Journal of Biomedical Informatics

Longitudinal electronic health records (EHRs) contain rich information about the evolution of a patient's clinical state, but temporal measurements and events are often represented using summary statistics or complex learned representations that can be difficult to interpret clinically. We propose an interpretable trajectory-based feature representation that transforms heterogeneous longitudinal EHR data into compact, human-readable predictive features. Numerical temporal variables are represented by trajectory states such as INCREASING, DECREASING, and STABLE, while categorical clinical events are represented by interpretable states describing repeated occurrence, stability, or change. These trajectory features are combined with static patient and encounter characteristics and evaluated using L1-regularized logistic regression, which provides sparse feature selection and direct identification of positive and negative predictive features. The approach is evaluated using MIMIC-IV in two clinically distinct prediction tasks: in- hospital mortality following ICU admission and hospital readmission within 30 days after discharge. For ICU mortality, multiple observation windows ranging from 1 to 48 hours are investigated to examine how the availability of longitudinal information affects prediction and the relative contribution of trajectory features. The highest AUROC of 0.8751 is obtained with a 32-hour observation window. For 30-day readmission, trajectories from the final 72 hours of the index hospitalization are evaluated using both three-state and five-state categorical representations. The two representations produce essentially identical discriminative performance (AUROC 0.6875 and 0.6876, respectively), indicating that increasing trajectory granularity provides little predictive benefit in this setting. The results demonstrate that heterogeneous longitudinal EHR observations can be transformed into compact and directly interpretable temporal features while retaining useful predictive information. The proposed framework therefore provides a simple and model-compatible approach for identifying clinically interpretable patterns of patient evolution and can be extended with more detailed trajectory definitions or applied with other predictive models.

Background and Objective: Early and reliable disease prediction from structured clinical data remains challenging when datasets are small, highly imbalanced, and contain limited positive disease cases. Conventional machine learning (ML) and deep learning approaches often struggle to capture clinically meaningful relationships under such low-data representation conditions due to weak statistical associations between features and prediction targets. This study proposes a clinically grounded GPT2-based table-to-text framework for disease prediction using structured healthcare datasets, motivated by the contextual reasoning capability of GPT models to better capture clinically meaningful relationships when statistical learning alone becomes insufficient due to limited data availability. Methods & Materials: Structured clinical records were transformed into physician-style textual descriptions and enriched through GPT4-generated medical paraphrasing to improve minority-class representation while preserving clinical meaning. Both the original and generated clinical texts were used to fine-tune a GPT2 model across four public healthcare datasets, including heart disease, heart failure, chronic kidney disease, and thyroid cancer recurrence. Gradient-based explainable AI analysis was additionally incorporated to identify clinically important features influencing prediction outcomes. Results: The proposed framework demonstrated consistently strong predictive performance with average precision, specificity, sensitivity, and F1-score of 0.96, 0.97, 0.96, and 0.96, respectively. The model achieved improved sensitivity, stronger generalization, and more stable predictive behavior compared with traditional ML, deep learning, transformer-based, and GAN-augmented approaches. Importantly, the framework consistently emphasized clinically meaningful variables even under severe class imbalance where conventional ML and neural network models often struggled. Conclusions: The proposed GPT2-based table-to-text framework provides a practical and clinically interpretable approach for disease prediction from limited structured healthcare data. By integrating contextual clinical reasoning with explainable prediction mechanisms, the framework demonstrates strong potential for early risk detection, transparent clinical decision support, and reliable deployment in real-world low-resource healthcare environments.

