Artificial Intelligence in Medicine

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.

We present FHIRBench, a benchmark evaluating six FHIR clinical data serialization strategies across four frontier LLMs (Claude Sonnet 4.5, GPT-5.4, DeepSeek V3.2, Qwen3 32B) on three clinical tasks using 100 stratified synthetic FHIR R4 patient bundles. We employ two evaluation layers: token-level F1 and LLM-as-judge rubric on four clinical dimensions, yielding 7,200 evaluations per layer. Our findings reveal four results. First, serialization significantly impacts quality but the direction diverges between layers: Condensed outperforms Raw JSON on F1 for 3/4 models (Wilcoxon p < 10^-17), while Raw JSON achieves higher judge scores for 3/4 models (p < 10^-7). Narrative achieves 95% of Raw JSON's quality at 83% fewer tokens. Second, model rankings completely reverse between layers -- Claude ranks last on F1 but first on clinical quality (p = 1.0 x 10^-6), demonstrating that single-metric evaluation produces misleading model selection. Third, a significant Model x Serializer interaction (Friedman p = 0.0009) precludes universal format recommendations, with GPT-5.4 favoring Raw JSON while open-weight models favor compressed formats. Fourth, Llama 3.1 70B exhibits 100% inference failure on complex patients despite operating within its nominal context window, revealing a patient-safety gap where AI fails for the patients who need it most. These findings establish that clinical AI systems require model-aware serialization middleware, multi-layer evaluation frameworks, and capacity verification before deployment. Code and data publicly available.

INTRODUCTION: The biomarker-based amyloid/ tau/ neurodegeneration (A/T/N) framework has become a popular staging method for Alzheimer's disease (AD) research. Previous studies use the framework either as a rule-based or data-driven approach but typically sacrifice either adaptivity or interpretability. METHODS: We present an interpretable, hybrid method, called Neurosymodal Data Fusion, for predicting incident AD in the ADNI dataset. Specifically, we encode the A/T/N framework as a logic program, where the input biomarker features are extracted by one or more neural networks. RESULTS: Our pipeline predicted four-year incident AD with a sensitivity of up to 0.84. Additionally, our models learned scores for each A/T/N profile, denoting relative importances to model predictions. These scores also indicated that empirically-derived cut-off values for the A and T criteria might be uninformative for the ADNI data. DISCUSSION: Our pipeline provides a novel way to use the A/T/N framework that could potentially improve early AD screening years before clinical manifestations.

The therapeutic landscape for hepatocellular carcinoma (HCC) is evolving rapidly, necessitating scalable approaches to synthesize the expanding scientific literature. We characterized thematic shifts in HCC treatment and prognosis research by conducting a retrospective bibliometric analysis of influential publications from 2023 and 2024. Using the OpenAlex database, we identified the 50 most highly cited papers from each year based on eighteen-month post-publication citation counts. Large language models were deployed to extract, normalize, and classify concepts from unstructured text into canonical topics and parent themes, enabling quantitative year-over-year frequency comparisons. Analysis of these 100 papers revealed a distinct maturation in research focus. Although broad categories like general immunotherapy remained prevalent, their relative frequency declined in favor of specific dual immune checkpoint regimens, notably CTLA-4 inhibition and the durvalumab plus tremelimumab combination. Concurrently, parent themes related to radiomics, imaging, and health systems exhibited significant growth in the 2024 cohort. These findings demonstrate a thematic transition in high-impact HCC research from foundational immuno-oncology toward optimized combination therapies and precision diagnostics. Furthermore, this study highlights the utility of artificial intelligence-driven bibliometrics for objectively tracking dynamic conceptual shifts in oncology. A web interface for exploring the data is available at https://pri.pepkio.com/.

We conducted a scaling evaluation of unlabeled pretraining for electrocardiogram foundation model performance. One-dimensional vision transformer masked autoencoders were pretrained across increasing ECG volumes and fine-tuned for rhythm, morphology, diagnostic, and structural heart disease tasks. Models pretrained below 400,000 ECGs failed to consistently exceed controls without self-supervised pre-training, whereas 600,000 to 800,000 ECGs improved AUROC across tasks, suggesting a minimum threshold for effective ECG representation learning.

