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

Association between Serum Biomarkers and Patient-Reported Outcome of Disability in Multiple Sclerosis

Chen, Chenyi (2022) Association between Serum Biomarkers and Patient-Reported Outcome of Disability in Multiple Sclerosis. Master's Thesis, University of Pittsburgh. (Unpublished)

Download (1MB) | Preview


Multiple sclerosis (MS) is a chronic inflammatory demyelinating disease of the central nervous system. Currently, more than 20 FDA-approved disease-modifying therapies are available on the market. Despite the rapid therapeutic advancements, clinicians still rely on traditional clinical manifestations and magnetic resonance imaging to determine disease activity, progression, and treatment responses. There is an urgent need to find alternative methods to determine disease activity and progression. This thesis tested the hypothesis that serum protein profiles, in conjunction with clinical profiles, were associated with clinically relevant patient-reported disease progression.
To analyze the association between serum protein concentration and clinical features in relation to the patient-reported disability, we applied two statistical learning methods for classifications, namely least absolute shrinkage and selection operator (LASSO) and random forest. We included seven clinical variables, including age, sex, race/ethnicity, disease subtypes, disease duration, disease-modifying therapies (DMT) efficacy, the time interval between serum collection and the patient-reported outcome assessment after sample collection), and 19 proteins.
We compared the predictive performance of LASSO models and random forest models in three feature sets: the clinical feature set, the 19 serum protein set, and the combined feature set. Models with combined clinical and protein features consistently outperformed those with clinical features only or protein features only. All models selected one clinical feature (disease duration) and three protein features (CDCP1, IL12B, and NEFL). This analysis may provide direction for future biomarker studies for MS.


Social Networking:
Share |


Item Type: University of Pittsburgh ETD
Status: Unpublished
CreatorsEmailPitt UsernameORCID
Chen, Chenyichc259@pitt.educhc259
ETD Committee:
TitleMemberEmail AddressPitt UsernameORCID
Thesis AdvisorBuchanich, Jeaninejeanine@pitt.edujeanine
Committee MemberPark, Yongseokyongpark@pitt.eduyongpark
Committee MemberXia, Zongqizxia1@pitt.eduzxia1
Date: 10 May 2022
Date Type: Publication
Defense Date: 22 April 2022
Approval Date: 10 May 2022
Submission Date: 29 April 2022
Access Restriction: 2 year -- Restrict access to University of Pittsburgh for a period of 2 years.
Number of Pages: 42
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: Multiple sclerosis, LASSO, Random Forest
Date Deposited: 10 May 2022 20:49
Last Modified: 10 May 2024 05:15


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item