Multiple Myeloma Curated Dataset

**Overview**
This Multiple Myeloma data set begins with casting a wide net and ends with gathering a highly granular observations for tens of thousands of de-identified patients. The broad inclusion criteria, U.S. patients with at least one date-indexed diganosis code for multiple myeloma, allows for population-level analyses. Meanwhile, curated tables for patients who meet lab, medication, or other clinical requirements make this data set a research-ready ground for multivariate associations and risk modeling.

**Key Features**
The clinically rich, recent and representative data includes:
- 130K+ patients with the ICD code for MM
- Unique Demographics- 22% african american, 75% white, 3% AAPI
- 102K with a first MM Dx since 1/1/2010
- 63K with MM-specific treatment data
- 57% with observations 12 or more months prior to Dx
- 38% with at least 2 years of post-Dx monitoring labs and procedures
- 29% with treatment data spanning at least 12 months
- 30K ECOG scores

**Use cases**
- Trial design
- External control arms
- Comparative safety and efficacy
- Care access and outcome disparities

搜集汇总

背景与挑战

背景概述

该多发性骨髓瘤数据集涵盖13万余名美国患者，包含人口统计特征、治疗记录及长期监测数据，支持人群水平分析和临床研究。其细化的治疗数据表（如63K患者治疗记录、30K ECOG评分）特别适用于试验设计、疗效比较等医疗研究需求。