Electronic health record (EHR)-linked cohorts support association, prediction, and causal studies using longitudinally measured markers of health. However, a lab biomarker measurement is recorded only when a patient first has a medical encounter (visit process) and, a clinician orders the corresponding test and the patient follows through (observation process). These two stages may induce informative presence (IP) and informative observation (IO), respectively. Yet their drivers remain largely uncharacterized, despite evidence that understanding this recording mechanism is essential for selecting appropriate strategies for downstream analysis that treat these markers as longitudinally measured outcomes. We characterize this two-stage recording hierarchy using a stochastic recurrent-event model for the outpatient visit process and a visit-process-weighted generalized estimating equation model for biomarker recording conditional on an outpatient visit. We characterize descriptors of both processes in three EHR-linked cohorts in the US (All of Us [AoU], n=599,423; Yale New Haven Health System [YNHHS], n=319,666; Michigan Genomics Initiative [MGI], n=82,372), reporting descriptive statistics for longitudinal visits and for a panel of 68 lab biomarkers commonly measured in EHRs. We conduct detailed model-based analyses of ten biomarkers spanning multiple domains: routine monitoring, general laboratory assessment, and symptom-triggered testing. These include glucose, hemoglobin A1c [HbA1c], creatinine, hemoglobin [Hgb], white blood cell count [WBC], low-density lipoprotein [LDL] and high-density lipoprotein [HDL] cholesterol, triglycerides, C-reactive protein [CRP], and thyroid-stimulating hormone [TSH]. Across the three cohorts, the median number of outpatient visits ranged from 1.7 to 6.1 per year over a median follow-up of 4.4 to 7.2 years. Among patients with at least one recorded measurement, the median within-person proportion of visits containing a given biomarker ranged from 0.4% to 19.5%, demonstrating that more frequent visits did not necessarily translate into greater per-visit biomarker capture. In the visit-process models, chronic disease burden, and a recent history of outpatient visits were consistently associated with higher visit rates across all three cohorts whereas associations with race, ethnicity, and neighborhood-level income varied across cohorts. In per-visit observation models, the association of covariates depended on the biomarker under consideration; for example, prior cancer diagnosis was associated with more frequent measurement of blood counts but with less frequent measurement of lipids. These findings provide a deeper understanding of how to model who seeks care and what is measured as two distinct recording processes in EHR. Our empirical findings show that the descriptors of these processes vary across cohorts and biomarkers, providing guidance on how to construct these models for downstream longitudinal analyses with irregular EHR visits.

Objective. To determine which model family a hospital should use to extract structured data (sections, medication records, laboratory tuples) from Russian/Kazakh stroke discharge summaries, bounded against measured human agreement. Materials and Methods. Three families were compared under identical inputs: a multilingual BERT-style encoder with CRF heads, a locally fine-tuned Qwen3-4B, and zero-shot GPT-5.5, on three tasks of increasing granularity: section segmentation (4,327 annotated documents), seven-field medication records (708 documents), and dated lab tuples (1,888 documents). All arms shared a block-ID representation (extraction as tagging over a fixed segmentation). Blind re-annotation of 50 documents per task provided the human-agreement ceiling; model-vs-ceiling claims use paired same-document tests with Holm correction. Results. On section segmentation all arms fall within {+/-}0.03 of the ceiling (0.905; models 0.919-0.932). On medication detection the cloud model is above it (0.966 vs 0.959); on full-record assembly, re-scored symmetrically against a blind annotator as common reference, both the fine-tuned LLM and the cloud model reach 0.344 agreement versus the gold annotator's 0.183. On lab assembly the fine-tuned LLM matches the full-tuple ceiling (0.898 vs 0.902) while the encoder is far below (0.476). Residual errors concentrate in annotation conventions the annotators themselves could not agree on. Discussion. Detection is solved at the human ceiling even for non-English clinical text, and a minutes-scale fine-tune reaches it with no data egress. Assembly separates the families and is convention-bound: benchmark consumers should read "above human agreement" against what the guidelines fixed. Conclusion. Annotation guidelines and task representation, not model capacity, are the binding constraints for this task family.

While Directed Acyclic Graphs (DAGs) are essential for causal inference, their construction often relies on expert heuristics, which bypasses systematic evidence synthesis and creates a critical "evidence retrieval gap" in causal modeling. This study introduces EpiKG2DAG, a framework that supports evidence-anchored candidate DAG generation by transforming unstructured biomedical abstracts into structured epidemiological associations. We utilized DeepSeek-V3 to extract exposure-outcome association triplets from 189,266 abstracts and employed SapBERT for semantic normalization against UMLS concepts. The resulting Epidemiological Knowledge Graph (EpiKG) enables the automated identification of candidate confounders, mediators, and colliders based on graph-theoretic motifs and literature-derived evidence. A case study on COVID-19 and AKI demonstrates that the framework uncovers non-obvious confounders, such as air pollution, while ensuring evidence traceability. This work contributes to the field by mitigating the knowledge-acquisition bottleneck and providing a transparent, reproducible foundation for evidence-based causal modeling.

