Enhancing Named Entity Recognition for immunology and immune-mediated disorders.

Text mining is increasingly used to manage the accelerating pace of the biomedical literature. Many text mining applications depend on accurate named entity recognition (NER) and normalization (grounding). While high performing machine learning methods trainable for many entity types exist for NER, normalization methods are usually specialized to a single entity type. NER and normalization systems are also typically used in a serial pipeline, causing cascading errors and limiting the ability of the NER system to directly exploit the lexical information provided by the normalization. We propose the first machine learning model for joint NER and normalization during both training and prediction. The model is trainable for arbitrary entity types and consists of a semi-Markov structured linear classifier, with a rich feature approach for NER and supervised semantic indexing for normalization. We also introduce TaggerOne, a Java implementation of our model as a general toolkit for joint NER and normalization. TaggerOne is not specific to any entity type, requiring only annotated training data and a corresponding lexicon, and has been optimized for high throughput. We validated TaggerOne with multiple gold-standard corpora containing both mention- and concept-level annotations. Benchmarking results show that TaggerOne achieves high performance on diseases (NCBI Disease corpus, NER f-score: 0.829, normalization f-score: 0.807) and chemicals (BioCreative 5 CDR corpus, NER f-score: 0.914, normalization f-score 0.895). These results compare favorably to the previous state of the art, notwithstanding the greater flexibility of the model. We conclude that jointly modeling NER and normalization greatly improves performance. The TaggerOne source code and an online demonstration are available at: http://www.ncbi.nlm.nih.gov/bionlp/taggerone zhiyong.lu@nih.gov Supplementary data are available at Bioinformatics online.

Using clinical decision support systems (CDSSs) for breast cancer management necessitates to extract relevant patient data from textual reports which is a complex task although efficiently achieved by machine learning but black box methods. We proposed a rule-based natural language processing (NLP) method to automate the translation of breast cancer patient summaries into structured patient profiles suitable for input into the guideline-based CDSS of the DESIREE project. Our method encompasses named entity recognition (NER), relation extraction and structured data extraction to systematically organize patient data. The method demonstrated strong alignment with treatment recommendations generated for manually created patient profiles (gold standard) with only 2% of differences. Moreover, the NER pipeline achieved an average F1-score of 0.9 across the main entities (patient, side, and tumor), of 0,87 for relation extraction, and 0.75 for contextual information, showing promising results for rule-based NLP.

Report on the Barbados Workshop

Extracting entities and relations for types of interest from text is important for understanding massive text corpora. Traditionally, systems of entity relation extraction have relied on human-annotated corpora for training and adopted an incremental pipeline. Such systems require additional human expertise to be ported to a new domain, and are vulnerable to errors cascading down the pipeline. In this paper, we investigate joint extraction of typed entities and relations with labeled data heuristically obtained from knowledge bases (i.e., distant supervision). As our algorithm for type labeling via distant supervision is context-agnostic, noisy training data poses unique challenges for the task. We propose a novel domain-independent framework, called CoType, that runs a data-driven text segmentation algorithm to extract entity mentions, and jointly embeds entity mentions, relation mentions, text features and type labels into two low-dimensional spaces (for entity and relation mentions respectively), where, in each space, objects whose types are close will also have similar representations. CoType, then using these learned embeddings, estimates the types of test (unlinkable) mentions. We formulate a joint optimization problem to learn embeddings from text corpora and knowledge bases, adopting a novel partial-label loss function for noisy labeled data and introducing an object "translation" function to capture the cross-constraints of entities and relations on each other. Experiments on three public datasets demonstrate the effectiveness of CoType across different domains (e.g., news, biomedical), with an average of 25% improvement in F1 score compared to the next best method.

