Quantifying human movement (kinematics) and musculoskeletal forces (kinetics) at scale, such as estimating quadriceps force during a sit-to-stand movement, could transform prediction, treatment, and monitoring of mobility-related conditions. However, quantifying kinematics and kinetics traditionally requires costly, time-intensive analysis in specialized laboratories, limiting clinical translation. Scalable, accurate tools for biomechanical assessment are needed. We introduce OpenCap Monocular, an algorithm that estimates 3D skeletal kinematics and kinetics from a single smartphone video. The method refines 3D human pose estimates from a monocular pose estimation model (WHAM) via optimization, computes kinematics of a biomechanically constrained skeletal model, and estimates kinetics via physics-based simulation and machine learning. We validated OpenCap Monocular against marker-based motion capture and force plate data for walking, squatting, and sit-to-stand tasks. OpenCap Monocular achieved low kinematic error (4.8° mean absolute error for rotational degrees of freedom; 3.4 cm for pelvis translations), outperforming a regression-only computer vision baseline by 48% in rotational accuracy (p = 0.036) and 69% in translational accuracy (p < 0.001). OpenCap Monocular also estimated ground reaction forces during walking with accuracy comparable to, or better than, our prior two-camera OpenCap system. We demonstrate that the algorithm estimates important kinetic outcomes with clinically meaningful accuracy in applications related to frailty and knee osteoarthritis, including estimating knee extension moment during sit-to-stand transitions and knee adduction moment during walking. OpenCap Monocular is deployed via a smartphone app, web app, and secure cloud computing (https://opencap.ai), enabling free, accessible single-smartphone biomechanical assessments.
Helal El-Zaatari, Liubov Arbeeva, Amanda E. Nelson
Data used to understand knee osteoarthritis (KOA) often involves knee-level, rather than person-level information. Failure to account for the correlation between joints within a person may lead to inaccurate inferences. The aim of this study was to develop a flexible, data-driven framework for predicting knee pain outcomes, incorporating the advantages of both random forest (RF) and mixed effects models for correlated data. Specifically, we utilized data from the baseline visit of the Osteoarthritis Initiative (OAI) and applied the Binary Mixed Models (BiMM) algorithm to predict two binary dependent variables. 1) presence of knee pain, stiffness or aching in the past 12 months and 2) presence of knee pain indicated by a KOOS pain score > 85. This novel approach was compared to standard random forests (RF), which do not account for correlations among knees. This study demonstrates the potential of BiMM as a predictive tool for KOA pain, achieving a comparable or slightly improved performance over traditional RF models while simultaneously accounting for within-person correlation among knees. This is a significant advancement, as most machine learning models to date have only considered each knee individually. These findings support the integration of BiMM in KOA outcome prediction, providing a nuanced alternative to existing models and advancing our understanding of important KOA outcomes on the person level. Although demonstrated here for KOA, this method is relevant to any situation where within-person correlations are relevant, including other joints and other musculoskeletal conditions.
The evolutionary origins of ageing and age-associated diseases continue to pose a fundamental question in biology. This study is concerned with a recently proposed framework, which conceptualises development and ageing as a continuous process, driven by genetically encoded epigenetic changes in target sets of cells. According to the Evolvable Soma Theory of Ageing (ESTA), ageing reflects the cumulative manifestation of epigenetic changes that are predominantly expressed during the post-reproductive phase. These late-acting modifications are not yet evolutionarily optimised but are instead subject to ongoing selection, functioning as somatic "experiments" through which evolution explores novel phenotypic variation. These experiments are often detrimental, leading to progressive physical decline and eventual death, while a small subset may produce beneficial adaptations, that evolution can exploit to shape future developmental trajectories. According to ESTA, ageing can be understood as evolution in action, yet old age is also the strongest risk factor for major diseases such as cardiovascular diseases, cancer, neurodegenerative disorders, and metabolic syndrome. We argue that this association is not merely correlational but causal: the same epigenetic process that drive development and ageing also underlie age-associated diseases. Growing evidence points to epigenetic regulation as a central factor in these pathologies, since no consistent patterns of genetic mutations have been identified, whereas widespread regulatory and epigenetic disruptions are observed. From this perspective, evolution is not only the driver of ageing but also the ultimate source of the diseases that accompany it, making it the root cause of most age-related pathologies.
