Predicting cancer mortality using machine learning methods: a global vs. Iran analysis.
Uložené v:
| Názov: | Predicting cancer mortality using machine learning methods: a global vs. Iran analysis. |
|---|---|
| Autori: | Sadeghi H; Department of Physics, Faculty of Sciences, Arak University, Arak, 38156-8-8349, Iran. H-Sadeghi@araku.ac.ir., Seif F; Department of Radiotherapy and Medical Physics, Arak University of Medical Sciences, Arak, Iran. |
| Zdroj: | BMC cancer [BMC Cancer] 2025 Aug 18; Vol. 25 (1), pp. 1329. Date of Electronic Publication: 2025 Aug 18. |
| Spôsob vydávania: | Comparative Study; Journal Article |
| Jazyk: | English |
| Informácie o časopise: | Publisher: BioMed Central Country of Publication: England NLM ID: 100967800 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2407 (Electronic) Linking ISSN: 14712407 NLM ISO Abbreviation: BMC Cancer Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : BioMed Central, [2001- |
| Výrazy zo slovníka MeSH: | Global Health*/statistics & numerical data , Neoplasms*/mortality , Machine Learning*/statistics & numerical data , Prediction Algorithms*, Iran/epidemiology ; Datasets as Topic ; Registries ; Boosting Machine Learning Algorithms ; Random Forest ; Support Vector Machine ; Humans |
| Abstrakt: | Competing Interests: Declarations. Ethics approval and consent to participate: The Ethics Committee of Arak University of Medical Sciences approved the studies involving human participants (Approval number IR.ARAKMU.REC.1403.158). The research adhered to local jurisdiction regulations and institutional standards. Given the retrospective nature of the study, the ethics committee or institutional review board waived the requirement for written informed consent from the participants or their legal guardians/next of kin. Competing interests: The authors declare no competing interests. Background: Cancer remains a leading cause of morbidity and mortality worldwide, with significant variations in incidence, mortality, and survival rates across regions. This study leverages Machine Learning (ML) to analyze global and Iran-specific cancer data, aiming to improve predictive accuracy for cancer mortality. Methods: Using datasets from Global Cancer Observatory (GLOBOCAN) and the Iran National Cancer Registry (INCR), we evaluate the performance of ML models, including XGBoost, Random Forest, and Support Vector Machines, in predicting cancer outcomes. Results: XGBoost achieved superior performance globally ([Formula: see text] = 0.83, AUC-ROC = 0.93) compared to Iran-specific data ([Formula: see text] = 0.79, AUC-ROC = 0.89), highlighting the influence of region-specific risk factors such as Helicobacter pylori infections in Ardabil. Additionally, we explore the application of ML in predicting Second Primary Cancer (SPC) risk, emphasizing the role of radiation dose, age, and genetic mutations as key predictors. Conclusion: This research underscores the potential of ML to inform personalized treatment plans and improve cancer care while addressing challenges such as data imbalances and regional disparities. The findings provide valuable insights for policymakers, researchers, and healthcare providers in developing targeted interventions to reduce the global cancer burden. (© 2025. The Author(s).) |
| References: | J Cancer Res Clin Oncol. 2016 Feb;142(2):365-71. (PMID: 26298838) Genet Med. 2021 Sep;23(9):1726-1737. (PMID: 34113011) JAMA Oncol. 2022 Mar 01;8(3):420-444. (PMID: 34967848) J Healthc Eng. 2021 Jan 27;2021:6679512. (PMID: 33575021) PLoS One. 2020 Oct 15;15(10):e0237658. (PMID: 33057328) Asian Pac J Cancer Prev. 2025 Jan 01;26(1):239-248. (PMID: 39874007) CA Cancer J Clin. 2018 Nov;68(6):394-424. (PMID: 30207593) Arch Iran Med. 2009 Nov;12(6):576-83. (PMID: 19877751) Cancers (Basel). 2020 Dec 17;12(12):. (PMID: 33348826) Breast Cancer Res Treat. 2020 Jun;181(2):255-268. (PMID: 32303988) Bioelectron Med. 2020 Jul 10;6:14. (PMID: 32665967) Artif Intell Med. 2020 Jul;107:101858. (PMID: 32828461) Cancer Med. 2024 Sep;13(18):e70231. (PMID: 39300964) Comput Biol Med. 2025 May;189:110008. (PMID: 40081210) |
| Contributed Indexing: | Keywords: Early prediction; Healthcare; Machine learning; Predicting cancer mortality |
| Entry Date(s): | Date Created: 20250819 Date Completed: 20250915 Latest Revision: 20250915 |
| Update Code: | 20250916 |
| PubMed Central ID: | PMC12359947 |
| DOI: | 10.1186/s12885-025-14796-4 |
| PMID: | 40826340 |
| Databáza: | MEDLINE |
Full Text 
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | Competing Interests: Declarations. Ethics approval and consent to participate: The Ethics Committee of Arak University of Medical Sciences approved the studies involving human participants (Approval number IR.ARAKMU.REC.1403.158). The research adhered to local jurisdiction regulations and institutional standards. Given the retrospective nature of the study, the ethics committee or institutional review board waived the requirement for written informed consent from the participants or their legal guardians/next of kin. Competing interests: The authors declare no competing interests.<br />Background: Cancer remains a leading cause of morbidity and mortality worldwide, with significant variations in incidence, mortality, and survival rates across regions. This study leverages Machine Learning (ML) to analyze global and Iran-specific cancer data, aiming to improve predictive accuracy for cancer mortality.<br />Methods: Using datasets from Global Cancer Observatory (GLOBOCAN) and the Iran National Cancer Registry (INCR), we evaluate the performance of ML models, including XGBoost, Random Forest, and Support Vector Machines, in predicting cancer outcomes.<br />Results: XGBoost achieved superior performance globally ([Formula: see text] = 0.83, AUC-ROC = 0.93) compared to Iran-specific data ([Formula: see text] = 0.79, AUC-ROC = 0.89), highlighting the influence of region-specific risk factors such as Helicobacter pylori infections in Ardabil. Additionally, we explore the application of ML in predicting Second Primary Cancer (SPC) risk, emphasizing the role of radiation dose, age, and genetic mutations as key predictors.<br />Conclusion: This research underscores the potential of ML to inform personalized treatment plans and improve cancer care while addressing challenges such as data imbalances and regional disparities. The findings provide valuable insights for policymakers, researchers, and healthcare providers in developing targeted interventions to reduce the global cancer burden.<br /> (© 2025. The Author(s).) |
|---|---|
| ISSN: | 1471-2407 |
| DOI: | 10.1186/s12885-025-14796-4 |