SCI 발표논문

SCI 발표논문

← SCI 발표논문 목록

NPJ Precis Oncol. 2023;7(1):46.

ML-based sequential analysis to assist selection between VMP and RD for newly diagnosed multiple myeloma.

, , , , , , , , , , ,

제1저자 박성수, 이종철, 변자민 · 교신저자 민창기, 구자민

PMID 37210456 PMC10199943 DOI 10.1038/s41698-023-00385-w IF 9.9 혈액종양내과
소속 (15)
  1. Catholic Research Network for Multiple Myeloma, Catholic Hematology Hospital, College of Medicine, The Catholic University of Korea, Seoul, 06591, Republic of Korea.
  2. Department of Hematology, Seoul St. Mary's Hospital, The Catholic University of Korea, Seoul, 06591, Republic of Korea.
  3. Department of Otorhinolaryngology, GangNeung Asan Hospital, University of Ulsan College of Medicine, Gangneung-si, Gangwon-do, 25440, Republic of Korea.
  4. Department of Internal Medicine, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, Republic of Korea.
  5. ImpriMedKorea, Inc., Seoul, 08507, Republic of Korea.
  6. ImpriMed, Inc., Palo Alto, CA, 94303, USA.
  7. Division of Hematology, Mayo Clinic, Rochester, MN, 55905, USA.
  8. Department of Hematology, Yeoido St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, 07345, Republic of Korea.
  9. Department of Hematology, Incheon St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Incheon, 22711, Republic of Korea.
  10. Department of Hematology, Eunpyeong St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, 03312, Republic of Korea.
  11. Catholic Research Network for Multiple Myeloma, Catholic Hematology Hospital, College of Medicine, The Catholic University of Korea, Seoul, 06591, Republic of Korea. ckmin@catholic.ac.kr.
  12. Department of Hematology, Seoul St. Mary's Hospital, The Catholic University of Korea, Seoul, 06591, Republic of Korea. ckmin@catholic.ac.kr.
  13. ImpriMedKorea, Inc., Seoul, 08507, Republic of Korea. jaminkoo@alumni.stanford.edu.
  14. ImpriMed, Inc., Palo Alto, CA, 94303, USA. jaminkoo@alumni.stanford.edu.
  15. Department of Chemical Engineering, Hongik University, Seoul, 04066, Republic of Korea. jaminkoo@alumni.stanford.edu.

Abstract

Optimal first-line treatment that enables deeper and longer remission is crucially important for newly diagnosed multiple myeloma (NDMM). In this study, we developed the machine learning (ML) models predicting overall survival (OS) or response of the transplant-ineligible NDMM patients when treated by one of the two regimens-bortezomib plus melphalan plus prednisone (VMP) or lenalidomide plus dexamethasone (RD). Demographic and clinical characteristics obtained during diagnosis were used to train the ML models, which enabled treatment-specific risk stratification. Survival was superior when the patients were treated with the regimen to which they were low risk. The largest difference in OS was observed in the VMP-low risk & RD-high risk group, who recorded a hazard ratio of 0.15 (95% CI: 0.04-0.55) when treated with VMP vs. RD regimen. Retrospective analysis showed that the use of the ML models might have helped to improve the survival and/or response of up to 202 (39%) patients among the entire cohort (N = 514). In this manner, we believe that the ML models trained on clinical data available at diagnosis can assist the individualized selection of optimal first-line treatment for transplant-ineligible NDMM patients.

© 2023. The Author(s).

Figures

Fig. 1
Fig. 1 Study profile. Flow diagram describing the construction of a the development and b test cohort.
Fig. 2
Fig. 2 ML survival models and treatment-specific risk stratification. a ROC–AUC of the ML survival models predicting OS (t = 36 months) of the transplant-ineligible NDMM patients who received VMP or b RD regimen as the first-line treatment. c OS by the risk stratification based on the ML survival models (VMP- and RD-treated at the top and bottom, respectively). The left and right figures represent the results from the development vs. test cohort, respectively. The accuracies of the models, when applied to the independent test cohort, are marked as a dot in each graph.
Fig. 3
Fig. 3 Combinatorial risk stratification of the development cohort with respect to VMP and RD regimen. a Number of NDMM patients in the four combinatorial risk subgroups. b OS of the patients in each subgroup treated by VMP or RD regimen.
Fig. 4
Fig. 4 ML response models and their application to further refine treatment for the Group I and IV of the development cohort. a ROC–AUC of the ML response models predicting the early optimal response of the transplant-ineligible NDMM patients who received VMP or RD as the first-line treatment. b Distribution of the probabilities of early optimal response estimated by the ML response models. c Proportions of the EOR and ESR in Groups I and IV based on the conventional treatment selection. Each box plot displays the interquartile range (IQR), with the lower boundary representing the 25th percentile and the upper boundary representing the 75th percentile. The line within the box displays the median, and the whiskers extend to ±1.5 × IQR. d Predicted proportions of the EOR and ESR to VMP and RD based on the ML response models.
Fig. 5
Fig. 5 Schematic of the proposed methodology that assists treatment selection for the transplant-ineligible NDMM based on the application of ML survival and response models.

그림 출처: PubMed Central 공개 논문 (PMC10199943)

Conflict of interest statement

S.S.P. and J.C.L. are advisors for ImpriMed, Inc. J.K., S.L., and G.C. have a patent application about the methodology used to develop the ML models described in this study. S.S.P. has received honoraria for lectures and participation in advisory boards from Janssen Korea and Amgen Korea. D.D. has received honoraria for lectures and participation in advisory boards from Alexion, Apellis, Roche, Janssen, Novartis, and Sanofi, as well as research grants from K36 Pharmaceuticals. No disclosures were reported by the other authors not listed in this section.

그 밖의 정보
출판 형태
Journal Article
저널
NPJ precision oncology · ISSN 2397-768X
전자 출판
2023-05-20
연구비
National IT Industry Promotion Agency (National ICT Industry Promotion Agency) A1503211006 · National Research Foundation of Korea (NRF) NRF-2021H1D3A2A01098743 · Ministry of Health and Welfare (Ministry of Health, Welfare and Family Affairs) HA21C0013
참고문헌
45편