Search NASA⌕ Search

SEARCH · Search NASA

Results for “clinical text”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

33 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Leveraging large language models to automate the identification of healthcare access barriers for veterans

Objective: To develop and evaluate an automated system for identifying healthcare barriers focusing on transportation issues in veterans’ clinical notes using large language models (LLMs) and to assess the impact of different prompting strategies on classification performance and explanation consistency. Methods: We developed a hybrid system combining pattern matching for templated notes with LLM analysis for free-text notes. Using 2000 manually annotated clinical notes, we compared four prompting strategies (dual-role short, dual-role long, analysis-first, analysis-only) across Mistral-7B and Llama-3.1 models. We evaluated classification performance using standard metrics and assessed explanation consistency through embedding similarity analysis. Results: The analysis-first strategy achieved superior performance, with Mistral-7B reaching an F1 score of 0.914, outperforming traditional machine learning approaches (GBM: 0.786, BERT: 0.811). LLMs demonstrated higher explanation consistency within models (mean cosine similarity 0.887–0.908) compared to cross-model similarities (0.767–0.872). Pattern matching successfully handled 6.7% of templated notes deterministically. Mistral-7B showed greater internal consistency but higher abstention rates compared to Llama-3.1. Conclusion: Requiring LLMs to analyze evidence before classification improves both accuracy and explanation consistency for identifying transportation barriers in clinical notes. This approach enables automated barrier detection at scale while providing clinically relevant explanations, supporting both population-level healthcare planning and individual patient care decisions.

Healthcare access barriers↗
DOE OSTI2020

Using case-level context to classify cancer pathology reports

Individual electronic health records (EHRs) and clinical reports are often part of a larger sequence—for example, a single patient may generate multiple reports over the trajectory of a disease. In applications such as cancer pathology reports, it is necessary not only to extract information from individual reports, but also to capture aggregate information regarding the entire cancer case based off case-level context from all reports in the sequence. In this paper, we introduce a simple modular add-on for capturing case-level context that is designed to be compatible with most existing deep learning architectures for text classification on individual reports. We test our approach on a corpus of 431,433 cancer pathology reports, and we show that incorporating case-level context significantly boosts classification accuracy across six classification tasks—site, subsite, laterality, histology, behavior, and grade. We expect that with minimal modifications, our add-on can be applied towards a wide range of other clinical text-based tasks.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2021

Deep active learning for classifying cancer pathology reports

Abstract Background Automated text classification has many important applications in the clinical setting; however, obtaining labelled data for training machine learning and deep learning models is often difficult and expensive. Active learning techniques may mitigate this challenge by reducing the amount of labelled data required to effectively train a model. In this study, we analyze the effectiveness of 11 active learning algorithms on classifying subsite and histology from cancer pathology reports using a Convolutional Neural Network as the text classification model. Results We compare the performance of each active learning strategy using two differently sized datasets and two different classification tasks. Our results show that on all tasks and dataset sizes, all active learning strategies except diversity-sampling strategies outperformed random sampling, i.e., no active learning. On our large dataset (15K initial labelled samples, adding 15K additional labelled samples each iteration of active learning), there was no clear winner between the different active learning strategies. On our small dataset (1K initial labelled samples, adding 1K additional labelled samples each iteration of active learning), marginal and ratio uncertainty sampling performed better than all other active learning techniques. We found that compared to random sampling, active learning strongly helps performance on rare classes by focusing on underrepresented classes. Conclusions Active learning can save annotation cost by helping human annotators efficiently and intelligently select which samples to label. Our results show that a dataset constructed using effective active learning techniques requires less than half the amount of labelled data to achieve the same performance as a dataset constructed using random sampling.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

ARCH: Large-scale knowledge graph via aggregated narrative codified health records analysis

