Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 8:15:1517961.
doi: 10.3389/fonc.2025.1517961. eCollection 2025.

Development and validation of machine learning model to predict early death of melanoma brain metastasis patients

Maierdanjiang Maihemuti #  1 , Maiheliya Kamaierjiang #  2 , Aierpati Maimaiti #  3 , Junshen Wu  1 , Zhibing Dai  1 , Renbing Jiang  1
Affiliations

Development and validation of machine learning model to predict early death of melanoma brain metastasis patients

Maierdanjiang Maihemuti et al. Front Oncol. .

Abstract

Background: Melanoma has the third highest rate of brain metastases among all cancers and is associated with poor long-term survival. This study aimed to develop machine learning models to predict early death in melanoma brain metastasis (MBM) patients to guide clinical decision-making.

Methods: We analyzed MBM patients from the SEER database and Xinjiang Medical University. Patients were randomly divided into training and testing cohorts (7:3 ratio). Seven machine learning models were developed and validated using cross-validation, ROC analysis, decision curve analysis, and calibration curves to predict cancer-specific early death (CSED) and all-cause early death (ACED) within 3 months of diagnosis.

Results: Among 1,547 MBM patients, 531 (34.3%) experienced CSED, and 554 (35.8%) experienced ACED. Key predictive factors included age, treatment modalities (radiation, chemotherapy, surgery), tumor characteristics (ulceration), and extracranial metastases (bone, liver). XGBoost achieved the best performance for ACED prediction (AUC=0.776), while logistic regression performed best for CSED prediction (AUC=0.694). External validation confirmed model reliability with comparable performance.

Conclusion: These machine learning models demonstrate strong predictive performance and may assist clinicians in early risk stratification and treatment planning for MBM patients. The models provide objective risk assessment tools that could improve patient counseling and guide aggressive versus palliative care decisions.

Keywords: brain metastasis; early death; machine learning; melanoma; prognosis.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
Flowchart of the study process.
Figure 2
Figure 2
The 10x cross-validation analysis of ACED (A), and CSED (B).
Figure 3
Figure 3
The ROCAUC (A), PRAUC (B), calibration curve (C), and DCA analysis (D) of ACED in the test cohort.
Figure 4
Figure 4
The ROCAUC (A), PRAUC (B), calibration curve (C), and DCA analysis (D) of ACED in the external validation cohort.
Figure 5
Figure 5
The nomogram of ACED (A), and CSED (B).
Figure 6
Figure 6
The ROCAUC (A), PRAUC (B), calibration curve (C), and DCA analysis (D) of CSED in the test cohort.
Figure 7
Figure 7
The ROCAUC (A), PRAUC (B), calibration curve (C), and DCA analysis (D) of CSED in the external validation cohort.
Figure 8
Figure 8
Machine Learning SHAP Analysis Comparison for ACED Outcomes. Subfigures (A–G) illustrate the influence of various features (e.g., Age, Chemotherapy, Surgery) on the ACED predictions of seven machine learning models (Logistic Regression, XGBoost, KNN, LightGBM, Random Forest, Decision Tree, and SVM). The violin plots in each subfigure display the distribution of SHAP values for each feature, with color indicating different feature values. Deeper colors represent higher SHAP values, signifying a greater impact of the feature on the prediction results.
Figure 9
Figure 9
(A–G) Machine learning SHAP analysis comparison for CSED outcomes.
See this image and copyright information in PMC

References

    1. Gutzmer R, Vordermark D, Hassel JC, Krex D, Wendl C, SChadendorf D, et al. Melanoma brain metastases - Interdisciplinary management recommendations 2020. Cancer Treat Rev. (2020) 89:102083. doi: 10.1016/j.ctrv.2020.102083, PMID: - DOI - PubMed
    1. Conway JW, Rawson RV, Lo S, Ahmed T, Vergara IA, Gide TN, et al. Unveiling the tumor immune microenvironment of organ-specific melanoma metastatic sites. J Immunother Cancer. (2022) 10(9):e004884. doi: 10.1136/jitc-2022-004884, PMID: - DOI - PMC - PubMed
    1. Ascha MS, Ostrom QT, Wright J, Kumthekar P, Bordeaux JS, Sloan AE, et al. Lifetime occurrence of brain metastases arising from lung, breast, and skin cancers in the elderly: A SEER-medicare study. Cancer Epidemiol Biomarkers Prev. (2019) 28:917–25. doi: 10.1158/1055-9965.EPI-18-1116, PMID: - DOI - PMC - PubMed
    1. Cohen JV, Tawbi H, Margolin KA, Amravadi R, Bosenberg M, Brastianos PK, et al. Melanoma central nervous system metastases: current approaches, challenges, and opportunities. Pigment Cell Melanoma Res. (2016) 29:627–42. doi: 10.1111/pcmr.12538, PMID: - DOI - PMC - PubMed
    1. Sadetsky N, Hernandez A, Wallick CJ, McKenna EF, Surinach A, Colburn DE. Survival outcomes in an older US population with advanced melanoma and central nervous system metastases: SEER-Medicare analysis. Cancer Med. (2020) 9:6216–24. doi: 10.1002/cam4.3256, PMID: - DOI - PMC - PubMed

LinkOut - more resources