搜索结果：Electroencephalography and clinical neurophysiology

Current clinical artificial intelligence (AI) systems are evaluated almost exclusively on clean, standardised, English-language inputs, conditions that do not reflect the realities of healthcare delivery in low-resource settings. This study presents the first systematic dual audit of two orthogonal safety vulnerabilities in clinical AI: adversarial image fragility and cross-lingual diagnostic drift. Using DenseNet121, the architecture underlying CheXNet, fine-tuned on the COVID-QU-Ex chest X-ray dataset (85,318 images; COVID-19, Non-COVID Pneumonia, Normal), we demonstrate that diagnostic accuracy collapses from 89.3% to 62.0% under a Fast Gradient Method (FGM) perturbation of epsilon=0.021, a magnitude imperceptible to the human eye. Standard defensive strategies including Gaussian smoothing and ensemble voting failed to restore clinical safety. In a parallel language fragility experiment, we tested Llama3.1:8b and NatLAS (N-ATLAS) on 20 COVID-19 clinical cases presented in Standard English, Nigerian Pidgin (Naija), and Yoruba-inflected English. Both models exhibited significant accuracy degradation: Llama3.1:8b dropped from 80.0% to 65.0% on Pidgin; NatLAS, an African-context mod

Empiric antibiotic prescribing in high-risk clinical contexts often requires decision making under conditions of incomplete information, where inappropriate coverage or unjustified escalation may compromise safety and antimicrobial stewardship. While clinical decision-support systems have been proposed to assist in this process, many approaches lack explicit governance and evaluation mechanisms defining scope, abstention conditions, recommendation permissibility, and expected system behavior. This work specifies a governance and evaluation framework for deterministic clinical decision-support systems operating under explicitly constrained scope. Deterministic behavior is adopted to ensure that identical inputs yield identical outputs, supporting transparency, auditability, and conservative decision support in high-risk prescribing contexts. The framework treats governance as a first-class design component, separating clinical decision logic from rule-based mechanisms that determine whether a recommendation may be issued. Explicit abstention, deterministic stewardship constraints, and exclusion rules are formalized as core constructs. The framework defines an evaluation methodology

Accurate segmentation of pulmonary vessels plays a very critical role in diagnosing and assessing various lung diseases. Currently, many automated algorithms are primarily targeted at CTPA (Computed Tomography Pulmonary Angiography) types of data. However, the segmentation precision of these methods is insufficient, and support for NCCT (Non-Contrast Computed Tomography) types of data is also a requirement in some clinical scenarios. In this study, we propose a 3D image segmentation algorithm for automated pulmonary vessel segmentation from both contrast-enhanced and non-contrast CT images. In the network, we designed a Vessel Lumen Structure Optimization Module (VLSOM), which extracts the centerline (Cl) of vessels and adjusts the weights based on the positional information and adds a Cl-Dice Loss to supervise the stability of the vessels structure. We used 427 sets of high-precision annotated CT data from multiple vendors and countries to train the model and achieved Cl-DICE, Cl-Recall, and Recall values of 0.892, 0.861, 0.924 for CTPA data and 0.925, 0.903, 0.949 for NCCT data. This shows that our model has achieved good performance in both accuracy and completeness of pulmonary

Developing AI models that are useful in clinical practice, requires efficient collaboration between clinicians and AI developers. This poses a practical challenge: clinicians must repeatedly communicate and refine their requirements with AI developers before those requirements can be translated into executable model development. This iterative process is time-consuming, and even after repeated discussion, misalignment may still exist because the two sides do not fully share each other's expertise. Coding agents may help close this gap. They can write and refine code on their own, and they carry working knowledge of both medicine and AI to understand commands formulated by both medical experts and developers. We present a prototype that lets clinicians drive AI development directly. A clinician describes the task in plain language, and the system turns the description into a working pipeline, refines it through repeated experiments together with the clinician, and returns a model that meets the stated clinical objective. Across five clinical tasks, the system reliably produces models that matched the clinician's request and reached competitive performance. Most notably, on chest rad

We introduce Clinical ModernBERT, a transformer based encoder pretrained on large scale biomedical literature, clinical notes, and medical ontologies, incorporating PubMed abstracts, MIMIC IV clinical data, and medical codes with their textual descriptions. Building on ModernBERT the current state of the art natural language text encoder featuring architectural upgrades such as rotary positional embeddings (RoPE), Flash Attention, and extended context length up to 8,192 tokens our model adapts these innovations specifically for biomedical and clinical domains. Clinical ModernBERT excels at producing semantically rich representations tailored for long context tasks. We validate this both by analyzing its pretrained weights and through empirical evaluation on a comprehensive suite of clinical NLP benchmarks.