Metabolic dysfunction-associated steatotic liver disease (MASLD) is highly prevalent among individuals with type 2 diabetes (T2D), yet accurate identification from electronic health records (EHRs) remains challenging because clinically relevant information is fragmented across structured data and unstructured clinical documentation. We developed a rule-based computable phenotype (CP) framework that integrates structured EHRs with clinical notes for scalable MASLD identification in patients with T2D. The framework comprises five complementary CP algorithms derived from validated fibrosis indices and liver injury biomarkers, together with a lightweight natural language processing module that identifies MASLD-related evidence using keyword matching, contextual filtering, and negation detection. The proposed framework was systematically evaluated across multiple threshold settings, with additional validation through age- and sex-stratified analyses and manual chart review. The findings demonstrate that integrating structured and unstructured EHR data provides an accurate and scalable framework for real-world MASLD phenotyping and offers a practical strategy for developing CPs for other chronic diseases.

Automatic coding from clinical notes has been studied extensively for International Classification of Diseases (ICD) codes, yet broad Current Procedural Terminology (CPT) and Healthcare Common Procedure Coding System (HCPCS) recommendation remains comparatively underexplored. Existing studies often focus on one specialty, a limited code vocabulary, or a single model family, leaving it unclear how different artificial intelligence (AI) paradigms perform under a common, clinically meaningful evaluation. We formulate CPT and HCPCS coding as an AI-assisted recommendation task in which a physician or professional coder reviews a short, ranked list of candidate codes supported by the clinical note. Using operative notes from Vanderbilt University Medical Center (VUMC) and discharge summaries from Medical Information Mart for Intensive Care IV (MIMIC-IV), we compare lexical retrieval, Clinical-Longformer, GPT-5.6-Sol, MedGemma-27B, and an inspectable agentic-style retrieve-and-verify system under a controlled review budget. Micro-averaged recall within a fixed number of recommendations measures whether reference codes reach the reviewable list; micro-F1 is reported only where reference labels are sufficiently complete. Zero-shot GPT-5.6-Sol achieves the highest recall within five and ten candidates: 0.717 and 0.800 on VUMC and lower-bound values of 0.689 and 0.738 on MIMIC-IV. The retrieve-and-verify system reaches 0.695 and 0.784 on VUMC and lower-bound values of 0.575 and 0.657 on MIMIC-IV, with a candidate-linked evidence window attached to each retained recommendation. Diagnostic analyses reveal distinct failure sources, including output-length underfilling, confusion among closely related codes, out-of-knowledge-base generation, and incomplete evidence support. These findings establish a systematic evaluation framework for procedure-code recommendation and identify practical requirements for future systems that are accurate, review-efficient, and grounded in clinical evidence.

Clinical decisions for determining optimal patient-specific interventions are complicated prediction tasks that rely on health care professionals' understanding of physiological mechanisms and their dynamics. These decisions are challenged by (a) observational data sparsity and (b) patient heterogeneity. Here, we focus on estimating and forecasting specific physiological properties--that are not explicitly present in clinical observations--to provide additional features using only data available bedside at the time of decision-making. Mechanistic models of physiological system(s), e.g., physiological ordinary differential equation (ODE) models, provide pathways to compensate for data sparsity by synchronizing the model with observations of an individual patient using data assimilation (DA). However, DA used in a standard computational workflow to estimate constant model parameters from presently-known data is less effective at optimizing state forecasts of the model governed by physiological processes that evolve before new observations are available. Stated simply, we cannot forecast the future evolution of the model because we cannot forecast model parameters. To support next-generation clinical decision support, we develop a new DA and machine learning (ML) hybrid pipeline to estimate and forecast individual future physiological processes by forecasting ODE model parameters. This pipeline overcomes model and DA workflow limitations by stacking a DA-estimated posterior empirical distribution of physiological parameters with longitudinal ML forecasting models. We work within the context of glycemic management in an ICU using EHR data to construct and test a use case. We use synthetic data and real-world clinical data to validate the integrated pipeline and quantify uncertainties.

