Applied Clinical Informatics

National Library Of Medicine

Investigators

Linked publications, trials & patents

Abstract

NLP and Indexing - Developing a multi-model system for automatic classification of MeSH Publication Types for MEDLINE articles. - Continuing to study the growth in Author Supplied Keywords in MEDLINE and if they might improve automatic indexing of articles. A prior study showed several keywords were used to drive readers to an article even if the keywords were not relevant to the article itself. - Completed development of an updated Machine Learning approach to MeSH Check Tag detection in MEDLINE articles - Work is now focused on transitioning MTI over to the PMDM team in NCBI as MTIX with the goal of them being fully operational before the new MEDLINE year begins (Fall CY23). - Continuing to update the SPECIALIST Lexicon, SemMedDB, and MetaMap datasets in support of COVID-19. Clinical Image Processing - The provisional patent application for the models, entitled as SYSTEMS AND METHODS FOR DEEP LEARNING TO DETECT RETINAL VASCULITIS ON COLOR FUNDUS PHOTOGRAPHS OF PATIENTS WITH UVEITIS, was filed in the United States Patent and Trademark Office (USPTO) on February 1, 2023. - Continuing development of deep learning algorithms to monitor and measure blood leakages from fluorescein angiography (FA) of uveitis patients. - Continuing development using deep learning algorithms to classify uveitis from retinal fundus images and OCT images. - Finalized our experiments for the successfully finished PCOR project on detecting tuberculosis drug resistance to summarize our results in a paper. Our experiments used radiological and genomic information from NIAID's TB Portals database (https://tbportals.niaid.nih.gov/). - Malaria Screener is the first smartphone-based system evaluated on the patient level in a real field environment, where it showed great potential to make malaria screening more efficient. We made the data acquired for this field study publicly available to the research community. Center for Clinical Observational Investigations (CCOI) - formerly the Clinical Data Processing - The Center for Clinical Observational Investigations (CCOI) has also been funded, opened, and we have begun to hire staff for it. - Office of AIDS Research Award for our successful proposal: Leveraging large-scale clinical datasets for HIV outcomes research: Automating dataset characterization from reproducible HIV cohort definitions found in HIV clinical datasets. As far as we know, this is the first OAR award for NLM. - Federal Hire for Data Custodian Position for CCOI(7/16/2023). - Expanding the OMOP mapping to more years of the CMS data. Standards/FHIR - Continuing to design a new API for the dbGaP clinical studies variables to support the joint LHC-NCBI dbGaP FHIR project. This will include a table-based, shopping cart-like UI as the primary interface for querying the dbGaP FHIR server. - Improving the NLM Form Builder software suite by adding support for the new FHIR R5 version and adding SNOMED CT support (at SNOMEDs request). - Moving FHIR related software products into the LHC Cloud which entails migrating all software into the LHC Continuous Integration/Continuous Development (CI/CD) process for software development. FISMA Moderate Environment for Health-Related Data about Individuals (FEHRDI) - Data Custodian has been hired and has already taken on the mantel of the role working with the first two teams finishing up paperwork and ensuring that all dataset paperwork has been collected. - Approval for opening up the FISMA Moderate Environment has been granted now after policy and procedures have been put into place. All personnel involved with the FISMA Moderate Environment are now required to complete a Code of Conduct form. - The next two teams moving to the environment have been selected and we will be working with them to get all of the paperwork and their tool requirements in place to ensure an easy transition. Deidentification - Continuing to develop a new version of the NLM-Scrubber designed to capture more information from external knowledge sources and represent them in the new data structures, so that we can not only better recognize PII elements in clinical text but also better recognize clinical and scientific information and other non-PII elements of clinical notes. - Moving the NLM Scrubber software and PII data into the new FEHRDI environment so that the Scrubber has access to PII data for training and testing the software.