Clinical free-text notes contain vital patient information. They are structured into labelled sections; recognizing these sections has been shown to support clinical decision-making and downstream NLP tasks. In this paper, we advance clinical section segmentation through three key contributions. First, we curate a new de-identified, section-labeled obstetrics notes dataset, to supplement the medical domains covered in public corpora such as MIMIC-III, on which most existing segmentation approaches are trained. Second, we systematically evaluate transformer-based supervised models for section segmentation on a curated subset of MIMIC-III (in-domain), and on the new obstetrics dataset (out-of-domain). Third, we conduct the first head-to-head comparison of supervised models for medical section segmentation with zero-shot large language models. Our results show that while supervised models perform strongly in-domain, their performance drops substantially out-of-domain. In contrast, zero-shot models demonstrate robust out-of-domain adaptability once hallucinated section headers are corrected. These findings underscore the importance of developing domain-specific clinical resources and h
Clinician skepticism toward opaque AI hinders adoption in high-stakes healthcare. We present AICare, an interactive and interpretable AI copilot for collaborative clinical decision-making. By analyzing longitudinal electronic health records, AICare grounds dynamic risk predictions in scrutable visualizations and LLM-driven diagnostic recommendations. Through a within-subjects counterbalanced study with 16 clinicians across nephrology and obstetrics, we comprehensively evaluated AICare using objective measures (task completion time and error rate), subjective assessments (NASA-TLX, SUS, and confidence ratings), and semi-structured interviews. Our findings indicate AICare's reduced cognitive workload. Beyond performance metrics, qualitative analysis reveals that trust is actively constructed through verification, with interaction strategies diverging by expertise: junior clinicians used the system as cognitive scaffolding to structure their analysis, while experts engaged in adversarial verification to challenge the AI's logic. This work offers design implications for creating AI systems that function as transparent partners, accommodating diverse reasoning styles to augment rather t
Effective physician-patient communications in pre-diagnostic environments, and most specifically in complex and sensitive medical areas such as infertility, are critical but consume a lot of time and, therefore, cause clinic workflows to become inefficient. Recent advancements in Large Language Models (LLMs) offer a potential solution for automating conversational medical history-taking and improving diagnostic accuracy. This study evaluates the feasibility and performance of LLMs in those tasks for infertility cases. An AI-driven conversational system was developed to simulate physician-patient interactions with ChatGPT-4o and ChatGPT-4o-mini. A total of 70 real-world infertility cases were processed, generating 420 diagnostic histories. Model performance was assessed using F1 score, Differential Diagnosis (DDs) Accuracy, and Accuracy of Infertility Type Judgment (ITJ). ChatGPT-4o-mini outperformed ChatGPT-4o in information extraction accuracy (F1 score: 0.9258 vs. 0.9029, p = 0.045, d = 0.244) and demonstrated higher completeness in medical history-taking (97.58% vs. 77.11%), suggesting that ChatGPT-4o-mini is more effective in extracting detailed patient information, which is cr
Three-dimensional (3D) ultrasound promises various medical applications for abdominal, obstetrics, and breast imaging. However, ultrasound matrix arrays have extremely high element counts limiting their field of view (FOV). Current reduced element count architectures, such as row-column arrays, diverging lenses, or sparse arrays, suffer from limited resolution and high side- and grating-lobe levels. This work seeks to demonstrate an increased field-of-view using a reduced element count array design. The approach is to increase the element size and use advanced beamformers to maintain image quality. The delay and sum (DAS), Null Subtraction Imaging (NSI), directional coherence factor (DCF), and Minimum Variance (MV) beamformers were compared. K-wave simulations of the 3D point-spread functions (PSF) of NSI, DCF, and MV display reduced side lobes and narrowed main lobes compared to DAS. Experiments were conducted using a multiplexed 1024-element matrix array on a Verasonics 256 system. Elements were electronically coupled to imitate a larger pitch and element size. Then, a virtual large aperture was created by using a positioning system to collect data in sections with the matrix arr