This paper describes our approach to the MEDIQA-CORR shared task, which involves error detection and correction in clinical notes curated by medical professionals. This task involves handling three subtasks: detecting the presence of errors, identifying the specific sentence containing the error, and correcting it. Through our work, we aim to assess the capabilities of Large Language Models (LLMs) trained on a vast corpora of internet data that contain both factual and unreliable information. We propose to comprehensively address all subtasks together, and suggest employing a unique prompt-based in-context learning strategy. We will evaluate its efficacy in this specialized task demanding a combination of general reasoning and medical knowledge. In medical systems where prediction errors can have grave consequences, we propose leveraging self-consistency and ensemble methods to enhance error correction and error detection performance.

We introduce SoftTiger, a clinical large language model (CLaM) designed as a foundation model for healthcare workflows. The narrative and unstructured nature of clinical notes is a major obstacle for healthcare intelligentization. We address a critical problem of structuring clinical notes into clinical data, according to international interoperability standards. We collect and annotate data for three subtasks, namely, international patient summary, clinical impression and medical encounter. We then supervised fine-tuned a state-of-the-art LLM using public and credentialed clinical data. The training is orchestrated in a way that the target model can first support basic clinical tasks such as abbreviation expansion and temporal information extraction, and then learn to perform more complex downstream clinical tasks. Moreover, we address several modeling challenges in the healthcare context, e.g., extra long context window. Our blind pairwise evaluation shows that SoftTiger outperforms other popular open-source models and GPT-3.5, comparable to Gemini-pro, with a mild gap from GPT-4. We believe that LLMs may become a step-stone towards healthcare digitalization and democratization.

Bioinformatics platforms have significantly changed clinical diagnostics by facilitating the analysis of genomic data, thereby advancing personalized medicine and improving patient care. This study examines the integration, usage patterns, challenges, and impact of the Galaxy platform within clinical diagnostics laboratories. We employed a convergent parallel mixed-methods design, collecting quantitative survey data and qualitative insights from structured interviews with fifteen participants across various clinical roles. The findings indicate a wide adoption of Galaxy, with participants expressing high satisfaction due to its user-friendly interface and notable improvements in workflow efficiency and diagnostic accuracy. Challenges such as data security and training needs were also identified, highlighting the platform's role in simplifying complex data analysis tasks. This study contributes to understanding the transformative potential of Galaxy in clinical practice and offers recommendations for optimizing its integration and functionality. These insights are crucial for advancing clinical diagnostics and enhancing patient outcomes.

Deep Learning (DL) has the potential to optimize machine learning in both the scientific and clinical communities. However, greater expertise is required to develop DL algorithms, and the variability of implementations hinders their reproducibility, translation, and deployment. Here we present the community-driven Generally Nuanced Deep Learning Framework (GaNDLF), with the goal of lowering these barriers. GaNDLF makes the mechanism of DL development, training, and inference more stable, reproducible, interpretable, and scalable, without requiring an extensive technical background. GaNDLF aims to provide an end-to-end solution for all DL-related tasks in computational precision medicine. We demonstrate the ability of GaNDLF to analyze both radiology and histology images, with built-in support for k-fold cross-validation, data augmentation, multiple modalities and output classes. Our quantitative performance evaluation on numerous use cases, anatomies, and computational tasks supports GaNDLF as a robust application framework for deployment in clinical workflows.

Clinical trials are critical in advancing medical treatments but often suffer from immense time and financial burden. Advances in statistical methodologies and artificial intelligence (AI) present opportunities to address these inefficiencies. Here we introduce Prognostic Covariate-Adjusted Mixed Models for Repeated Measures (PROCOVA-MMRM) as an advantageous combination of prognostic covariate adjustment (PROCOVA) and Mixed Models for Repeated Measures (MMRM). PROCOVA-MMRM utilizes time-matched prognostic scores generated from AI models to enhance the precision of treatment effect estimators for longitudinal continuous outcomes, enabling reductions in sample size and enrollment times. We first provide a description of the background and implementation of PROCOVA-MMRM, followed by two case study reanalyses where we compare the performance of PROCOVA-MMRM versus the unadjusted MMRM. These reanalyses demonstrate significant improvements in statistical power and precision in clinical indications with unmet medical need, specifically Alzheimer's Disease (AD) and Amyotrophic Lateral Sclerosis (ALS). We also explore the potential for sample size reduction with the prospective implementati

