Improved Survival Prediction by Combining Radiological Imaging and S-100B Levels Into a Multivariate Model in Metastatic Melanoma Patients Treated With Immune Checkpoint Inhibition

Machine learning in the prediction of immunotherapy response and prognosis of melanoma: a systematic review and meta-analysis

Background

The emergence of immunotherapy has changed the treatment modality for melanoma and prolonged the survival of many patients. However, a handful of patients remain unresponsive to immunotherapy and effective tools for early identification of this patient population are still lacking. Researchers have developed machine learning algorithms for predicting immunotherapy response in melanoma, but their predictive accuracy has been inconsistent. Therefore, the present systematic review and meta-analysis was performed to comprehensively evaluate the predictive accuracy of machine learning in melanoma response to immunotherapy.

Methods

Relevant studies were searched in PubMed, Web of Sciences, Cochrane Library, and Embase from their inception to July 30, 2022. The risk of bias and applicability of the included studies were assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Meta-analysis was performed on R4.2.0.

Results

A total of 36 studies consisting of 30 cohort studies and 6 case-control studies were included. These studies were mainly published between 2019 and 2022 and encompassed 75 models. The outcome measures of this study were progression-free survival (PFS), overall survival (OS), and treatment response. The pooled c-index was 0.728 (95%CI: 0.629-0.828) for PFS in the training set, 0.760 (95%CI: 0.728-0.792) and 0.819 (95%CI: 0.757-0.880) for treatment response in the training and validation sets, respectively, and 0.746 (95%CI: 0.721-0.771) and 0.700 (95%CI: 0.677-0.724) for OS in the training and validation sets, respectively.

Conclusion

Machine learning has considerable predictive accuracy in melanoma immunotherapy response and prognosis, especially in the former. However, due to the lack of external validation and the scarcity of certain types of models, further studies are warranted.

Machine Learning Improves the Prediction of Responses to Immune Checkpoint Inhibitors in Metastatic Melanoma

Pretreatment LDH is a standard prognostic biomarker for advanced melanoma and is associated with response to ICI. We assessed the role of machine learning-based radiomics in predicting responses to ICI and in complementing LDH for prognostication of metastatic melanoma. From 2008-2022, 79 patients with 168 metastatic hepatic lesions were identified. All patients had arterial phase CT images 1-month prior to initiation of ICI. Response to ICI was assessed on follow-up CT at 3 months using RECIST criteria. A machine learning algorithm was developed using radiomics. Maximum relevance minimum redundancy (mRMR) was used to select features. ROC analysis and logistic regression analyses evaluated performance. Shapley additive explanations were used to identify the variables that are the most important in predicting a response. mRMR selection revealed 15 features that are associated with a response to ICI. The machine learning model combining both radiomics features and pretreatment LDH resulted in better performance for response prediction compared to models that included radiomics or LDH alone (AUC of 0.89 (95% CI: [0.76-0.99]) vs. 0.81 (95% CI: [0.65-0.94]) and 0.81 (95% CI: [0.72-0.91]), respectively). Using SHAP analysis, LDH and two GLSZM were the most predictive of the outcome. Pre-treatment CT radiomic features performed equally well to serum LDH in predicting treatment response.

Prognostic Value of Lactate Dehydrogenase, Melanoma Inhibitory Protein, and S-100B Protein in Patients with Malignant Melanoma

Objective

This investigation probed the prognostic potential for lactate dehydrogenase (LDH), melanoma inhibitory activity protein (MIA), and S-100B protein in cases of malignant melanoma.

Methods

84 cases were segregated into effective cohort (n = 64) and ineffective cohort (n = 20) depending on clinical efficacy. The cases were followed up for three years and segregated into mortality cohort (n = 29) and survival cohort (n = 55) depending upon 3-year survival. Serum LDH, MIA, and S-100B levels were compared across the effective and ineffective cohorts. Serum LDH, MIA, and S-100B levels in cases of different clinical stages were comparatively analyzed, with correlations of these indicators with the clinical stage being evaluated. ROC evaluated the prognostic potential of serum LDH, MIA, and S-100B. Cases were segregated into the high-level and low-level cohorts according to serum LDH, MIA, and S-100B levels, and the survival rates of cases were compared.

Results

The levels of LDH, MIA, and S-100B in the effective cohort were significantly lower than those in the ineffective cohort. The AUC value of the composite indicator of serum LDH, MIA, and S-100B for effectiveness evaluation was (0.839). Serum LDH, MIA, and S-100B levels were positively linked to the clinical stage. AUC value of the composite indicator of serum LDH, MIA, and S-100B for prognosis evaluation prediction (0.942) was elevated compared to LDH (0.632), MIA (0.732), or S-100B (0.828) alone. Survival rate of cases of LDH ≥30.56 mg/L (57.14%, 32/56) was lower than that of cases of LDH <30.56 mg/L (82.14%, 23/28) (log-rank χ 2  = 4.672, P < 0.05). The survival rate of MIA ≥5.34 ng/mL cases was lower than that of MIA <5.34 ng/mL cases. The survival rate of cases of S-100B ≥ 1.03ug/L was lower than that of S-100B < 1.03ug/L.

Conclusion

Serum LDH, MIA, and S-100B protein levels are linked to the clinical stage. The lactate dehydrogenase, melanoma inhibitory protein, and S-100B protein are of good clinical effectiveness and have the prognostic potential for cases of malignant melanoma.