Havell Markus

Graduate Trainee, Pennsylvania State University, College of Medicine

1 active project

SLE Prediction

We are exploring the electronic health record data to explore whether we can predict SLE diagnosis in patients prior to diagnosis. The idea is to create an accurate model that could be used to identify high risk patients and enable…

Scientific Questions Being Studied

We are exploring the electronic health record data to explore whether we can predict SLE diagnosis in patients prior to diagnosis. The idea is to create an accurate model that could be used to identify high risk patients and enable more accurate prediction of SLE. SLE is a very heterogenous disease, thus such a model would be useful.

Project Purpose(s)

  • Disease Focused Research (systemic lupus erythematosus)
  • Methods Development
  • Control Set

Scientific Approaches

We are planning to use EHR data prior to SLE diagnosis as predictors to train a machine learning model for SLE prediction. We will encode previous diagnosis code, laboratory codes, procedure codes, and medication codes into binary features indicating whether a patient has a history of that given code or not. We will train various ML models to predict SLE diagnosis. We will evaluate the model based on accuracy.

Anticipated Findings

A model to predict SLE more accurately than currently available laboratory markers. This will also us to identify clinical features of patients that are at a high risk of developing SLE prior to diagnosis. This model could be readily used in clinic, as electronic health record data is widely available and requires no further cost.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Controlled Tier

Research Team

Owner:

  • Havell Markus - Graduate Trainee, Pennsylvania State University, College of Medicine
1 - 1 of 1
<
>
Request a Review of this Research Project

You can request that the All of Us Resource Access Board (RAB) review a research purpose description if you have concerns that this research project may stigmatize All of Us participants or violate the Data User Code of Conduct in some other way. To request a review, you must fill in a form, which you can access by selecting ‘request a review’ below.