Clinical framing -- the linguistic manner in which clinical information is presented -- can influence patient understanding and decision-making, with important implications for healthcare outcomes. Obstetrics is a high-stakes domain in which physicians counsel patients on delivery mode choices such as vaginal birth after cesarean (VBAC) and repeat cesarean section (RCS), yet counseling language remains underexplored in large-scale clinical text analysis. In this work, we analyze physician counseling language in 2,024 obstetric history and physical narratives for a rigorously defined cohort of patients for whom both VBAC and RCS were clinically viable options. To control for confounding due to medical contraindications, we first construct a VBAC-eligible cohort using structured clinical data supplemented by a large language model (LLM)-based extraction pipeline constrained to grounded, verbatim evidence from free-text narratives. We then apply a zero-shot LLM framework to categorize counseling segments into predefined framing categories capturing how physicians linguistically present delivery options. Our analysis reveals a significant difference in counseling framing distributions
Multiple-choice medical benchmarks are increasingly saturated, and recent rubric-based evaluations such as HealthBench have shown that open-ended clinical performance is far from solved - its "Hard" subset top score remains 32%. We present a small, deliberately difficult evaluation dataset of five clinician-authored clinical scenarios spanning four specialties (anaesthesia, internal/family medicine, emergency medicine, and obstetrics), each accompanied by an atomic, weighted, MECE rubric (25-62 criteria per task; 184 criteria total) authored from a clinician-drafted golden answer. We evaluate three frontier models: GPT 5.4, Claude Opus 4.7, and Gemini 3.1 Pro. Mean rubric pass rates were 0.47 (Claude), 0.39 (GPT), and 0.37 (Gemini). The central finding is an inversion of clinical priority: the highest-weighted (weight-5, critical) criteria passed at only 32.4-41.7%, while low-stakes weight-1 criteria passed at 80-90%. 56 of 108 critical (weight-5) criteria (52%) were satisfied by no model. Three LLM autoraters reproduced expert met/not-met labels on 92.8-94.7% of 552 graded criteria. We position this as a methods-and-preliminary-findings contribution: the five tasks demonstrate a s
Health systems are rapidly deploying large language models (LLMs) that use clinical notes for clinical decision support applications. However, modern documentation practices rely heavily on templates, copy--paste shortcuts, and auto-populated fields, producing extensive duplicated text (``note bloat'') that dilutes clinically meaningful signal and substantially increases the computational cost of LLM use. We introduce TRACE, a scalable preprocessing pipeline that removes note bloat by leveraging EHR attribution metadata to identify templated and copied content and applying frequency-based deduplication when metadata are unavailable. We evaluated TRACE across four real--world clinical cohorts spanning liver transplantation, obstetrics, and inpatient care (5.3 million notes) using blinded physician review and downstream modeling tasks. TRACE removed 47.3% of chart text while preserving performance for information extraction and clinical outcome prediction. At a large academic medical center, this reduction corresponds to an estimated $9.5 million annual decrease in LLM inference costs assuming one query per encounter. These findings show how underutilized EHR metadata can enable more
