A5102921689- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Computational Drug Discovery Methods
- Pharmaceutical Practices and Patient Outcomes
- Pharmacogenetics and Drug Metabolism
- Pharmacovigilance and Adverse Drug Reactions
- Electronic Health Records Systems
- Pharmaceutical studies and practices
- Bioinformatics and Genomic Networks
- Advanced Text Analysis Techniques
- Mobile Health and mHealth Applications
- Health Systems, Economic Evaluations, Quality of Life
- Dementia and Cognitive Impairment Research
- Atrial Fibrillation Management and Outcomes
- Topic Modeling
- Machine Learning in Healthcare
- Respiratory Support and Mechanisms
- Scientific Computing and Data Management
- Cannabis and Cannabinoid Research
- Patient Safety and Medication Errors
- Schizophrenia research and treatment
- Health Policy Implementation Science
- Healthcare Systems and Technology
- Ethics in Clinical Research
- Drug Transport and Resistance Mechanisms
University of Pittsburgh
2015-2024
Pittsburg State University
2021
City of Hope
2020
Washington State University Spokane
2020
University of Utah
2020
Covance (United States)
2020
Health Economics and Outcomes Research (United Kingdom)
2019
McGill University
2016
Douglas Mental Health University Institute
2016
University of Washington
2005-2008
Abstract Introduction This study aims to explore machine learning (ML) methods for early prediction of Alzheimer's disease (AD) and related dementias (ADRD) using the real‐world electronic health records (EHRs). Methods A total 23,835 ADRD 1,038,643 control patients were identified from OneFlorida+ Research Consortium. Two ML used develop models. Both knowledge‐driven data‐driven approaches explored. Four computable phenotyping algorithms tested. Results The gradient boosting tree (GBT)...
Abstract Translational research requires data at multiple scales of biological organization. Advancements in sequencing and multi-omics technologies have increased the availability these data, but researchers face significant integration challenges. Knowledge graphs (KGs) are used to model complex phenomena, methods exist construct them automatically. However, tackling biomedical problems flexibility way knowledge is modeled. Moreover, existing KG construction provide robust tooling cost...
Although potential drug–drug interactions (PDDIs) are a significant source of preventable drug-related harm, there is currently no single complete PDDI information. In the current study, all publically available sources information that could be identified using comprehensive and broad search were combined into dataset. The dataset merged fourteen different including 5 clinically-oriented sources, 4 Natural Language Processing (NLP) Corpora, Bioinformatics/Pharmacovigilance sources. As...
Pre-emptive pharmacogenomic (PGx) testing of a panel genes may be easier to implement and more cost-effective than reactive if sufficient number medications are covered by single test future medication exposure can anticipated. We analysed the incidence individual patients in United States multiple drugs for which guidelines available (PGx drugs) within selected four-year period (2009–2012) order identify quantify pharmacotherapy nation-wide patient population that could impacted pre-emptive...
PCR amplification using COnsensus DEgenerate Hybrid Oligonucleotide Primers (CODEHOPs) has proven to be highly effective for identifying unknown pathogens and characterizing novel genes. We describe iCODEHOP; a new interactive web application that simplifies the process of designing selecting CODEHOPs from multiply-aligned protein sequences. iCODEHOP intelligently guides user through degenerate primer design including uploading sequences, creating multiple alignment, deriving calculating...
Members of the W3C Health Care and Life Sciences Interest Group (HCLS IG) have published a variety genomic drug-related data sets as Resource Description Framework (RDF) triples. This experience has helped interest group define general workflow for mapping health care life science (HCLS) to RDF linking it with other Linked Data sources. paper presents along four case studies that demonstrate addresses many challenges may be faced when creating new resources. The first study describes...
Data quality and fitness for analysis are crucial if outputs of analyses electronic health record data or administrative claims should be trusted by the public research community.We describe a tool (called Achilles Heel) developed Observational Health Sciences Informatics Collaborative (OHDSI) compare from this as it was applied to 24 large healthcare datasets across seven different organizations.We highlight 12 rules that identified issues in at least 10 provide full set 71 one dataset....
