Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 8, 2025Blood

Machine learning replicates and extends clinician-informed disease severity grading classification for acute pain and CKD in sickle cell disease

View Full Paper
Ask AI
Bookmark
Share

Authors

MZMinzhang ZhengJHJane S. Hankins

Discussion

Loading...

Member takes

Overview

Machine learning demonstrates accurate disease severity grading for acute pain and CKD in sickle cell disease, suggesting improved clinical application and data coverage.

Key Points

  • To evaluate how machine learning can replicate and expand clinician-informed grading for acute pain and chronic kidney disease in sickle cell disease.
  • Developed the Sickle Cell Organ Grading System (SCOGS) for grading SCD complications.
  • Trained random forest classifiers with longitudinal data to replicate clinician grades.
  • Evaluated model performance using cross-validation and measured predictive accuracy with AUC.
  • Analyzed feature importance through SHAP for model interpretation.
  • Achieved 0.97 AUC and 90% accuracy for acute pain grading.
  • Achieved 0.98 AUC and 97% accuracy for CKD grading.
  • Increased CKD grading coverage from 21% to over 90% using model-based imputation.
  • Models reflected known clinical reasoning, supporting SCOGS internal consistency.

Cite This Study

Zheng et al. (2025) studied this question.

synapsesocial.com/papers/69362f634fa91c937236ddfchttps://doi.org/10.1182/blood-2025-4733
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Assessing replicability in chronic kidney disease severity scoring classifications using the sickle cell outcome grading system2025
  2. 2Application and challenges of the sickle cell outcome grading system (SCOGS) for classifying acute chest syndrome severity2025
  3. 3Explainable AI-based prediction of chronic kidney disease as a long-term outcome of sickle cell disease in a large, multi-site observational data cohort2025
  4. 4Evaluating the Diagnostic Performance of AI and Machine Learning in Sickle Cell Disease Detection: A Systematic Review2026
  5. 5Early prediction of severity progression in patients with chronic kidney disease: A Machine Learning Predictive Modelling analysis with retrospective data of a tertiary care hospital2025