Skip to main content
SpringerLink
Log in

Machine learning algorithm to predict response to immunotherapy in real-life settings for patients with advanced melanoma

  • Investigative Report
  • Published:
European Journal of Dermatology

Abstract

Background

Melanoma is one of the most fatal forms of skin cancer. Defining relevant biomarkers to predict treatment outcome based on immune checkpoint inhibitors (ICIs) is needed in order to increase overall survival of metastatic melanoma patients (MM).

Objectives

This study compared different machine learning models in terms of performance to identify biomarkers from clinical diagnosis and follow-up of MM patients, to predict treatment response to ICIs under real-life conditions.

Materials & Methods

Clinical data from melanoma patients with an AJCC status of III C/D or IV, having received ICIs, were extracted from the RIC-MEL database for this pilot study. Light Gradient Boosting Machine, linear regression, Random Forest (RF), Support Vector Machine and Extreme Gradient Boosting were compared in terms of performance. The SHAP (SHapley Additive exPlanations) method was used to assess the link between the different clinical features investigated and the prediction of response to ICIs.

Results

RF showed the highest scores for accuracy (0.63) and sensitivity (0.64) and high scores for precision (0.61) and specificity (0.63). AJCC stage (0.076) showed the highest SHAP mean value, thus being the most suitable feature to predict response to treatment. The number of metastatic sites per year (0.049), number of months since first treatment initiation and the Breslow index (both 0.032) were less predictive, but still showed relatively high predictive power.

Conclusion

This machine learning approach confirms that a certain number of biomarkers may enable prediction of treatment success with ICIs.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Data availability statement: The data that support the findings of this study are available from the corresponding author upon reasonable request.

References

  1. Matthews NH, Li WQ, Qureshi AA. Epidemiology of Melanoma. WH W, JM F, editors. Brisbane 2017.

  2. Globocan. Cancer Incidence and Mortality Worldwide: IARC CancerBase No. 11 2012 [Available from: http://globocan.iarc.fr.]

  3. Robert C, Thomas L, Bondarenko I, et al. Ipilimumab plus dacarbazine for previously untreated metastatic melanoma. N Engl J Med 2011; 364: 2517–26.

    Article  CAS  PubMed  Google Scholar 

  4. Lee AY, Brady MS. Neoadjuvant immunotherapy for melanoma. J Surg Oncol 2021; 123: 782–8.

    Article  CAS  PubMed  Google Scholar 

  5. Thomas D, Bello DM. Adjuvant immunotherapy for melanoma. J Surg Oncol 2021; 123: 789–97.

    Article  CAS  PubMed  Google Scholar 

  6. van Breeschoten J, Wouters M, Hilarius DL, et al. First-line BRAF/ MEK inhibitors versus anti-PD-1 monotherapy in BRAF(V600)-mutant advanced melanoma patients: a propensity-matched survival analysis. Br J Cancer 2021; 124: 1222–30.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Donia M, Ellebaek E, Øllegaard TH, et al. The real-world impact of modern treatments on the survival of patients with metastatic melanoma. Eur J Cancer 2019; 108: 25–32.

    Article  PubMed  Google Scholar 

  8. Moser JC, Chen D, Hu-Lieskovan S, et al. Real-world survival of patients with advanced BRAF V600 mutated melanoma treated with front-line BRAF/MEK inhibitors, anti-PD-1 antibodies, or nivolumab/ ipilimumab. Cancer Med 2019; 8: 7637–43.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. Weber J, Mandala M, Del Vecchio M, et al. Adjuvant nivolumab versus ipilimumab in resected stage III or IV melanoma. N Engl J Med 2017; 377: 1824–35.

    Article  CAS  PubMed  Google Scholar 

  10. Mourah S, Louveau B, Dumaz N. Mechanisms of resistance and predictive biomarkers of response to targeted therapies and immunotherapies in metastatic melanoma. Curr Opin Oncol 2020; 32: 91–7.

