MMRF CoMMpass: Multimodal Survival Prediction for Multiple Myeloma

This reproducibility package contains processed data and outputs for a dynamic-t multimodal landmark survival prediction framework for multiple myeloma. It includes processed MMRF CoMMpass resources, external validation resources, and training/evaluation outputs, supporting reproducible model training, benchmarking, and visualization. The framework utilizes laboratory time-series, drug exposure, and imaging-derived features for survival modeling.

Use Cases

• Training dynamic survival models based on laboratory time-series data
• Benchmarking predictive performance using C-index and AUC metrics
• Conducting external validation of multimodal prognostic frameworks
• Visualizing model predictions and evaluation outputs

Strengths

• Includes external validation resources, supporting model generalizability assessment
• Provides a complete reproducibility package with training outputs and processed data
• Licensed under CC-BY-4.0, facilitating open reuse

Limitations

• Column names and exact row counts are not specified, limiting immediate understanding of data structure
• The dataset is primarily a code and model output package, with the underlying clinical data likely requiring separate access

Provenance

Source

Processed from MMRF CoMMpass study resources

Collection Method

Created as part of a reproducibility package for a research framework

Freshness

Last updated 2026-03-18