De-identifying temporal protected health information (PHI) is challenging because temporal expressions appear in diverse formats and must be transformed while preserving clinically meaningful timelines. This study proposes and evaluates an LLM-based framework for temporal PHI de-identification in real-world clinical notes. Using 1,148 notes from 30 sarcoma patients (28,431 annotated temporal entities), we evaluated multiple modern LLMs for temporal entity extraction and surrogate generation. Proprietary models achieved strong extraction performance, with GPT-4o achieving the best overall results. Most models preserved temporal formatting (>99%), but surrogate generation remained challenging. GPT-5.4 achieved the highest shift correctness (90.2% on a shared-entity subset) and the lowest order violations. Error analysis revealed systematic shift deviations ({+/-}1, {+/-}30/31, {+/-}365 days), highlighting persistent limitations in LLM temporal reasoning. These findings suggest that reliable temporal de-identification will require hybrid or multi-agent approaches beyond standalone LLMs.

Biomedical artificial intelligence (AI) increasingly relies on heterogeneous data sources, yet differences in data structure, terminology, evidence quality, and provenance complicate their integration into reliable knowledge resources. Here, we develop an evidence-aware framework for processing and integrating heterogeneous pharmacovigilance data from FDA Adverse Event Reporting System (FAERS) reports, biomedical literature, clinical trials, and electronic health records in Mass General Brigham. The framework combines large language model (LLM)-based information extraction, ontology-driven semantic normalization, cross-source evidence assessment, statistical and machine learning-based prioritization, and ingredient-based adverse drug event (ADE) relationship inference to transform heterogeneous evidence into a structured and evidence-based knowledge resource. The constructed knowledge system contains 11,588 drug nodes, 44,843 ingredient nodes, 3,275 ADE nodes, 993 indication nodes, and more than 2.47 million relationships, with each drug-ADE relationship assigned a confidence score. We further developed a drug-level web interface for accessing the knowledge resource and validated its utility in downstream AI tasks. Specifically, incorporating the developed knowledge resource improved the comprehensiveness, relevance, and overall quality of LLM-based drug-specific ADE synthesis and improved the precision and F1 score of clinical ADE relation extraction. These results demonstrate that AI-assisted processing combined with evidence-aware curation can transform heterogeneous biomedical evidence into reusable, AI-ready knowledge with explicit provenance and evidence strength information. The framework provides a general strategy for integrating heterogeneous biomedical data to support reproducible knowledge construction and downstream biomedical AI applications.

Objectives: Searching a reference terminology such as SNOMED CT confronts two retrieval technologies of fundamentally opposite nature. Deterministic lexical matching is precise, order-independent and character-level, and lets a clinician refine a query incrementally, but it is confined to the wording and language of the curated descriptions. Learned semantic matching bridges paraphrase and language, but poorly represents abbreviations and partial, as-typed input. Their requirements and failure modes are so different that combining them naively can let the channel that is wrong for a given query degrade the one that is right. The conventional way to avoid adding a semantic channel at all has been to strengthen the lexical one (curating an additional local interface vocabulary so that more expressions match by surface form), but such vocabularies are labour-intensive to maintain and their quality degrades over time. We ask whether these two opposite paradigms can instead be made to *coexist* in one retrieval flow (each serving the input regime it is strong at, neither harming the other) over SNOMED CT's own curated descriptions, and study the query interpretation, rank fusion and re-ranking design that makes this coexistence safe. Materials and Methods: We implemented one reproducible instance of this architecture over the SNOMED CT International edition. It combines deterministic, order-independent multi-prefix search with three learned components: BioLORD-2023-M embeddings for semantic retrieval, an optional BGE cross-encoder for re-ranking, and a local LLM (gemma 4) for query normalization and structured clinical entity extraction. Lexical and semantic rankings are combined with Reciprocal Rank Fusion, and results can be constrained with a hierarchy (descendant) filter. As an external evaluation we measured search-only linking accuracy on 542 disease mentions from the DisTEMIST corpus (Spanish, zero-shot), resolving gold codes through SNOMED CT historical associations and ablating query pre-processing, re-ranking, and each retrieval channel in isolation; and, on a second corpus of English real-EHR discharge notes (the SNOMED CT Entity Linking Challenge, 12,897 mentions), we estimated field-scoped typeahead performance and tested a context-aware pre-process. Results: Illustrative tests showed complementary behaviour: the lexical and semantic paths resolved different query types, while LLM pre-processing supported cross-lingual and abbreviated input. On a search-only linking evaluation over 542 disease mentions from the DisTEMIST corpus (Spanish, zero-shot), the best and computationally cheapest configuration, semantic search with re-ranking and *no* LLM query pre-processing, placed the exact concept first for 60% of mentions (accuracy@1 = 0.60) and within the top-10 candidates a picker would show for 80% (recall@10 = 0.80). Because these search-only figures are computed on gold mention spans, they isolate normalization from mention detection and are not directly comparable to the DisTEMIST shared task's end-to-end scores. LLM query pre-processing helped dirty, lay input but slightly hurt clean terminology-like queries, and a near-miss analysis showed that many remaining cases retrieved a parent or child of the intended concept. Isolating the channels showed the two coexist without a trade-off: on this clean-normalization corpus the semantic channel carried the accuracy and adding the lexical channel neither helped nor harmed it (accuracy@1 0.60 vs 0.61), because rank fusion followed by re-ranking suppresses whichever channel is off-task; the lexical channel's own strength, partial as-typed input, is a regime this corpus does not test. On the English real-EHR corpus, a field-scoped typeahead (each query constrained to its entry field's domain) placed the concept on the top-10 picker list for 73% of 12,897 mentions across all clinical domains (accuracy@1 0.52; findings 0.54, close to DisTEMIST). Most residual errors were soft (the gold on the list but not first, or a hierarchical neighbour); the hard misses were dominated by ambiguous EHR shorthand, and a single context-aware pre-processing call (normalizing a mention with its surrounding note text) roughly doubled recovery of those hard misses, though, as with LLM normalization on the clean terms of DisTEMIST, applying it to every mention slightly lowered overall accuracy by perturbing the easy majority, so it is best used as a selective rescue. Results are specific to the evaluated configuration, not an architecture-independent estimate. Discussion: The findings support the technical feasibility of a reference architecture that computes additional access routes over SNOMED CT's curated descriptions, and indicate that making the lexical and semantic paradigms *coexist*, rather than choosing between them, is what makes those computed routes safe to add. This shifts rather than eliminates maintenance, from local phrase authoring toward governance and validation of retrieval services. Conclusion: Hybrid concept retrieval lets lexical precision and semantic flexibility coexist over SNOMED CT's maintained descriptions without a trade-off between them, offering an implementation pattern that may reduce additional local lexical curation where direct search is appropriate, while curated interface vocabularies remain useful in selected guided workflows.