Background. Translating a clinical guideline decision algorithm into a computational graph requires judgment, and unconstrained coding yields divergent graphs; any complexity measure computed from such a graph inherits that variation, so its reproducibility must be demonstrated rather than assumed. Objective. To develop, and prospectively test, an empirical method for making graph extraction reproducible, using the Clinical Guideline Complexity Index (CGCI) and four guideline algorithms as a case study. Methods. We built a Graph Representation Specification (an ontology, a motif catalogue, disambiguation conventions, decomposition rules, a deterministic validator, and a scoring engine) and refined it by error-driven grammar induction: measure inter-coder disagreement, localize its dominant class, induce a single grammar rule, and prospectively test whether that rule improves agreement in the anticipated class. Reproducibility was quantified with a pre-specified, topology-based endpoint (Decision Topology Agreement) rather than edge agreement, which is oversensitive to representational choices that do not affect the score. Two trained coders independently coded the diabetes, dyslipidemia, heart-failure, and hypertension algorithms. Results. A rule induced from the diabetes comorbidity panel (assessment topology) generated a pre-specified prediction that heart-failure figures, sharing the same motif, would converge; on a fresh, independently coded pair they did, with an absolute CGCI difference of approximately one. Decision topology reproduced closely (decision-order agreement at or near 1.00 for three of four guidelines), while breadth counting was rule-sensitive: an explicit modifier-counting rule reduced the largest disagreement from 27 to 4 tokens. Residual disagreement was bounded and localizable to specific, nameable representational choices. Conclusions. Graph-extraction reproducibility can be systematically improved through iterative grammar refinement, and a prospectively derived rule can be confirmed to improve agreement. These results establish the measurement foundation (reliability, not construct validity) for a companion study interpreting CGCI as cognitive load, and the method may apply wherever graphs are extracted from structured source artifacts.

Accurately attributing causes of death is vital for global health, yet fewer than 5% of deaths in resource-constrained regions are medically certified. To assign causes to these unlabeled deaths at scale, practitioners traditionally rely on verbal autopsy, using supervised statistical models to classify based on structured survey data. However, modern mortality surveillance increasingly collects rich, unstructured multimodal data, such as free-text caregiver narratives and postmortem diagnostics, which traditional supervised statistical models struggle to seamlessly integrate. In this paper, we present a comprehensive, multimodal benchmark for cause-of-death classification using data from the Child Health and Mortality Prevention Surveillance (CHAMPS) network, a unique surveillance platform spanning nine countries across South Asia and Sub-Saharan Africa. Using this dataset, we introduce an evaluation framework designed to rigorously assess diagnostic reasoning, moving beyond traditional metrics that fail to capture complex clinical realities. We demonstrate the utility of this benchmark by evaluating zero-shot large language models against supervised baselines across various data modalities. Our results reveal distinct differences in how these modeling approaches synthesize unstructured medical evidence. This benchmark provide a rigorously defined resource for assessing clinical reasoning in next-generation mortality surveillance.

Automated interpretation of neuroimaging studies requires simultaneous assessment of multiple imaging evidence variables, each tied to distinct anatomical structures. Vision-language models (VLMs) offer a unified framework for multi-task analysis, but adapting pre-trained VLMs remains challenging. Full fine-tuning is computationally prohibitive, and joint multi-task training requires simultaneous access to all task data, which is often infeasible in clinical settings. Although model merging enables multi-task composition without joint re-training, existing methods focus on post-hoc algorithms with limited extension to VLMs and minimal application to neuroimaging. Here, we present GRadient-guided Adapter Merging (GRAM), a layer-selective low-rank adaptation (LoRA)-based fine-tuning and merging framework for multi-task neuroimaging visual question-answering (VQA). GRAM uses a gradient ratio that contrasts class-specific gradients to identify task-discriminative layers, and applies subspace-constrained projected gradient descent to restrict LoRA updates to directions consistent with the geometry of the pre-trained model. We leveraged a structured VQA benchmark, developed from the National Alzheimer's Coordinating Center (NACC) dataset, that pairs multi-sequence brain MRI studies with question-answer pairs across clinically relevant imaging evidence variables. Experiments on the VQA benchmark showed that GRAM outperformed or matched all-layer LoRA fine-tuning and a standard merging baseline while reducing inter-task interference during merging, and approached or surpassed the performance of joint multi-task training without joint re-training.