Colchicine has a narrow therapeutic index. Its toxicity can be increased due to concomitant exposure drugs inhibiting its metabolic pathway; these are cytochrome P450 3A4 (CYP3A4) and P-glycoprotein (P-gp).To examine clinical outcomes associated with colchicine drug interactions using the spontaneous reports of US Food Drug Administration (FDA) Adverse Event Reporting System (FAERS).We conducted disproportionality analysis FAERS data from January 2004 through June 2020. The reporting odds...
Importance β-lactam (BL) allergies are the most common drug allergy worldwide, but reported in error. BL also well-established risk factors for adverse events and antibiotic-resistant infections during inpatient health care encounters, understanding of long-term outcomes patients with remains limited. Objective To evaluate clinical allergies. Design, Setting, Participants This longitudinal retrospective cohort study was conducted at a single regional system western Pennsylvania. Electronic...
Temporal predictive models have the potential to improve decisions in health care, public services, and other domains, yet they often fail effectively support decision-makers. Prior literature shows that many misalignments between model behavior decision-makers' expectations stem from issues of specification, namely how, when, for whom predictions are made. However, specifications tasks highly technical difficult non-data-scientist stakeholders interpret critique. To address this challenge...
Reusable machine-processable clinical decision support system (CDSS) rules have not been widely achieved in the medical informatics field. This study introduces process, results, challenges faced, and lessons learned while converting Centers for Disease Control Prevention (CDC)-recommended immunization schedules (2022) to CDSS rules. The presents our experience vaccination into tabular, charts, MS Excel, quality language (CQL) formats. CQL format can be automatically converted using existing...
The entire drug safety enterprise has a need to search, retrieve, evaluate, and synthesize scientific evidence more efficiently. This discovery synthesis process would be greatly accelerated through access common framework that brings all relevant information sources together within standardized structure. presents an opportunity establish open-source community effort develop global knowledge base, one standardizes available for drugs health outcomes of interest (HOIs) from electronic...
Medication exposure is a potential risk factor for falls and subsequent death functional decline among older adults. However, controversy remains on the best way to assess medication which approach predicts falls. The objective of current study was examine association between different measures community-dwelling adults.This retrospective cohort conducted using Falls Free PA program data linked prescription claims from Pennsylvania's Pharmaceutical Assistance Contract Elderly program....
Between 2012 and 2017, the U.S. Food Drug Administration (FDA) approved 10 antidiabetic indicated therapies. Due to limited literature on voluntarily reported safety outcomes for recently drugs, this study investigated adverse drug reactions (ADRs) in FDA Adverse Event Reporting System (FAERS).A disproportionality analysis of spontaneously ADRs was conducted. FAERS reports from January 1, March 31, 2022 were compiled, allowing a 5-year buffer following approval 2017. odds ratios calculated...
First, existing sleep stage classifier sensors and algorithms are reviewed compared in terms of classification accuracy, level automation, implementation complexity, invasiveness, targeted application. Next, the a miniature microsystem for low-latency automatic rodents is presented. The algorithm uses one EMG (electromyogram) two EEG (electroencephalogram) signals as inputs order to detect REM (rapid eye movement) sleep, optimized low complexity power consumption. It implemented an on-board...
Background. Pharmacogenomic testing has the potential to improve safety and efficacy of pharmacotherapy, but clinical application pharmacogenetic knowledge remained uncommon. Clinical Decision Support (CDS) systems could help overcome some barriers implementation. The aim this study was evaluate perception usability a web- mobile-enabled CDS system for pharmacogenetics-guided drug therapy–the Medication Safety Code (MSC) system–among users (i.e., physicians pharmacists). Furthermore, sought...
The botanical natural product goldenseal can precipitate clinical drug interactions by inhibiting cytochrome P450 (CYP) 3A and CYP2D6. Besides P‐glycoprotein, effects of on other clinically relevant transporters remain unknown. Established transporter‐expressing cell systems were used to determine the inhibitory a extract, standardized major alkaloid berberine, transporter activity. Using recommended basic models, extract was predicted inhibit efflux BCRP uptake OATP1B1/3. cocktail approach,...