SearcharxivSearch

arXiv subjects

Spiros Denaxas

Publications and source records attributed to Spiros Denaxas.

15 recordsLinked to original sources

Learning Human Health and Diseases from 24-hour Wrist Movement

Much of human health and function unfolds beyond the clinic, through the movements of everyday life. Wrist-worn accelerometers capture these movements continuously, yet their rich signals are often reduced to a small set of predefined behavioural summary measures. Here, we present Sensori, a self-supervised foundation model that learns general-purpose health representations directly from 24 hours of raw tri-axial wrist movement. We developed and evaluated the model across four population-based cohorts from the United Kingdom, China and the United States, comprising 122,640 participants contributing 683,617 person-days of free-living recordings. Sensori condensed each day of movement into a representation that captured diverse movement behaviours, demographic characteristics, health axes and physical function. Evaluation in independent cohorts showed that these representations generalised across populations and measurement settings without retraining. When added to common clinical covariates, Sensori significantly improved prevalent disease classification for 52 of 102 eligible conditions (median delta AUROC, 0.060; range, 0.012-0.242) and incident disease risk prediction for 26 of 87 eligible conditions (median delta Uno's C-index, 0.064; range, 0.025-0.172), with the largest gains for neurological and psychiatric disorders. These findings establish 24-hour wrist movement as a rich and scalable source of health information, with the potential to support passive health monitoring and disease prediction at population scale.

cs.LG

Foresight-England: Development of a National-Scale Generative AI Model of Electronic Health Records for Medical Event Prediction across the COVID-19 Pandemic

Foresight-England (Foresight-E) is the first national-scale generative foundation model of electronic health records (EHRs), developed as a research pilot strictly for COVID-19 research. We evaluated its ability to model the direct and indirect effects of the pandemic. Trained from scratch entirely within the NHS England Secure Data Environment, Foresight-E is a 243-million-parameter transformer decoder. It was trained and evaluated on de-identified, longitudinal EHRs of approximately 61 million individuals, integrating primary/secondary care, death registrations, and COVID-19 data. Training and validation used a 90% subset (54.9 million) spanning November 2018 to December 2022; the remaining 10% (6.1 million) was held out for evaluation. Foresight-E models patient timelines autoregressively, predicting the next medical event given their prior history. At inference, it operates zero-shot, predicting any concept in its ~40,000-code vocabulary without task-specific training. Our tokenisation scheme retains the clinical granularity of ICD-10, OPCS-4, and SNOMED CT codes, jointly representing absolute and relative timing. We designed an evaluation framework for 30-day COVID-19 hospitalisation and mortality, including subgroup analyses by demographic factors and vaccination status. To assess generalisation to unseen future data and the pandemic's indirect effects, we tested the model on medical events from 2023 (beyond its training period), benchmarking against logistic regression and XGBoost. As detailed in the Project Status section, NHS England has paused access to data for the Foresight-E project, meaning quantitative results are currently unavailable. Instead, we share our strategy for tokenisation, architecture, training, inference, and evaluation as a methodological template and case study in the challenges of building population-scale EHR foundation models.

cs.LG

Nomenclature Ontology for Medical And Disease names (NOMAD): taxonomy of types and origins of disease names

The nomenclature of human disease has developed organically over the past centuries using Greek, Latin, and Arabic terminology and reflects the idiosyncrasies of different eras of medical discovery. Despite evident heterogeneity in naming practices, no systematic framework exists for characterising these conventions across all diseases. In this paper, we describe the Nomenclature Ontology for Medical And Disease names (NOMAD), a meta-taxonomy that classifies disease names according to their naming conventions. We developed a two-level taxonomy comprising 9 top-level categories and 20 subcategories and applied it to 22,548 index entries from the ICD-10-CM 2026 Alphabetical Index in a scalable three-stage machine learning-driven classification pipeline. Classification was multi-label, reflecting the compositional nature of medical nomenclature. We classified 99.1% of terms with a mean of 2.12 labels per entry. Anatomical categories were the most prevalent (63.8% of entries), followed by Descriptive (48.4%) and Pathophysiological (40.2%), while Eponymous and Geographical labels were less common than their cultural prominence might suggest (9.7% and 1.9% respectively). Among all Eponymous diseases, we identified only 57 (2.6%) of diseases named after a female person. We manually reviewed a random sample of n=2,255 entries (10%) for accuracy and calculated a full agreement rate of 70% and partial agreement rate of 26% (macro-averaged Cohen's Kappa score 0.832). Naming convention profiles varied substantially across ICD-10-CM chapters, reflecting specialty-specific epistemological traditions: infectious disease chapters were dominated by etiological labels and showed the highest proportion of geographical region related labels, the circulatory chapter by anatomical and pathophysiological labels, and mental and behavioural disorders showed the highest prevalence of socio-behavioral labels.