    Article  CAS  PubMed  Google Scholar 

  11. Brahmer JR, Lacchetti C, Schneider BJ, et al. Management of immune-related adverse events in patients treated with immune checkpoint inhibitor therapy: american society of clinical oncology clinical practice guideline. J Clin Oncol 2018; 36: 1714–68.

    Article  CAS  PubMed  Google Scholar 

  12. Chan S, Reddy V, Myers B, Thibodeaux Q, Brownstone N, Liao W. Machine learning in dermatology: current applications, opportunities, and limitations. Dermatol Ther (Heidelb) 2020; 10: 365–86.

    Article  PubMed  Google Scholar 

  13. Richter AN, Khoshgoftaar TM. Efficient learning from big data for cancer risk modeling: a case study with melanoma. Comput Biol Med 2019; 110: 29–39.

    Article  PubMed  Google Scholar 

  14. González-Cruz C, Jofre MA, Podlipnik S, et al. Machine learning in melanoma diagnosis limitations about to be overcome. Actas Dermosifiliogr (Engl Ed) 2020; 111: 313–6.

    Article  PubMed  Google Scholar 

  15. Auslander N, Zhang G, Lee JS, et al. Robust prediction of response to immune checkpoint blockade therapy in metastatic melanoma. Nat Med 2018; 24: 1545–9.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. Jiang P, Gu S, Pan D, et al. Signatures of T cell dysfunction and exclusion predict cancer immunotherapy response. Nat Med 2018; 24: 1550–8.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Samstein RM, Lee CH, Shoushtari AN, et al. Tumor mutational load predicts survival after immunotherapy across multiple cancer types. Nat Genet 2019; 51: 202–6.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Johannet P, Coudray N, Donnelly DM, et al. Using machine learning algorithms to predict immunotherapy response in patients with advanced melanoma. Clin Cancer Res 2021; 27: 131–40.

    Article  CAS  PubMed  Google Scholar 

  19. Lee Y. Support vector machines for classification: a statistical portrait. Methods Mol Biol 2010; 620: 347–68.

    Article  PubMed  Google Scholar 

  20. Dalle S, Varey E, Nguyen JM, et al. Management of adjuvant settings for Stage III melanoma patients in France prior to checkpoint inhibitors: epidemiological data from the RIC-Mel database. Eur J Dermatol 2020; 30: 389–96.

    Article  CAS  PubMed  Google Scholar 

  21. Keung EZ, Gershenwald JE. The eighth edition American Joint Committee on Cancer (AJCC) melanoma staging system: implications for melanoma treatment and care. Expert Rev Anticancer Ther 2018; 18: 775–84.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  22. Coomans D, Massart DL. Alternative k-nearest neighbour rules in supervised pattern recognition: Part 1. k-Nearest neighbour classification by using alternative voting rules. Anal Chim Acta 1982; 136: 15–27.

    Article  CAS  Google Scholar 

  23. Hearst MA, Dumais ST, Osuna E, Platt J, Scholkopf B. Support vector machines. IEEE Intell Syst Appl 1998; 13: 18–28.

    Article  Google Scholar 

  24. Breiman L. Random forests. Mach Learn 2001; 45: 5–32.

    Article  Google Scholar 

  25. Manning C, Schutze H. Foundations of statistical natural language processing: MIT press; 1999.

  26. Ogami C, Tsuji Y, Seki H, et al. An artificial neural network-pharmacokinetic model and its interpretation using Shapley additive explanations. CPT Pharmacometrics Syst Pharmacol 2021; 10: 760–8.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  27. Mogensen UB, Ishwaran H, Gerds TA. Evaluating random forests for survival analysis using prediction error curves. J Stat Softw 2012; 50: 1–23.

