BMC Medical Informatics and Decision Making

Background: Adverse event (AE) coding is essential for safety monitoring in oncology clinical trials, particularly in acute myeloid leukemia (AML), where intensive therapies are associated with frequent and heterogeneous toxicities requiring standardized MedDRA (Medical Dictionary for Regulatory Activities) coding. However, manual Low-Level Term (LLT) assignment remains labor-intensive, subjective, and difficult to scale. Although large language models (LLMs) have emerged as promising decision-support tools for automated coding, unguided zero-shot generation remains insufficient for reliable fine-grained MedDRA coding. Objective: To develop and evaluate a retrieval-augmented reasoning pipeline for clinically aligned LLT-level MedDRA coding of free-text adverse events from prospective AML clinical trials. Methods: We implemented a retrieval-augmented reasoning pipeline inspired by the retrieval-augmented generation (RAG) paradigm using LLaMA-3.3-70B-Instruct as the primary backbone and benchmarked the framework across multiple open instruction-tuned LLMs. Dense semantic retrieval first generated a constrained top-100 LLT candidate set for each AE, followed by structured LLM reasoning to select a single best-matching LLT and deterministic mapping to Preferred Term (PT) and System Organ Class (SOC) levels. The pipeline was evaluated retrospectively on AE datasets from three prospective AML clinical trials (MOSAIC, DELTA, and DaunoDouble) with automated LLT/PT/SOC metrics and expert-assessed Clinical Correctness Rate (CCR). Results: Clinical expert review showed high clinical acceptability of the RAG pipeline across datasets (91-97%). Under automated evaluation, the pipeline achieved LLT exact accuracy of 50-58%, PT accuracy of 78-85%, and SOC accuracy of 90-93%. Zero-shot generation and random candidate selection performed substantially worse. Semantic retrieval more often included the coder-assigned LLT among the candidate terms available to the model than retrieval based on lexical similarity. Multi-model benchmarking showed that backbone choice mainly affected LLT exact agreement, whereas PT and SOC performance remained comparatively stable. Conclusions: Retrieval-augmented reasoning supports clinically aligned MedDRA coding of free-text adverse events under realistic candidate constraints in AML clinical trials. Evaluation across three AML clinical trials showed that strict LLT-level string agreement underestimated clinical ap-propriateness, highlighting the importance of combining hierarchical evaluation metrics with clini-cal expert validation for AI-assisted MedDRA coding in hematology trials.

Objective: Acute kidney injury (AKI) affects a large proportion of patients in the intensive care unit (ICU) and is a major contributor to morbidity, mortality, and cost. Although electronic health records (EHRs) capture rich longitudinal data, many predictive models fail to detect AKI early enough for effective intervention. Non-temporal methods such as logistic regression and XGBoost treat patient history as aggregated risk factors, discarding the temporal evolution of clinical state. A recent trend is to employ temporal models, such as recurrent neural networks, to capture sequential patterns, but these models struggle with irregular sampling and limited long- range contextual awareness. To address the challenge, we propose RenalTransLSTM, a hybrid temporal deep learning framework for early, multi-horizon AKI prediction and identification of modifiable risk factors. Methods: RenalTransLSTM integrates Long Short-Term Memory (LSTM) networks with Transformer encoders to model both local temporal dynamics and global contextual depen- dencies in ICU time-series data. Using 48-hour patient histories from MIMIC-IV (61,735 admissions), the model predicts AKI at 6-, 12-, and 24-hour lead times. We benchmark the model against SVM, XGBoost, LSTM, TG-LSTM, and a Transformer, and apply Integrated Gradients and counterfactual analysis to identify modifiable risk factors. Results: RenalTransLSTM outperforms all baselines across most horizons and metrics, achiev- ing AUROC above 0.90 and F1-scores reaching 0.85 while maintaining balanced precision and recall on imbalanced data. Ablation studies confirm that combining LSTM and Transformer components improved robustness and predictive performance. Counterfactual analysis identifies clinically meaningful, modifiable risk factors associated with AKI progression. Conclusion: RenalTransLSTM offers an effective, interpretable framework for early AKI prediction in the ICU, supporting proactive intervention and clinical decision support.

Clinical oncology datasets often store systemic therapy as a regimen label with a start date and an end date. Those records are clinically recognizable but can be analytically incomplete when the research question concerns whether a patient was exposed to a concurrent CNS-active drug (cCNS-aD) or an adjuvant CNS-active drug (aCNS-aD) around radiotherapy. Contemporary CNS-oncology studies usually define CNS activity by empiric drug lists and define concurrency by fixed calendar windows, although the literature shows substantial heterogeneity across both concepts. This paper proposes a generalizable framework for converting raw systemic therapy records into reproducible cCNS-aD and aCNS-aD variables, useful in subgrouping for clinical studies. The framework uses a transparent CNS scoring model based on three clinical evidence components: intracranial objective response rate, consensus CNS endorsement, and intrathecal route of administration. It then defines a pharmacokinetic exposure proxy as the recorded end date plus five half-lives. Concurrent exposure is classified by overlap with the radiotherapy interval, while post-radiotherapy exposure is classified by overlap with a prespecified post-RT attribution window. The framework separately identifies post-RT pharmacokinetic persistence and post-RT treatment initiation, allowing investigators to distinguish continued exposure from true adjuvant initiation. This is a methodological framework and reference implementation. Implementation audits and endpoint-specific sensitivity analyses remain necessary before use as a definitive exposure classifier

Cancer registries enable cancer surveillance at the population level. These registries require significant human-time to read through many different parts of the electronic health record, including structured data and lengthy, free-text clinical reports, to abstract values for hundreds of required variables. Large language models (LLMs) offer the possibility to significantly improve this process by supporting and speeding up cancer registry data abstraction. However, it is unclear how well these models perform at real-world cancer registry abstraction involving multiple cancer types and large patient volumes. Here, we evaluate five foundational LLMs for their ability to reliably abstract cancer registry variables. We leverage hospital cancer registry data from a large regional health system as the ground truth and use LLMs to abstract from clinical reports eight registry variables for 5,939 patients with seven different cancer types. We use a zero-shot prompting strategy to compare LLM ability on commonly abstracted cancer variables with different data types. The results show that larger and more advanced models (Claude Sonnet 4.5, GPT-OSS-120b, GPT-OSS-20b) generally outperform smaller models (Gemma 12b, LLaMA 3.1 8b). The best performing models show F1 scores around 0.8 for cancer registry variables with low cardinality (grade, summary stage, laterality), with only slightly lower F1 scores for variables with high cardinality (primary site, regional nodes examined, regional nodes positive). On the more complex task of precise date extraction, all models showed decreased performance on both diagnosis and treatment dates (exact accuracy ~0.55 for the best performing models), which increased to ~0.85 for a tolerance within {+/-}30 days. These results quantify the performance of various models as well as the potential and limitations of LLMs in cancer registry abstraction tasks.

Background: Postoperative delirium (POD) is a complication associated with most types of surgery, and is associated with a number of detrimental effects. Therefore, it is of interest to determine which patients may be at higher risk of POD so that mitigating steps may be taken. We sought to determine whether POD can be accurately predicted with common machine learning (ML) models. Methods: Using the Medical Information Mart for Intensive Care (MIMIC)-IV database, we identified 8026 abdominal surgery procedures across 7215 adult patients. Using demographic information, such as age, type of surgery, sex; as well as commonly measured laboratory values (such as electrolytes and blood counts) and comorbidity indices, we determined to what extend common ML models, such as random forests, support vector machines, extreme gradient boosted machines, and neural networks, could predict POD. Results: Random forests outperformed logistic regression, support vector machines, extreme gradient boosted machines, and neural networks, with respect to individual t-tests. The random forest model had a sensitivity of 73.11, a specificity of 71.14, and an area under the receiver operator characteristic curve of 0.800. Age, comorbidity indices, gender, and alcohol use carried significant predictive weight in this cohort. Conclusions: Machine learning models are effective predictors of postoperative delirium, although further work is required to increase clinical utility of such tools. Markers of inflammation, comorbidity indices, and alcohol use are important predictive features alongside better-known features such as age.