cs.IR

AutoForest: Automatically Generating Forest Plots from Biomedical Studies with End-to-End Evidence Extraction and Synthesis

Systematic reviews rely on forest plots to synthesise quantitative evidence across biomedical studies, but generating them remains a fragmented and labour-intensive process. Researchers must interpret complex clinical texts, manually extract outcome data from trials, define appropriate interventions and comparators, harmonise inconsistent study designs, and carry out meta-analytic computations-typically using specialised software that demands structured inputs and domain expertise. While recent work has demonstrated that large language models can extract study-level data from unstructured text, no existing system automates the complete pipeline from raw documents to synthesised forest plots. To address this gap, we introduce AutoForest, the first end-to-end system that generates publication-ready forest plots directly from biomedical papers. Given one or more study papers, AutoForest automatically suggests ICO (Intervention, Comparator, Outcome) elements, extracts outcome data, performs statistical synthesis, and renders the final forest plot. We describe the system architecture, user interface and demonstrate its effectiveness on real-world examples through a user study involving clinicians, showing how AutoForest can accelerate evidence synthesis and substantially lower the barrier to conducting meta-analyses.

cs.CL

A vision for a colorectal digital twin that enables proactive and personalized disease management

Colorectal cancer, inflammatory bowel disease, and diverticular disease are progressive conditions that affect millions of individuals worldwide and impose substantial clinical and economic burdens. Early detection and personalized management are essential for slowing disease progression and improving patient outcomes. Current care pathways rely primarily on episodic clinical encounters, laboratory testing, and reactive interventions, limiting early detection and personalized longitudinal management. This paper introduces a conceptual framework for an integrated colorectal digital twin that supports non-invasive, continuous monitoring and personalized disease management. The framework integrates multimodal physiological and behavioral data streams, hybrid mechanistic-machine learning modeling of colorectal function, and a personalized artificial intelligence engine to support proactive disease management. Rather than presenting a deployed clinical system, this work outlines a clear vision and a structured approach for colorectal digital twins, identifying key technical, modeling, and translational challenges necessary for future implementation and validation.

cs.ET

Grounding Large Language Models in Clinical Evidence: A Retrieval-Augmented Generation System for Querying UK NICE Clinical Guidelines

This paper presents the development and evaluation of a Retrieval-Augmented Generation (RAG) system for querying the United Kingdom's National Institute for Health and Care Excellence (NICE) clinical guidelines using Large Language Models (LLMs). The extensive length and volume of these guidelines can impede their utilisation within a time-constrained healthcare system, a challenge this project addresses through the creation of a system capable of providing users with precisely matched information in response to natural language queries. The system's retrieval architecture, composed of a hybrid embedding mechanism, was evaluated against a corpus of 10,195 text chunks derived from three hundred guidelines. It demonstrates high performance, with a Mean Reciprocal Rank (MRR) of 0.814, a Recall of 81% at the first chunk and of 99.1% within the top ten retrieved chunks, when evaluated on 7901 queries. The most significant impact of the RAG system was observed during the generation phase. When evaluated on a manually curated dataset of seventy question-answer pairs, RAG-enhanced models showed substantial gains in performance. Faithfulness, the measure of whether an answer is supported by the source text, was increased by 64.7 percentage points to 99.5% for the RAG-enhanced O4-Mini model and significantly outperformed the medical-focused Meditron3-8B LLM, which scored 43%. Clinical evaluation by seven Subject Matter Experts (SMEs) further validated these findings, with GPT-4.1 achieving 98.7% accuracy while reducing unsafe responses by 67% compared to O4-Mini (from 3.0 to 1.0 per evaluator). This study thus establishes RAG as an effective, reliable, and scalable approach for applying generative AI in healthcare, enabling cost-effective access to medical guidelines.

