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

In support of the Improving Primary Care Understanding of Resources and Screening for Urinary Incontinence to Enhance Treatment initiative with the Veterans Health Administration, we developed a clinical dashboard to support primary care providers in identifying underdiagnosed, undertreated women Veterans with urinary incontinence. This paper describes our dashboard development and evaluation. We employed a user-centered design in determining dashboard requirements, interface design, and functionality. We invited early users at three pilot sites to formal usability reviews. We quantified the dashboard usability using the System Usability Scale and administered surveys and interviews for insights on performance. We employed process maps to uncover processes of end-users' dashboard engagements within local environments. User evaluations demonstrated the dashboard as a helpful instrument in identifying women Veterans with good to excellent usability performance. User feedback offers a user-driven pathway to develop our dashboard that supports clinicians to better care for women Veterans with urinary incontinence.

The performance of deep learning models in the health domain is desperately limited by the scarcity of labeled data, especially for specific clinical-domain tasks. Conversely, there are vastly available clinical unlabeled data waiting to be exploited to improve deep learning models where their training labeled data are limited. This paper investigates the use of task-specific unlabeled data to boost the performance of classification models for the risk stratification of suspected acute coronary syndrome. By leveraging large numbers of unlabeled clinical notes in task-adaptive language model pretraining, valuable prior task-specific knowledge can be attained. Based on such pretrained models, task-specific fine-tuning with limited labeled data produces better performances. Extensive experiments demonstrate that the pretrained task-specific language models using task-specific unlabeled data can significantly improve the performance of the downstream models for specific classification tasks.

The evaluation of completeness of real-world data is a particularly challenging component of data quality assessment because the degree of truly versus erroneously absent data is unknown. Among inpatient data sets, while absolute counts of admissions having specific categories of diagnoses in the principal or any position may vary depending on hospital size, we hypothesized that the ratio of these parameters will be preserved across sites, with outliers suggesting the potential for erroneously absent data. For several categories of clinical conditions assigned to inpatient admissions, we analyzed the ratio of their recording as the principal diagnosis versus any diagnosis across several hospitals and compared the ratios against a national benchmark. Our analysis showed ratios that matched clinical expectations, with reasonable preservation of ratios across sites. However, some conditions exhibited more variability in the ratios and some sites had many outliers possibly reflecting data quality issues that warrant further attention.

In the era of big data, there is an increasing need for healthcare providers, communities, and researchers to share data and collaborate to improve health outcomes, generate valuable insights, and advance research. The Health Insurance Portability and Accountability Act of 1996 (HIPAA) is a federal law designed to protect sensitive health information by defining regulations for protected health information (PHI). However, it does not provide efficient tools for detecting or removing PHI before data sharing. One of the challenges in this area of research is the heterogeneous nature of PHI fields in data across different parties. This variability makes rule-based sensitive variable identification systems that work on one database fail on another. To address this issue, our paper explores the use of machine learning algorithms to identify sensitive variables in structured data, thus facilitating the de-identification process. We made a key observation that the distributions of metadata of PHI fields and non-PHI fields are very different. Based on this novel finding, we engineered over 30 features from the metadata of the original features and used machine learning to build classification models to automatically identify PHI fields in structured Electronic Health Record (EHR) data. We trained the model on a variety of large EHR databases from different data sources and found that our algorithm achieves 99% accuracy when detecting PHI-related fields for unseen datasets. The implications of our study are significant and can benefit industries that handle sensitive data.

Understanding medication regimen complexity is important to understand what patients may benefit from pharmacist interventions. Medication Regimen Complexity Index (MRCI), a 65-item tool to quantify the complexity by incorporating the count, dosage form, frequency, and additional administration instructions of prescription medicines, provides a more nuanced way of assessing complexity. The goal of this study was to construct and validate a computational strategy to automate the calculation of MRCI. The performance of our strategy was evaluated by comparing our calculated MRCI values with gold-standard values, using correlation coefficients and population distributions. The results revealed satisfactory performance to calculate the sub-score of MRCI that includes dosage form and frequency (76 to 80% match with gold standard), and fair performance for sub-score related to additional direction (52% match with gold standard). Our automated strategy shows potential to help reduce the effort for manually calculating MRCI and highlights areas for future development efforts.