Symbolic clinical natural language processing (NLP) systems remain widely used for extracting clinical concepts from electronic health record (EHR) narratives, but maintaining rule resources requires extensive manual error analysis and rule refinement. This study investigates whether large language models (LLMs) can assist in identifying extraction errors and generating candidate rules to improve symbolic clinical NLP systems. Using error reports derived from a multi-site evaluation of a previously validated symbolic model for cognitive and neuropsychiatric-related clinical concepts, we developed a human-in-the-loop framework, REFINE. The framework first uses LLMs to classify extraction errors and generate explanatory reasoning, which can then be incorporated into prompts for rule generation. Three LLMs (GPT-5.2, GPT-4o, GPT-4o-mini) were evaluated under four prompting conditions. LLM-generated rule sets improved performance compared with the baseline NLP-CAM system, increasing F1-score from 0.37 to 0.58. These findings suggest that LLMs can support scalable rule refinement for symbolic clinical NLP systems.

Electronic health records provide a source of real-world information for disease risk prediction, but many machine learning models learn implicit associations that are difficult to inspect or use for clinical reasoning. Causal Bayesian networks (CBNs) offer a form of causal-interpretable machine learning by representing conditional dependencies, putative directional relations, and probabilistic evidence propagation in a directed acyclic graph. However, conventional CBN structure learning becomes unstable and computationally expensive when applied to large-scale EHR data. To address this limitation, we propose UPEBNL, a scalable framework for causal-interpretable cancer prescreening based on parallel CBN learning. UPEBNL integrates adaptive data slicing, quality-aware structure aggregation, and global DAG construction to learn stable and interpretable dependency structures from large-scale observational data. We evaluated UPEBNL in high-dimensional and multi-million-sample simulations and applied it to EHR-based prescreening for esophageal and colorectal cancer. In simulations, UPEBNL improved structural recovery accuracy by nearly 40% and achieved up to a 221.28-fold speedup over conventional CBN learning strategies. For cancer risk prediction, the learned CBNs provided interpretable evidence paths and achieved validation AUCs of 0.8171 for esophageal cancer and 0.784 for colorectal cancer. Calibration and decision curve analyses further supported the reliability and clinical utility of the models. These findings suggest that scalable CBN learning can support interpretable cancer prescreening from large-scale EHR data.

