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

Use of survival trees and random forests for modeling time to end stage renal disease

Hurd, Alex (2019) Use of survival trees and random forests for modeling time to end stage renal disease. Master's Thesis, University of Pittsburgh. (Unpublished)

Submitted Version

Download (898kB) | Preview


Polycystic kidney disease (PKD) is an inherited disorder distinguished by kidney cyst growth and a corresponding decline in renal function. With minimal treatment options available, often times PKD progresses to chronic kidney disease (CKD) and eventually, end-stage renal disease (ESRD), a complete loss of kidney function. The Consortium for Radiologic Imaging Studies of Polycystic Kidney Disease (CRISP) is a longitudinal cohort study that has been studying participants with PKD since 2001, including analysis of imaging and biomarker data. CRISP studies have characterized renal cyst growth, as well as important prognostic biomarkers for CKD. Identifying PKD patients at greatest risk for developing ESRD can help design future studies.

In this study, survival methods, including decision trees, were applied to baseline CRISP data to determine which characteristics were associated with ESRD-free survival. Results of Cox proportional hazard, survival tree, and random survival forests models showed that height-adjusted total kidney volume (htTKV), total kidney cyst volume (TCV), and glomular filtration rate (GFR) had the strongest association with ESRD-free survival.

Public health significance: Determination of which characteristics are associated with ESRD-free survival can inform preventative treatments and programs for PKD patients and give better insight to medical professionals.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Thesis AdvisorLandsittel,
Committee MemberYouk,
Committee MemberJeong,
Date: 24 June 2019
Date Type: Publication
Defense Date: 12 April 2019
Approval Date: 24 June 2019
Submission Date: 4 April 2019
Access Restriction: 5 year -- Restrict access to University of Pittsburgh for a period of 5 years.
Number of Pages: 75
Institution: University of Pittsburgh
Schools and Programs: School of Public Health > Biostatistics
Degree: MS - Master of Science
Thesis Type: Master's Thesis
Refereed: Yes
Uncontrolled Keywords: Survival trees
Date Deposited: 24 Jun 2019 17:43
Last Modified: 01 May 2024 05:15


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item