cs.CL

Unlocking Electronic Health Records: A Hybrid Graph RAG Approach to Safe Clinical AI for Patient QA

Electronic health record (EHR) systems present clinicians with vast repositories of clinical information, creating a significant cognitive burden where critical details are easily overlooked. While Large Language Models (LLMs) offer transformative potential for data processing, they face significant limitations in clinical settings, particularly regarding context grounding and hallucinations. Current solutions typically isolate retrieval methods focusing either on structured data (SQL/Cypher) or unstructured semantic search but fail to integrate both simultaneously. This work presents MediGRAF (Medical Graph Retrieval Augmented Framework), a novel hybrid Graph RAG system that bridges this gap. By uniquely combining Neo4j Text2Cypher capabilities for structured relationship traversal with vector embeddings for unstructured narrative retrieval, MediGRAF enables natural language querying of the complete patient journey. Using 10 patients from the MIMIC-IV dataset (generating 5,973 nodes and 5,963 relationships), we generated enough nodes and data for patient level question answering (QA), and we evaluated this architecture across varying query complexities. The system demonstrated 100\% recall for factual queries which means all relevant information was retrieved and in the output, while complex inference tasks achieved a mean expert quality score of 4.25/5 with zero safety violations. These results demonstrate that hybrid graph-grounding significantly advances clinical information retrieval, offering a safer, more comprehensive alternative to standard LLM deployments.

cs.CL

Diffsurv: Differentiable sorting for censored time-to-event data

Survival analysis is a crucial semi-supervised task in machine learning with numerous real-world applications, particularly in healthcare. Currently, the most common approach to survival analysis is based on Cox's partial likelihood, which can be interpreted as a ranking model optimized on a lower bound of the concordance index. This relation between ranking models and Cox's partial likelihood considers only pairwise comparisons. Recent work has developed differentiable sorting methods which relax this pairwise independence assumption, enabling the ranking of sets of samples. However, current differentiable sorting methods cannot account for censoring, a key factor in many real-world datasets. To address this limitation, we propose a novel method called Diffsurv. We extend differentiable sorting methods to handle censored tasks by predicting matrices of possible permutations that take into account the label uncertainty introduced by censored samples. We contrast this approach with methods derived from partial likelihood and ranking losses. Our experiments show that Diffsurv outperforms established baselines in various simulated and real-world risk prediction scenarios. Additionally, we demonstrate the benefits of the algorithmic supervision enabled by Diffsurv by presenting a novel method for top-k risk prediction that outperforms current methods.

cs.LG

Phenotyping with Positive Unlabelled Learning for Genome-Wide Association Studies

Identifying phenotypes plays an important role in furthering our understanding of disease biology through practical applications within healthcare and the life sciences. The challenge of dealing with the complexities and noise within electronic health records (EHRs) has motivated applications of machine learning in phenotypic discovery. While recent research has focused on finding predictive subtypes for clinical decision support, here we instead focus on the noise that results in phenotypic misclassification, which can reduce a phenotypes ability to detect associations in genome-wide association studies (GWAS). We show that by combining anchor learning and transformer architectures into our proposed model, AnchorBERT, we are able to detect genomic associations only previously found in large consortium studies with 5$\times$ more cases. When reducing the number of controls available by 50\%, we find our model is able to maintain 40\% more significant genomic associations from the GWAS catalog compared to standard phenotype definitions. \keywords{Phenotyping \and Machine Learning \and Semi-Supervised \and Genetic Association Studies \and Biological Discovery}

stat.AP

How to estimate the association between change in a risk factor and a health outcome?