Carson Dudley, Reiden Magdaleno, Christopher Harding
et al.
Infectious disease forecasting in novel outbreaks or low-resource settings is hampered by the need for large disease and covariate data sets, bespoke training, and expert tuning, all of which can hinder rapid generation of forecasts for new settings. To help address these challenges, we developed Mantis, a foundation model trained entirely on mechanistic simulations, which enables out-of-the-box forecasting across diseases, regions, and outcomes, even in settings with limited historical data. We evaluated Mantis against 48 forecasting models across six diseases with diverse modes of transmission, assessing both point forecast accuracy (mean absolute error) and probabilistic performance (weighted interval score and coverage). Despite using no real-world data during training, Mantis achieved lower mean absolute error than all models in the CDC's COVID-19 Forecast Hub when backtested on early pandemic forecasts which it had not previously seen. Across all other diseases tested, Mantis consistently ranked in the top two models across evaluation metrics. Mantis further generalized to diseases with transmission mechanisms not represented in its training data, demonstrating that it can capture fundamental contagion dynamics rather than memorizing disease-specific patterns. These capabilities illustrate that purely simulation-based foundation models such as Mantis can provide a practical foundation for disease forecasting: general-purpose, accurate, and deployable where traditional models struggle.
Abdullah Al Shafi, Rowzatul Zannat, Abdul Muntakim
et al.
Disease-symptom datasets are significant and in demand for medical research, disease diagnosis, clinical decision-making, and AI-driven health management applications. These datasets help identify symptom patterns associated with specific diseases, thus improving diagnostic accuracy and enabling early detection. The dataset presented in this study systematically compiles disease-symptom relationships from various online sources, medical literature, and publicly available health databases. The data was gathered through analyzing peer-reviewed medical articles, clinical case studies, and disease-symptom association reports. Only the verified medical sources were included in the dataset, while those from non-peer-reviewed and anecdotal sources were excluded. The dataset is structured in a tabular format, where the first column represents diseases, and the remaining columns represent symptoms. Each symptom cell contains a binary value, indicating whether a symptom is associated with a disease. Thereby, this structured representation makes the dataset very useful for a wide range of applications, including machine learning-based disease prediction, clinical decision support systems, and epidemiological studies. Although there are some advancements in the field of disease-symptom datasets, there is a significant gap in structured datasets for the Bangla language. This dataset aims to bridge that gap by facilitating the development of multilingual medical informatics tools and improving disease prediction models for underrepresented linguistic communities. Further developments should include region-specific diseases and further fine-tuning of symptom associations for better diagnostic performance
Medical artificial intelligence (AI) systems frequently lack systematic domain expertise integration, potentially compromising diagnostic reliability. This study presents an ontology-based framework for bone disease diagnosis, developed in collaboration with Ho Chi Minh City Hospital for Traumatology and Orthopedics. The framework introduces three theoretical contributions: (1) a hierarchical neural network architecture guided by bone disease ontology for segmentation-classification tasks, incorporating Visual Language Models (VLMs) through prompts, (2) an ontology-enhanced Visual Question Answering (VQA) system for clinical reasoning, and (3) a multimodal deep learning model that integrates imaging, clinical, and laboratory data through ontological relationships. The methodology maintains clinical interpretability through systematic knowledge digitization, standardized medical terminology mapping, and modular architecture design. The framework demonstrates potential for extension beyond bone diseases through its standardized structure and reusable components. While theoretical foundations are established, experimental validation remains pending due to current dataset and computational resource limitations. Future work will focus on expanding the clinical dataset and conducting comprehensive system validation.
Aniketh Garikaparthi, Manasi Patwardhan, Lovekesh Vig
et al.