To improve pathophysiology research, biomarker discovery and drug development, cell culture models should adequately mimic human (patho)physiology and provide reproducible results. This requires comparison between cultured cells/tissue and actual histopathology in the patient, as well as standardization of culture experiments to ensure experimental reproducibility, preferably in a quantitative manner1. 10-15 signal transduction pathways govern major cellular processes, e.g. cell division, differentiation and migration. The past decade we developed tests to quantitatively measure functional activity of signal transduction pathways in individual cell/tissue samples, based on Bayesian computational model inference of pathway activity from measurements of mRNA levels of target genes of the transcription factor associated with the respective signalling pathway. Tests provide quantitative pathway activity scores and are intended to be used for diagnostics and life sciences research2-4. Method: Tests have been developed for androgen (AR) and estrogen receptor (ER), Hedgehog (HH), Wnt, TGFβ, Notch, NFκB, PI3K, JAK-STAT 1/2 and 3, and MAPK pathways. After calibration and freezing of the models, extensive biological test validation was performed on healthy/diseased cell and tissue types, including multiple cancer, fibroblast and immune cell types. Using Affymetrix expression microarray data (GEO database) >900 cell lines of most cell and cancer types were analyzed, as well as primary cultures of most immune cell types. LnCaP (prostate), MCF7, BT474 (breast), HCC827 (lung) and A2780 (ovarian) cancer cell lines were compared across laboratories. Results: Typical expected single or combined pathway activities were confirmed, e.g. ER activity in breast, AR activity in prostate, and Wnt activity in colon cancer; HH activity in soft tissue tumor, NFκB activity in lymphoma, frequently combined with PI3K and/or MAPK and/or JAK-STAT growth factor pathways. Quantitative pathway activities were reproducible within studies, but highly variable between labs, and dependent on culture conditions. Conclusion: Our pathway tests measure signaling pathway activity in many cell and tissue types, and can be used as quantitative readout for cell/tissue culture. Applications are: standardization of cell/tissue culture to ensure reproducibility; comparison between culture-based disease model and patient histopathology; quantitative assessment of drug efficacy on disease models; assessment of toxicity on healthy cell/tissue models. A number of tests have been adapted to qPCR, enabling use on FFPE tissue and small samples. 1 Ben-David U, et al. Nature, 2018;560(7718):325; 2 Verhaegh W, et al. Cancer Res 2014;74(11):2936-45; 3 Verhaegh W, Stolpe A van de. Oncotarget, 2014:5(14):5196-7; 4 Ooijen H. van, et al. Am J Pathol 2018;188(9):1956-1972 Citation Format: Anja Van De Stolpe, Marcia Alves de Inda, Eveline den Biezen-Timmermans, Laurent Holtzer, Henk van Ooijen, Wim Verhaegh. Quantitative measurement of multiple signal transduction pathway activities in cell and tissue culture, including cancer, fibroblast, and immune cell types [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 2645.

BackgroundBioinformatics tools for automatic processing of biomedical literature are invaluable for both the design and interpretation of large-scale experiments. Many information extraction (IE) systems that incorporate natural language processing (NLP) techniques have thus been developed for use in the biomedical field. A key IE task in this field is the extraction of biomedical relations, such as protein-protein and gene-disease interactions. However, most biomedical relation extraction systems usually ignore adverbial and prepositional phrases and words identifying location, manner, timing, and condition, which are essential for describing biomedical relations. Semantic role labeling (SRL) is a natural language processing technique that identifies the semantic roles of these words or phrases in sentences and expresses them as predicate-argument structures. We construct a biomedical SRL system called BIOSMILE that uses a maximum entropy (ME) machine-learning model to extract biomedical relations. BIOSMILE is trained on BioProp, our semi-automatic, annotated biomedical proposition bank. Currently, we are focusing on 30 biomedical verbs that are frequently used or considered important for describing molecular events.ResultsTo evaluate the performance of BIOSMILE, we conducted two experiments to (1) compare the performance of SRL systems trained on newswire and biomedical corpora; and (2) examine the effects of using biomedical-specific features. The experimental results show that using BioProp improves the F-score of the SRL system by 21.45% over an SRL system that uses a newswire corpus. It is noteworthy that adding automatically generated template features improves the overall F-score by a further 0.52%. Specifically, ArgM-LOC, ArgM-MNR, and Arg2 achieve statistically significant performance improvements of 3.33%, 2.27%, and 1.44%, respectively.ConclusionWe demonstrate the necessity of using a biomedical proposition bank for training SRL systems in the biomedical domain. Besides the different characteristics of biomedical and newswire sentences, factors such as cross-domain framesets and verb usage variations also influence the performance of SRL systems. For argument classification, we find that NE (named entity) features indicating if the target node matches with NEs are not effective, since NEs may match with a node of the parsing tree that does not have semantic role labels in the training set. We therefore incorporate templates composed of specific words, NE types, and POS tags into the SRL system. As a result, the classification accuracy for adjunct arguments, which is especially important for biomedical SRL, is improved significantly.

