Date of Award

2025-05-01

Degree Name

Doctor of Philosophy

Department

Data Science

Advisor(s)

Ming-Ying Leung

Abstract

Prostate cancer (PrCa) remains a critical challenge in precision oncology due to several reasons including its apparent heterogenous condition, recurrence following treatment and rapid progressive forms. Therefore, identifying patients at risk of progression is essential to fast-track therapeutic decisions and improve outcomes. Despite recent advances in genomic and molecular profiling, conventional PrCa risk assessment tools heavily rely on a few clinical parameters, neglecting the prognostic potential of genomic biomarkers in the presence of clinical biomarkers. This study presents a computational pipeline to harmonize and evaluate the prognostic value of clinicogenomic profiles of patients in modelling progression free survival (PFS). PFS, defined as the time from treatment initiation to disease progression or death whichever comes first, offers a meaningful proxy for overall survival (OS). Since PFS is convenient in cases where long term follow-up is impractical, it is considered useful for speeding up insights into treatment effect and the drug development process. We deployed several existing survival models with extensive tuning strategies across different clinicogenomic data experimental settings, taking into consideration the interplay of relevant and highly ranked clinicogenomic features in all models as well as their discriminative accuracy in ranking patient risks. These models revealed distinct dynamics but consistent multifactorial relevance of clinical and genomic factors to determine association with PrCa progression with good discrimination ability. This study reinforced the use of PFS as a surrogate for OS in PrCa research. Also, the recurrence of specific clinicogenomic biomarkers across different settings highlighted the relevance for further wet lab investigation. Ultimately, these findings upvotes the incorporation of genomics data into survival modelling pipelines, thereby strengthening the case for clinicogenomic risk stratification insights for precision oncology.

Language

en

Provenance

Received from ProQuest

File Size

169 p.

File Format

application/pdf

Rights Holder

Kelvin Ofori-Minta

Download

Share

COinS