BACKGROUND: Artificial intelligence (AI) medical scribes rely on speech-to-text (STT) models for transcription. Evaluations of STT models in non-English settings remain scarce. We benchmarked ten STT models on medical consultations from Latin American (LatAm) Spanish and assessed whether fine-tuning improves transcription accuracy. METHODS: Ten YouTube videos depicting medical consultations. Human transcriptions were the ground truth. Five open-source models were evaluated: Whisper Large, Whisper Large v3, Whisper Large v3 Turbo, Voxtral Mini 3B, and Canary 1B v2; and so were five close-source models: gpt-4o-transcribe, gpt-4o-mini-transcribe, gemini-2.5-pro, Eleven Labs, and Assembly AI. Whisper Large v3 was fine-tuned. One video was withheld from training. Performance assessed using Word Error Rate (WER), Character Error Rate (CER), BLEU Score, ROUGE-L, BERT Score, and Semantic Similarity on the one withheld video. RESULTS: None of the fine-tuning iterations outperformed the vanilla Whisper Large v3. With the withheld video, Gemini-2.5-pro was the close-source model with the best performance in four of six metrics. In comparison to the close-source models, the fine-tuned model never outperformed the other models (withheld video); conversely, in comparison to the close-source models, the fine-tuned model showed better performance across metrics, for instance: BLEU score (63% vs to 58% for the second-ranking model), BERT (89% vs to 86%), and semantic similarity (89% vs to 83%), CER (19% vs 20%). CONCLUSIONS: Whisper Large v3 and its fine-tuned variant are the best open-source STT models for transcribing medical conversations in LatAm Spanish. These findings provide an evidence base for developing AI medical scribes tailored to Spanish-speaking LatAm.

Hypertension is commonly defined as a binary condition despite substantial heterogeneity in diagnosis, treatment, and blood pressure (BP) control. We propose a three-axis state model integrating diagnosis status, treatment intensity, and BP control to better characterize hypertension phenotypes. The framework generates 27 possible states that can be condensed into seven clinically meaningful groups. We applied the model to 5,129,584 Japanese adults using the National Database of Health Insurance Claims and Specific Health Checkups. Hierarchical cluster analysis, sensitivity analysis excluding patients with cardiovascular diseases other than hypertension, and validation against antihypertensive medication use were performed. Overall, 64% of participants were classified as normotensive, whereas 36% belonged to hypertension-related groups, including 11% with unrecognized hypertension and 7% with diagnosed but untreated hypertension. Agreement with data-driven hierarchical cluster analysis was substantial (weighted {kappa}=0.87). The group distribution remained largely unchanged in the sensitivity analysis, supporting the robustness of the proposed classification. Hypertension diagnosis also showed high validity, with a sensitivity of 96.5%, specificity of 91.8%, and substantial agreement with antihypertensive medication use ({kappa}=0.78). This three-axis framework provides a robust and clinically interpretable approach for characterizing hypertension phenotypes, enabling systematic identification of care gaps and supporting research, clinical decision-making, and population health management.

Importance: Heart failure readmissions remain common following hospitalization, but accurately identifying which patients will be readmitted after discharge remains challenging. Improved prediction could support targeted transitional care interventions and more efficient allocation of clinical resources. Objective: In this study we attempted to improve readmission prediction after heart failure hospitalization by using variables chosen through a modified Delphi process, and using inpatient Electronic Medical Record (EMR) data, focusing on clinical notes. Design: This prognostic study developed competing risk survival models to predict readmission after heart failure hospitalization. Variables were chosen using a modified Delphi process, and extracted from EMR notes using various natural language processing techniques or from other EMR elements where appropriate. Patients were admitted between 2011 through 2019, and at least one year of follow-up was available for all patients. Models were evaluated using C-statistics, as well as sensitivity, specificity, positive and negative predictive values. Setting: During the study period, all acute-care facilities in Calgary, Alberta used the same EMR system, from which patients were selected. Participants: Patients were 18 years or older, resided in Alberta, and were admitted to a Calgary hospital. All corresponding admissions with a most responsible diagnosis of heart failure were included (n=15,160). Main Outcomes and Measures: The main outcome of interest was readmission within 30 days, though 90- and 365-day time frames were also analyzed. Death was treated as a competing risk and analysed at those time frames as well.