Objective: Electronic health record (EHR) systems contain a wealth of clinical data stored as both codified data and free-text narrative notes (NLP). The complexity of EHR presents challenges in feature representation, information extraction, and uncertainty quantification. Here, to address these challenges, we proposed an efficient Aggregated naRrative Codified Health (ARCH) records analysis to generate a large-scale knowledge graph (KG) for a comprehensive set of EHR codified and narrative features. Methods: Using data from 12.5 million Veterans Affairs patients, ARCH first derives embedding vectors and generates similarities along with associated p-values to measure the strength of relatedness between clinical features with statistical certainty quantification. Next, ARCH performs a sparse embedding regression to remove indirect linkage between features to build a sparse KG. Finally, ARCH was validated on various clinical tasks, including detecting known relationships between entity pairs, predicting drug side effects, disease phenotyping, as well as sub-typing Alzheimer’s disease patients. Results: ARCH produces high-quality clinical embeddings and KG for over 60,000 codified and narrative EHR concepts. The KG and embeddings are visualized in the R-shiny powered web-API.3 ARCH achieved high accuracy in detecting EHR concept relationships, with AUCs of 0.926 (codified) and 0.861 (NLP) for similar EHR concepts, and 0.810 (codified) and 0.843 (NLP) for related pairs. It detected drug side effects with a 0.723 AUC, which improved to 0.826 after fine-tuning. Using both codified and NLP features, the detection power increased significantly. Compared to other methods, ARCH has superior accuracy and enhances weakly supervised phenotyping algorithms’ performance. Notably, it successfully categorized Alzheimer’s patients into two subgroups with varying mortality rates. Conclusion: The proposed ARCH algorithm generates large-scale high-quality semantic representations and knowledge graph for both codified and NLP EHR features, useful for a wide range of predictive modeling tasks.

Electronic health records↗
DOE OSTI2020

JSONize: A Scalable Machine Learning Pipeline to Model Medical Notes as Semi-structured Documents

The Department of Veteran's Affairs (VA) archives the largest corpora of clinical notes in their corporate data warehouse (CDW) as unstructured text data. Unstructured text easily supports keyword searches and regular expressions. Often these simple searches do not adequately support the complex searches that need to be performed on notes. For example, a researcher may want all notes with a Duke Treadmill Score less than 5 or people that smoke more than 1 pack per day. Range queries like this and more can be supported by modelling text as semi-structured documents. In this paper, we implement a scalable machine learning pipeline that models plain medical text as useful semi-structured documents. We improve on existing models and achieve a F1-score of 0.912 and scale our methods to the entire VA corpus.

Rush III, Everett↗
DOE OSTI2020

Unified Medical Language System resources improve sieve-based generation and Bidirectional Encoder Representations from Transformers (BERT)–based ranking for concept normalization

Concept normalization, the task of linking phrases in text to concepts in an ontology, is useful for many downstream tasks including relation extraction, information retrieval, etc. We present a generate-and-rank concept normalization system based on our participation in the 2019 National NLP Clinical Challenges Shared Task Track 3 Concept Normalization. The shared task provided 13 609 concept mentions drawn from 100 discharge summaries. We first design a sieve-based system that uses Lucene indices over the training data, Unified Medical Language System (UMLS) preferred terms, and UMLS synonyms to generate a list of possible concepts for each mention. We then design a listwise classifier based on the BERT (Bidirectional Encoder Representations from Transformers) neural network to rank the candidate concepts, integrating UMLS semantic types through a regularizer. Our generate-and-rank system was third of 33 in the competition, outperforming the candidate generator alone (81.66% vs 79.44%) and the previous state of the art (76.35%). During postevaluation, the model’s accuracy was increased to 83.56% via improvements to how training data are generated from UMLS and incorporation of our UMLS semantic type regularizer. Analysis of the model shows that prioritizing UMLS preferred terms yields better performance, that the UMLS semantic type regularizer results in qualitatively better concept predictions, and that the model performs well even on concepts not seen during training. Our generate-and-rank framework for UMLS concept normalization integrates key UMLS features like preferred terms and semantic types with a neural network–based ranking model to accurately link phrases in text to UMLS concepts.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗
DOE OSTI2023