    Article  PubMed  PubMed Central  Google Scholar 

  28. Madonna G, Masucci GV, Capone M, et al. Clinical Categorization Algorithm (CLICAL) and Machine Learning Approach (SRF-CLICAL) to predict clinical benefit to immunotherapy in metastatic melanoma patients: real-world evidence from the istituto nazionale tumori IRCCS Fondazione Pascale, Napoli, Italy. Cancers (Basel) 2021; 13.

  29. Gibney GT, Weiner LM, Atkins MB. Predictive biomarkers for checkpoint inhibitor-based immunotherapy. Lancet Oncol 2016; 17: e542–e51.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Lee EY, Kulkarni RP. Circulating biomarkers predictive of tumor response to cancer immunotherapy. Expert Rev Mol Diagn 2019; 19: 895–904.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  31. Goodman AM, Kato S, Bazhenova L, et al. Tumor mutational burden as an independent predictor of response to immunotherapy in diverse cancers. Mol Cancer Ther 2017; 16: 2598–608.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  32. Otoshi T, Nagano T, Tachihara M, Nishimura Y. Possible biomarkers for cancer immunotherapy. Cancers (Baselj 2019; 11: 935.

    Article  CAS  Google Scholar 

  33. Rizk EM, Seffens AM, Trager MH, et al. Biomarkers predictive of survival and response to immune checkpoint inhibitors in melanoma. Am J Clin Dermatol 2020; 21: 1–11.

    Article  PubMed  PubMed Central  Google Scholar 

  34. Kambayashi Y, Fujimura T, Hidaka T, Aiba S. Biomarkers for predicting efficacies of anti-PD1 antibodies. Front Med (Lausanne) 2019; 6: 174.

    Article  PubMed  Google Scholar 

  35. Chasseuil E, Saint-Jean M, Chasseuil H, et al. Blood predictive biomarkers for nivolumab in advanced melanoma. Acta Derm Venereol 2018; 98: 406–10.

    Article  CAS  PubMed  Google Scholar 

  36. Ascierto PA, Long GV, Robert C, et al. Survival outcomes in patients with previously untreated BRAF wild-type advanced melanoma treated with nivolumab therapy: three-year follow-up of a randomized phase 3 trial. JAMA Oncol 2019; 5: 187–94.

    Article  PubMed  Google Scholar 

Download references

Acknowledgments: the authors acknowledge the writing and editing support of Karl Patrick Göritz, SMWS-Scientific and Medical Writing Services, France.

Funding

Funding: none.

Author information

Authors and Affiliations

  1. Department of Dermato-Cancerology, CHU Nantes, CIC 1413, CRCINA, University Nantes, Nantes, France

    Cécile Frenard, Emilie Varey & Amir Khammari

  2. Department of Dermatology, CIC 1413, IT services, CHU Nantes, 44000, Nantes, France

    Katleen Blanchet & Brigitte Dréno

  3. IT services, CHU Nantes, 44000, Nantes, France

    Philippe Lecerf

  4. INSERM, CNRS, Immunology and New Concepts in ImmunoTherapy, INCIT, UMR 1302/EMR6001, Nantes Université, Nantes, France

    Amir Khammari

Authors
  1. Cécile Frenard
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Katleen Blanchet
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Philippe Lecerf
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Emilie Varey
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Amir Khammari
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Brigitte Dréno
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Brigitte Dréno.

Ethics declarations

Conflicts of interest: none.

Statement of Ethics: RIC-Mel received, prior to initiation, both ethics committee approval on 9th February 2012 (n°12.108) and the authorization of the French Data Protection Agency (CNIL, DR-2012-259, 28 May 2012).

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Frenard, C., Blanchet, K., Lecerf, P. et al. Machine learning algorithm to predict response to immunotherapy in real-life settings for patients with advanced melanoma. Eur J Dermatol 33, 75–80 (2023). https://doi.org/10.1684/ejd.2023.4447

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1684/ejd.2023.4447

Key words

Search

Navigation