Leveraging a Joint of Phenotypic and Genetic Features on Cancer Patient Subgrouping

TL;DR

This paper presents a novel system that combines phenotypic and genetic data from electronic health records and genetic tests to improve cancer patient subgrouping through classification and clustering techniques.

Contribution

It introduces an integrated approach leveraging joint phenotypic and genetic features for more accurate cancer patient stratification, utilizing multiple machine learning models and graph-based embeddings.

Findings

Effective feature filtering enhances model performance.

Multiple machine learning models achieve high classification accuracy.

Graph-based embeddings improve patient clustering quality.

Abstract

Cancer is responsible for millions of deaths worldwide every year. Although significant progress has been achieved in cancer medicine, many issues remain to be addressed for improving cancer therapy. Appropriate cancer patient stratification is the prerequisite for selecting appropriate treatment plan, as cancer patients are of known heterogeneous genetic make-ups and phenotypic differences. In this study, built upon deep phenotypic characterizations extractable from Mayo Clinic electronic health records (EHRs) and genetic test reports for a collection of cancer patients, we developed a system leveraging a joint of phenotypic and genetic features for cancer patient subgrouping. The workflow is roughly divided into three parts: feature preprocessing, cancer patient classification, and cancer patient clustering based. In feature preprocessing step, we performed filtering, retaining the most relevant features. In cancer patient classification, we utilized joint categorical features to build a patient-feature matrix and applied nine different machine learning models, Random Forests (RF), Decision Tree (DT), Support Vector Machine (SVM), Naive Bayes (NB), Logistic Regression (LR), Multilayer Perceptron (MLP), Gradient Boosting (GB), Convolutional Neural Network (CNN), and Feedforward Neural Network (FNN), for classification purposes. Finally, in the cancer patient clustering step, we leveraged joint embeddings features and patient-feature associations to build an undirected feature graph and then trained the cancer feature node embeddings.