Background: Free-text notes in electronic health records (EHRs) contain fine-grained psychiatric information that is essential for psychiatric research and clinical care, and often absent or under-recorded in structured codes alone. Clinical natural language processing (cNLP) can support extraction of this information from EHR notes, yet Spanish-language cNLP remains under-developed. Moreover, broad evaluations comparing multiple encoder-based language models across extensive, fine-grained psychiatric concept sets remain scarce, and it remains unclear how these models compare with traditional NLP (tNLP) systems and much larger generative large language models (LLMs). In addition, cross-site performance of fine-tuned models is rarely tested, and limited annotated training data remains a major challenge, especially for rare symptoms. Objectives: We aimed to advance scalable, global psychiatric cNLP by fine-tuning multiple encoder-based models with differing architectures and pre-training strategies for detecting fine-grained psychiatric concepts in Spanish EHRs. We further evaluated the impact of augmenting the fine-tuning data with precision-weighted weak labels for less-frequent concepts, and compared the performance of the encoder-based models to that of tNLP and a fine-tuned generative LLM trained on the same data. Finally, we evaluated model cross-site generalizability on an external EHR dataset. Methods: Three encoder-based models (BETO, XLM-RoBERTa-large, and bsc-bio-ehr-es) were fine-tuned on 1,642 clinician-annotated EHR documents from Colombia to detect 110 psychiatric concepts in Spanish text. To address the limited annotated examples available for less-frequent concepts, 12,000 additional documents were weakly-labeled for less-frequent concepts using tNLP, and incorporated into the fine-tuning data with labels weighted by pattern precision. Models were compared with tNLP and a generative LLM, and evaluated on an external EHR dataset from another psychiatric hospital in Colombia. Results: Encoder model performance varied substantially, with macro-F1 ranging from 0.64 to 0.81. BETO achieved the highest macro-F1 (0.81; median F1=0.88 [IQR=0.77-0.96]). Adding precision-weighted weak labels for less-frequent concepts improved BETO's overall macro-F1 to 0.83 and increased mean F1 for the 55 augmented concepts from 0.82 to 0.86. Under matched fine-tuning conditions, fine-tuned BETO and the tNLP method were equivalent in F1, whereas the LLM significantly outperformed BETO in F1. After weak-label augmentation, BETO significantly outperformed tNLP in F1 (PFDR<.001) and narrowed the performance gap with the LLM, although equivalence was not established. Lastly, fine-tuned BETO maintained reasonably strong performance on data from an external hospital not used for model fine-tuning (out-of-domain macro-F1=0.78). Conclusions: General-purpose pre-trained encoders had strong performance for psychiatric concept extraction from Spanish EHRs. Weak-label augmentation improved BETO's performance and strengthened results relative to a tNLP baseline, while reducing, but not eliminating, the performance gap with a much larger fine-tuned generative LLM. These findings highlight the utility of these relatively lightweight models for scalable, accurate and reproducible detection of psychiatric concepts in Spanish-language EHRs.

Objective: Taking a blood pressure medication is not a single fact but a trajectory of fills, gaps, and regimen changes. Dispensing records capture that trajectory, yet risk calculators reduce it to a yes/no treatment indicator and quality programs to proportion of days covered (PDC). We asked how much of that discarded signal is recoverable. Materials and Methods: We studied 7,625 adults treated for hypertension using linked electronic health record and pharmacy dispensing data. From a 1-year medication-history window, we predicted 3-year myocardial infarction, stroke, or all-cause death. Holding cohort, covariates, horizon, and validation fixed, we compared PDC, engineered temporal and regimen features, and the ordered fill sequence modeled with an attention-based bidirectional LSTM survival network. Factorial analyses separated representation from model class. Results: C-index increased from 0.7113 with clinical factors alone to 0.7131 with PDC, 0.7273 with engineered summaries, and 0.7396 with the ordered sequence ({Delta}C=0.0283; 95% CI, 0.0189-0.0382). The sequence exceeded engineered summaries by 0.0123 (0.0040-0.0202). Richer representations improved discrimination by 0.0181-0.0191, approximately three times the 0.0059-0.0078 from changing model class. Among patients with PDC [&ge;]0.80, PDC ranked risk poorly (C=0.4628), whereas sequence-model strata had 3-year event rates of 3.6%-22.8%. Discussion: A medication history's prognostic value lies in its temporal structure, which aggregate adherence measures discard, so the sequence advantage reflects preserved information rather than model complexity. External validation is needed. Conclusion: Traditional metrics of antihypertensive treatment conceal substantial risk heterogeneity, whereas a tokenized dispensing timeline recovers a prognostic treatment signature that improves cardiovascular risk prediction from existing records.