The rapid advancement in capabilities of large language models (LLMs) raises a pivotal question: How can LLMs accelerate scientific discovery? This work tackles the crucial first stage of research, generating novel hypotheses. While recent work on automated hypothesis generation focuses on multi-agent frameworks and extending test-time compute, none of the approaches effectively incorporate transparency and steerability through a synergistic Human-in-the-loop (HITL) approach. To address this gap, we introduce IRIS: Interactive Research Ideation System, an open-source platform designed for researchers to leverage LLM-assisted scientific ideation. IRIS incorporates innovative features to enhance ideation, including adaptive test-time compute expansion via Monte Carlo Tree Search (MCTS), fine-grained feedback mechanism, and query-based literature synthesis. Designed to empower researchers with greater control and insight throughout the ideation process. We additionally conduct a user study with researchers across diverse disciplines, validating the effectiveness of our system in enhancing ideation. We open-source our code at https://github.com/Anikethh/IRIS-Interactive-Research-Ideation-System
Modeling disease progression through multiple stages is critical for clinical decision-making for chronic diseases, e.g., cancer, diabetes, chronic kidney diseases, and so on. Existing approaches often model the disease progression as a uniform trajectory pattern at the population level. However, chronic diseases are highly heterogeneous and often have multiple progression patterns depending on a patient's individual genetics and environmental effects due to lifestyles. We propose a personalized disease progression model to jointly learn the heterogeneous progression patterns and groups of genetic profiles. In particular, an end-to-end pipeline is designed to simultaneously infer the characteristics of patients from genetic markers using a variational autoencoder and how it drives the disease progressions using an RNN-based state-space model based on clinical observations. Our proposed model shows improvement on real-world and synthetic clinical data.
AbstractCutaneous exposure to the DNA alkylating class of chemotherapeutic agents including nitrogen mustard (NM) leads to both skin injury and systemic inflammation. Circulating myeloid subsets recruited to the skin act to further exacerbate local tissue damage while interfering with the wound healing process. We demonstrate herein that intravenous delivery of poly(lactic-co-glycolic acid) immune-modifying nanoparticles (PLGA-IMPs) shortly after NM exposure restricts accumulation of macrophages and inflammatory monocytes at the injury site, resulting in attenuated skin pathology. Furthermore, PLGA-IMPs induce an early influx and local enrichment of Foxp3+ regulatory T cells (Treg) in the skin lesions critical for the suppression of myeloid cell-pro-inflammatory responses via induction of IL-10 and TGF-β in the cutaneous milieu. Functional depletion of CD4+ Tregs ablates the efficacy of PLGA-IMPs accompanied by a loss of local accumulation of anti-inflammatory cytokines essential for wound healing. Thus, in severe skin trauma, PLGA-IMPs may have therapeutic potential via modulation of inflammatory myeloid cells and regulatory T lymphocytes.
Philip D. Bonomi, Jeffrey Crawford, Richard F. Dunne
et al.
Abstract Cachexia, with weight loss (WL) as a major component, is highly prevalent in patients with cancer and indicates a poor prognosis. The primary objective of this study was to conduct a meta‐analysis to estimate the risk of mortality associated with cachexia (using established WL criteria prior to treatment initiation) in patients with non‐small‐cell lung cancer (NSCLC) in studies identified through a systematic literature review. The review was conducted according to PRISMA guidelines. Embase® and PubMed were searched to identify articles on survival outcomes in adult patients with NSCLC (any stage) and cachexia published in English between 1 January 2016 and 10 October 2021. Two independent reviewers screened titles, abstracts and full texts of identified records against predefined inclusion/exclusion criteria. Following a feasibility assessment, a meta‐analysis evaluating the impact of cachexia, defined per the international consensus criteria (ICC), or of pre‐treatment WL ≥ 5% without a specified time interval, on overall survival in patients with NSCLC was conducted using a random‐effects model that included the identified studies as the base case. The impact of heterogeneity was evaluated through sensitivity and subgroup analyses. The standard measures of statistical heterogeneity were calculated. Of the 40 NSCLC publications identified in the review, 20 studies that used the ICC for cachexia or reported WL ≥ 5% and that performed multivariate analyses with hazard ratios (HRs) or Kaplan–Meier curves were included in the feasibility assessment. Of these, 16 studies (80%; n = 6225 patients; published 2016–2021) met the criteria for inclusion in the meta‐analysis: 11 studies (69%) used the ICC and 5 studies (31%) used WL ≥ 5%. Combined criteria (ICC plus WL ≥ 5%) were associated with an 82% higher mortality risk versus no cachexia or WL < 5% (pooled HR [95% confidence interval, CI]: 1.82 [1.47, 2.25]). Although statistical heterogeneity was high (I2 = 88%), individual study HRs were directionally aligned with the pooled estimate, and there was considerable overlap in CIs across included studies. A subgroup analysis of studies using the ICC (HR [95% CI]: 2.26 [1.80, 2.83]) or WL ≥ 5% (HR [95% CI]: 1.28 [1.12, 1.46]) showed consistent findings. Assessments of methodological, clinical and statistical heterogeneity indicated that the meta‐analysis was robust. Overall, this analysis found that ICC‐defined cachexia or WL ≥ 5% was associated with inferior survival in patients with NSCLC. Routine assessment of both weight and weight changes in the oncology clinic may help identify patients with NSCLC at risk for worse survival, better inform clinical decision‐making and assess eligibility for cachexia clinical trials.
