Umang Chaudhry

About Dr. Phil Lieberman, Jewish Studies Research Context 1 The Torah was originally transcribed in Medieval times, where medieval scholars transcribed the consonants. This could produce ambiguity; consider the New York Times – if you read the words “sh rd ths”… Read More

About Clinical notes and other free-text documents provide a breadth of clinical information that is not often available within structured data. Transformer-based natural language processing (NLP) models, such as BERT, have demonstrated great promise to improve clinical text processing. However, these models are commonly trained on generic corpora,… Read More

About The goal of this project is to employ deep learning on paired EEG-MRI data in order to make MRI predictions based on EEG alone. The project currently has ~40 subjects with paired MRI-EEG data (collected separately but with the same task design), which will grow… Read More

About The Education and Brain Science Research Lab is beginning the Student Teacher Interaction Analytic (STiA) project to determine the relationship between executive function language used by teachers during reading instruction and reading outcomes. Executive function (EF) is a set of cognitive controls that support us in planning,… Read More

Current Project: Using automatic speech recognition to transcribe audio files from patients with depression to determine efficacy of therapy. Before and after outcomes will be assessed using telephone audio files where participants were called and asked what they were “thinking” at the moments just before the call. These audio files… Read More

Our team is interested in developing natural language processing (NLP) systems using transformers to classify whether patients have drug-related adverse events from patients’ clinical notes in Vanderbilt University Medical Center electronic health records (EHRs), which could be potentially associated with a specific drug of interest. The Initial approach to this… Read More

Clinical notes and other free-text documents provide a breadth of clinical information that is not often available within structured data. Transformer-based natural language processing (NLP) models, such as BERT, have demonstrated great promise in using transfer learning to  improve clinical text processing. However, these models are commonly trained on generic corpora, which do not necessarily reflect many… Read More

As part of a larger exploration of the British Culture of Litigation (from a literary perspective), we are working on developing text-mining techniques with the corpus of Proquest British Periodicals, which contains (of its total 3.4 mil) roughly a million articles in the relevant timeframe of 1770-1850 produced in several… Read More

Project WISE is working to develop a measurement tool that can measure teachers’ implementation of evidence-based behavior management practices in general and special education classrooms. Typically, researchers and school administrators will use systematic direct observation (SDO) to collect data on teacher practices; however, this can be resource intensive… Read More