Social media platforms like TikTok have become a key source of health information, with studies reporting inaccuracies in posts. As Large Language Model (LLM) providers increasingly integrate LLMs into digital platforms to fact-check content (e.g., Grok and Perplexity on X and WhatsApp, respectively) and are being used by people to fact-check information, deploying these systems in critical areas such as reproductive health without rigorous evaluation can cause serious harm. We introduce RELIANCE, an expert-annotated dataset of health information on TikTok surrounding pregnancy and postpartum queries, serving as both an analysis of the reproductive health information landscape and an evaluation of LLMs' capabilities in fact-checking this content. Our dataset comprises 409 annotated sentences from 336 videos across 56 clinician-reviewed queries, annotated by three expert clinicians in Obstetrics, Gynecology, and Internal Medicine. Our findings reveal that nearly 60\% of the health information in the videos we sampled is accurate. Furthermore, LLM evaluations reveal a gap between evaluating specific claims and evaluating the entire content (15\%). We believe that our methodology, dat
Blind Sweep Obstetric Ultrasound (BSOU) enables scalable fetal imaging in low-resource settings by allowing minimally trained operators to acquire standardized sweep videos for automated Artificial Intelligence(AI) interpretation. However, the reliability of such AI systems depends critically on the quality of the acquired sweeps, and little is known about how deviations from the intended protocol affect downstream predictions. In this work, we present a systematic evaluation of BSOU quality and its impact on three key AI tasks: sweep-tag classification, fetal presentation classification, and placenta-location classification. We simulate plausible acquisition deviations, including reversed sweep direction, probe inversion, and incomplete sweeps, to quantify model robustness, and we develop automated quality-assessment models capable of detecting these perturbations. To approximate real-world deployment, we simulate a feedback loop in which flagged sweeps are re-acquired, showing that such correction improves downstream task performance. Our findings highlight the sensitivity of BSOU-based AI models to acquisition variability and demonstrate that automated quality assessment can pla
Segmenting fetal head structures from prenatal ultrasound remains a practical bottleneck in obstetric imaging. The current state-of-the-art baseline, proposed alongside the published dataset, adapts the Segment Anything Model with per-class Dice and Lovász losses but still depends on bounding-box prompts at test time. We build a prompt-free pipeline on top of YOLO26-Seg that jointly detects and segments three structures, Brain, Cavum Septi Pellucidi (CSP), and Lateral Ventricles (LV), in a single forward pass. Three modifications are central to our approach: (i) a composite BCE-Dice-Lovász segmentation loss with inverse-frequency class weighting, injected into the YOLO26 training loop via runtime monkey-patching; (ii) domain-guided copy-paste augmentation that transplants minority-class structures while respecting their anatomical location relative to the brain boundary; and (iii) inter-patient stratified splitting to prevent data leakage. On 575 held-out test images, the composite loss variant reaches a mean Dice coefficient of 0.9253, exceeding the baseline (0.9012) by 2.68 percentage points, despite reporting over three foreground classes only, whereas the baseline's reported me
The fragmentation of obstetric information across electronic health record modules, device repositories, and laboratory systems, as it is common in hospitals, hinders both intrapartum care and reproducible research. In this work, we present a practical blueprint for transforming heterogeneous peripartum records into computable, queryable assets by designing and prototyping a unified peripartum relational database with natural-language-to-SQL (NL2SQL) capabilities at the Obstetrics Clinic of Udine University Hospital. Requirements were co-defined with clinicians and formalized as an Entity-Relationship diagram, from which the logical schema and SQL implementation of the database were then derived. The latter integrates heterogeneous sources to connect maternal anamnestic and longitudinal history, current-pregnancy findings, intrapartum course, and delivery and neonatal outcomes. The NL2SQL layer enables clinicians to pose natural-language queries to the system, lowering barriers to audit and exploratory analysis.