Deep learning-enabled natural language processing to identify directional pharmacokinetic drug–drug interactions

Background. During drug development, it is essential to gather information about the change of clinical exposure of a drug (object) due to the pharmacokinetic (PK) drug-drug interactions (DDIs) with another drug (precipitant). While many natural language processing (NLP) methods for DDI have been published, most were designed to evaluate if (and what kind of) DDI relationships exist in the text, without identifying the direction of DDI (object vs. precipitant drug). Here we present a method for the automatic identification of the directionality of a PK DDI from literature or drug labels. Methods. We reannotated the Text Analysis Conference (TAC) DDI track 2019 corpus for identifying the direction of a PK DDI and evaluated the performance of a fine-tuned BioBERT model on this task by following the training and validation steps prespecified by TAC. Results. This initial attempt showed the model achieved an F-score of 0.82 in identifying sentences as containing PK DDI and an F-score of 0.97 in identifying object versus precipitant drugs in those sentences. Discussion and conclusion. Despite a growing list of NLP methods for DDI extraction, most of them use a common set of corpora to perform general purpose tasks (e.g., classifying a sentence into one of several fixed DDI categories). There is a lack of coordination between the drug development and biomedical informatics method development community to develop corpora and methods to perform specific tasks (e.g., extract clinical exposure changes due to PK DDI). We hope that our effort can encourage such a coordination so that more “fit for purpose” NLP methods could be developed and used to facilitate the drug development process.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2023

PRIMED for the Future: Purposing Raw Intake for Machine Learning-Enabled Detection (Final Report)

The COVID-19 pandemic demonstrated how a novel, elusive, and diffuse biological threat can engender uncertainty and misinformation, and it underscored the need for flexible analytical modalities agnostic to the identity of biological material. Yet even before the pandemic, recognition of the limitations of the current, list-based approach, which focuses on known pathogens and biotoxins, and of the importance of agent-agnostic biodetection was growing within the biosecurity community. In a 2018 report on “Biodefense in the Age of Synthetic Biology,” for example, the National Academy of Sciences stated that “an overreliance on the Select Agent List is a systematic weakness affecting many aspects of the United States’ current biodefense mitigation capability”. More recently, a group of biodefense researchers proposed the identification and adoption of “bioagent-agnostic signatures (BASs)” as a way of detecting and characterizing not only existing agents but also novel ones, an approach they believe will “enable a more flexible and resilient biodefense posture”. Indeed, the future of biodetection requires us to begin developing novel analytics that can identify anomalies and/or characteristics that indicate a potential threat, whether known or unknown, without looking for a specific signature that has been identified previously. To assess potential threats more rapidly, it is critical to develop agnostic artificial intelligence (AI)/machine learning (ML) systems that can be employed for real-time assessment of the nature and source of a perturbation. Such systems should be multi scale and multi-dimensional, integrating sensor data from a range of biological, chemical, and physical application spaces. Emerging deep learning (DL) models demonstrate exceptional promise for identification of discriminatory features within multi-dimensional datasets. DL models have the capacity to recognize and encode highly complex patterns in a wide range of input data modalities, including images, text, and biological/chemical/physical spectra. As such, they can execute a wide range of assessments and determinations that have traditionally required a human operator. The promise of advances in DL is apparent in the realm of human health and medicine. DL models have been validated for evaluating a variety of clinical threats to human health in a range of contexts, including infection and cancer, and they demonstrated improved performance in predicting stroke relative to human neurologists in some categories of data. Continuously evolving advances in AI/ML are expected to support more efficient evaluation of raw sequence, spectroscopy, and spectrometry data. For instance, recent advances and deployment of large language models (LLM) such as Generative Pre training Transformer (GPT) and Bidirectional Encoder Representations from Transformers (BERT) have already motivated application of these models for biological function prediction. As frameworks such as LLMs become larger and more complex in their representations, their capacity to serve as pre-trained models that can be fine-tuned for biological/biodetection purposes will similarly be amplified. While existing and emerging AI/ML have found broad applicability and use cases in the clinical sciences, development for environmental evaluation and biodetection has been limited. Functionalizing such capabilities for this purpose requires an understanding of the existing technical landscape and how the respective tools and algorithms are currently being employed. This landscape awareness then allows an assessment of the current practical capabilities of existing models and the anticipated requirements and development efforts that will be needed to adapt available algorithms for biodetection applications relevant to DHS. Leveraging expertise in biodetection, ML, and operational biodetection, the effort described in this report is comprised of a systematic landscape assessment (Subtask 2.1), comparative evaluation (Subtask 2.2), and formulation of a value proposition (Subtask 2.3) for the prospect of ML-enabled, agnostic biodetection from raw, or minimally-processed, datasets.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Development of message passing-based graph convolutional networks for classifying cancer pathology reports

