Prognostic value of clinical and radiomic parameters in patients with liver metastases from uveal melanoma

• Published in: Pigment cell and melanoma research 2024-11, Vol.37 (6), p.831-838
• Main Authors: Lever, Mael, Bogner, Simon, Giousmas, Melina, Mairinger, Fabian D., Baba, Hideo A., Richly, Heike, Gromke, Tanja, Schuler, Martin, Bechrakis, Nikolaos E., Kalkavan, Halime
• Format: Article
• Language: English
• Subjects: Adult; Aged; Aged, 80 and over; Algorithms; Aspartate transaminase; biomarker; Biomarkers; Decision making; Diagnosis; Female; hepatic metastases; Humans; L-Lactate dehydrogenase; Lactate dehydrogenase; Learning algorithms; Liver; Liver Neoplasms - diagnostic imaging; Liver Neoplasms - secondary; Machine Learning; Male; Melanoma; Melanoma - diagnostic imaging; Melanoma - pathology; Melanoma - secondary; Metastases; Metastasis; Middle Aged; Parameter identification; Patients; Population studies; Prognosis; Radiomics; Retrospective Studies; Risk; Risk groups; Subgroups; Survival; Thrombocytes; Transaminase; uveal melanoma; Uveal Neoplasms - diagnostic imaging; Uveal Neoplasms - pathology
• ISSN: 1755-1471; 1755-148X; 1755-148X
• DOI: 10.1111/pcmr.13184

Approximately every second patient with uveal melanoma develops distant metastases, with the liver as the predominant target organ. While the median survival after diagnosis of distant metastases is limited to a year, yet‐to‐be‐defined subgroups of patients experience a more favorable outcome. Therefore, prognostic biomarkers could help identify distinct risk groups to guide patient counseling, therapeutic decision‐making, and stratification of study populations. To this end, we retrospectively analyzed a cohort of 101 patients with newly diagnosed hepatic metastases from uveal melanoma by using Cox‐Lasso regression machine learning, adapted to a high‐dimensional input parameter space. We show that substantial binary risk stratification can be performed, based on (i) clinical and laboratory parameters, (ii) measures of quantitative overall hepatic tumor burden, and (iii) radiomic parameters. Yet, combining two or all three domains failed to improve prognostic separation of patients. Additionally, we identified highly relevant clinical parameters (including lactate dehydrogenase, thrombocyte counts, aspartate transaminase, and the metastasis‐free interval) at first diagnosis of metastatic disease as predictors for time‐to‐treatment failure and overall survival. Taken together, the risk stratification models, built by our machine‐learning algorithm, identified a comparable and independent prognostic value of clinical, radiological, and radiomic parameters in uveal melanoma patients with hepatic metastases. Machine learning enables binary risk stratification for time‐to‐treatment failure and overall survival by radiomic parameters and clinical biomarkers for mUM patients. Combination of parameters from different diagnostic domains does not add prognostic value.