Staging System to Predict the Risk of Relapse in Multiple Myeloma Patients Undergoing Autologous Stem Cell Transplantation

Abstract

Over the last decade autologous stem cell transplantation (ASCT) has emerged as the standard of care in the management of Multiple Myeloma (MM). However, the cases of early relapse (within 36 months) after the stem cell rescue remains a significant challenge. For a lot of practical purposes, it is crucial to identify whether a patient undergoing ASCT falls into the high-risk group (likely to relapse within 36 months) or a low risk one. Our analysis showed that existing MM staging systems (International Staging System or ISS and Durie Salmon Staging or DSS) are not sufficient to discriminate between the risk groups significantly. To address this, we gathered a total of 39 clinical and laboratory parameters of 347 patients from the Department of Medical Oncology of All India Institute of Medical Sciences (AIIMS). We employed a stacked machine learning model consisting spectral clustering and Fast and Frugal Tree (FFT) technique to come up with a 3-factor multivariate 2-stage staging scheme, which turns out to be extremely decisive about the outcome of the stem cell rescue. Our model comes up with a three-factor (1. if patients has relapsed following remission, 2. response to induction, 3. pre-transplant Glomerular Filtration Rate or GFR) staging scheme. The resulting model stratifies patients into high-risk and low-risk groups with markedly distinct progression-free (median survival-24 months vs. 91 months) and overall survival (median survival-51 months vs. 135 months) patterns.

Keywords: autologous stem cell transplantation; fast and frugal tree; multiple myeloma; multivariate survival analysis; risk of relapse; spectral clustering.

Figure 1

Overall survival (OS) in 253 patients with multiple myeloma stratified by spectral clustering. Median OS was more than 90 months for low risk group (number of patients = 166, events = 40) (orange color), whereas it was 47 months for high risk group (number of patients = 87, events = 42) (black color).

Figure 2

Progression Free survival (PFS) in 253 patients with multiple myeloma stratified by spectral clustering. Median PFS was 74 months for low risk group (number of patients = 166, events = 70) (orange color), whereas it was 24 months for high risk group (number of patients = 87, events = 50) (black color).

Figure 3

Fast-and-frugal tree based staging scheme for patients undergoing ASCT. CR, Complete Response; VGPR, Very Good Partial Response; PR, Partial Response; NR, No Response; SD, Stable Disease; PD, Progressive disease.

Figure 4

Overall survival (OS) in 253 patients with multiple myeloma stratified by FFT rules. Median OS was 135 months for low risk group (number of patients = 156, events = 36) (orange color), whereas it was 51 months for high risk group (number of patients = 97, events = 58) (black color).

Figure 5

Progression Free survival (PFS) in 253 patients with multiple myeloma stratified by FFT rules. Median PFS was 91 months for low risk group (number of patients = 156, events = 62) (orange color), whereas it was 24 months for high risk group (number of patients = 97, events = 58) (black color).