Abstract Background Applying graph convolutional networks (GCN) to the classification of free-form natural language texts leveraged by graph-of-words features (TextGCN) was studied and confirmed to be an effective means of describing complex natural language texts. However, the text classification models based on the TextGCN possess weaknesses in terms of memory consumption and model dissemination and distribution. In this paper, we present a fast message passing network (FastMPN), implementing a GCN with message passing architecture that provides versatility and flexibility by allowing trainable node embedding and edge weights, helping the GCN model find the better solution. We applied the FastMPN model to the task of clinical information extraction from cancer pathology reports, extracting the following six properties: main site, subsite, laterality, histology, behavior, and grade. Results We evaluated the clinical task performance of the FastMPN models in terms of micro- and macro-averaged F1 scores. A comparison was performed with the multi-task convolutional neural network (MT-CNN) model. Results show that the FastMPN model is equivalent to or better than the MT-CNN. Conclusions Our implementation revealed that our FastMPN model, which is based on the PyTorch platform, can train a large corpus (667,290 training samples) with 202,373 unique words in less than 3 minutes per epoch using one NVIDIA V100 hardware accelerator. Our experiments demonstrated that using this implementation, the clinical task performance scores of information extraction related to tumors from cancer pathology reports were highly competitive.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2025

The Evolution of Randomized Clinical Trial Designs to Assess Therapeutics in Alzheimer Disease

Importance The success of recent randomized clinical trials (RCTs) for Alzheimer disease (AD), particularly those focusing on anti-amyloid therapies, has been discussed at length. However, the evolution of RCT design features for AD that preceded this success remain underexplored. Objective To describe temporal changes in the features of RCT design for interventions in AD. Evidence Review PubMed, Scopus, and Web of Science databases were searched in January 2025 for phase 2 and 3 AD RCTs published between January 1992 and December 2024. RCTs that investigated an intervention for AD, with a placebo or standard-of-care control group, were included. Four assessors independently reviewed full-text articles to capture study characteristics. Main Outcomes and Measures The number of participants and the duration of RCTs as well as the target population, outcomes, and funding were extracted from published reports. These features were analyzed with respect to time using linear regression and χ 2 analyses. Results The study included 203 RCTs with 79 589 participants testing interventions in AD. From 1992 to 2024, the mean sample size increased by 464% for phase 2 RCTs (from 42 to 237), and 50% for phase 3 RCTs (from 632 to 951), while the mean trial duration increased by 188% (from 16 to 46 weeks) for phase 2, and 256% (from 20 to 71 weeks) for phase 3 RCTs. This longer duration of RCTs may be partially attributed by a greater share of disease-modifying rather than symptomatic treatments. Similarly, more recent trials required AD biomarker evidence for enrollment (from 1 of 36 [2.7%] before 2006 to 40 of 76 [52.6%] since 2019). A substantial difference in the type of therapeutics researched was observed, with anti-amyloid and anti-tau RCTs being more likely to be funded by the pharmaceutical industry compared with neurotransmitter or other RCTs (anti-amyloid or anti-tau, 68 of 71 [95.8%]; neurotransmitter, 52 of 69 [77.6%]; other, 33 of 52 [63.5%]). RCT transparency improved, with more frequent data accessibility statements, registered reports, and better reporting on race and ethnicity. Conclusions and Relevance This methodology research of AD RCTs highlights substantial changes in key features of AD clinical trials from 1992 to 2024. AD RCTs have become larger and longer, such that they are powered to detect smaller clinical differences. The increased sample sizes and duration should enable the detection of smaller and more slowly occurring outcomes, which may lead to successful RCTs of therapies with slower and more subtle efficacy.

