clinical data curation and annotation

Clinical workflow fragmentation severely impedes efficiency: heterogeneous scripting, ad-hoc model ensembles, and lack of data-driven modality identification and standardized outputs result in high deployment overhead, costly monitoring, and poor interoperability. To address this, we propose a healthcare-first vision-language unified framework that pioneers the use of a single vision-language model (VLM) for two-tier clinical decision-making—first, an auditable, three-stage routing mechanism matches inputs to expert-defined model cards; second, domain-specific multi-task joint inference (with early-exit capability and candidate arbitration) adheres to clinical risk constraints. Leveraging phased prompting, a candidate answer selector, and specialty-specific fine-tuning, our framework unifies modality identification, abnormality classification, model selection, and multi-task reasoning. Evaluated across gastroenterology, hematology, ophthalmology, and pathology, our single-model solution achieves performance on par with specialized models while substantially reducing deployment complexity, operational overhead, and integration effort.

Clinical pathway modeling traditionally relies on manual design and struggles to adapt to disease variants and comorbidities. To address this, we propose a two-stage process mining framework: (1) automatic discovery of process models from electronic health records (using Synthea-simulated SARS-CoV-2 data) via algorithms such as Heuristic Miner; and (2) dynamic expansion of the clinical pathway knowledge base through conformance checking, enabling subtype- and comorbidity-aware fine-grained modeling. Our key contribution lies in tightly coupling process mining with iterative, feedback-driven knowledge base updates—balancing real-world practice diversity with model interpretability. Experimental evaluation demonstrates that our method achieves 95.62% AUC in pathway identification and 67.11% arc simplicity, significantly outperforming static modeling approaches.

Multi-center critical care data in OMOP CDM format exhibits institutional heterogeneity, inconsistent terminology, and massive scale, hindering interoperable clinical AI research. Method: We propose a modular, parallel processing framework integrating SNOMED-CT–based terminology standardization, cross-source deduplication, and unit-of-measure harmonization, coupled with end-to-end audit tracing and benchmark model evaluation. We innovatively design a cross-terminology mapping mechanism and a transparent data quality governance pipeline. Contribution/Results: The framework achieves full-scale, end-to-end processing within 24 hours on standard hardware, producing machine-learning–ready datasets. Our open-source pipeline and baseline models reduce preprocessing effort from months to under one day, significantly lowering barriers to entry. This enables reproducible, generalizable clinical AI research grounded in standardized, auditable, and high-quality multi-center critical care data.

This study addresses the scarcity of structured, context-rich experimental data in targeted protein degradation (TPD), which has hindered the development of computational models. To overcome this limitation, the authors propose the first expert-in-the-loop large language model (LLM) agent framework tailored for TPD. By integrating lightweight prompt optimization, terminology-aware transfer, and a triangulation-based validation mechanism, the framework automatically extracts multidimensional information—including compounds, targets, recruiters, and critical experimental conditions—from scientific literature. Requiring only minimal annotated data, it achieves high-accuracy cross-task transfer. The resulting molecular glue and PROTAC databases are expanded by 81% and 92%, respectively, with expert-validated accuracy rates of 92% and 82.5%, substantially enhancing condition-aware modeling of degrader activity.

Scientists frequently record experimental metadata in spreadsheets, yet ensuring consistency and standards compliance remains challenging. This paper introduces a spreadsheet-native metadata governance paradigm: customized Excel/CSV templates embed HuBMAP standards; OWL/SKOS ontology-driven controlled vocabularies are integrated; and a web-based real-time semantic validation tool enables immediate, on-entry verification. The approach seamlessly incorporates semantic constraints into familiar spreadsheet workflows—requiring no platform switching or new system adoption. Deployed across the HuBMAP Consortium, it significantly improved multi-omics metadata compliance rates, increased data entry efficiency, and reduced error identification and correction time by over 70%. To our knowledge, this is the first work to deeply embed ontology-based constraints and real-time semantic validation directly within spreadsheet environments, establishing a scalable, practical paradigm for biomedical metadata standardization.

This study addresses the critical yet underexamined role of data filtering in clinical machine learning, which alters statistical structures and directly impacts task complexity and model performance. Despite these effects, existing research frequently treats filtering as routine preprocessing with insufficient transparency. This work reconceptualizes data filtering as a core component of the scientific method, advocating its integration into the broader research paradigm rather than its treatment as a mere technical step. To this end, we develop a transparent and interpretable clinical data preprocessing pipeline and release the corresponding code as open source. Our analysis elucidates the mechanisms through which filtering decisions critically influence data distributions and downstream model efficacy. Ultimately, this research provides a novel framework for enhancing methodological rigor and reproducibility in clinical artificial intelligence studies.

This study addresses the frequent violations of clinical coding standards—such as ICD-10, CPT, and HL7 FHIR—by large language models when generating structured medical data, which impedes integration with electronic health record systems. To mitigate this, the authors propose and validate a closed-loop verification-and-repair framework that automatically detects and iteratively corrects formatting errors. The approach is evaluated using three open-source models—Qwen2.5-7B, Llama3.1-8B, and Gemma2-9B—deployed locally across 320 clinical scenarios. Results demonstrate a substantial improvement in schema compliance across all models, achieving an overall adherence rate of 99.0% and increasing individual model performance by 7.8 to 12.5 percentage points. Notably, 96% of detected errors were attributable to repairable representation-layer issues, with most resolved within one or two correction rounds, effectively compensating for the models’ limited understanding of healthcare IT standards.

研究针对肿瘤文档信息提取难题，提出并评估了一种名为nMAS的多代理系统工作流方法，实现临床相关结构化数据的高效提取。

This work addresses the scarcity of real-world clinical text due to privacy constraints, which hinders the development of clinical AI systems. The authors propose a modular synthetic data generation pipeline that integrates structured patient modeling, semi-structured clinical course simulation, and large language model (LLM)-driven generation of unstructured clinical notes. This approach ensures longitudinal consistency and clinical plausibility while enabling diverse writing styles. Innovatively, the framework incorporates an LLM-based validation and refinement mechanism to enhance the fidelity and realism of the synthetic data. The study releases a benchmark dataset comprising 70 virtual patients, each with 20–50 clinical notes spanning their entire hospitalization, offering a high-quality, scalable resource for developing and evaluating clinical AI tools.

本文提出数据医院概念，通过十阶段工作流结合人为控制与交互模型解决研究数据质量问题，提高评估、干预及过程可追溯性。