AMIA ... Annual Symposium proceedings. AMIA Symposium最新文献

In 2021, the Association of American Medical Colleges published Telehealth Competencies Across the Learning Continuum, a roadmap for designing telemedicine curricula and evaluating learners. While this document advances educators' shared understanding of telemedicine's core content and performance expectations, it does not include turn-key-ready evaluation instruments. At the University of Oklahoma School of Community Medicine, we developed a year-long telemedicine curriculum for third-year medical and second-year physician assistant students. We used the AAMC framework to create program objectives and instructional simulations. We designed and piloted an assessment rubric for eight AAMC competencies to accompany the simulations. In this monograph, we describe the rubric development, scores for students participating in simulations, and results comparing inter-rater reliability between faculty and standardized patient evaluators. Our preliminary work suggests that our rubric provides a practical method for evaluating learners by faculty during telemedicine simulations. We also identified opportunities for additional reliability and validity testing.

Natural Language Processing (NLP) methods have been broadly applied to clinical tasks. Machine learning and deep learning approaches have been used to improve the performance of clinical NLP. However, these approaches require sufficiently large datasets for training, and trained models have been shown to transfer poorly across sites. These issues have led to the promotion of data collection and integration across different institutions for accurate and portable models. However, this can introduce a form of bias called confounding by provenance. When source-specific data distributions differ at deployment, this may harm model performance. To address this issue, we evaluate the utility of backdoor adjustment for text classification in a multi-site dataset of clinical notes annotated for mentions of substance abuse. Using an evaluation framework devised to measure robustness to distributional shifts, we assess the utility of backdoor adjustment. Our results indicate that backdoor adjustment can effectively mitigate for confounding shift.

The structure and semantics of clinical notes vary considerably across different Electronic Health Record (EHR) systems, sites, and institutions. Such heterogeneity hampers the portability of natural language processing (NLP) models in extracting information from the text for clinical research or practice. In this study, we evaluate the contextual variation of clinical notes by measuring the semantic and syntactic similarity of the notes of two sets of physicians comprising four medical specialties across EHR migrations at two Mayo Clinic sites. We find significant semantic and syntactic variation imposed by the context of the EHR system and between medical specialties whereas only minor variation is caused by variation of spatial context across sites. Our findings suggest that clinical language models need to account for process differences at the specialty sublanguage level to be generalizable.

Computed tomography (CT) is one of the modalities for effective lung cancer screening, diagnosis, treatment, and prognosis. The features extracted from CT images are now used to quantify spatial and temporal variations in tumors. However, CT images obtained from various scanners with customized acquisition protocols may introduce considerable variations in texture features, even for the same patient. This presents a fundamental challenge to downstream studies that require consistent and reliable feature analysis. Existing CT image harmonization models rely on GAN-based supervised or semi-supervised learning, with limited performance. This work addresses the issue of CT image harmonization using a new diffusion-based model, named DiffusionCT, to standardize CT images acquired from different vendors and protocols. DiffusionCT operates in the latent space by mapping a latent non-standard distribution into a standard one. DiffusionCT incorporates a U-Net-based encoder-decoder, augmented by a diffusion model integrated into the bottleneck part. The model is designed in two training phases. The encoder-decoder is first trained, without embedding the diffusion model, to learn the latent representation of the input data. The latent diffusion model is then trained in the next training phase while fixing the encoder-decoder. Finally, the decoder synthesizes a standardized image with the transformed latent representation. The experimental results demonstrate a significant improvement in the performance of the standardization task using DiffusionCT.

We present a method to enrich controlled medication terminology from free-text drug labels. This is important because, while controlled medication terminology capture well-structured medication information, much of the information pertaining to medications is still found in free-text. First, we compared different Named Entity Recognition (NER) models including rule-based, feature-based, deep learning-based models with Transformers as well as ChatGPT, few-shot and fine-tuned GPT-3 to find the most suitable model that accurately extracts medication entities (ingredients, brand, dose, etc.) from free-text. Then, a rule-based Relation Extraction algorithm transforms NER results into a well-structured medication knowledge graph. Finally, a Medication Searching method takes the knowledge graph and matches it to relevant medications in the terminology server. An empirical evaluation on real-world drug labels shows that BERT-CRF was the most effective NER model with F-measure 95%. After performing terms normalization, the Medication Searching achieved an accuracy of 77% for when matching a label to relevant medication in the terminology server. The NER and Medication Searching models could be deployed as a web service capable of accepting free-text queries and returning structured medication information; thus providing a useful means of better managing medications information found in different health systems.