Diagnostic errors, including misdiagnoses and delayed clinical diagnoses, could affect outcomes of a significant patient population, particularly individuals presenting with rare diseases or non-specific symptoms. From rule-based diagnostic decision supporting systems (DDSS) to large language model (LLM) based tools for clinical reasoning have been developed to address these limitations. However, existing DDSS are often proprietary and difficult to integrate, and recent LLM-based tools remain hindered by operational challenges such as cost, resources constraint, and privacy concerns. Moreover, existing systems interpret electronic medical records (EMR) and generate diagnoses separately, limiting continuous evidence-based analysis and imposing repeated clinician involvement. In this paper, we present DDx-Finder, an open-source framework that leverages Model Context Protocol (MCP) servers for direct EMR and literature access, enabling prompt-driven clinical state extraction and reliable case-report re- trieval via generating searching query by LLM, while addressing limitations related to resource demands and privacy concerns. A clinical case study demonstrates the systems feasibility and its potential to provide accessible, transparent, and systematic differential diagnostic support for complex cases.

Background: Clinical terminology pipelines must first extract candidate spans from narrative notes and then determine whether those spans map to existing concepts or warrant further review. Evaluation is difficult because span boundaries vary between annotators and because downstream decisions depend on the terminology evidence retrieved for each span. Objective: We evaluated clinical concept extraction, terminology linking across controlled evidence conditions, and ontology-extension triage for terms that remained unmatched after initial terminology screening. Methods: We conducted 3 complementary pilot evaluations that used distinct units of analysis and were analyzed separately. Study 1 compared 5 automated extraction pipelines and a union-merge analysis with 2 human annotation sets in 66 deidentified clinical notes from 3 health systems. Agreement was evaluated by exact string matching and BGE-large-en-v1.5 embedding matching. Study 2 evaluated 56 clinical spans, including 28 with reference Unified Medical Language System concepts and 28 adjudicated as unsuitable for ontology extension, under complete retrieval, matched-concept masking, and large language model-only inference, yielding 168 span-condition outputs. The graph retrieval pipeline used BGE-large-en-v1.5 embeddings, and the decision model was Gemma 3 27B. Study 3 applied full vector retrieval to 84 terms previously not matched in either UMLS or BioPortal. Results: In Study 1, interannotator exact-match F1 was 0.29 and embedding-match F1 was 0.75. Automated exact-match F1 scores ranged from 0.07 to 0.17; embedding-match F1 was highest for MedGemma (0.55), followed by Gemma (0.53), sci_md and SciBERT (each 0.43), and Llama 3.3 (0.32). In Study 2, complete retrieval returned a reference-matched link for 28/28 known-concept spans (100%; 95% CI, 87.9%-100%). Masking assigned POSSIBLE_CANDIDATES to all 28; large language model-only inference assigned POSSIBLE_CANDIDATES to 25/28 (89.3%) and LINKED to 3/28 (10.7%). Across the 3 evidence conditions, the same 12/28 unsuitable-extension spans were classified as NOT_MEANINGFUL (42.9%) and the same 16/28 as POSSIBLE_CANDIDATES (57.1%). In Study 3, the pipeline assigned PLAUSIBLE_EXISTING_CONCEPT to all 84 terms, none was flagged for extension, and top-candidate similarity averaged 0.914 (SD 0.027); extension status was not independently adjudicated. Conclusions: Measured extraction performance varied substantially by matching definition, whereas exact-link decisions varied with the availability of matched terminology evidence. In the follow-up sample, initial nonmatching did not establish ontology novelty: after semantic retrieval, the pipeline classified all 84 terms as plausible existing concepts and proposed none for extension. These findings support separate evaluation of extraction, retrieval, evidence-grounded linking, and extension candidacy.

