Search AMIA.org

To adapt and evaluate a deep learning language model for answering why-questions based on patient-specific clinical text.

To design, develop, and evaluate a scalable clinical data normalization pipeline for standardizing unstructured electronic health record (EHR) data leveraging the HL7 Fast Healthcare Interoperability Resources (FHIR) specification.

To implement an open-source tool that performs deterministic privacy-preserving record linkage (RL) in a real-world setting within a large research network.

Electronic health record (EHR) data aggregated from multiple, non-affiliated, sources provide an important resource for biomedical research, including digital phenotyping. Unlike work with EHR data from a single organization, aggregate EHR data introduces a number of analysis challenges.

Precision behavioral medicine techniques integrating wearable ultraviolet radiation (UVR) sensors may help individuals avoid sun exposure that places them at-risk for skin cancer. As a preliminary step in our patient-centered process of developing a just-in-time adaptive intervention, this study evaluated reactions and preferences to UVR sensors among melanoma survivors.

An important component of processing medical texts is the identification of synonymous words or phrases. Synonyms can inform learned representations of patients or improve linking mentioned concepts to medical ontologies. However, medical synonyms can be lexically similar ("dilated RA" and "dilated RV") or dissimilar ("cerebrovascular accident" and "stroke"); contextual information can determine if 2 strings are synonymous. Medical professionals utilize extensive variation of medical terminology, often not evidenced in structured [...]

Most population-based cancer databases lack information on metastatic recurrence. Electronic medical records (EMR) and cancer registries contain complementary information on cancer diagnosis, treatment and outcome, yet are rarely used synergistically. To construct a cohort of metastatic breast cancer (MBC) patients, we applied natural language processing techniques within a semisupervised machine learning framework to linked EMR-California Cancer Registry (CCR) data.

Achieving unbiased recognition of eligible patients for clinical trials from their narrative longitudinal clinical records can be time consuming. We describe and evaluate a knowledge-driven method that identifies whether a patient meets a selected set of 13 eligibility clinical trial criteria from their longitudinal clinical records, which was one of the tasks of the 2018 National NLP Clinical Challenges.

Managing registries with continual data collection poses challenges, such as following reproducible research protocols and guaranteeing data accessibility. The University of Kansas (KU) Alzheimer's Disease Center (ADC) maintains one such registry: Curated Clinical Cohort Phenotypes and Observations (C3PO). We created an automated and reproducible process by which investigators have access to C3PO data.

Scalable informatics solutions that provide molecularly tailored treatment recommendations to clinicians are needed to streamline precision oncology in care settings.