Igor Shuryak

Early Career Tenure-track Researcher, Columbia University

2 active projects

Machine learning analysis of breast cancer metastasis predictors

We are interested in developing machine learning models to identify the predictors of breast cancer metastasis, and to make quantitative predictions

Scientific Questions Being Studied

We are interested in developing machine learning models to identify the predictors of breast cancer metastasis, and to make quantitative predictions

Project Purpose(s)

  • Disease Focused Research (breast cancer)

Scientific Approaches

We will analyze data on breast cancer metastasis using machine learning tools such as random forests, xgboost and causal forests.

Anticipated Findings

We anticipate to develop predictive models of breast cancer metastasis and identify patient sub-populations who are most at risk of developing metastases. Such knowledge can advance clinical practice.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Registered Tier

Research Team

Owner:

  • Igor Shuryak - Early Career Tenure-track Researcher, Columbia University

ML study of cancer outcomes

We are interested in using state of the art ML techniques to predict cancer outcomes, assess heterogeneity of these outcomes between patients, and look for potential drivers of such heterogeneity. This research is important because it can help to identify…

Scientific Questions Being Studied

We are interested in using state of the art ML techniques to predict cancer outcomes, assess heterogeneity of these outcomes between patients, and look for potential drivers of such heterogeneity. This research is important because it can help to identify those patient sub-populations for which particular cancer treatments are most effective.

Project Purpose(s)

  • Disease Focused Research (Cancer)
  • Other Purpose (Develop ML-based approaches to predict cancer outcomes and assess their heterogeneity between patients)

Scientific Approaches

We plan to explore cancer-related data sets within the All of Us database and implement state of the art ML techniques (e.g. random forests, gradient boosting).

Anticipated Findings

We plan to develop predictive models of cancer outcomes and to identify the most important predictors. This can improve clinical practice and enhance scientific knowledge by identifying which treatment approaches may be best suited for particular patient sub-populations.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Controlled Tier

Research Team

Owner:

  • Igor Shuryak - Early Career Tenure-track Researcher, Columbia University
1 - 2 of 2
<
>
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.