Alzheimer's disease (AD) is a complex heterogeneous neurodegenerative disease that requires an in-depth understanding of its progression pathways and contributing factors to develop effective risk stratification and prevention strategies. In this study, we proposed an outcome-oriented model to identify progression pathways from mild cognitive impairment (MCI) to AD using electronic health records (EHRs) from the OneFlorida+ Clinical Research Consortium. To achieve this, we employed the long short-term memory (LSTM) network to extract relevant information from the sequential records of each patient. The hierarchical agglomerative clustering was then applied to the learned representation to group patients based on their progression subtypes. Our approach identified multiple progression pathways, each of which represented distinct patterns of disease progression from MCI to AD. These pathways can serve as a valuable resource for researchers to understand the factors influencing AD progression and to develop personalized interventions to delay or prevent the onset of the disease.

Documentation burden is experienced by clinical end-users of the electronic health record. Flowsheet measure reuse and clinical concept redundancy are two contributors to documentation burden. In this paper, we described nursing flowsheet documentation hierarchy and frequency of use for one month from two hospitals in our health system. We examined respiratory care management documentation in greater detail. We found 59 instances of reuse of respiratory care flowsheet measure fields over two or more templates and groups, and 5 instances of clinical concept redundancy. Flowsheet measure fields for physical assessment observations and measurements were the most frequently documented and most reused, whereas respiratory intervention documentation was less frequently reused. Further research should investigate the relationship between flowsheet measure reuse and redundancy and EHR information overload and documentation burden.

Physical activity is important for prostate cancer survivors. Yet survivors face significant barriers to traditional structured exercise programs, limiting engagement and impact. Digital programs that incorporate fitness trackers and peer support via social media have potential to improve the reach and impact of traditional support. Using a digital walking program with prostate cancer survivors, we employed mixed methods to assess program outcomes, engagement, perceived utility, and social influence. After 6 weeks of program use, survivors and loved ones (n=18) significantly increased their average daily step count. Although engagement and perceived utility of using a fitness tracker and interacting with walking buddies was high, social media engagement and utility were limited. Group strategies associated with social influence were driven more by group attraction to the collective task of walking than by interpersonal bonds. Findings demonstrate the feasibility of a digital walking program to improve physical activity and extend the reach of traditional support.

The types of clinical notes in electronic health records (EHRs) are diverse and it would be great to standardize them to ensure unified data retrieval, exchange, and integration. The LOINC Document Ontology (DO) is a subset of LOINC that is created specifically for naming and describing clinical documents. Despite the efforts of promoting and improving this ontology, how to efficiently deploy it in real-world clinical settings has yet to be explored. In this study we evaluated the utility of LOINC DO by mapping clinical note titles collected from five institutions to the LOINC DO and classifying the mapping into three classes based on semantic similarity between note titles and LOINC DO codes. Additionally, we developed a standardization pipeline that automatically maps clinical note titles from multiple sites to suitable LOINC DO codes, without accessing the content of clinical notes. The pipeline can be initialized with different large language models, and we compared the performances between them. The results showed that our automated pipeline achieved an accuracy of 0.90. By comparing the manual and automated mapping results, we analyzed the coverage of LOINC DO in describing multi-site clinical note titles and summarized the potential scope for extension.

Automatic identification of clinical trials for which a patient is eligible is complicated by the fact that trial eligibility are stated in natural language. A potential solution to this problem is to employ text classification methods for common types of eligibility criteria. In this study, we focus on seven common exclusion criteria in cancer trials: prior malignancy, human immunodeficiency virus, hepatitis B, hepatitis C, psychiatric illness, drug/substance abuse, and autoimmune illness. Our dataset consists of 764 phase III cancer trials with these exclusions annotated at the trial level. We experiment with common transformer models as well as a new pre-trained clinical trial BERT model. Our results demonstrate the feasibility of automatically classifying common exclusion criteria. Additionally, we demonstrate the value of a pre-trained language model specifically for clinical trials, which yield the highest average performance across all criteria.