Related Experiment Video
Updated: May 26, 2025
Simplified Intrafemoral Injections Using Live Mice Allow for Continuous Bone Marrow Analysis
Published on: November 10, 2023
A model for predicting day-100 stem cell transplant-related mortality in AL amyloidosis
Eli Muchtar1, Angela Dispenzieri2, Vaishali Sanchorawala3
1Division of Hematology, Mayo Clinic, Rochester, MN, USA. muchtar.eli@mayo.edu.
Insights
Autologous stem cell transplant (ASCT) in AL amyloidosis has high mortality. A new 4-variable model using NT-proBNP/BNP, albumin, ECOG PS, and systolic blood pressure predicts day-100 transplant-related mortality (TRM).
Area of Science:
- Hematology
- Oncology
- Clinical Research
Background:
- Autologous stem cell transplant (ASCT) is a treatment for AL amyloidosis.
- Transplant-related mortality (TRM) remains a significant concern following ASCT in AL amyloidosis patients.
- Accurate prediction of early TRM is crucial for patient management and decision-making.
Purpose of the Study:
- To identify pre-transplant predictors of day-100 all-cause mortality after ASCT in AL amyloidosis.
- To develop and validate a predictive model for early TRM in this patient population.
Main Methods:
- A retrospective analysis of 1718 AL amyloidosis patients who underwent ASCT between 2003-2020 across 9 centers.
- Random forest (RF) classification with 10-fold cross-validation was used for variable selection.
- A final logistic regression model incorporating NT-proBNP/BNP, serum albumin, ECOG performance status (PS), and systolic blood pressure was developed.
Main Results:
- Day-100 TRM occurred in 4.4% of patients, primarily due to shock, arrhythmia, or organ failure.
- The final 4-variable model demonstrated good predictive performance with an AUC of 0.70 ± 0.12.
- A scoring system based on the model predicted TRM risk ranging from 0.46% for a score of 0 to 14.5% for a score of ≥3.
Conclusions:
- A novel, parsimonious model effectively predicts day-100 TRM in AL amyloidosis patients undergoing ASCT.
- This predictive tool can aid clinicians in better-informed decision-making for ASCT in AL amyloidosis.
- The model highlights key clinical factors influencing early transplant outcomes in this heterogeneous disease.
Abstract:
Autologous stem cell Transplant (ASCT)-related mortality (TRM) in AL amyloidosis remains elevated. AL amyloidosis patients (n = 1718) from 9 centers, transplanted 2003-2020 were included. Pre-ASCT variables of interest were assessed for association with day-100 all-cause mortality. A random forest (RF) classifier with 10-fold cross-validation assisted in variable selection. The final model was fitted using logistic regression. The median age at ASCT was 58 years. Day-100 TRM occurred in 75 patients (4.4%) with the predominant causes being shock, high-grade arrhythmia, and organ failure. Ten factors were associated with day-100 TRM on univariate analysis. RF classifier using these variables generated a model with an area under the curve (AUC) of 0.72 ± 0.12. To refine the model selection using importance hierarchy function, a 4-variable model [NT-proBNP/BNP, serum albumin, ECOG performance status (PS), and systolic blood pressure] was built with an AUC of 0.70 ± 0.12. Based on logistic regression coefficients, ECOG PS 2/3 was assigned two points while other adverse predictors 1-point each. The model score range was 0-5, with a day-100 TRM of 0.46%, 3.2%, 5.8%, and 14.5% for 0, 1, 2, and ≥3 points, respectively. This model to predict day-100 TRM in AL amyloidosis allows better-informed decision-making in this heterogeneous disease.
