Derivation and validation of the SEER-Medicare myelodysplastic syndromes risk score (SMMRS)

Area of Science:

• Hematology
• Medical Informatics
• Cancer Research

Background:

• The SEER-Medicare dataset is a valuable resource for Myelodysplastic Syndromes (MDS) research.
• Existing MDS prognostic models often lack complete data within the SEER-Medicare dataset.
• There is a need for a validated risk stratification tool tailored for MDS research using SEER-Medicare data.

Purpose of the Study:

• To develop and validate a novel risk score for MDS patients within the SEER-Medicare database.
• To create a tool that facilitates comparative effectiveness research for MDS using SEER-Medicare.
• To assess the performance of the new score against established prognostic models.

Main Methods:

• A new MDS risk score, the SMMRS, was developed using SEER-Medicare data (n=9820) for training and internal validation.
• External validation was performed using clinical data from an independent institutional cohort (n=307).
• Risk stratification performance of the SMMRS was compared to the International Prognostic Scoring System (IPSS).

Main Results:

• The SMMRS was successfully developed and validated for use with the SEER-Medicare dataset.
• Risk stratification by the SMMRS demonstrated comparable performance to the IPSS.
• The net reclassification improvement index was 0.0, indicating similar stratification capabilities.

Conclusions:

• The SMMRS is a useful research tool for stratifying MDS patients within SEER-Medicare studies.
• This novel risk score enhances the utility of the SEER-Medicare dataset for MDS comparative effectiveness research.
• The SMMRS provides a reliable method for risk assessment in large-scale MDS research utilizing SEER-Medicare data.