Despite the plethora of AI-based algorithms developed for anomaly detection in radiology, subsequent integration into clinical setting is rarely evaluated. In this work, we assess the applicability and utility of an AI-based model for brain aneurysm detection comparing the performance of two readers with different levels of experience (2 and 13 years). We aim to answer the following questions: 1) Do the readers improve their performance when assisted by the AI algorithm? 2) How much does the AI algorithm impact routine clinical workflow? We reuse and enlarge our open-access, Time-Of-Flight Magnetic Resonance Angiography dataset (N=460). We use 360 subjects for training/validating our algorithm and 100 as unseen test set for the reading session. Even though our model reaches state-of-the-art results on the test set (sensitivity=74%, false positive rate=1.6), we show that neither the junior nor the senior reader significantly increase their sensitivity (p=0.59, p=1, respectively). In addition, we find that reading time for both readers is significantly higher in the "AI-assisted" setting than in the "Unassisted" (+15 seconds, on average; p=3x10^(-4) junior, p=3x10^(-5) senior). The c

Background: LLM judges increasingly score whether clinical language models give overconfident answers under incomplete evidence, yet whether a measured "safety gain" reflects real behavior change or the judge's calibration is unresolved. Using a structured evidence-sufficiency prompt as a test case, we asked whether it reduces unsafe overconfident answers, how far that effect depends on the scoring judge, and what it costs in helpfulness. Methods: In a retrospective public-data benchmark (Real-POCQi, HealthBench, MedRBench), four models (GPT-5.5, Claude Opus 4.8, Gemini 3.5 Flash, Grok 4.3) answered a fully paired common panel (1,200 cells) with a standard prompt and the wrapper. The pre-specified endpoint was the paired reduction in unsafe overconfidence scored by the primary judge (GPT-5.4-nano); secondary analyses added a different-family judge (Claude Sonnet 5), a correctness judge, matched scaffold controls, and a blinded three-clinician review. Results: Unsafe overconfidence fell from 49.3% to 24.7%, a paired reduction of 24.7 points (95% CI 21.8-27.7; p<0.001), robust in direction across models and paraphrases. Magnitude was judge-dependent: Sonnet agreed on direction but

The increasing availability of unstructured clinical narratives in electronic health records (EHRs) has created new opportunities for automated disease characterization, cohort identification, and clinical decision support. However, modeling long, domain-specific clinical text remains challenging due to limited labeled data, severe class imbalance, and the high computational cost of adapting large pretrained language models. This study presents a GPT-based architecture for clinical text classification that adapts a pretrained decoder-only Transformer using a selective fine-tuning strategy. Rather than updating all model parameters, the majority of the GPT-2 backbone is frozen, and training is restricted to the final Transformer block, the final layer normalization, and a lightweight classification head. This approach substantially reduces the number of trainable parameters while preserving the representational capacity required to model complex clinical language. The proposed method is evaluated on radiology reports from the MIMIC-IV-Note dataset using uncertainty-aware CheXpert-style labels derived directly from report text. Experiments cover multiple problem formulations, includi

Clinical NLP increasingly relies on electronic health record (EHR) data to detect suicidal behaviors, treating clinical documentation as more reliable ground truth than social media. We argue that this framing obscures how EHR-based suicidality datasets encode a particular operationalization of suicidality, shaped by who authors the data, how episodes are bounded, and how ambiguity is resolved. We ground this argument in a case study of the ScAN dataset, built over MIMIC-III clinical notes. We show how governance constraints, ICD-based cohort selection, single-annotator labeling, and hospital-stay-level aggregation produce labels that reflect clinician-documented judgments, treat suicidality as a bounded episode, and assume that intent can be reliably inferred from documentation. A linguistic analysis demonstrates that identical labels subsume heterogeneous clinical framings differing in temporality, negation, and uncertainty. We argue that clinical NLP should examine the assumptions embedded in suicidality datasets before interpreting their labels as ground truth.