The Cancer Genome Atlas (TCGA) holds clinical data for over 11,000 patients across 33 cancer types, but access is hard because of complex file structures, heterogeneous formats, and the need for programming. We present an agentic system for natural language querying and statistical analysis of TCGA clinical data. The system uses a large language model as an autonomous ReAct agent that selects from eight computational tools, including data extraction, descriptive statistics, Kaplan-Meier survival analysis with log-rank tests, hypothesis testing, and verification against the curated TCGA Pan-Cancer Clinical Data Resource (CDR). The agent reasons about intermediate results, adapts its approach, and returns clinically contextualized responses with source attribution and auditable traces. We introduce TCGA-Agent-Bench, 440 queries across five difficulty tiers with ground truth from the independently curated TCGA-CDR, evaluated with dual metrics of numerical accuracy and clinical completeness. The system achieves 93.4% overall accuracy (100% single-patient lookups, 99.1% cohort statistics, 92.8% comparative analyses), outperforming a fixed rule-based pipeline (87.1%), a single-pass LLM (81.8%), and retrieval-augmented generation (66.9% on a subset). Most of the benchmark is answerable from the CDR alone, so we locate the extraction layer's value in fields the CDR lacks (drug treatments, TNM components, biomarkers, biospecimen metadata): on 26 queries targeting these, the full system answers 100% versus 3.8% for CDR-only. Ablations show the reasoning loop is most impactful (+9.1% accuracy, +22.0 completeness points). A tool-based agentic architecture enables accurate, auditable analysis of clinical repositories, with value driven by tool design and recovered fields rather than model scale.

Patients and caregivers seek informational and emotional support throughout medical care, especially when interpreting unfamiliar laboratory test results. Although resources such as patient portals and online health communities (OHCs) help address questions, gaps remain. The emergence of large language models (LLMs) offers the potential to be a complementary source of support to assist patients and caregivers in understanding and using their test results. The objective of our study is to empirically compare LLM responses to patients online questions containing their laboratory test results to responses written by peers in an OHC. We compared the 519 peer replies to 122 laboratory test-related posts from an OHC to 488 responses generated from four LLMs using mixed computational and qualitative methods. LLMs frequently provided clear explanations of medical terminology and structured interpretations of numeric results but were longer and less readable. Peers offered more personalized, context-specific emotional support. Overall, LLMs have the potential to complement peer responses in OHCs, but require greater emotional depth, reasoning transparency, and alignment with community norms.

Mapping hierarchical brain networks within traditional Euclidean space causes significant structural distortion, undermining neuroimaging diagnostic frameworks. While hyperbolic models like the Poincare ball preserve these nested topologies, they demand heavy computational overhead due to intricate Mobius operations and curved geodesics. This paper introduces a highly efficient non-Euclidean framework for analyzing neurocognitive decline utilizing the Beltrami-Klein ball model. By projecting hyperbolic geodesics as Euclidean straight lines, this approach converts complex distance calculations into simple dot products, radically reducing processing demands. We validated our methodology against state-of-the-art Poincare and Lorentz baselines using datasets for Schizophrenia, Parkinsons Disease, and Alzheimers Disease. The Klein-based framework demonstrates superior performance, delivering both higher diagnostic precision and accelerated processing velocities across all three neurocognitive disorders.