Tabular synthetic data generation (SDG) can facilitate research and development in the health domain, as access to health data is restricted. To accommodate for its structural complexity, such as multimodal distributions and fragmentation, transformer models provides an alternative to conventional SDG methods since they are better equipped to infer global spatial coherence due to textual context of tabular records. However, methods for optimising their adaption to tabular SDG are still largely unexplored. We contribute to the understanding of transformer-based SDG by evaluating fidelity and privacy of three prompting regimes, zero shot, one shot and few shot training, for tabular health SDG using small transformer models. We evaluated llama 3.2 (1B and 3B parameters) and Phi (1.3B and 2.7B parameters), on a real clinical dataset. Our results showed that zero shot learning was less prone to hallucinations and performed overall better for fidelity, but at the loss of privacy in comparison to the other regimes. Our results showed no differences between model sizes and families. Future studies should extend the analysis to other models and datasets, and explore strategies to reduce hallucinations.

Background Clinical trials conducted in Germany are registered across multiple registries, including the German Clinical Trials Register (DRKS), ClinicalTrials.gov, the EU Clinical Trials Register (EUCTR), and, since 2023, the Clinical Trials Information System (CTIS). These registries record health conditions using different classification systems and terminologies, including ICD-10-GM, MeSH, MedDRA, and free text, making cross-registry analyses difficult. We developed and evaluated a pipeline for harmonizing trial condition descriptions to WHO ICD-10 and compared its performance with that of a large language model (LLM) and to health conditions coded by humans. Methods We developed a four-stage, registry-aware mapping pipeline consisting of: (i) condition mention extraction and normalization; (ii) classification of ICD-mappable versus non-mappable mentions; (iii) ontology-based candidate generation using UMLS links between MeSH, MedDRA, ICD-10-GM, and WHO ICD-10; and (iv) SapBERT-based semantic retrieval with hybrid confidence scoring. A second variant additionally applied cross-encoder reranking of the top candidate codes. A stratified sample of 500 condition mentions was manually coded to create an expert reference standard. GPT-4o was evaluated in parallel using the same structured decision framework as the human reviewers. Performance was assessed using accuracy, precision, F1 score, and Cohen's {kappa} at the three-character, block, and chapter levels of ICD-10. Results The pipeline was applied to 23,061 clinical trials and identified 39,512 ICD-mappable condition mentions, of which 72.4% received a high-confidence assignment. Against 390 expert-coded mentions, the baseline pipeline achieved 49.0% accuracy at the three-character ICD-10 level ({kappa} = 0.487), increasing to 58.7% at the chapter level ({kappa} = 0.561). The cross-encoder method produced small but consistent improvements across all evaluation levels. Candidate-recall analysis showed that the correct code was present in the retrieved candidate set in only 73.7% of cases. The LLM substantially outperformed both pipeline variants, achieving 96.7% accuracy and near-perfect agreement with expert coding ({kappa} = 0.966) at the three-character level. The LLM also assigned clinically plausible codes to 82.4% of rejected mentions, 62.8% of Tier-3 exclusions, and 92.3% of review-band mentions. Conclusion Automated harmonization of clinical trial condition data across heterogeneous registries is feasible and supports the use of a common ICD-10 framework for cross-registry analyses. The LLMs achieved high agreement with expert coding, and performed better than the deterministic ontology and embedding pipeline, which achieved moderate agreement. These findings indicate that LLMs can support analyses of the distribution of health conditions investigated in clinical trials in Germany.They are a promising tool for classification of other non-standardised trial characteristics in registries. Keywords: Clinical trial registries; ICD-10; disease harmonization; UMLS; entity linking; SapBERT; large language models; clinical research; natural language processing.

Objectives Transformer models for electronic health records require converting clinical data into token sequences, however standardized tokenization and evaluation frameworks are lacking. We introduce DBToken, an open-source library, and bits-per-row (BPR), a metric for comparing tokenization strategies. Materials and Methods DBToken accepts Medical Event Data Standard (MEDS)-compatible input and supports multiple text, numeric, and temporal tokenization strategies. BPR extends the bits-per-byte metric used in language models to enable comparison across tokenization strategies. Results DBToken efficiently tokenized data across configurations. BPR identified the vocabulary size associated with the best clinical outcome performance and localized differences in numeric tokenization performance by token class. Discussion Optimal tokenization strategies for medical foundation models are a subject of active research. DBToken enables reproducible tokenization experiments, while BPR efficiently screens vocabulary sizes and numeric representations before downstream evaluation. Conclusion DBToken and the BPR metric provide open-source infrastructure for reproducible EHR tokenization and cross-strategy evaluation.