Elective surgery late cancellations and ``did not attend'' (LCDNA) events waste theatre capacity, lengthen waiting lists, and impose avoidable costs on NHS Trusts. We present a decision-support approach that ranks upcoming elective procedures by expected cancellation cost and supports capacity-constrained outreach by selecting the highest-risk Top-K cases for intervention. Using cost-sensitive learning and a clinically grounded cost model, the policy reduces expected cost from approximately 103 GBP per case under business-as-usual to 77.08 GBP per case in a hospital-holdout (cross-site) evaluation designed to mimic deployment to a new hospital. In a complementary time-forward evaluation, representing prospective use within the same service environment, expected cost falls further to 70.97 GBP per case. The 6.11 GBP per-case difference between the two regimes highlights the added uncertainty introduced by cross-site operational shift and supports a conservative roll-out with local calibration and monitoring. Explainability analyses suggest that booking-to-procedure lead time, specialty or service line, calendar effects, and prior cancellation history are the strongest drivers of prediction, helping to inform tiered intervention workflows that prioritise near-term bookings and use model--pathway mismatches as an audit signal. Overall, the framework turns predictive performance into practical, capacity-aware policy guidance for reducing avoidable cancellations while supporting safe and equitable implementation.

Background: In Japan, acute inpatient care is divided into approximately 335 secondary medical care areas, which serve as the basic units for planning healthcare delivery systems under the 8th National Health Care Plan. While comparisons between regions and facilities typically rely on a single risk-adjusted metric, this approach confuses differences in patient demographics with differences in the actual infrastructure of intensive care units (ICUs). This paper presents a framework - MedZone Embedder - for deriving data-driven indicators of regional structural vulnerability by mapping secondary medical care areas onto a learned similarity space, together with its working implementation. The paper sets out the concept, the method, a proof of concept, and an explicit staged validation program, rather than national empirical results. Methods: Each area is represented by a feature vector consisting of aggregated values of intensive care provision indicators derived directly from the Japan Intensive Care Patient Database (JIPAD) - specifically, risk-adjusted mortality rates (standardized mortality ratios and an in-hospital composite indicator), technical efficiency, length of stay, readmission rates, case severity, and case composition - with the within-area variance of these indicators also taken into account. No hierarchical processing by facility type is performed. A contrastive autoencoder (multilayer perceptron encoder 32 -> 16 -> 8, symmetric decoder) is trained by self-supervised learning, using an objective function that combines reconstruction and normalized temperature cross-entropy (NT-Xent) on noise-augmented views. The resulting 8-dimensional embedding supports area searches based on cosine similarity and anomaly scoring in the embedding space (using isolation forest, Mahalanobis distance, or k-nearest-neighbor density), which is normalized to a vulnerability score ranging from 0 to 1. If deep learning libraries are unavailable, or if the number of areas is small, an alternative method using deterministic principal component analysis is employed. Results: This method was implemented and deployed within an operational ICU decision support system on a managed cloud platform. The proof of concept (PoC) is structured around five secondary medical care areas within Kyoto Prefecture and runs entirely on synthetic facility-level aggregate data constructed to follow the JIPAD indicator schema; no registry data were accessed. It generated: an aggregate provision profile for each area; an area embedding space equipped with a similar-area search function; and a vulnerability ranking that identifies areas with low patient numbers and low diversity that exhibit overall poor outcomes. At this scale, the contrastive autoencoder falls back to principal component projection. The deep learning pathway has been implemented and unit testing has been completed; training and evaluation on actual registry data are pending data-use approval and the expansion of data integration. Validation is staged: Stage 2 will train the contrastive pathway over JIPAD-covered areas to assess construct validity against public structural indicators (ICU/HCU beds, population, accessibility), and Stage 3 will extend coverage to all areas via National Database (NDB) linkage. Conclusion: MedZone Embedder reframes regional comparison from single-indicator ranking to structural representation: which areas are alike, and which are structural outliers. The contribution of this paper is the framework - the proposal that the intensive care provision structure of Japanese secondary medical care areas can be learned from a national outcomes registry and read through the lens of what we call institutional debt - together with a deployed implementation and a pre-specified validation program. To our knowledge, this is a candidate first application of contrastive representation learning to Japanese secondary medical care areas.