General & Internal Medicine↗
DOE OSTI2025

Consistent performance of large language models in rare disease diagnosis across ten languages and 4917 cases

Background Large language models (LLMs) are increasingly used medicine for diverse applications including differential diagnostic support. The training data used to create LLMs such as the Generative Pretrained Transformer (GPT) predominantly consist of English-language texts, but LLMs could be used across the globe to support diagnostics if language barriers could be overcome. Initial pilot studies on the utility of LLMs for differential diagnosis in languages other than English have shown promise, but a large-scale assessment on the relative performance of these models in a variety of European and non-European languages on a comprehensive corpus of challenging rare-disease cases is lacking. Methods We created 4917 clinical vignettes using structured data captured with Human Phenotype Ontology (HPO) terms with the Global Alliance for Genomics and Health (GA4GH) Phenopacket Schema. These clinical vignettes span a total of 360 distinct genetic diseases with 2525 associated phenotypic features. We used translations of the Human Phenotype Ontology together with language-specific templates to generate prompts in English, Chinese, Czech, Dutch, French, German, Italian, Japanese, Spanish, and Turkish. We applied GPT-4o, version gpt-4o-2024-08-06, and the medically fine-tuned Meditron3-70B to the task of delivering a ranked differential diagnosis using a zero-shot prompt. An ontology-based approach with the Mondo disease ontology was used to map synonyms and to map disease subtypes to clinical diagnoses in order to automate evaluation of LLM responses. Findings For English, GPT-4o placed the correct diagnosis at the first rank 19.9% and within the top-3 ranks 27.0% of the time. In comparison, for the nine non-English languages tested here the correct diagnosis was placed at rank 1 between 16.9% and 20.6%, within top-3 between 25.4% and 28.6% of cases. The Meditron3 model placed the correct diagnosis within the first 3 ranks for 20.9% of cases in English and between 19.9% and 24.0% for the other nine languages. Interpretation The differential diagnostic performance of LLMs across a comprehensive corpus of rare-disease cases was largely consistent across the ten languages tested. This suggests that the utility of LLMs in clinical settings may extend to non-English clinical settings.

Artificial intelligence↗
DOE OSTI2025

The Unified Phenotype Ontology : a framework for cross-species integrative phenomics

Phenotypic data are critical for understanding biological mechanisms and consequences of genomic variation, and are pivotal for clinical use cases such as disease diagnostics and treatment development. For over a century, vast quantities of phenotype data have been collected in many different contexts covering a variety of organisms. The emerging field of phenomics focuses on integrating and interpreting these data to inform biological hypotheses. A major impediment in phenomics is the wide range of distinct and disconnected approaches to recording the observable characteristics of an organism. Phenotype data are collected and curated using free text, single terms or combinations of terms, using multiple vocabularies, terminologies, or ontologies. Integrating these heterogeneous and often siloed data enables the application of biological knowledge both within and across species. Existing integration efforts are typically limited to mappings between pairs of terminologies; a generic knowledge representation that captures the full range of cross-species phenomics data is much needed. We have developed the Unified Phenotype Ontology (uPheno) framework, a community effort to provide an integration layer over domain-specific phenotype ontologies, as a single, unified, logical representation. uPheno comprises (1) a system for consistent computational definition of phenotype terms using ontology design patterns, maintained as a community library; (2) a hierarchical vocabulary of species-neutral phenotype terms under which their species-specific counterparts are grouped; and (3) mapping tables between species-specific ontologies. This harmonized representation supports use cases such as cross-species integration of genotype-phenotype associations from different organisms and cross-species informed variant prioritization.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Leveraging BERT and Network-Based Attention Analysis for Identifying Treatment Milestones in EHRs