The International Society of Ultrasound advocates Intrapartum Ultrasound (US) Imaging in Obstetrics and Gynecology (ISUOG) to monitor labour progression through changes in fetal head position. Two reliable ultrasound-derived parameters that are used to predict outcomes of instrumental vaginal delivery are the angle of progression (AoP) and head-symphysis distance (HSD). In this work, as part of the Intrapartum Ultrasounds Grand Challenge (IUGC) 2024, we propose an automated fetal biometry measurement pipeline to reduce intra- and inter-observer variability and improve measurement reliability. Our pipeline consists of three key tasks: (i) classification of standard planes (SP) from US videos, (ii) segmentation of fetal head and pubic symphysis from the detected SPs, and (iii) computation of the AoP and HSD from the segmented regions. We perform sparse sampling to mitigate class imbalances and reduce spurious correlations in task (i), and utilize ensemble-based deep learning methods for task (i) and (ii) to enhance generalizability under different US acquisition settings. Finally, to promote robustness in task iii) with respect to the structural fidelity of measurements, we retain th
Placenta Accreta Spectrum (PAS) is a life-threatening obstetric complication involving abnormal placental invasion into the uterine wall. Early and accurate prenatal diagnosis is essential to reduce maternal and neonatal risks. This study aimed to develop and validate a deep learning framework that enhances PAS detection by integrating multiple imaging modalities. A multimodal deep learning model was designed using an intermediate feature-level fusion architecture combining 3D Magnetic Resonance Imaging (MRI) and 2D Ultrasound (US) scans. Unimodal feature extractors, a 3D DenseNet121-Vision Transformer for MRI and a 2D ResNet50 for US, were selected after systematic comparative analysis. Curated datasets comprising 1,293 MRI and 1,143 US scans were used to train the unimodal models and paired samples of patient-matched MRI-US scans was isolated for multimodal model development and evaluation. On an independent test set, the multimodal fusion model achieved superior performance, with an accuracy of 92.5% and an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.927, outperforming the MRI-only (82.5%, AUC 0.825) and US-only (87.5%, AUC 0.879) models. Integrating MRI an
In medical practices across the United States, physicians have begun implementing generative artificial intelligence (AI) tools to perform the function of scribes in order to reduce the burden of documenting clinical encounters. Despite their widespread use, no established methods exist to gauge the quality of AI scribes. To address this gap, we developed a blinded study comparing the relative performance of large language model (LLM) generated clinical notes with those from field experts based on audio-recorded clinical encounters. Quantitative metrics from the Physician Documentation Quality Instrument (PDQI9) provided a framework to measure note quality, which we adapted to assess relative performance of AI generated notes. Clinical experts spanning 5 medical specialties used the PDQI9 tool to evaluate specialist-drafted Gold notes and LLM authored Ambient notes. Two evaluators from each specialty scored notes drafted from a total of 97 patient visits. We found uniformly high inter rater agreement (RWG greater than 0.7) between evaluators in general medicine, orthopedics, and obstetrics and gynecology, and moderate (RWG 0.5 to 0.7) to high inter rater agreement in pediatrics and
As large language models (LLMs) become primary sources of health information for millions, their accuracy in women's health remains critically unexamined. We introduce the Women's Health Benchmark (WHB), the first benchmark evaluating LLM performance specifically in women's health. Our benchmark comprises 96 rigorously validated model stumps covering five medical specialties (obstetrics and gynecology, emergency medicine, primary care, oncology, and neurology), three query types (patient query, clinician query, and evidence/policy query), and eight error types (dosage/medication errors, missing critical information, outdated guidelines/treatment recommendations, incorrect treatment advice, incorrect factual information, missing/incorrect differential diagnosis, missed urgency, and inappropriate recommendations). We evaluated 13 state-of-the-art LLMs and revealed alarming gaps: current models show approximately 60\% failure rates on the women's health benchmark, with performance varying dramatically across specialties and error types. Notably, models universally struggle with "missed urgency" indicators, while newer models like GPT-5 show significant improvements in avoiding inappro
While machine learning shows promise for maternal health risk prediction, clinical adoption in resource-constrained settings faces a critical barrier: lack of explainability and trust. This study presents a hybrid explainable AI (XAI) framework combining ante-hoc fuzzy logic with post-hoc SHAP explanations, validated through systematic clinician feedback. We developed a fuzzy-XGBoost model on 1,014 maternal health records, achieving 88.67% accuracy (ROC-AUC: 0.9703). A validation study with 14 healthcare professionals in Bangladesh revealed strong preference for hybrid explanations (71.4% across three clinical cases) with 54.8% expressing trust for clinical use. SHAP analysis identified healthcare access as the primary predictor, with the engineered fuzzy risk score ranking third, validating clinical knowledge integration (r=0.298). Clinicians valued integrated clinical parameters but identified critical gaps: obstetric history, gestational age, and connectivity barriers. This work demonstrates that combining interpretable fuzzy rules with feature importance explanations enhances both utility and trust, providing practical insights for XAI deployment in maternal healthcare.
