Clinical and radiomics parameter prognostication in metastatic uveal melanoma patients treated with hepatic arterial infusion chemotherapy
Bibliographic record
Abstract
INTRODUCTION: Metastatic uveal melanoma (MUM) has a poor prognosis, but hepatic arterial infusion chemotherapy (HAIC) may improve outcomes in patients with hepatic metastases. To identify reliable prognostic factors for patient stratification and treatment allocation, we analyzed the clinical and imaging data from a large single-center cohort using machine learning (ML) models. METHODS: Pre- and post-first treatment clinical data of 235 patients with MUM treated with HAIC between 2009 and 2019 were retrospectively analyzed using Cox regression to identify prognostic factors for overall survival (OS) and time to change treatment strategy (TTCS). Furthermore, ML models were trained on clinical and computed tomography (CT) data for endpoint prediction. RESULTS: Pre-treatment multi-variate analysis identified elevated lactate dehydrogenase (LDH) (OS: 6.5 vs. 16.4 months, hazard ratio [HR]) = 1.87, P = 0.006) and gamma-glutamyl transpeptidase (GGT) (OS: 7.6 vs. 16.4 months, HR = 1.67, P = 0.012) as prognostic factors for inferior OS. Decreased albumin (TTCS: 1.3 vs. 6.1 months, HR = 6.26, P < 0.001) and elevated LDH (TTCS: 2.9 vs. 7.6 months, HR = 1.72, P = 0.011) and alanine aminotransferase (ALT) (TTCS: 3.7 vs. 6.4 months, HR = 1.65, P = 0.004) predicted shorter TTCS. Scoring enhanced the power of the prognosticators for OS and TTCS. Post-first treatment multi-variate analysis emphasized the importance of inflammation management and liver protection. ML models incorporating radiomics features from baseline CT imaging were not superior to models based on pre-treatment clinical data alone. CONCLUSION: We identified independent but synergistic prognostic factors for outcome stratification to guide treatment decisions and optimize patient management. ML-based radiomics features did not significantly enhance prognostic performance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".