Background Machine learning (ML) models are increasingly used to predict adverse outcomes after surgery. However, most rely on static patient characteristics (e.g., age, comorbidities) and overlook clinician-controlled treatment decisions that can be actively modified at the point of care. Discharge opioid prescribing is a key modifiable, clinician-controlled decision, yet optimizing prescribing choices across multiple adverse outcomes remains underexplored in predictive modeling. This study addresses that gap by introducing a novel ML framework that explicitly separates fixed patient risk factors from modifiable prescribing options to support personalized, risk-informed opioid prescribing decisions. Methods We developed the Hierarchical Clinical Fusion Transformer (HCF-Transformer), an ML model designed to estimate patient-specific risks across four postoperative outcomes: prolonged opioid use (POU), chronic pain (CP), 30-day readmission, and opioid-associated outcomes (OAO). The model constructs patient risk profiles from fixed, non-modifiable baseline factors, followed by a transformer layer. Clinician-controllable discharge opioid regimens are modeled as alternative intervention candidates and fused with the fixed risk representation through a clinical fusion mechanism, enabling assessment and ranking based on predicted risks. A Total Relative Risk (TRR) metric, calibrated to each outcome prediction threshold, guides the recommendation process. We evaluated the model in diabetic surgical patients, a common high-risk population. Results The study included 157,853 unique diabetic surgical patients, with outcome prevalences ranging from 47.2% (POU) to 1.8% (OAO). The HCF-Transformer achieved the highest AUROCs, 0.798 for POU, 0.712 for 30-day readmission, 0.808 for CP, and 0.922 for OAO, outperforming Random Forest, FT-Transformer, and ResNet-based models. Compared to these baselines, HCF-Transformer generated more stable and discriminative risk estimates and demonstrated significant variation in TRR scores across discharge opioid options (ANOVA p < .01, eta-squared > .01). This enabled consistent identification of lower-risk regimens tailored to patient-specific profiles. Conclusions The HCF-Transformer introduces a novel hierarchical fusion approach to optimize opioid prescribing by integrating static patient risk profiles with modifiable discharge options. Using transformer-based modeling and a quantifiable TRR metric, the model delivers personalized, risk-aware recommendations. This approach enables data-driven opioid prescribing tailored to individual risk and has the potential to improve postoperative outcomes in high-risk populations. Our findings demonstrate that integrating modifiable factors with structured risk profiles through a transformer-based fusion architecture can enhance decision-support systems, paving the way for more actionable and personalized AI in healthcare.

Background Hepatocellular carcinoma (HCC) treatment selection demands nuanced integration of heterogeneous patient data, yet prevailing predictive models rely on restricted data modalities and oversimplified therapeutic frameworks, compromising clinical translation. Objective We developed and validated a multimodal artificial intelligence framework to guide optimal treatment strategy selection across the full spectrum of HCC interventions. Methods This retrospective study comprised 1,043 HCC patients (development cohort, January 2017-December 2023) and 55 external validation patients (2023) from Wuxi Peoples Hospital. We engineered Embedding-Augmented Extra Trees (ET-Emb), a novel model fusing structured clinical variables with contextual text embeddings derived from medical histories and radiology reports. ET-Emb quantifies probabilities for five primary treatments: open/laparoscopic resection, transarterial chemoembolization, radiofrequency ablation (RFA), and chemotherapy. Model performance was rigorously assessed via 10-fold cross-validation and external validation using ROC-AUC and PR-AUC metrics. Results ET-Emb demonstrated robust performance in the development cohort (ROC-AUC: 0.84 {+/-} 0.04; PR-AUC: 0.55 {+/-} 0.06), significantly outperforming established benchmarks. This generalizability was preserved in external validation (ROC-AUC: 0.77 {+/-} 0.02; PR-AUC: 0.47 {+/-} 0.03). SHAP analysis identified textual clinical narratives and socioeconomic determinants as critical predictive drivers. Conclusions By unifying structured and unstructured data modalities, ET-Emb delivers accurate, multi-treatment strategy prediction for HCC. Its clinical validity and the demonstrated significance of textual features establish multimodal AI as an essential paradigm for simulating complex oncological decision-making, positioning ET-Emb as a transformative tool for precision HCC management.

