Luke V. Rasmussen
A5071369319- Biomedical Text Mining and Ontologies
- Machine Learning in Healthcare
- Genomics and Rare Diseases
- Electronic Health Records Systems
- Ethics in Clinical Research
- Scientific Computing and Data Management
- BRCA gene mutations in cancer
- Semantic Web and Ontologies
- Clinical practice guidelines implementation
- Genetic Associations and Epidemiology
- Topic Modeling
- Meta-analysis and systematic reviews
- Cancer Genomics and Diagnostics
- Data Quality and Management
- Sepsis Diagnosis and Treatment
- Research Data Management Practices
- Pharmacogenetics and Drug Metabolism
- Data-Driven Disease Surveillance
- Genetics, Bioinformatics, and Biomedical Research
- Primary Care and Health Outcomes
- Artificial Intelligence in Healthcare
- Pneumonia and Respiratory Infections
- Artificial Intelligence in Healthcare and Education
- Chronic Kidney Disease and Diabetes
- Gene expression and cancer classification
Northwestern University
2016-2025
General Department of Preventive Medicine
2019-2023
National University of Singapore
2016
Marshfield Clinic
2007-2014
University of Pennsylvania
2014
Vanderbilt University
2013
Pennsylvania State University
2013
National Human Genome Research Institute
2013
National Institutes of Health
2013
Essentia Health
2013
Genetic studies require precise phenotype definitions, but electronic medical record (EMR) data are recorded inconsistently and in a variety of formats.To present lessons learned about validation EMR-based phenotypes from the Electronic Medical Records Genomics (eMERGE) studies.The eMERGE network created validated 13 EMR-derived algorithms. Network sites Group Health, Marshfield Clinic, Mayo Northwestern University, Vanderbilt University.By validating we that: (1) multisite improves...
Clinical data captured in electronic medical records accurately identify cases and controls for genome-wide association studies.
Abstract Objective Health care generated data have become an important source for clinical and genomic research. Often, investigators create iteratively refine phenotype algorithms to achieve high positive predictive values (PPVs) or sensitivity, thereby identifying valid cases controls. These the greatest utility when validated shared by multiple health systems. Materials Methods We report current status impact of Phenotype KnowledgeBase (PheKB, http://phekb.org ), online environment...
Genome-wide association studies (GWAS) are being conducted at an unprecedented rate in population-based cohorts and have increased our understanding of the pathophysiology complex disease. Regardless context, practical utility this information will ultimately depend upon quality original data. Quality control (QC) procedures for GWAS computationally intensive, operationally challenging, constantly evolving. Here we enumerate some challenges QC data describe approaches that electronic MEdical...
We describe here the design and initial implementation of eMERGE-PGx project. eMERGE-PGx, a partnership Electronic Medical Records Genomics Network Pharmacogenomics Research Network, has three objectives: (i) to deploy PGRNseq, next-generation sequencing platform assessing sequence variation in 84 proposed pharmacogenes, nearly 9,000 patients likely be prescribed drugs interest 1- 3-year time frame across several clinical sites; (ii) integrate well-established clinically validated...
Background— ECG QRS duration, a measure of cardiac intraventricular conduction, varies ≈2-fold in individuals without disease. Slow conduction may promote re-entrant arrhythmias. Methods and Results— We performed genome-wide association study to identify genomic markers duration 5272 disease selected from electronic medical record algorithms at 5 sites the Electronic Medical Records Genomics (eMERGE) network. The most significant loci were evaluated within Cohorts for Heart Aging Research...
The objective of this study was to identify the number people with diabetes from a DataLink developed as part SUPREME-DM (SUrveillance, PREvention, and ManagEment Diabetes Mellitus) project, consortium 11 integrated health systems that use comprehensive EHR data for research.
Electronic health records (EHRs) are increasingly used for clinical and translational research through the creation of phenotype algorithms. Currently, algorithms most commonly represented as noncomputable descriptive documents knowledge artifacts that detail protocols querying diagnoses, symptoms, procedures, medications, and/or text-driven medical concepts, primarily meant human comprehension. We present desiderata developing a computable representation model (PheRM).A team clinicians...
Objective: There is increasing interest in using electronic health records (EHRs) to identify subjects for genomic association studies, due part the availability of large amounts clinical data and expected cost efficiencies subject identification. We describe construction validation an EHR-based algorithm with age-related cataracts. Materials methods: used a multi-modal strategy consisting structured database querying, natural language processing on free-text documents, optical character...
Federal value-based payment programs require primary care practices to conduct quality improvement activities, informed by the electronic reports on clinical measures that their health records (EHRs) generate. To determine whether EHRs produce adequate task, we examined survey responses from 1,492 across twelve states, supplemented with qualitative data. Meaningful-use participation, which requires use of a federally certified EHR, was associated ability generate reports—but did not...
Abstract Objective Integrating patient-reported outcomes (PROs) into electronic health records (EHRs) can improve patient-provider communication and delivery of care. However, new system implementation in health-care institutions is often accompanied by a change clinical workflow organizational culture. This study examines how well an EHR-integrated PRO fits workflows individual needs different provider groups within 2 clinics. Materials Methods Northwestern Medicine developed implemented...
BACKGROUNDDespite guidelines promoting the prevention and aggressive treatment of ventilator-associated pneumonia (VAP), importance VAP as a driver outcomes in mechanically ventilated patients, including patients with severe COVID-19, remains unclear. We aimed to determine contribution unsuccessful mortality for pneumonia.METHODSWe performed single-center, prospective cohort study 585 respiratory failure, 190 whom had who underwent at least 1 bronchoalveolar lavage. A panel intensive care...
AIR data sharing is integral to spur research reproducibility, promote reuse, and accelerate research.However, the first step in using these assets -discovering that they exist -is compounded by problems incentives, standardization, coordination of efforts.In 2023, National Institutes Health (NIH) implemented their updated Data Sharing Policy, which mandates timely all NIH-funded data.However, for policy shift culture, improve several changes must happen.In a companion piece 1 , we present...
WIRELESS COMMUNICATIONS (Twireless) contains high-quality technical manuscripts on advances in the state of art wireless communications.Both theoretical contributions (including new techniques, concepts, and analyses) practical system experiments, prototypes, applications) are encouraged.Tutorial expositions permanent reference value also welcome.All members IEEE eligible for membership Society upon payment annual fee $30.00.
Abstract Objective Clinicians’ ability to use and interpret genetic information depends upon how those data are displayed in electronic health records (EHRs). There is a critical need develop systems effectively display EHRs augment clinical decision support (CDS). Materials Methods The National Institutes of Health (NIH)-sponsored Clinical Sequencing Exploratory Research Electronic Medical Records & Genomics EHR Working Groups conducted multiphase, iterative process involving working...
Abstract Genome‐wide association studies (GWAS) are a useful approach in the study of genetic components complex phenotypes. Aside from large cohorts, GWAS have generally been limited to one or few diseases traits. The emergence biobanks linked electronic medical records (EMRs) allows efficient reuse data yield meaningful genotype–phenotype associations for multiple phenotypes Phase I MEdical Records and GEnomics (eMERGE‐I) Network is National Human Genome Research Institute‐supported...