Diseases of the musculoskeletal system, Human anatomy
Abstract Aims Knee osteoarthritis (KOA) is a common degenerative joint disease characterized by pain and functional limitations. Current treatments offer symptomatic relief but do not address the underlying pathology. This study explores the role of the infrapatellar fat pad (IFP) in KOA and evaluates the efficacy of its partial arthroscopic excision. Methods A retrospective review was conducted on 37 KOA patients who underwent partial IFP excision. Pain and function were assessed using the WOMAC and VAS scores, while MRI evaluations focused on cartilage health. Results Significant postoperative improvements were observed in both pain and functional outcomes, with substantial reductions in WOMAC and VAS scores (P < 0.001). MRI findings demonstrated notable enhancements in cartilage integrity, reflected in significantly improved WORMS scores (P < 0.001). Conclusions Partial excision of the IFP significantly reduces pain and improves function in KOA patients, while also promoting cartilage health. These findings support the IFP’s role in KOA pathology and highlight the potential benefits of targeted surgical intervention.
Orthopedic surgery, Diseases of the musculoskeletal system
Abstract Inflammatory reactions are involved in the development of steroid-induced osteonecrosis of the femoral head(ONFH). Studies have explored the therapeutic efficacy of inhibiting inflammatory reactions in steroid-induced ONFH and revealed that inhibiting inflammation may be a new strategy for preventing the development of steroid-induced ONFH. Exosomes derived from M2 macrophages(M2-Exos) display anti-inflammatory properties. This study aimed to examine the preventive effect of M2-Exos on early-stage steroid-induced ONFH and explore the underlying mechanisms involved. In vitro, we explored the effect of M2-Exos on the proliferation and osteogenic differentiation of bone marrow-derived mesenchymal stem cells(BMMSCs). In vivo, we investigated the role of M2-Exos on inflammation, osteoclastogenesis, osteogenesis and angiogenesis in an early-stage rat model of steroid-induced ONFH. We found that M2-Exos promoted the proliferation and osteogenic differentiation of BMMSCs. Additionally, M2-Exos effectively attenuated the osteonecrotic changes, inhibited the expression of proinflammatory mediators, promoted osteogenesis and angiogenesis, reduced osteoclastogenesis, and regulated the polarization of M1/M2 macrophages in steroid-induced ONFH. Taken together, our data suggest that M2-Exos are effective at preventing steroid-induced ONFH. These findings may be helpful for providing a potential strategy to prevent the development of steroid-induced ONFH.
Orthopedic surgery, Diseases of the musculoskeletal system
The medical domain is vast and diverse, with many existing embedding models focused on general healthcare applications. However, these models often struggle to capture a deep understanding of diseases due to their broad generalization across the entire medical field. To address this gap, I present DisEmbed, a disease-focused embedding model. DisEmbed is trained on a synthetic dataset specifically curated to include disease descriptions, symptoms, and disease-related Q\&A pairs, making it uniquely suited for disease-related tasks. For evaluation, I benchmarked DisEmbed against existing medical models using disease-specific datasets and the triplet evaluation method. My results demonstrate that DisEmbed outperforms other models, particularly in identifying disease-related contexts and distinguishing between similar diseases. This makes DisEmbed highly valuable for disease-specific use cases, including retrieval-augmented generation (RAG) tasks, where its performance is particularly robust.
