Machine learning approaches for predicting differentiated thyroid cancer recurrence using thyroglobulin levels and whole-body scans: a retrospective cohort study

Reza Nouri, Erfan Ayubi, Shiva Borzouei, Sajjad Farashi · 2026

Read Machine learning approaches for predicting differentiated thyroid cancer recurrence using thyroglobulin levels and whole-body scans: a retrospective cohort study by Reza Nouri, Erfan Ayubi, Shiva Borzouei, Sajjad Farashi (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13522623.txt.

Description

Reza Nouri, Erfan Ayubi, Shiva Borzouei, and Sajjad Farashi apply machine learning to predict thyroid cancer recurrence in a 2026 retrospective study. Three hundred fifty-five patients with differentiated thyroid cancer were followed for ten years after thyroid removal and radioactive iodine treatment. Records supplied tumor, treatment, and blood marker data, and six learning algorithms were compared head to head.

One boosted-tree model performed best, reaching accuracy near ninety-eight percent with an almost perfect discrimination score. The strongest predictors were prior recurrence count, a stimulated blood marker level in the first year, spread to neck nodes, and first response to treatment. The authors also propose reserving whole-body scans for high-risk patients, which could spare low-risk patients unnecessary testing while keeping close watch where recurrence is likely.

Catalog record

CREATORReza Nouri, Erfan Ayubi, Shiva Borzouei, Sajjad Farashi
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE37056
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13522623

Browse the full library · About the Tower of Babel