Decision tree model to predict one-year survival in ambulatory patients with advanced cancer
PLOS One · 14.07.2026 · 21 (7) · e0353195
DOI: 10.1371/journal.pone.0353195 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 14.07.2026. Verfasst von Yusuke Hiratsuka und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Palliative Medicine, Takeda General Hospital, Aizu Wakamatsu, Japan. Hauptthemen laut MEDLINE: Neoplasms, Decision Trees. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science and ICT, South Korea.
Abstract (Originalsprache)
Background
An accurate prognostication is crucial for end-of-life decision-making in advanced cancer care. While existing prognostic tools focus on short-term survival (weeks/months), there is a paucity of studies that have examined the long-term prediction at one year. A one-year timeframe is regarded as a general indicator of palliative care referral; however, there are many uncertain issues. This study aimed to develop a one-year survival prediction model using objective parameters for patients with advanced cancer.
Methods
This was a secondary analysis of data from a Korean prospective cohort study. Participants, with clinician-predicted survival of ≤1 year, were assessed using clinical data, performance status, laboratory data and chemotherapy response. Recursive partitioning analyses (RPA) were used to identify the prognostic factors and build a prediction model.
Results
Of the 200 advanced cancer patients (mean age 64.4, 36% female; 33.5% lung cancer), the median survival was 228 days. Using three variables (chemotherapy response, C reactive protein -Albumin Ratio, and lactate dehydrogenase level), we developed a 4-node survival tree. The model demonstrated an optimism-corrected area under the curve of 0.749 (95% confidence interval: 0.696–0.800) at one year, after 200 bootstrap resampling. The Brier score was 0.161, and the calibration slope was 0.99, indicating high predictive accuracy.
Conclusions
We developed an RPA model to facilitate one-year survival prediction in patients with advanced cancer. The 4-leaf model incorporated only three readily available variables. Following external validation, this model may prove valuable in assisting clinicians with one-year survival prognostication.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Palliative Medicine, Takeda General Hospital, Aizu Wakamatsu, Japan.
- Department of Palliative Medicine, Tohoku University Graduate School of Medicine, Sendai, Japan.
- Department of Family Medicine, Chungnam National University Hospital, Daejeon, Republic of Korea.
- Department of Family Medicine, Dongguk University Ilsan Hospital, Goyang-si, Republic of Korea.
- Department of Medicine, College of Medicine, Dongguk University, Seoul, Republic of Korea.
- Division of Hematology and Medical Oncology, Department of Internal Medicine, Seoul National University Bundang Hospital, Seoul National University College of Medicine, Seongnam, Republic of Korea.
ORCID-Profile: Yusuke Hiratsuka, Sang-Yeon Suh
Förderung
- Ministry of Science and ICT, South Korea
Zitieren
APA
Hiratsuka, Y., Yoon, S. J., Suh, S. Y., & Kim, Y. J. (2026). Decision tree model to predict one-year survival in ambulatory patients with advanced cancer. PLOS One, 21(7), e0353195. https://doi.org/10.1371/journal.pone.0353195
Vancouver
Hiratsuka Y, Yoon SJ, Suh SY, Kim YJ. Decision tree model to predict one-year survival in ambulatory patients with advanced cancer. PLOS One. 2026;21(7):e0353195. doi:10.1371/journal.pone.0353195
BibTeX
@article{Hiratsuka2026,
author = {Hiratsuka, Yusuke and Yoon, Seok-Joon and Suh, Sang-Yeon and Kim, Yu Jung},
title = {Decision tree model to predict one-year survival in ambulatory patients with advanced cancer},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {7},
pages = {e0353195},
doi = {10.1371/journal.pone.0353195}
}
EUVIMED