<div>Abstract<p>Oncology drug efficacy is evaluated in mouse models by continuously monitoring tumor volumes, which can be mathematically described by growth kinetic models. Although past studies have investigated various growth models, their reliance on small datasets raises concerns about whether their findings are truly representative of tumor growth in diverse mouse models under different vehicle or drug treatments. In this study, we systematically evaluated six parametric models (exponential, exponential quadratic, monomolecular, logistic, Gompertz, and von Bertalanffy) and the semiparametric generalized additive model (GAM) on fitting tumor volume data from more than 30,000 mice in 930 experiments conducted in patient-derived xenografts, cell line–derived xenografts, and syngeneic models. We found that the exponential quadratic model is the best parametric model and can adequately model 87% studies, higher than other models including von Bertalanffy (82%) and Gompertz (80%) models; the latter is often considered the standard growth model. At the mouse group level, 7.5% of growth data could not be fit by any parametric model and were fitted by GAM. We show that endpoint gain integrated in time, a GAM-derived efficacy metric, is equivalent to exponential growth rate, a metric we previously proposed and conveniently calculated by simple algebra. Using five studies on paclitaxel, anti-PD1 antibody, cetuximab, irinotecan, and sorafenib, we showed that exponential and exponential quadratic models achieve similar performance in uncovering drug mechanism and biomarkers. We also compared exponential growth rate–based association analysis and exponential modeling approach in biomarker discovery and found that they complement each other. Modeling methods herein are implemented in an open-source R package freely available at <a href="https://github.com/hjzhou988/TuGroMix" target="_blank">https://github.com/hjzhou988/TuGroMix</a>.</p>Significance:<p>We present a general strategy for mathematically modeling tumor growth in mouse models using data from 30,000 mice and show that modeling and nonmodeling approaches are complementary in biomarker discovery and drug mechanism studies.</p></div>

Several recent studies showed that the application of deep neural networks advanced the state-of-the-art in named entity recognition (NER), including biomedical NER. However, the impact on performance and the robustness of improvements crucially depends on the availability of sufficiently large training corpora, which is a problem in the biomedical domain with its often rather small gold standard corpora. We evaluate different methods for alleviating the data sparsity problem by pretraining a deep neural network (LSTM-CRF), followed by a rather short fine-tuning phase focusing on a particular corpus. Experiments were performed using 34 different corpora covering five different biomedical entity types, yielding an average increase in F1-score of ∼2 pp compared to learning without pretraining. We experimented both with supervised and semi-supervised pretraining, leading to interesting insights into the precision/recall trade-off. Based on our results, we created the stand-alone NER tool HUNER incorporating fully trained models for five entity types. On the independent CRAFT corpus, which was not used for creating HUNER, it outperforms the state-of-the-art tools GNormPlus and tmChem by 5-13 pp on the entity types chemicals, species and genes. HUNER is freely available at https://hu-ner.github.io. HUNER comes in containers, making it easy to install and use, and it can be applied off-the-shelf to arbitrary texts. We also provide an integrated tool for obtaining and converting all 34 corpora used in our evaluation, including fixed training, development and test splits to enable fair comparisons in the future. Supplementary data are available at Bioinformatics online.

This paper reviews the current research on Alzheimer's disease and the use of deep learning, particularly 3D-convolutional neural networks (3D-CNN), in analyzing brain images. It presents a predictive model based on MRI and clinical data from the ADNI dataset, showing that deep learning can improve diagnosis accuracy and sensitivity. We also discuss potential applications in biomarker discovery, disease progression prediction, and personalised treatment planning, highlighting the ability to identify sensitive features for early diagnosis.