This study introduces a sophisticated data-driven framework for analyzing Electronic Health Records (EHRs) using transformer-based models to identify and disentangle overlapping treatment contexts. The framework leverages a preprocessing pipeline that transforms structured procedural codes into semantically enriched descriptive text, enabling the use of attention mechanisms to cluster medical events into treatment milestones—cohesive and distinct components of care processes. The methodology is rigorously validated using synthetic datasets derived from the MIMIC-III database, designed to simulate the heterogeneity and overlapping procedural contexts characteristic of real-world EHR scenarios. Quantitative evaluation highlights the framework’s robustness in disentangling concurrent care pathways, with attention metrics and unsupervised clustering approaches demonstrating the ability to preserve intra-context relationships while distinguishing inter-context dependencies. By addressing challenges inherent in data heterogeneity, this approach provides a foundation for uncovering complex treatment patterns, advancing clinical decision-making, and optimizing resource allocation in diverse healthcare environments.

Kim, Minsu [ORNL] (ORCID:0000000224185535)↗
DOE OSTI2022

A scalable, open-source implementation of a large-scale mechanistic model for single cell proliferation and death signaling

Mechanistic models of how single cells respond to different perturbations can help integrate disparate big data sets or predict response to varied drug combinations. However, the construction and simulation of such models have proved challenging. Here, we developed a python-based model creation and simulation pipeline that converts a few structured text files into an SBML standard and is high-performance- and cloud-computing ready. We applied this pipeline to our large-scale, mechanistic pan-cancer signaling model (named SPARCED) and demonstrate it by adding an IFNγ pathway submodel. We then investigated whether a putative crosstalk mechanism could be consistent with experimental observations from the LINCS MCF10A Data Cube that IFNγ acts as an anti-proliferative factor. The analyses suggested this observation can be explained by IFNγ-induced SOCS1 sequestering activated EGF receptors. This work forms a foundational recipe for increased mechanistic model-based data integration on a single-cell level, an important building block for clinically-predictive mechanistic models.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2023

Comparative Analysis of Imaging and Measurements of Micrometer-Scale Fracture Aperture Fields Within a Heterogeneous Rock Using PET and X-ray CT

Knowledge of the spatial distribution of fracture apertures is essential for reliable characterization of flow and transport processes in fractured systems and for better understanding of physicochemical matrix–fracture interactions. Here, we propose and test two image-based methods, thereby extending the current experimental capabilities to characterize aperture size distribution in structurally heterogeneous geologic porous media noninvasively. The first approach utilizes an inversion method based on the dataset acquired from positron emission tomography (PET) and the second approach considers an extension of the classic missing attenuation technique that relies on clinical X-ray computed tomography (X-ray CT). Independent sets of imaging experiments are conducted on a fractured basalt core with heterogeneous matrix properties and aperture distributions to compare the two methodologies. A repeat of each experiment is conducted to verify the proposed workflows. The performance of these two imaging techniques is systematically evaluated through the analysis of signal-to-noise ratio, minimum fracture size detectability, and measurement errors. While both approaches provide a reliable estimation of fracture aperture distributions, PET yields a signal-to-noise ratio that is substantially higher than the corresponding X-ray CT measurements. Furthermore, uncertainties of the aperture values for PET are considerably lower ($\bar {\sigma}_{\text {d}} = 15\%$) compared to those obtained from X-ray CT ($\bar {\sigma}_{\text {d}} = 29\%$), allowing for the detection of minimum aperture sizes of 20 $\mu$m with 70% confidence level. Finally, these approaches provide key experimental tools for better understanding dynamic hydromechanical fracture properties in geologic systems.

58 GEOSCIENCES↗