Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Personalized medicine: application to a breast cancer study

Yang, Chenxin (2019) Personalized medicine: application to a breast cancer study. Master's Thesis, University of Pittsburgh. (Unpublished)

[img] PDF
Submitted Version
Restricted to University of Pittsburgh users only until April 2021.

Download (2MB) | Request a Copy

Abstract

In randomized clinical trials, investigators compare the clinical outcomes among treatment arms and make claims on the effectiveness of experimental treatments versus the standard ones. Recent developments in biotechnology and associated biomarkers have led to advances in evaluating heterogeneous patient response and the relationship between treatment responses and certain biomarkers. Precision medicine, therefore, is becoming very popular in the healthcare industry. It is of great public health significance that proper implementation of precision medicine leads to informed and efficient decision making and patient management in clinical practice. Traditionally discovery of a predictive marker of treatment benefit is performed via a test of the interaction term between treatment and the marker of interest in a regression model that predicts the clinical outcome of interest. Recently a new paradigm has been proposed by redefining the search for predictive markers, as the search for an optimal individualized treatment rule (ITR) on treatment selection. Here we describe this new approach and apply those methods to a breast cancer study to identify clinical and genomic markers that are predictive of treatment benefit. The R package “personalized” was used in the implementation. Application of some of these methods does identify optimal ITRs that lead to improved outcomes based on the empirical estimates. However, validation via random splitting of training and testing datasets suggested that the findings may be resulted from over-fitting. These ITR-based methods provide a powerful tool for us to identify predictive markers for treatment response, but caution should be taken especially with high-dimensional marker data.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: University of Pittsburgh ETD
Status: Unpublished
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Yang, Chenxinchy83@pitt.educhy830000-0002-9816-2790
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Thesis AdvisorGong, Tanggot1@pitt.edugot1
Committee MemberLandsittel, Douglasdpl12@pitt.edudpl12
Committee MemberKang, Chaeryoncrkang@pitt.educrkang
Date: 25 June 2019
Date Type: Publication
Defense Date: 15 April 2019
Approval Date: 25 June 2019
Submission Date: 3 April 2019
Access Restriction: 2 year -- Restrict access to University of Pittsburgh for a period of 2 years.
Number of Pages: 61
Institution: University of Pittsburgh
Schools and Programs: Graduate School of Public Health > Biostatistics
Degree: MS - Master of Science
Thesis Type: Master's Thesis
Refereed: Yes
Uncontrolled Keywords: Individualized Treatment Rules (ITR), Breast Cancer, Trastuzumab, Lapatinib, Treatment effects
Date Deposited: 25 Jun 2019 18:18
Last Modified: 25 Jun 2019 18:18
URI: http://d-scholarship.pitt.edu/id/eprint/36236

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item