Back

Survival Analysis on Papillary Thyroid Cancer Through Cox Proportional Hazards Model

Abeywardana, D.; Iluppangama, M.; Tsokos, C.

2025-12-30 oncology
10.64898/2025.12.23.25342949 medRxiv
Show abstract

Cancer accounts for one in six deaths globally, making patient survivorship critical for medical professionals. Thyroid cancer incidence is rising in the United States, with Papillary Thyroid Cancer (PTC) representing approximately 80% of cases. This study develops a semi-parametric Cox Proportional Hazards model to investigate associations between PTC patient survival time and five risk factors: age, sex, malignant tumor size, race, and cancer stage. Our final Cox-PH model, which satisfies all necessary assumptions, identified three statistically significant individual risk factors and three two-way interaction terms that influence mortality hazard rates. We ranked all factors and their interactions by hazard ratio to determine the strongest contributors to patient mortality. These findings provide insights into how demographic and clinical characteristics affect PTC prognosis, potentially informing risk stratification and treatment planning for this increasingly prevalent cancer type.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.