Survival Analysis of Cancer Patients Based on Chemotherapy Response Data
Othman A. Hansal, Marwah Sami Kzar, Bushra Jabbar Abdul-Kareem, Anil Kumar Sagar · Digitalen Hochschulbibliothek Sachsen-Anhalt (Universitäts- und Landesbibliothek Sachsen-Anhalt) · 2026
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
Digitalen Hochschulbibliothek Sachsen-Anhalt (Universitäts- und Landesbibliothek Sachsen-Anhalt) · Universitäts Frauenklinik · other · 2026
Abstract
Background: Chemotherapy is still a key part of cancer treatment, but survival rates vary a lot and are mostly based on how well the treatment works. It is important to figure out how important response is for predicting outcomes and to use modern computational methods to improve patient stratification. To assess the influence of chemotherapy response on overall survival (OS) and progression-free survival (PFS) utilizing both classical and advanced survival models. A retrospective cohort study involving 420 cancer patients was conducted.
According to RECIST v1.1, the response was classified as a complete response (CR), a partial response (PR), stable disease (SD), or progressive disease (PD). We used Kaplan-Meier and Cox regression to figure out how long people would live, and we used Accelerated Failure Time (AFT) and Random Survival Forest (RSF) models to check the results for sensitivity and robustness. CR and PR were independently correlated with markedly extended overall survival (OS) and progression-free survival (PFS) in contrast to progressive disease (PD). RSF showed better predictive accuracy (C-index=0.82) than Cox (C-index=0.76). Chemotherapy response is a strong sign of how long someone will live.
The incorporation of sophisticated computational models improves forecasting and facilitates clinical application.
Open the resolved locator · 10.25673/123767
Metadata licence: OpenAlex metadata (CC0)