Background Primary care in China lacks structured mental-health assessment, and the machine-learning models that could support such screening are typically developed on heavily selected samples. Cumulative inclusion and exclusion criteria, though usually treated as neutral data-cleaning steps, can create heterogeneity in predictive reliability among retained participants. Using the China Health and Retirement Longitudinal Study (CHARLS) 2011 baseline, we quantified how selection funnels distort epidemiological associations and inflate machine-learning metrics, and tested selective prediction as mitigation. Methods Using the CHARLS 2011 baseline with temporal external validation in CHARLS-2018, we built a four-level selection funnel (L0-L3), evaluated five classifiers with nested cross-validation and SMOTE, and compared model-embedded uncertainty with a decoupled predictor-selector framework; XGBoost cross-validation residuals drove risk stratification and classification and regression tree (CART) rules. Results Sample sizes fell from L0 n=17,705 to L3 n=4,256 (24.0%). The cancer-depression odds ratio attenuated from 1.78 (95% CI 1.32-2.41) to 1.39 (0.74-2.63), losing significance. AUC rose with selection but not after multiple-comparison correction, whereas calibration error increased for four of five models. Model-embedded uncertainty succeeded only for XGBoost; with the decoupled XGBoost residual selector, all five models achieved selective prediction at approximately 20% coverage (test AUC 0.90, 95% CI 0.85-0.95), abstaining on approximately 80% of cases for individual safety. Risk stratification was stable (residual Spearman correlations >0.95; multi-seed Jaccard 0.88), and CART rules used self-rated health, education, pain, and marital status. Conclusions The findings support a deployable primary-care triage pathway: a four-variable rule identifies patients suitable for algorithm-assisted scoring (approximately 20% coverage) and routes the remainder to human evaluation. Methodologically, cumulative selection bias produces a dual distortion: epidemiological associations are compressed and machine-learning metrics inflated. Selective prediction is limited mainly by uncertainty-indicator design. Performance metrics should be reported with selection level, coverage, and calibration trajectory. Decoupled selective prediction with CART rule extraction provides an actionable framework for quality-controlled, tiered-care deployment. Keywords: selective prediction, selection bias, CHARLS, depression, predictor-selector decoupling, uncertainty quantification, classification and regression tree, triage, clinical decision support, health management.

Minimally invasive endovascular procedures offer reduced surgical trauma, shorter recovery times, and improved outcomes, but rely on 2D fluoroscopic X-ray imaging, which provides limited depth perception and exposes patients and clinicians to ionizing radiation. Here we present an augmented reality (AR) system that fuses intravascular ultrasound (IVUS) and electromagnetic (EM) position tracking with preoperative computed tomography (CT) to produce an anatomically accurate, deformation-corrected navigational reference. A robotic device performs ECG-gated pullback of the IVUS probe, capturing 4D aortic motion across the cardiac cycle. We introduce a deep learning architecture for extracting vascular lumen boundaries and side-branch orifices from artifact-prone IVUS streams, and a semantically driven non-rigid CT-IVUS fusion pipeline robust to false positive landmarks. We evaluate the platform with trained surgeons in benchtop phantom studies and in-vivo ovine models, and demonstrate its application to fenestrated endovascular aneurysm repair (FEVAR). Compared to fluoroscopy alone, AR guidance significantly reduces cannulation time, radiation exposure, and cognitive workload, while improving procedural efficiency and safety. Our IVUS-EM and CT aortic datasets are released open source.

Background: Unplanned emergency readmissions remain common following hospitalisation for heart failure (HF). Residual congestion, atrial fibrillation, frailty, and other comorbidities contribute to adverse outcomes after discharge. Identifying patients at high risk of readmission or death may help target post-discharge management. Methods: We conducted a retrospective cohort study of patients hospitalised with HF in selected New South Wales hospitals who were discharged alive and not documented as receiving end-of-life care. Clinical, laboratory, medication, and text-derived variables extracted from electronic health records were used to develop predictive models and corresponding risk scores for emergency readmission and all-cause mortality within 180 days of discharge. Feature importance methods were used to identify key predictors and explain individual risk estimates. To illustrate model predictions while preserving patient privacy, we generated representative synthetic patient profiles by summarising the characteristics of groups of patients with similar predicted risk patterns and visualised the major contributors to their predicted risks using Shapley values. Results: The study included 5,202 hospitalisations among 3,933 patients. Within 180 days of discharge, 45.2% of patients experienced at least one emergency readmission and 12.4% died. The most common causes of emergency readmission were recurrent HF, followed by atrial fibrillation, chest pain, and pneumonia. Predictive performance was moderate for emergency readmission (AUC 0.70; calibration slope 1.30) and good for mortality (AUC 0.84; calibration slope 1.01). Emergency readmission risk was primarily associated with greater prior healthcare utilisation, a higher number of active medical problems, high risk of falls, older age, and impaired kidney function. Mortality risk was most strongly associated with abnormal red blood cell distribution width, elevated blood urea, older age, and lower systolic blood pressure. A lower number of discharge medications, particularly cardiovascular therapies, was associated with a higher risk of emergency readmission and a lower risk of mortality. Representative synthetic patient profiles demonstrated heterogeneity in the factors contributing to predicted risks, illustrating the value of patient-level risk visualisation. Conclusions: Predictive models identified clinically meaningful predictors of emergency readmission and mortality following HF hospitalisation. Patient-level visualisation of individual risk drivers may support more personalised post-discharge management.