Objective. To evaluate whether open-weight large language models (LLMs) can accurately extract clinical findings from Finnish-language pediatric records, and whether prediction uncertainty can be used to triage cases for expert review to minimize manual work. Materials and Methods. Retrospective cohort of 97 pediatric ischaemic stroke patients (1 month - 17 years) from Helsinki University Hospital (2010 - 2023). Three open LLMs (gpt-oss-20b, DeepSeek-R1-Distill-Qwen-32B, and medgemma-27b-text-it) were prompted in English to detect four extraction targets (hemiplegia, headache, seizure, and stroke as a positive control) from each patient's full free-text record. Each combination received 15 calls (five temperatures x three repeats). Performance was benchmarked against a clinician reference (accuracy, recall, precision, F1). Shannon entropy across the 15 calls quantified within-model uncertainty; inter-model disagreement provided an ensemble signal. Patients were ranked by uncertainty for a simulated selective-review workflow. Findings were externally validated in an independent neonatal stroke cohort (n = 88). Results. Gpt-oss-20b achieved the best balance of recall (0.91 - 1.00) and precision (0.83 - 0.92), with F1 0.89 - 0.95 across non-control extraction targets. Entropy in misclassified cases was 2.4 - 3.4 times higher than in correctly classified cases. Entropy-based triage achieved complete error coverage by reviewing <10% of patients for hemiplegia (8.3%) and headache (8.2%), and 19.6% for seizure. Neonatal validation reached F1 0.95 for Apgar 1 min and binary seizure, and F1 0.87 for 4-class stroke-subtype classification. Discussion. Within-model entropy and inter-model disagreement provided complementary, calibrated signals of likely error in a non-English clinical setting. Conclusion. Open LLMs can extract clinical findings from Finnish pediatric records with accuracy comparable to published English benchmarks, and uncertainty-based triage substantially reduces required expert workload.

Background: Heart failure (HF) and chronic obstructive pulmonary disease (COPD) are among the leading causes of morbidity and mortality globally, with effective management heavily dependent on accurate severity staging using the New York Heart Association (NYHA) and Global Initiative for Chronic Obstructive Lung Disease (GOLD) classification systems. However, severity information is frequently embedded within unstructured clinical narratives rather than standardized Electronic Health Record (EHR) fields, limiting automated clinical decision support, disease surveillance, and retrospective healthcare analytics. Existing Natural Language Processing (NLP) approaches primarily rely on rule-based keyword extraction or supervised deep learning methods requiring large annotated corpora, which are often unavailable in many healthcare settings. Equally, most current systems inadequately integrate clinical ontologies for semantic reasoning and explainable classification, limiting interoperability and clinical applicability. Objective: This study aims to develop and evaluate an ontology-integrated NLP framework for automated extraction and severity staging of HF and COPD symptoms from de-identified clinical notes using NYHA and GOLD classification systems. Methods: The study will employ a Design Science Research (DSR) methodology to design, implement, and evaluate a hybrid NLP framework integrating rule-based extraction, SNOMED-CT ontology reasoning, and a Bidirectional Long Short-Term Memory with Conditional Random Field (Bi-LSTM-CRF) deep learning architecture for clinical sequence labeling. Approximately 1,000 de-identified clinical notes will be sampled proportionately from publicly available repositories including MIMIC-III/IV, eICU Collaborative Research Database, AmsterdamUMCdb, and MTSamples. Clinical text preprocessing will include tokenization, lemmatization, dependency parsing, abbreviation expansion, and negation detection. Ontology-guided semantic normalization will map extracted symptom entities to standardized SNOMED-CT concepts to support severity staging. Framework performance will be evaluated using precision, recall, F1-score, Cohens Kappa, sensitivity, specificity, positive predictive value, negative predictive value, confusion matrices, and correlation analyses against confirmed diagnoses and guideline-based severity classifications. Expected Outcomes: The proposed framework is expected to automate NYHA and GOLD severity staging across heterogeneous clinical note types without reliance on manually annotated severity labels. The ontology-integrated architecture is anticipated to improve semantic consistency, interpretability, and explainability of NLP outputs while enhancing EHR analytics, retrospective clinical audit, and AI-assisted clinical decision support. Conclusion: Findings from this study may provide a scalable and transferable framework for automated severity classification in data-rich but label-poor healthcare environments.