Named entity recognition (NER) plays a vital role in extracting critical medical entities from health care records, facilitating applications such as clinical decision support and data mining. Developing robust NER models for low-resource languages, such as Estonian, remains a challenge due to the scarcity of annotated data and domain-specific pretrained models. Large language models (LLMs) have proven to be promising in understanding text from any language or domain. This study addresses the development of medical NER models for low-resource languages, specifically Estonian. We propose a novel approach by generating synthetic health care data and using LLMs to annotate them. These synthetic data are then used to train a high-performing NER model, which is applied to real-world medical texts, preserving patient data privacy. Our approach to overcoming the shortage of annotated Estonian health care texts involves a three-step pipeline: (1) synthetic health care data are generated using a locally trained GPT-2 model on Estonian medical records, (2) the synthetic data are annotated with LLMs, specifically GPT-3.5-Turbo and GPT-4, and (3) the annotated synthetic data are then used to fine-tune an NER model, which is later tested on real-world medical data. This paper compares the performance of different prompts; assesses the impact of GPT-3.5-Turbo, GPT-4, and a local LLM; and explores the relationship between the amount of annotated synthetic data and model performance. The proposed methodology demonstrates significant potential in extracting named entities from real-world medical texts. Our top-performing setup achieved an F1-score of 0.69 for drug extraction and 0.38 for procedure extraction. These results indicate a strong performance in recognizing certain entity types while highlighting the complexity of extracting procedures. This paper demonstrates a successful approach to leveraging LLMs for training NER models using synthetic data, effectively preserving patient privacy. By avoiding reliance on human-annotated data, our method shows promise in developing models for low-resource languages, such as Estonian. Future work will focus on refining the synthetic data generation and expanding the method's applicability to other domains and languages.

The rapid digitization of healthcare data has led to an exponential increase in unstructured clinical text, necessitating the integration of Natural Language Processing (NLP) in Medical Information Science. This research explores deep learning-based NLP techniques for clinical text analysis, focusing on Named Entity Recognition (NER), disease classification, adverse drug reaction detection, and clinical text summarization. The study leverages state-of-the-art transformer models such as BioBERT, ClinicalBERT, and GPT-4 Medical, which demonstrate superior performance in extracting key medical entities, classifying diseases, and summarizing electronic health records (EHRs). Experimental results on benchmark datasets such as MIMIC-III, i2b2, and ClinicalTrials.gov show that ClinicalBERT outperforms traditional ML models by achieving an F1-score of 89.9% in NER tasks, while GPT-4 Medical improves EHR summarization efficiency by 40%. By means of automated medical documentation, clinical decision support, and real-time adverse drug event detection which integrates NLP into healthcare systems diagnostic accuracy, physician efficiency, and patient safety are much improved. NLP-driven medical text analysis has great potential to transform clinical procedures and raise patient outcomes despite obstacles like computing costs, data privacy issues, and model interpretability. Improving domain-specific AI models, maximising real-time processing, and guaranteeing ethical AI deployment in healthcare should be the key priorities of next studies.

The introduction of foundational models, specifically large language models, has promised a health care transformation. However, the field is rapidly evolving toward autonomous agent systems, defined as artificial intelligence (AI) entities that perceive and react to their environment to achieve specific goals-representing a paradigm shift from passive information retrieval to proactive, goal-oriented clinical assistance. Agentic AI systems transcend static knowledge limitations through core capabilities including persistent memory systems that maintain context across patient encounters, knowledge retrieval tools connecting to medical repositories through retrieval-augmented generation techniques, and computer use functionality enabling navigation of clinical software interfaces. Agentic workflows introduce sophisticated coordination mechanisms including hierarchical, collaborative, and sequential patterns demonstrating superior performance compared with single-agent approaches. Multiagent systems can autonomously coordinate entire clinical workflows across the entire radiology life cycle, from preacquisition protocol optimization through initial image analysis, specialized tool deployment, and preliminary report generation. However, successful clinical deployment requires systematic consideration of complexity thresholds, economic sustainability, cybersecurity frameworks, bias mitigation strategies, and appropriate governance structures. Critical challenges include managing the probabilistic nature of underlying models within deterministic clinical workflows, ensuring adequate human supervision, and preventing overcomplication of established processes. A structured four-phase implementation roadmap addresses these considerations through incremental progression from low-risk automation to comprehensive workflow orchestration while maintaining rigorous safety standards. As foundation models advance and interoperability standards mature, agentic AI will reshape radiology practice paradigms. Success depends on resolving stakeholder responsibility questions while orchestrating technological capabilities with clinical accountability, ensuring autonomous systems augment rather than replace professional judgment in pursuit of improved patient outcomes. Keywords: Informatics, Named Entity Recognition, Patient Scheduling/No-Show Prediction, Resource Allocation, Impact of AI on Education, Artificial Intelligence, Large Language Models, Agentic AI, Multi-Agent Systems, Radiology Workflow, Clinical Decision Support, Health Care Automation © RSNA, 2026.