Objective: Integrating EHR data with other resources is essential in rare disease research due to low disease prevalence. Such integration is dependent on the alignment of ontologies used for data annotation. The International Classification of Diseases (ICD) is used to annotate clinical diagnoses; the Human Phenotype Ontology (HPO) to annotate phenotypes. Although these ontologies overlap in biomedical entities described, the extent to which they are interoperable is unknown. We investigate how well aligned these ontologies are and whether such alignments facilitate EHR data integration. Materials and Methods: We conducted an empirical analysis of the coverage of mappings between ICD and HPO. We interpret this mapping coverage as a proxy for how easily clinical data can be integrated with research ontologies such as HPO. We quantify how exhaustively ICD codes are mapped to HPO by analyzing mappings in the UMLS Metathesaurus. We analyze the proportion of ICD codes mapped to HPO within a real-world EHR dataset. Results and Discussion: Our analysis revealed that only 2.2% of ICD codes have direct mappings to HPO in UMLS. Within our EHR dataset, less than 50% of ICD codes have mapping

Defining the Inclusion/Exclusion (I/E) criteria of a trial is one of the most important steps during a trial design. Increasingly complex I/E criteria potentially create information imbalance and transparency issues between the people who design and run the trials and those who consume the information produced by the trials. In order to better understand and quantify the impact of a category of I/E criteria on observed treatment effects, a concept, named the Selection Induced Contrast Estimate (SICE) effect, is introduced and formulated in this paper. The SICE effect can exist in controlled clinical trials when treatment affects the correlation between a marker used for selection and the response of interest. This effect is demonstrated with both simulations and real clinical trial data. Although the statistical elements behind the SICE effect have been well studied, explicitly formulating and studying this effect can benefit several areas, including better transparency in I/E criteria, meta-analysis of multiple clinical trials, treatment effect interpretation in real-world medical practice, etc.

Introduction: Semantic search, which retrieves documents based on conceptual similarity rather than keywords, offers advantages for retrieval of clinical information. However, deploying semantic search across health systems, comprising hundreds of millions of clinical notes, presents formidable engineering, cost, and governance challenges that have prevented institutional adoption. Methods: We deployed a semantic search system at a large children's hospital indexing 166 million clinical notes (484 million embedding vectors) from 1.68 million patients. The system uses instruction-tuned qwen3-embedding-0.6B embeddings, stores vectors with storage-optimized indexing, maintains full-text metadata in a low-latency key-value store, and operates within a HIPAA-compliant governance framework. We evaluated the system by optimizing the model and chunking strategy using a physician-authored benchmark, characterizing full-scale performance (cost, latency, retrieval quality), and assessing clinical utility via chart abstraction efficiency and comparison to ICD-10 cohort generation. Results: The system delivers sub-second query latency with monthly operational costs of ~USD 4,000. Qwen3 embeddin

Temporal information extraction from unstructured text is essential for contextualizing events and deriving actionable insights, particularly in the medical domain. We address the task of extracting clinical events and their temporal relations using the well-studied I2B2 2012 Temporal Relations Challenge corpus. This task is inherently challenging due to complex clinical language, long documents, and sparse annotations. We introduce GRAPHTREX, a novel method integrating span-based entity-relation extraction, clinical large pre-trained language models (LPLMs), and Heterogeneous Graph Transformers (HGT) to capture local and global dependencies. Our HGT component facilitates information propagation across the document through innovative global landmarks that bridge distant entities. Our method improves the state-of-the-art with 5.5% improvement in the tempeval $F_1$ score over the previous best and up to 8.9% improvement on long-range relations, which presents a formidable challenge. We further demonstrate generalizability by establishing a strong baseline on the E3C corpus. This work not only advances temporal information extraction but also lays the groundwork for improved diagnosti

Background: Well-designed phase II trials must have acceptable error rates relative to a pre-specified success criterion, usually a statistically significant p-value. Such standard designs may not always suffice from a clinical perspective because clinical relevance may call for more. For example, proof-of-concept in phase II often requires not only statistical significance but also a sufficiently large effect estimate. Purpose: We propose dual-criterion designs to complement statistical significance with clinical relevance, discuss their methodology, and illustrate their implementation in phase II. Methods: Clinical relevance requires the effect estimate to pass a clinically motivated threshold (the decision value). In contrast to standard designs, the required effect estimate is an explicit design input whereas study power is implicit. The sample size for a dual-criterion design needs careful considerations of the study's operating characteristics (type-I error, power). Results: Dual-criterion designs are discussed for a randomized controlled and a single-arm phase II trial, including decision criteria, sample size calculations, decisions under various data scenarios, and operati