Background: Machine learning models leveraging electronic health records (EHRs) can support earlier detection of sepsis in intensive care units (ICUs). However, their clinical utility depends on reproducibility across institutions and patient populations. Building on a published pipeline from the Children's Hospital of Philadelphia (CHOP), this study examines how a neonatal sepsis prediction framework performs and can be adapted to a range of intensive care environments, paediatric, cardiac, and neonatal, at Great Ormond Street Hospital (GOSH). Methods: We extracted de-identified ICU EHR data from GOSH and applied feature derivation, unit harmonisation, and temporal sampling to align with the CHOP dataset used by Masino et al. (2019). Seven classifiers were first evaluated using CHOP-trained weights to characterise cross-domain behaviour and then retrained on local data to assess recoverability and site-specific adaptation. Model discrimination was summarised by AUC and F1, and learning curves were used to explore sample efficiency and bias-variance dynamics. Results: Models achieved strong discrimination on the CHOP neonatal cohort but demonstrated reduced performance when transferred to the mixed GOSH ICU population, reflecting anticipated domain and population shift. Retraining on GOSH data restored discrimination (AUC range 0.69-0.86), with Gradient Boosting (AUC 0.86 vs AUC 0.87 at CHOP) and KNN (AUC 0.80 vs AUC 0.79 at CHOP) models performing comparably to their CHOP benchmarks. DeLong's test confirmed statistically significant gains across all classifiers (p < 0.001). Conclusion: ICU cohort and baseline demographic differences between CHOP and GOSH introduced domain shift that limited direct model transfer. Elements of the original preprocessing pipeline could not be reproduced, further constraining transportability. Yet, retraining on local data restored high discrimination, showing that the modelling framework remains robust when re-estimated in new settings. These results highlight local adaptation as a practical route to recover performance and support safe, generalisable deployment of clinical prediction models in mixed clinical environments.

Machine learning workflows frequently incorporate data preprocessing to enhance predictive performance. However, the need for Super Learner ensembles made up only of preprocessing-invariant tree-based algorithms remains unexplored. Using three benchmark clinical classification datasets, this study examined how preprocessing affected the Super Learner's prediction performance, learner weight distribution, and oracle behavior. The Heart Disease (207 observations), Indian Liver Patient Dataset (583 observations), and Pima Indians Diabetes (768 observations) datasets were used to create a Super Learner ensemble model that included Classification and Regression Trees (CART), Random Forest, Ranger, and Extreme Gradient Boosting (XGBoost). Models were evaluated under raw and preprocessed data conditions using repeated cross-validation. Predictive performance was assessed using the area under the receiver operating characteristic curve (AUC), Matthews correlation coefficient (MCC), and Brier score. Learner weight allocation and Oracle Gap were compared using paired Wilcoxon signed-rank tests with Benjamini-Hochberg adjustment. Preprocessing produced negligible changes in predictive performance for the Heart Disease and Pima datasets. For the ILPD dataset, preprocessing significantly improved AUC (0.746 to 0.752; adjusted p = 0.0017) and reduced the Brier score (0.177 to 0.175; adjusted p < 0.001). Learner weights remained largely stable, although Random Forest replaced Ranger as the dominant learner for the Heart Disease dataset. Oracle Gaps remained extremely small (<0.002) across all datasets and did not differ significantly between preprocessing conditions. Preprocessing provides limited benefit for Super Learner ensembles composed of preprocessing-invariant learners and does not materially alter their oracle behavior. Preprocessing decisions should therefore be guided by dataset characteristics rather than adopted as a universal modelling practice.

Acute kidney injury (AKI) is a frequent complication within intensive care units, with its sudden onset often missed. This is especially important because a timely window for intervention is required as delayed detection leads to progressively worse outcomes. Existing machine learning and deep learning models have contributed to closing this gap, but their complexity, requiring hundreds to thousands of features, and lack of generalisation pose a limitation that prevents them from being integrated into clinical workflows across different electronic health-record ecosystems. This study presents a 37-feature XGBoost model trained on the MIMIC-IV dataset with 5.4% positive cases, with hyperparameters optimised via Optuna and probabilities calibrated using isotonic regression, designed for transportability across clinical settings. Validation was conducted internally using a temporal patient-level split simulating prospective deployment, training on 2008-2016 data and testing on 2017-2022 data"External validation was performed on the eICU Collaborative Research Database, a multi-centre dataset spanning 208 US hospitals, using the trained model without retraining. SHAP TreeExplainer was used to provide feature-level explainability for individual predictions. Internal testing yielded an AUROC score of 0.794 for predicting AKI onset within a 12-24 hour window. External validation produced a 0.750 AUROC without retraining. Equitable discrimination was observed across gender, age, chronic kidney disease presence, race, and AKI stages on both datasets, with a 95% internal CI of 0.789-0.799 confirming the model's estimate stability. These results suggest that clinically useful prediction systems are achievable with substantially fewer features than current models require.