Estimating the effect of a change in a particular risk factor and a chronic disease requires information on the risk factor from two time points; the enrolment and the first follow-up. When using observational data to study the effect of such an exposure (change in risk factor) extra complications arise, namely (i) when is time zero? and (ii) which information on confounders should we account for in this type of analysis? From enrolment or the 1st follow-up? Or from both?. The combination of these questions has proven to be very challenging. Researchers have applied different methodologies with mixed success, because the different choices made when answering these questions induce systematic bias. Here we review these methodologies and highlight the sources of bias in each type of analysis. We discuss the advantages and the limitations of each method ending by making our recommendations on the analysis plan.

stat.ME

Selective recruitment designs for improving observational studies using electronic health records

Large scale electronic health records (EHRs) present an opportunity to quickly identify suitable individuals in order to directly invite them to participate in an observational study. EHRs can contain data from millions of individuals, raising the question of how to optimally select a cohort of size n from a larger pool of size N. In this paper we propose a simple selective recruitment protocol that selects a cohort in which covariates of interest tend to have a uniform distribution. We show that selectively recruited cohorts potentially offer greater statistical power and more accurate parameter estimates than randomly selected cohorts. Our protocol can be applied to studies with multiple categorical and continuous covariates. We apply our protocol to a numerically simulated prospective observational study using an EHR database of stable acute coronary disease patients from 82,089 individuals in the U.K. Selective recruitment designs require a smaller sample size, leading to more efficient and cost-effective studies.

stat.AP

Application of Clinical Concept Embeddings for Heart Failure Prediction in UK EHR data

Electronic health records (EHR) are increasingly being used for constructing disease risk prediction models. Feature engineering in EHR data however is challenging due to their highly dimensional and heterogeneous nature. Low-dimensional representations of EHR data can potentially mitigate these challenges. In this paper, we use global vectors (GloVe) to learn word embeddings for diagnoses and procedures recorded using 13 million ontology terms across 2.7 million hospitalisations in national UK EHR. We demonstrate the utility of these embeddings by evaluating their performance in identifying patients which are at higher risk of being hospitalised for congestive heart failure. Our findings indicate that embeddings can enable the creation of robust EHR-derived disease risk prediction models and address some the limitations associated with manual clinical feature engineering.

cs.CL

Evaluation of Semantic Web Technologies for Storing Computable Definitions of Electronic Health Records Phenotyping Algorithms

Electronic Health Records are electronic data generated during or as a byproduct of routine patient care. Structured, semi-structured and unstructured EHR offer researchers unprecedented phenotypic breadth and depth and have the potential to accelerate the development of precision medicine approaches at scale. A main EHR use-case is defining phenotyping algorithms that identify disease status, onset and severity. Phenotyping algorithms utilize diagnoses, prescriptions, laboratory tests, symptoms and other elements in order to identify patients with or without a specific trait. No common standardized, structured, computable format exists for storing phenotyping algorithms. The majority of algorithms are stored as human-readable descriptive text documents making their translation to code challenging due to their inherent complexity and hinders their sharing and re-use across the community. In this paper, we evaluate the two key Semantic Web Technologies, the Web Ontology Language and the Resource Description Framework, for enabling computable representations of EHR-driven phenotyping algorithms.

cs.AI

Evaluating openEHR for storing computable representations of electronic health record phenotyping algorithms

Electronic Health Records (EHR) are data generated during routine clinical care. EHR offer researchers unprecedented phenotypic breadth and depth and have the potential to accelerate the pace of precision medicine at scale. A main EHR use-case is creating phenotyping algorithms to define disease status, onset and severity. Currently, no common machine-readable standard exists for defining phenotyping algorithms which often are stored in human-readable formats. As a result, the translation of algorithms to implementation code is challenging and sharing across the scientific community is problematic. In this paper, we evaluate openEHR, a formal EHR data specification, for computable representations of EHR phenotyping algorithms.

q-bio.QM

A novel framework for assessing metadata quality in epidemiological and public health research settings

Metadata are critical in epidemiological and public health research. However, a lack of biomedical metadata quality frameworks and limited awareness of the implications of poor quality metadata renders data analyses problematic. In this study, we created and evaluated a novel framework to assess metadata quality of epidemiological and public health research datasets. We performed a literature review and surveyed stakeholders to enhance our understanding of biomedical metadata quality assessment. The review identified 11 studies and nine quality dimensions; none of which were specifically aimed at biomedical metadata. 96 individuals completed the survey; of those who submitted data, most only assessed metadata quality sometimes, and eight did not at all. Our framework has four sections: a) general information; b) tools and technologies; c) usability; and d) management and curation. We evaluated the framework using three test cases and sought expert feedback. The framework can assess biomedical metadata quality systematically and robustly.

cs.DL