Machine learning approaches for electronic health records phenoty**: a methodical review

S Yang, P Varghese, E Stephenson… - Journal of the …, 2023 - academic.oup.com
Objective Accurate and rapid phenoty** is a prerequisite to leveraging electronic health
records for biomedical research. While early phenoty** relied on rule-based algorithms …

[HTML][HTML] Generate analysis-ready data for real-world evidence: tutorial for harnessing electronic health records with advanced informatic technologies

J Hou, R Zhao, J Gronsbell, Y Lin, CL Bonzel… - Journal of medical …, 2023 - jmir.org
Although randomized controlled trials (RCTs) are the gold standard for establishing the
efficacy and safety of a medical treatment, real-world evidence (RWE) generated from real …

[HTML][HTML] MixEHR-Guided: A guided multi-modal topic modeling approach for large-scale automatic phenoty** using the electronic health record

Y Ahuja, Y Zou, A Verma, D Buckeridge, Y Li - Journal of biomedical …, 2022 - Elsevier
Abstract Electronic Health Records (EHRs) contain rich clinical data collected at the point of
the care, and their increasing adoption offers exciting opportunities for clinical informatics …

Large language models with retrieval-augmented generation for zero-shot disease phenoty**

WE Thompson, DM Vidmar, JK De Freitas… - ar** based on unsupervised embeddings from electronic health records
JK De Freitas, KW Johnson, E Golden, GN Nadkarni… - Patterns, 2021 - cell.com
Robust phenoty** of patients from electronic health records (EHRs) at scale is a challenge
in clinical informatics. Here, we introduce Phe2vec, an automated framework for disease …

Arch: Large-scale knowledge graph via aggregated narrative codified health records analysis

Z Gan, D Zhou, E Rush, VA Panickan, YL Ho… - Journal of Biomedical …, 2025 - Elsevier
Objective: Electronic health record (EHR) systems contain a wealth of clinical data stored as
both codified data and free-text narrative notes (NLP). The complexity of EHR presents …

Modeling electronic health record data using an end-to-end knowledge-graph-informed topic model

Y Zou, A Pesaranghader, Z Song, A Verma… - Scientific Reports, 2022 - nature.com
The rapid growth of electronic health record (EHR) datasets opens up promising
opportunities to understand human diseases in a systematic way. However, effective …

Automatic phenoty** by a seed-guided topic model

Z Song, Y Hu, A Verma, DL Buckeridge… - Proceedings of the 28th …, 2022 - dl.acm.org
Electronic health records (EHRs) provide rich clinical information and the opportunities to
extract epidemiological patterns to understand and predict patient disease risks with suitable …

GTM-decon: guided-topic modeling of single-cell transcriptomes enables sub-cell-type and disease-subtype deconvolution of bulk transcriptomes

LS Swapna, M Huang, Y Li - Genome Biology, 2023 - Springer
Cell-type composition is an important indicator of health. We present Guided Topic Model for
deconvolution (GTM-decon) to automatically infer cell-type-specific gene topic distributions …

Classifying pseudogout using machine learning approaches with electronic health record data

SK Tedeschi, T Cai, Z He, Y Ahuja… - Arthritis care & …, 2021 - Wiley Online Library
Objective Identifying pseudogout in large data sets is difficult due to its episodic nature and a
lack of billing codes specific to this acute subtype of calcium pyrophosphate (CPP) …