As machine learning and artificial intelligence systems are increasingly used in healthcare, rigorous evaluation of their classification performance has become critical. The F1 and F{beta} scores are widely adopted metrics for assessing performance in imbalanced biomedical data. Recently, we introduced psF1, a unified statistical framework for inference and study design for single and comparative F1 and F{beta} scores under the assumption of independent classifiers. In practice, however, benchmarking two classifiers on the same dataset creates a correlated paired setting. Ignoring this intrinsic dependency leads to overestimation of the standard error and a substantial loss of statistical power. To address this, we develop psF1pair, an advanced framework for statistical inference and power analysis that explicitly accounts for correlations between classifier pairs. Extensive simulation studies demonstrate the performance of psF1pair, and its utility is further illustrated through application to a real-world imaging classification system. As expected, higher correlation between classifiers yields narrower confidence intervals and enhanced statistical power. A freely available R package is provided to facilitate implementation, supporting accurate evaluation and study design for predictive and classification models in biomedical research.

Objective To develop and validate a risk model for predicting postoperative bleeding in patients with thyroid cancer. Methods A total of 2800 consecutive patients diagnosed with thyroid cancer in the Department of Thyroid and Breast Surgery of the Affiliated Hospital of Xuzhou Medical University between January 2020 and December 2023 were retrospectively analyzed. Patients were categorized into two groups based on postoperative bleeding occurrence: bleeding and non-bleeding groups. Univariate and multivariate logistic regression analyses were utilized to screen independent risk factors. Meanwhile, risk prediction models were developed and nomogram . Subgroup analysis was performed to identify independent risk factors. The predictive effects of the models were assessed using the Hosmer-Lemeshow test and receiver operating characteristic (ROC) curves. Results Of the 2800 recruited patients, 50 had postoperative bleeding, with an incidence rate of 1.7%. Multivariate logistic regression analysis showed that age, hypertension, total thyroidectomy, tumor size [&ge;]4 cm, and operation time [&ge;]90 min were the risk factors for postoperative bleeding in thyroid cancer patients (P<0.05). A risk prediction model was established based on the above factors, and the area under the ROC curve was 0.881, with a sensitivity of 94.0%, a specificity of 67.3%, and an accuracy of 74.0%. Decision curve analysis revealed that the model had good predictive ability. Conclusions The constructed risk prediction model has good predictive power and can provide a reference for healthcare professionals to predict the risk of bleeding in patients after thyroid cancer surgery.

We present FootNet, a 453-image multi-view smartphone foot dataset for binary foot segmentation, with expertannotated masks across six anatomical views (dorsal, medial, and plantar, both left and right). We benchmark four segmentation models under a controlled protocol: U-Net with a MobileNetV2 encoder achieves the best performance (IoU 0.9268, Dice 0.9608, 95 % CI [0.9209, 0.9320]); DeepLabV3 with MobileNetV3-Large scores IoU 0.8984 (Dice 0.9449); UNet++ with MobileNetV2 scores IoU 0.8913 (Dice 0.9391); and SAM ViT-B with oracle boundingbox prompt scores IoU 0.9219 on the matched 191-image subset. Bonferroni-corrected Wilcoxon signed-rank tests (k = 6 comparisons) show U-Net significantly outperforms DeepLab (p < 0.001, r = 0.638) and SAM ViT-B with oracle boundingbox (p = 0.005, r = 0.202); UNet++ does not significantly differ from DeepLab (p = 0.062). Connected-component postprocessing yields negligible benefit (mean {triangleup}IoU = +0.0003, 12 of 453 images improved). The extended dataset is available upon request