Objective: To evaluate whether multi-agent LLM architectures with explicit safety verification maintain guideline compliance when their clinical knowledge bases undergo temporal or institutional distribution shift. Materials and Methods: We designed a controlled evaluation framework using 50,000 synthetic type 2 diabetes patients with CKD and hypertension comorbidities (500 per experimental condition). Four architecture modes (single-agent, naive RAG, linear multi-agent, stateful graph with safety floor) were tested under four shift regimes: baseline, temporal drift (updated eGFR thresholds), institutional vocabulary transformation (11 term-pair substitutions producing 0.36 cosine similarity degradation), and metadata erasure. The clinical task was medication reconciliation with contraindication detection. Two embedding models (all-MiniLM-L6-v2, PubMedBERT) and two LLM backends (Llama3-8B, Mistral-7B) were compared. Results: Under institutional vocabulary shift, the linear pipeline's Guideline Compliance Score dropped from 1.00 to 0.36 because retrieval degradation rendered critical contraindication guidelines unretrievable. The stateful graph architecture maintained GCS = 1.00 across all shift conditions through its regime-aware safety floor, which operates independently of retrieval quality. This pattern held across both LLM backends and both embedding models. The safety mechanism added 32.2s latency per patient under shift versus 12.5s for single-agent mode. Discussion: Architectural choice (specifically whether audit findings are routed back to the summary agent) determines compliance under shift more than retrieval quality or model scale. The safety floor's value is compliance maintenance, not semantic fidelity improvement. Conclusion: Stateful multi-agent graphs with programmatic safety floors bound error propagation under clinical knowledge shift. The framework is reproducible on consumer hardware with no external API dependencies.

Background: The growing burden of lifestyle-related chronic diseases has increased the need for clinically interpretable decision-support tools capable of integrating artificial intelligence with evidence-based preventive nutrition. Although machine learning has shown considerable potential for health risk prediction, most existing approaches remain limited to isolated predictive models or conventional nutritional software, with little integration of multidimensional clinical assessment and personalized recommendations. Objective: To develop and internally validate NutrIA, a hybrid web-based Clinical Decision Support System (CDSS) that combines machine learning, validated clinical assessment, structured clinical reasoning and personalized nutritional recommendations for preventive medicine. Methods: NutrIA was developed using harmonized data from the National Health and Nutrition Examination Survey (NHANES, 1988 to 2018). A supervised machine learning model was trained to estimate 5-, 10- and 20-year all-cause mortality risk and subsequently integrated with an adaptive clinical questionnaire, validated screening instruments, nutritional indicators, dietary clustering, clinical phenotyping and a transparent rule-based recommendation engine within a unified web-based platform. Results: The predictive model achieved ROC-AUC values of 0.894, 0.914 and 0.923 for 5-, 10- and 20-year mortality prediction, respectively. The implemented CDSS incorporates an adaptive questionnaire (151 items), 39 validated clinical assessment instruments, 17 clinical phenotypes and 31 dietary clustering modules to generate individualized nutritional and lifestyle recommendations together with an automated clinical report. The integrated framework translates probabilistic risk estimates into clinically interpretable decision support for personalized preventive nutrition. Conclusions: NutrIA demonstrates the technical feasibility of integrating machine learning with knowledge-based clinical reasoning within a single web-based CDSS for preventive nutrition. Although external validation and prospective clinical evaluation are required before routine implementation, the proposed architecture represents a promising step toward clinically interpretable artificial intelligence for personalized nutritional care.

Structured reporting converts free-text radiology narratives into queryable data keys, facilitating cohort assembly, longitudinal tracking, and training label generation for medical AI. The prevailing paradigm follows a two-stage pipeline: (1) constructing a reporting template, (2) extracting information to populate it. While the extraction stage has benefited from advances in large language models (LLMs), template construction remains a manual bottleneck relying on labor-intensive expert consensus that is static, difficult to scale, and may fail to capture real-world reporting diversity. We address this limitation with ASTAR, an LLM-based framework for Automated induction of STAndardized radiology Reporting templates from large-scale clinical free-text corpora. Extensive experiments on 4,215 fetal brain MRI reports from multiple centers demonstrate that, in this reporting scenario, the ASTAR-induced template surpasses two expert-curated templates across template coverage, information fidelity, diagnostic fidelity, and expert-rated usability, reducing template development from weeks of committee deliberation to hours of automated processing.

