Kathryn Rough
YOU?
Author Swipe
Core Concepts in Pharmacoepidemiology: Principled Use of Artificial Intelligence and Machine Learning in Pharmacoepidemiology and Healthcare Research Open
Artificial intelligence (AI) and machine learning (ML) are important tools across many fields of health and medical research. Pharmacoepidemiologists can bring essential methodological rigor and study design expertise to the design and use…
Evaluation of Large Language Model Performance on the Biomedical Language Understanding and Reasoning Benchmark: Comparative Study (Preprint) Open
BACKGROUND The availability of increasingly powerful large language models (LLMs) has attracted substantial interest in their potential for interpreting and generating human-like text for biomedical and clinical applications. However, ther…
How well it works: Benchmarking performance of GPT models on medical natural language processing tasks Open
Importance The ability of large language models (LLMs) to generate high-quality, human-like text has been accompanied with speculation about their application in healthcare, alongside ethical and safety concerns. Objective Evaluate LLM per…
View article: Evaluation of Large Language Model Performance on the Biomedical Language Understanding and Reasoning Benchmark: Comparative Study
Evaluation of Large Language Model Performance on the Biomedical Language Understanding and Reasoning Benchmark: Comparative Study Open
Background The availability of increasingly powerful large language models (LLMs) has attracted substantial interest in their potential for interpreting and generating human-like text for biomedical and clinical applications. However, ther…
View article: Prediction of cardiovascular risk factors from retinal fundus photographs: Validation of a deep learning algorithm in a prospective non‐interventional study in Kenya
Prediction of cardiovascular risk factors from retinal fundus photographs: Validation of a deep learning algorithm in a prospective non‐interventional study in Kenya Open
Aim Hypertension and diabetes mellitus (DM) are major causes of morbidity and mortality, with growing burdens in low‐income countries where they are underdiagnosed and undertreated. Advances in machine learning may provide opportunities to…
Deep Learning for Epidemiologists: An Introduction to Neural Networks Open
Deep learning methods are increasingly being applied to problems in medicine and healthcare. However, few epidemiologists have received formal training in these methods. To bridge this gap, this article introduces to the fundamentals of de…
Predicting overdose among individuals prescribed opioids using routinely collected healthcare utilization data Open
We demonstrate that sophisticated algorithms using healthcare databases can be predictive of overdose, creating opportunities for active monitoring and early intervention.
Predicting Onset of COVID-19 with Mobility-Augmented SEIR Model Open
Timely interventions and early preparedness of healthcare resources are crucial measures to tackle the COVID-19 disease. To aid these efforts, we developed the Mobility-Augmented SEIR model (MA-SEIR) that leverages Google’s aggregate and a…
Predicting Inpatient Medication Orders From Electronic Health Record Data Open
In a general inpatient population, we predicted patient‐specific medication orders based on structured information in the electronic health record (EHR). Data on over three million medication orders from an academic medical center were use…
Birth Outcomes for Pregnant Women with HIV Using Tenofovir–Emtricitabine Open
The risk of adverse birth outcomes was not higher with TDF-FTC-LPV/r than with ZDV-3TC-LPV/r or TDF-FTC-ATV/r among HIV-infected women and their infants in the United States, although power was limited for some comparisons. (Funded by the …
Effect of Gestational Age at Tenofovir-Emtricitabine-Efavirenz Initiation on Adverse Birth Outcomes in Botswana Open
Among human immunodeficiency virus-positive women in Botswana on the recommended first-line antiretroviral therapy regimen, tenofovir-emtricitabine-efavirenz, initiated within the first or early second trimester, we found no increased risk…
Patterns of opioid initiation at first visits for pain in United States primary care settings Open
Purpose The primary objective of this study was to characterize variation in patterns of opioid prescribing within primary care settings at first visits for pain, and to describe variation by condition, geography, and patient characteristi…
Risk of neonatal drug withdrawal after intrauterine co-exposure to opioids and psychotropic medications: cohort study Open
Objectives To assess the impact of in utero co-exposure to psychotropic medications and opioids on the incidence and severity of neonatal drug withdrawal.Design Observational cohort study.Setting Nationwide sample of pregnancies in publicl…
Zidovudine use in pregnancy and congenital malformations Open
For most malformations, first-trimester zidovudine was not associated with increased risk. The potential increase in male genital malformations was small in absolute terms, and should be evaluated further.
Comparative Safety of Antiretroviral Drugs to Treat HIV During Pregnancy Open
Each year, nearly 1.5 million women with HIV become pregnant, and require antiretroviral treatment to reduce risk of perinatal transmission of the virus and improve their own health. The safety of currently approved antiretroviral medicati…
Suppression of Substance Abuse Claims in Medicaid Data and Rates of Diagnoses for Non–Substance Abuse Conditions Open
This study examines the association between implementation of a Centers for Medicare & Medicaid Services policy mandating suppression of substance abuse–related claims in Medicare and Medicaid Research Identifiable Files and rates of diagn…