2 citations · 4 across the 6 of their papers we have counts for
7 papers
EHRAdapt: Adapting Pretrained Language Models to Electronic Health Records with Semantic Priors for Rare Clinical Events
Andre R Goncalves, Vincent Liu, Priyadip Ray
Electronic health records (EHRs) encode clinical histories as (time, modality, code) tuples, whereas pretrained language models expect text tokens. Serializing them as text inflate…
Sequential Inference of Hospitalization Electronic Health Records Using Probabilistic Models
Alan D. Kaplan, Priyadip Ray, John D. Greene +1
In the dynamic hospital setting, decision support can be a valuable tool for improving patient outcomes. Data-driven inference of future outcomes is challenging in this dynamic set…
Unsupervised Probabilistic Models for Sequential Electronic Health Records
Alan D. Kaplan, John D. Greene, Vincent X. Liu +1
We develop an unsupervised probabilistic model for heterogeneous Electronic Health Record (EHR) data. Utilizing a mixture model formulation, our approach directly models sequences…
Performance metrics for intervention-triggering prediction models do not reflect an expected reduction in outcomes from using the model
Alejandro Schuler, Aashish Bhardwaj, Vincent Liu
Clinical researchers often select among and evaluate risk prediction models using standard machine learning metrics based on confusion matrices. However, if these models are used t…
A Causal Machine Learning Framework for Predicting Preventable Hospital Readmissions
Ben J. Marafino, Alejandro Schuler, Vincent X. Liu +2
Clinical predictive algorithms are increasingly being used to form the basis for optimal treatment policies--that is, to enable interventions to be targeted to the patients who wil…
Nonstationary Multivariate Gaussian Processes for Electronic Health Records
Rui Meng, Braden Soper, Herbert Lee +3
We propose multivariate nonstationary Gaussian processes for jointly modeling multiple clinical variables, where the key parameters, length-scales, standard deviations and the corr…
Modeling sepsis progression using hidden Markov models
Brenden K. Petersen, Michael B. Mayhew, Kalvin O. E. Ogbuefi +3
Characterizing a patient's progression through stages of sepsis is critical for enabling risk stratification and adaptive, personalized treatment. However, commonly used sepsis dia…