Background: Japan faces critical challenges in medical data interoperability, conceptualized as the "Ten Walls" obstructing the Japanese Health Data Space (JHDS) [1]. The Japanese Intensive Care Patient Database (JIPAD) - Japan's largest national ICU registry with 151 participating facilities - represents a high-quality critical care dataset that remains isolated from international data ecosystems. Objective: To develop a formal mapping of all 122 JIPAD variables to HL7 FHIR R4, characterize the nature and magnitude of semantic gaps, and assess the feasibility of JIPAD integration into the JHDS. Methods: All 122 JIPAD variables (Data Dictionary v3.7.2; Linkage Items List 20231020) were evaluated using ISO 21564 [8]-based semantic equivalence scoring across three tiers: High (direct FHIR R4 Core mapping), Partial (mapping via JP-Core Implementation Guide extensions [3]), and Low/No Equivalence (structural institutional gap). Semantically identical multi-instance fields (e.g., secondary disease codes x5) were consolidated into single mapping entries, yielding 114 mapping entries. Pseudonymization architecture was characterized from primary documentation. Results: Of 114 mapping entries representing the 122 JIPAD variables, 97 (85.1%) achieved High Equivalence via LOINC/SNOMED CT, and 12 (10.5%) achieved Partial Equivalence via JP-Core extensions, value-set translation, or FHIR R4 Core extension mechanisms - yielding a combined technical feasibility of 95.6% (109/114). Only 5 entries (4.4%) were classified as Low/No Equivalence, all attributable to Japan's proprietary disease classification system (288 adult codes; 165 pediatric codes) embedded in the DPC reimbursement framework, plus one Japan-specific procedure (PMX endotoxin adsorption) absent from international terminology systems. Variable-level mapping details are provided in Supplementary Table S1. Critically, JIPAD employs pseudonymization with record-linkage capability, enabling 99% DPC data matching - demonstrating that technical and design-level barriers to FHIR integration have already been resolved. Conclusion: JIPAD is technically and architecturally ready for FHIR integration at a 95.6% level. The remaining 4.4% barrier is exclusively institutional - rooted in MHLW policy frameworks governing the DPC disease classification system [6] - rather than technical. FHIR integration would further unlock pharmacoepidemiological and social epidemiological research currently inaccessible due to data isolation. As the sole national ICU registry providing high-acuity anchor data unavailable in general health records, JIPAD integration is essential for a clinically meaningful JHDS by 2027.

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: Iron Deficiency Anemia (IDA) is one of the most prevalent nutritional disorders globally and a leading cause of Disability Adjusted Life Years (DALYs). Conventional diagnostic methods fail to detect deficiencies at an early stage and rarely account for individual genetic5 predisposition. Methods: This study proposes an end-to-end AI-driven precision nutrition pipeline integrating public Genome-Wide Association Study (GWAS) data and NHANES phenotypic data encompassing demographics, dietary intake, anthropometrics, and hematology. A synthetic genotype matrix was simulated for 400 GWAS-filtered SNPs using Hardy-Weinberg Equilibrium. Data preprocessing included missing value imputation, feature engineering, and SMOTE class balancing. Four machine learning models namely, Logistic Regression, Random Forest, Artificial Neural Network (ANN), and XGBoost were implemented and evaluated for both IDA classification and haemoglobin regression tasks. Results: XGBoost achieved state-of-the-art performance with ROC-AUC = 0.9981 for classification and R2 = 0.9903 for haemoglobin prediction. Polygenic Risk Score (PRS) stratification classified participants into low (73%), moderate (18%), and high (9%) risk tiers. Pathway burden analysis identified the Hepcidin Regulation pathway as the highest burden pathway in high-risk individuals. Conclusion: The integration of genomics, machine learning, and nutritional science through a Pathway-Burden Precision Nutrition Engine produced gene-specific, evidence-graded dietary recommendations, demonstrating significant potential for early and personalised IDA prevention.