Placenta Accreta Spectrum (PAS) is a serious obstetric condition that can be challenging to diagnose with Magnetic Resonance Imaging (MRI) due to variability in radiologists' interpretations. To overcome this challenge, a hybrid 3D deep learning model for automated PAS detection from volumetric MRI scans is proposed in this study. The model integrates a 3D DenseNet121 to capture local features and a 3D Vision Transformer (ViT) to model global spatial context. It was developed and evaluated on a retrospective dataset of 1,133 MRI volumes. Multiple 3D deep learning architectures were also evaluated for comparison. On an independent test set, the DenseNet121-ViT model achieved the highest performance with a five-run average accuracy of 84.3%. These results highlight the strength of hybrid CNN-Transformer models as a computer-aided diagnosis tool. The model's performance demonstrates a clear potential to assist radiologists by providing a robust decision support to improve diagnostic consistency across interpretations, and ultimately enhance the accuracy and timeliness of PAS diagnosis.
The integration of Large Language Models (LLMs) into healthcare demands a safety paradigm rooted in \textit{primum non nocere}. However, current alignment techniques rely on generic definitions of harm that fail to capture context-dependent violations, such as administrative fraud and clinical discrimination. To address this, we introduce Medical Malice: a dataset of 214,219 adversarial prompts calibrated to the regulatory and ethical complexities of the Brazilian Unified Health System (SUS). Crucially, the dataset includes the reasoning behind each violation, enabling models to internalize ethical boundaries rather than merely memorizing a fixed set of refusals. Using an unaligned agent (Grok-4) within a persona-driven pipeline, we synthesized high-fidelity threats across seven taxonomies, ranging from procurement manipulation and queue-jumping to obstetric violence. We discuss the ethical design of releasing these "vulnerability signatures" to correct the information asymmetry between malicious actors and AI developers. Ultimately, this work advocates for a shift from universal to context-aware safety, providing the necessary resources to immunize healthcare AI against the nuance
Accurate fetal birth weight prediction is a cornerstone of prenatal care, yet traditional methods often rely on imaging technologies that remain inaccessible in resource-limited settings. This study presents a novel machine learning-based framework that circumvents these conventional dependencies, using a diverse set of physiological, environmental, and parental factors to refine birth weight estimation. A multi-stage feature selection pipeline filters the dataset into an optimized subset, demonstrating previously underexplored yet clinically relevant predictors of fetal growth. By integrating advanced regression architectures and ensemble learning strategies, the model captures non-linear relationships often overlooked by traditional approaches, offering a predictive solution that is both interpretable and scalable. Beyond predictive accuracy, this study addresses a question: whether birth weight can be reliably estimated without conventional diagnostic tools. The findings challenge entrenched methodologies by introducing an alternative pathway that enhances accessibility without compromising clinical utility. While limitations exist, the study lays the foundation for a new era in
Recent medical vision-language models have shown promise on tasks such as VQA, report generation, and anomaly detection. However, most are adapted to structured adult imaging and underperform in fetal ultrasound, which poses challenges of multi-view image reasoning, numerous diseases, and image diversity. To bridge this gap, we introduce FetalMind, a medical AI system tailored to fetal ultrasound for both report generation and diagnosis. Guided by clinical workflow, we propose Salient Epistemic Disentanglement (SED), which injects an expert-curated bipartite graph into the model to decouple view-disease associations and to steer preference selection along clinically faithful steps via reinforcement learning. This design mitigates variability across diseases and heterogeneity across views, reducing learning bottlenecks while aligning the model's inference with obstetric practice. To train FetalMind at scale, we curate FetalSigma-1M dataset, the first large-scale fetal ultrasound report corpus, comprising 20K reports from twelve medical centers, addressing the scarcity of domain data. Extensive experiments show that FetalMind outperforms open- and closed-source baselines across all g