In analyzing direct hospitalization cost and clinical data from an academic medical center, commonly used metrics such as diagnosis-related group (DRG) weight explain approximately 37% of cost variability, but a substantial amount of variation remains unaccounted for by case mix index (CMI) alone. Using CMI as a benchmark, we isolate and target individual DRGs with higher than expected average costs for specific quality improvement efforts. While DRGs summarize hospitalization care after discharge, a predictive model using only information known before admission explained up to 60% of cost variability for two DRGs with a high excess cost burden. This level of variability likely reflects underlying patient factors that are not modifiable (e.g., age and prior comorbidities) and therefore less useful for health systems to target for intervention. However, the remaining unexplained variation can be inspected in further studies to discover operational factors that health systems can target to improve quality and value for their patients. Since DRG weights represent the expected resource consumption for a specific hospitalization type relative to the average hospitalization, the data-driven approach we demonstrate can be utilized by any health institution to quantify excess costs and potential savings among DRGs.

Electronic medical records (EMRs) are stored in relational databases. It can be challenging to access the required information if the user is unfamiliar with the database schema or general database fundamentals. Hence, researchers have explored text-to-SQL generation methods that provide healthcare professionals direct access to EMR data without needing a database expert. However, currently available datasets have been essentially "solved" with state-of-the-art models achieving accuracy greater than or near 90%. In this paper, we show that there is still a long way to go before solving text-to-SQL generation in the medical domain. To show this, we create new splits of the existing medical text-to- SQL dataset MIMICSQL that better measure the generalizability of the resulting models. We evaluate state-of-the-art language models on our new split showing substantial drops in performance with accuracy dropping from up to 92% to 28%, thus showing substantial room for improvement. Moreover, we introduce a novel data augmentation approach to improve the generalizability of the language models. Overall, this paper is the first step towards developing more robust text-to-SQL models in the medical domain.

The use of Electronic Health Records (EHR) in pregnancy care and obstetrics-gynecology (OB/GYN) research has increased in recent years. In pregnancy, timing is important because clinical characteristics, risks, and patient management are different in each stage of pregnancy. However, the difficulty of accurately differentiating pregnancy episodes and temporal information of clinical events presents unique challenges for EHR phenotyping. In this work, we introduced the concept of time relativity and proposed a comprehensive framework of computational phenotyping for prenatal and postpartum episodes based on the Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM). We implemented it on the All of Us national EHR database and identified 6,280 pregnancies with accurate start and end dates among 5,399 female patients. With the ability to identify different episodes in pregnancy care, this framework provides new opportunities for phenotyping complex clinical events and gestational morbidities for pregnant women, thus improving maternal and infant health.

In traumatology physicians heavily rely on computed tomography (CT) 2D axial scans to identify and assess the patient's injuries after an accident. However, in some cases it can be difficult to rigorously evaluate the real extent of the damage considering only the bidimensional slices produced by the CT, and some life-threatening lesions can be missed. With the development of 3D holographic rendering and extended reality (XR) technology, CT images can be projected in a 3D format through head-mounted holographic displays, allowing multi-view from different angles and interactive slice intersections, thus increasing anatomical intelligibility. In this article, we explain how to import CT scans into holographic displays for 3D visualization and further compare the methodolgy with traditional bidimensional reading.

Pain is a complex concept that can interconnect with other concepts such as a disorder that might cause pain, a medication that might relieve pain, and so on. To fully understand the context of pain experienced by either an individual or across a population, we may need to examine all concepts related to pain and the relationships between them. This is especially useful when modeling pain that has been recorded in electronic health records. Knowledge graphs represent concepts and their relations by an interlinked network, enabling semantic and context-based reasoning in a computationally tractable form. These graphs can, however, be too large for efficient computation. Knowledge graph embeddings help to resolve this by representing the graphs in a low-dimensional vector space. These embeddings can then be used in various downstream tasks such as classification and link prediction. The various relations associated with pain which are required to construct such a knowledge graph can be obtained from external medical knowledge bases such as SNOMED CT, a hierarchical systematic nomenclature of medical terms. A knowledge graph built in this way could be further enriched with real-world examples of pain and its relations extracted from electronic health records. This paper describes the construction of such knowledge graph embedding models of pain concepts, extracted from the unstructured text of mental health electronic health records, combined with external knowledge created from relations described in SNOMED CT, and their evaluation on a subject-object link prediction task. The performance of the models was compared with other baseline models.