discussed specifically. This framework is, however, similarly applicable to improving efficiency in health systems where scarcity is not an issue.
Objective: To enhance health literacy and accessibility of health information for a diverse patient population by developing a patient-centered artificial intelligence (AI) solution using large language models (LLMs) and Fast Healthcare Interoperability Resources (FHIR) application programming interfaces (APIs). Materials and Methods: The research involved developing LLM on FHIR, an open-source mobile application allowing users to interact with their health records using LLMs. The app is built on Stanford's Spezi ecosystem and uses OpenAI's GPT-4. A pilot study was conducted with the SyntheticMass patient dataset and evaluated by medical experts to assess the app's effectiveness in increasing health literacy. The evaluation focused on the accuracy, relevance, and understandability of the LLM's responses to common patient questions. Results: LLM on FHIR demonstrated varying but generally high degrees of accuracy and relevance in providing understandable health information to patients. The app effectively translated medical data into patient-friendly language and was able to adapt its responses to different patient profiles. However, challenges included variability in LLM responses a