What question did this study set out to answer?

This research aims to validate DiaSurv, an AI-based prognostic assay, for identifying high-risk patients in stage I-II cutaneous melanoma.

Clinical validation of an AI-based prognostic assay for stage I-II cutaneous melanoma.

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates superior risk stratification in early-stage melanoma, suggesting improved treatment outcomes.

This research aims to validate DiaSurv, an AI-based prognostic assay, for identifying high-risk patients in stage I-II cutaneous melanoma.
Evaluated DiaSurv on a retrospective cohort of 456 stage I-II primary CM patients.
Analyzed whole-slide images (WSI) to classify risk based on tumor characteristics.
Performed Kaplan-Meier and multivariable Cox regression analyses to assess survival outcomes.
Low-risk patients had significantly better 5-year recurrence-free survival (92% vs 38%, HR = 7.71, p < 0.001).
In subgroup analysis, DiaSurv identified 23.4% of patients with high-risk profiles despite favorable AJCC staging.
Low-risk classification at 5 years showed a negative predictive value of 92.2% for RFS and 96.5% for OS.

Kanaan et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates superior risk stratification in early-stage melanoma, suggesting improved treatment outcomes.

This research aims to validate DiaSurv, an AI-based prognostic assay, for identifying high-risk patients in stage I-II cutaneous melanoma.
Evaluated DiaSurv on a retrospective cohort of 456 stage I-II primary CM patients.
Analyzed whole-slide images (WSI) to classify risk based on tumor characteristics.
Performed Kaplan-Meier and multivariable Cox regression analyses to assess survival outcomes.
Low-risk patients had significantly better 5-year recurrence-free survival (92% vs 38%, HR = 7.71, p < 0.001).
In subgroup analysis, DiaSurv identified 23.4% of patients with high-risk profiles despite favorable AJCC staging.
Low-risk classification at 5 years showed a negative predictive value of 92.2% for RFS and 96.5% for OS.

Kanaan et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark