Shalini Dhamodharan

Institution-Specific LLM Prompting Recovers PHI That De-identification Systems and Their Gold Standards Both Miss

Daniel Palacios, Matthew Brady Neeley, Angel Adetomike Otto, Shalini Dhamodharan et autres

Secondary use of electronic health records requires de-identification, yet existing systems miss \emph{institutionally situated} protected health information (PHI) such as hospital abbreviations, building names, and internal codes whose status is locally determined. We ask whether large language models (LLMs) with in-context learning …

Ethnic Differences in the Association Between SOD2 rs4880 and Hepatotoxicity in Pediatric Acute Lymphoblastic Leukemia: A Report From the REDIAL Consortium

Emily J. Mason, John P. Woodhouse, Joanna S. Yi, M. Monica Gramatges et autres

ABSTRACT Treatment‐associated hepatotoxicity (TAH) is a common complication of pediatric acute lymphoblastic leukemia (ALL) treatment, but genetic risk factors remain poorly understood. We evaluated the SOD2 rs4880 variant in 544 children with ALL at Texas Children's Hospital. After adjusting for demographic and …

us (code pays fourni par la source)

Big Data Quality Scoring for Structured Data Using MapReduce

Yalong Wu, Shalini Dhamodharan, Vinuthna Ghattamaneni, N. Kokila et autres

In the current big data landscape, where data forms the cornerstone of myriad applications, it is crucial to establish the reliability and credibility of application outcomes through the prism of high-quality data. Nonetheless, data quality has been facing significant evaluation challenges due …

us (code pays fourni par la source)

Liver Disease Prediction Using Bayesian Classification

Shalini Dhamodharan

Data mining is an activity of extracting meaningful data from a large database, using any of its techniques. In this paper we use Bayesian classification technique, which is one of the major classification models. There are many liver disorders that require clinical …