Machine learning for predicting overall survival in early-stage supraglottic cancer: a SEER-based population study

Toimittaja(t)

Universitetsforlaget
2026
Artikkeli
Tietoliikennetekniik|Tietoliikennetekniik
vertaisarvioitu
nbnfi-fe2026040124985.pdf
Hyväksytty kirjoittajan käsikirjoitus - 1.03 MB
Huom! Tiedosto avautuu julkiseksi: 05.01.2027
Lataukset3

Pysyvä osoite

https://urn.fi/URN:NBN:fi-fe2026040124985

Kuvaus

©2026 Taylor & Francis. This is an Accepted Manuscript of an article published by Taylor & Francis in Acta Oto-Laryngologica on 05 Jan 2026, available at: https://doi.org/10.1080/00016489.2025.2603595
Background Supraglottic squamous cell carcinoma (SGSCC) represents the second most prevalent form of laryngeal cancer and carries a poor prognosis. Aims/Objectives This study aimed to combine clinicopathological and treatment-related factors as integrative inputs to build a machine learning (ML) model to estimate the overall survival (OS) of patients with early-stage SGSCC. Furthermore, we explored the complementary prognostic potential of these input parameters. Material and Methods A total of 1171 patients with SGSCC were extracted from Surveillance, Epidemiology, and End Results (SEER) public data. We used feature importance analysis to examine the integrative inputs that are associated with OS. Results The ML model showed a weighted accuracy of 72.3% in predicting OS. The aggregate feature importance showed that age at diagnosis, marital status, number of malignancies, regional lymph nodes, and radiotherapy are the five most important features for enhancing OS among these patients. We found that as age increases, the chance of OS decreases. Being married, the absence of other primary indicators, surgical treatment, and radiotherapy were associated with improved OS. Conclusions and Significance Combining clinicopathological and treatment-related factors seems to predict accurately OS in patients with early-stage SGSCC. External independent geographic validation is warranted to evaluate model generalizability.

URI

https://doi.org/10.1080/00016489.2025.2603595
https://urn.fi/URN:NBN:fi-fe2026040124985

Emojulkaisu

ISBN

ISSN

1651-2251
0001-6489

Aihealue

Kausijulkaisu

Acta oto-laryngologica

OKM-julkaisutyyppi

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä (vertaisarvioitu)

Avainsanat

Machine learning (ML)supraglottic squamous cell carcinoma (SGSCC)overall survivalfeature importance
Tietueen kaikki tiedot