This data article presents a comprehensive maternal health risk dataset comprising 6058 samples (from an initially collected 6103 samples, after quality validation and outlier removal) collected through Internet of Things (IoT)-enabled Medical Cyber-Physical Systems (MCPS) across nine healthcare facilities in Bangladesh between February 2021 and January 2023. The dataset includes eight clinical features: age, body temperature, heart rate, systolic and diastolic blood pressure, body mass index (BMI), hemoglobin A1c (HbA1c), and fasting blood glucose levels, with expert- validated three-level risk classifications (high, mid, low). Data collection employed standardized IoT sensors with Raspberry Pi 4 controllers and medical-grade sensor arrays. Comprehensive quality validation removed 45 physio- logically implausible samples (0.74%), ensuring all values fall within clinically acceptable ranges. Comprehensive evaluation demonstrates dual-purpose utility(1) immediate clinical deployment for hos- pital decision support systems and (2) research baseline infrastructure for future temporal modeling studies-validated through rigorous experimental analysis. Traditional machine learning models achieved clinical-grade performance (defined as ≥95% accuracy with balanced precision/recall, consistent with established clinical decision support benchmarks), with XGBoost and Random Forest both reaching 99.34% accuracy (95% confidence interval: 98.84–99.75%), confirming exceptional data quality for immediate clinical deployment in hospital decision support systems. Feature importance analysis identified diastolic blood pressure (18.1%), body temperature (17.7%), and systolic blood pres- sure (17.0%) as primary predictive indicators. Additionally, recurrent neural network (RNN) models achieved 93.98% accuracy using synthetic temporal sequences (treating features as timesteps), establishing architectural baselines for future longitudinal studies. The 5.36% performance gap between XGBoost and Simple RNN (p < 0.001, McNemar’s test) confirms the dataset’s cross-sectional structure is optimally suited for ensemble learning methods, while RNN experiments provide proof-of-concept infrastructure for temporal modeling when genuine longitudinal measurements become available. This dataset addresses the critical need for maternal health risk prediction in resource-limited set- tings, supporting both immediate clinical deployment and future research directions. The data demonstrate readiness for integration into clinical decision support systems (validated by 99.34% accuracy), temporal modeling research infrastructure (93.98% RNN baseline), and healthcare technology development. All data underwent rigorous quality control with physiologically validated ranges, expert risk classification, and ethical approval (DUET-IRB-2021–034), making it suitable for academic research, clinical implementation, and public health policy formulation in developing countries.

Immunoproteomics is the branch of proteomics with an emphasis on the study of functional peptides and proteins related to the immune system. Combining proteomics techniques with immunological research aims to uncover the complex interactions of proteins involved in immune responses. This review discusses the methods, applications, and recent advancements in immunoproteomics, highlighting its critical role in understanding immune responses, discovering biomarkers, and developing vaccines and therapeutics. This study offers a comprehensive exploration of the methodologies, applications, and advancements within immunoproteomics. Techniques such as mass spectrometry, antibody-based assays, and computational analysis are pivotal in unraveling the complexities of the immune system at the protein level. Immunoproteomics finds diverse applications in biomarker discovery, vaccine development, autoimmune disease research, infectious disease diagnostics, and cancer immunotherapy. Challenges, including data integration, sample heterogeneity, and biomarker validation, persist, necessitating innovative approaches and interdisciplinary collaborations. In the future, immunoproteomics will likely play a major role in expanding our knowledge of immune-related diseases and accelerating the creation of targeted and precise immunotherapies.

Human saliva is a biological fluid with enormous diagnostic potential. Because saliva can be non-invasively collected, it provides an attractive alternative for blood, serum or plasma. It has been postulated that the blood concentrations of many components are reflected in saliva. Saliva harbors a wide array of proteins, which can be informative for the detection of diseases. Profiling the proteins in saliva over the course of disease progression could reveal potential biomarkers indicative of different stages of diseases, which may be useful in medical diagnostics. With advanced instrumentation and developed refined analytical techniques, proteomics is widely envisioned as a useful and powerful approach for salivary proteomic biomarker discovery. As proteomic technologies continue to mature, salivary proteomics have great potential for biomarker research and clinical applications. The progress and current status of salivary proteomics and its application in the biomarker discovery of oral and systematic diseases will be reviewed. The scientific and clinical challenges underlying this approach will also be discussed.