Objective: Our objective is to develop and validate TrajVis, an interactive tool that assists clinicians in using artificial intelligence (AI) models to leverage patients' longitudinal electronic medical records (EMR) for personalized precision management of chronic disease progression. Methods: We first perform requirement analysis with clinicians and data scientists to determine the visual analytics tasks of the TrajVis system as well as its design and functionalities. A graph AI model for chronic kidney disease (CKD) trajectory inference named DEPOT is used for system development and demonstration. TrajVis is implemented as a full-stack web application with synthetic EMR data derived from the Atrium Health Wake Forest Baptist Translational Data Warehouse and the Indiana Network for Patient Care research database. A case study with a nephrologist and a user experience survey of clinicians and data scientists are conducted to evaluate the TrajVis system. Results: The TrajVis clinical information system is composed of four panels: the Patient View for demographic and clinical information, the Trajectory View to visualize the DEPOT-derived CKD trajectories in latent space, the Clinical Indicator View to elucidate longitudinal patterns of clinical features and interpret DEPOT predictions, and the Analysis View to demonstrate personal CKD progression trajectories. System evaluations suggest that TrajVis supports clinicians in summarizing clinical data, identifying individualized risk predictors, and visualizing patient disease progression trajectories, overcoming the barriers of AI implementation in healthcare. Conclusion: TrajVis bridges the gap between the fast-growing AI/ML modeling and the clinical use of such models for personalized and precision management of chronic diseases.
The rising prevalence of vision-threatening retinal diseases poses a significant burden on the global healthcare systems. Deep learning (DL) offers a promising solution for automatic disease screening but demands substantial data. Collecting and labeling large volumes of ophthalmic images across various modalities encounters several real-world challenges, especially for rare diseases. Here, we introduce EyeDiff, a text-to-image model designed to generate multimodal ophthalmic images from natural language prompts and evaluate its applicability in diagnosing common and rare diseases. EyeDiff is trained on eight large-scale datasets using the advanced latent diffusion model, covering 14 ophthalmic image modalities and over 80 ocular diseases, and is adapted to ten multi-country external datasets. The generated images accurately capture essential lesional characteristics, achieving high alignment with text prompts as evaluated by objective metrics and human experts. Furthermore, integrating generated images significantly enhances the accuracy of detecting minority classes and rare eye diseases, surpassing traditional oversampling methods in addressing data imbalance. EyeDiff effectively tackles the issue of data imbalance and insufficiency typically encountered in rare diseases and addresses the challenges of collecting large-scale annotated images, offering a transformative solution to enhance the development of expert-level diseases diagnosis models in ophthalmic field.
Catarina Botelho, Alberto Abad, Tanja Schultz
et al.
Speech is a rich biomarker that encodes substantial information about the health of a speaker, and thus it has been proposed for the detection of numerous diseases, achieving promising results. However, questions remain about what the models trained for the automatic detection of these diseases are actually learning and the basis for their predictions, which can significantly impact patients' lives. This work advocates for an interpretable health model, suitable for detecting several diseases, motivated by the observation that speech-affecting disorders often have overlapping effects on speech signals. A framework is presented that first defines "reference speech" and then leverages this definition for disease detection. Reference speech is characterized through reference intervals, i.e., the typical values of clinically meaningful acoustic and linguistic features derived from a reference population. This novel approach in the field of speech as a biomarker is inspired by the use of reference intervals in clinical laboratory science. Deviations of new speakers from this reference model are quantified and used as input to detect Alzheimer's and Parkinson's disease. The classification strategy explored is based on Neural Additive Models, a type of glass-box neural network, which enables interpretability. The proposed framework for reference speech characterization and disease detection is designed to support the medical community by providing clinically meaningful explanations that can serve as a valuable second opinion.
Rare diseases pose significant challenges in diagnosis and treatment due to their low prevalence and heterogeneous clinical presentations. Unstructured clinical notes contain valuable information for identifying rare diseases, but manual curation is time-consuming and prone to subjectivity. This study aims to develop a hybrid approach combining dictionary-based natural language processing (NLP) tools with large language models (LLMs) to improve rare disease identification from unstructured clinical reports. We propose a novel hybrid framework that integrates the Orphanet Rare Disease Ontology (ORDO) and the Unified Medical Language System (UMLS) to create a comprehensive rare disease vocabulary. The proposed hybrid approach demonstrates superior performance compared to traditional NLP systems and standalone LLMs. Notably, the approach uncovers a significant number of potential rare disease cases not documented in structured diagnostic records, highlighting its ability to identify previously unrecognized patients.