Machine-learning based subgroups of AL amyloidosis and cumulative incidence of mortality and end stage kidney disease
Shankara K. Anand
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Department of Medicine, Stanford School of Medicine, Stanford, California, USA
Search for more papers by this authorAndrew Staron
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Hematology and Medical Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Search for more papers by this authorLisa M. Mendelson
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Hematology and Medical Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Search for more papers by this authorTracy Joshi
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Hematology and Medical Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Search for more papers by this authorNatasha Burke
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Hematology and Medical Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Search for more papers by this authorVaishali Sanchorawala
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Hematology and Medical Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Search for more papers by this authorCorresponding Author
Ashish Verma
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Nephrology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Correspondence
Ashish Verma, 650 Albany St. Office X521, Boston, MA 02118, USA.
Email: [email protected]
Search for more papers by this authorShankara K. Anand
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Department of Medicine, Stanford School of Medicine, Stanford, California, USA
Search for more papers by this authorAndrew Staron
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Hematology and Medical Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Search for more papers by this authorLisa M. Mendelson
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Hematology and Medical Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Search for more papers by this authorTracy Joshi
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Hematology and Medical Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Search for more papers by this authorNatasha Burke
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Hematology and Medical Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Search for more papers by this authorVaishali Sanchorawala
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Hematology and Medical Oncology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Search for more papers by this authorCorresponding Author
Ashish Verma
Amyloidosis Center, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Section of Nephrology, Department of Medicine, Boston University Chobanian & Avedisian School of Medicine and Boston Medical Center, Boston, Massachusetts, USA
Correspondence
Ashish Verma, 650 Albany St. Office X521, Boston, MA 02118, USA.
Email: [email protected]
Search for more papers by this authorAbstract
Immunoglobulin light chain (AL) amyloidosis is a multisystem disease with varied treatment options and disease-related outcomes. Current staging systems rely on a limited number of cardiac, renal, and plasma cell dyscrasia biomarkers. To improve prognostication for all-cause mortality and end-stage kidney disease (ESKD), we applied unsupervised machine learning using a comprehensive set of clinical and laboratory parameters. Our study cohort comprised 2067 patients with newly diagnosed, biopsy-proven AL amyloidosis from the Boston University Amyloidosis Center. Variables included 31 clinical symptoms and 28 baseline laboratory values. Our clustering algorithm identified three subgroups of AL amyloidosis (low-risk, intermediate-risk, and high-risk) with distinct clinical phenotypes and median overall survival (OS) estimates of 6.1, 3.7, and 1.2 years, respectively. The 10-year adjusted cumulative incidences of all-cause mortality were 66.8% (95% CI 63.4–70.1), 75.4% (95% CI 72.1–78.6), and 90.6% (95% CI 87.4–93.3) for low, intermediate, and high-risk subgroups. The 10-year adjusted cumulative incidences of end-stage kidney disease (ESKD) were 20.4% (95% CI 6.1–24.5), 37.6% (95% CI 31.8–43.8), and 6.7% (95% CI 2.8–11.3) for low-risk, intermediate-risk, and high-risk subgroups. Finally, we trained a classifier for external validation with high cross-validation accuracy (85% [95% CI 83–86]) using a subset of easily obtainable clinical parameters. This marks an initial stride toward integrating precision medicine into risk stratification of AL amyloidosis for both all-cause mortality and ESKD.
CONFLICT OF INTEREST STATEMENT
V.S. receives research support from Celgene, Millennium-Takeda, Janssen, Prothena, Sorrento, Karyopharm, Oncopeptide, Caelum, Alexion, is a consultant for Pfizer, Janssen, Attralus, GateBio, Abbvie, and is on the scientific advisory board of Proclara, Caelum, Abbvie, Janssen, Regeneron, Protego, Pharmatrace, Telix, Prothena, AstraZeneca, Nexcella. AV is supported by American Heart Association Career Development Award Number(24CDA1274501) and Department of Medicine Investment Award from Boston University Chobanian & Avedisian School of Medicine, Boston, MA.
Open Research
DATA AVAILABILITY STATEMENT
All analyses were performed using Python 3.11 and R 4.3. All code is publicly available for reproducibility at github.com/shankara-a/amyloidosis_bmc_2023.
Supporting Information
| Filename | Description |
|---|---|
| ajh27472-sup-0001-supinfo.docxWord 2007 document , 25.7 MB | Data S1. Supporting information. |
Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.
REFERENCES
- 1Merlini G, Dispenzieri A, Sanchorawala V, et al. Systemic immunoglobulin light chain amyloidosis. Nat Rev Dis Primers. 2018; 4(1): 38.
- 2Quock TP, Yan T, Chang E, Guthrie S, Broder MS. Epidemiology of AL amyloidosis: a real-world study using US claims data. Blood Adv. 2018; 2(10): 1046-1053.
- 3Buxbaum JN, Dispenzieri A, Eisenberg DS, et al. Amyloid nomenclature 2022: update, novel proteins, and recommendations by the International Society of Amyloidosis (ISA) nomenclature committee. Amyloid. 2022; 29(4): 213-219.
- 4Staron A, Zheng L, Doros G, et al. Marked progress in AL amyloidosis survival: a 40-year longitudinal natural history study. Blood Cancer J. 2021; 11(8): 139.
- 5Gustine JN, Staron A, Mendelson L, et al. Predictors of treatment response and survival outcomes in patients with advanced cardiac AL amyloidosis. Blood Adv. 2023; 7(20): 6080-6091.
- 6Gillmore JD, Wechalekar A, Bird J, et al. Guidelines on the diagnosis and investigation of AL amyloidosis. Br J Haematol. 2015; 168(2): 207-218.
- 7Fotiou D, Theodorakakou F, Kastritis E. Biomarkers in al amyloidosis. Int J Mol Sci. 2021; 22(20): 10916.
- 8Dispenzieri A, Kyle RA, Gertz MA, et al. Survival in patients with primary systemic amyloidosis and raised serum cardiac troponins. Lancet. 2003; 361(9371): 1787-1789.
- 9Ma KK, Ogawa T, de Bold AJ. Selective upregulation of cardiac brain natriuretic peptide at the transcriptional and translational levels by pro-inflammatory cytokines and by conditioned medium derived from mixed lymphocyte reactions via p38 MAP kinase. J Mol Cell Cardiol. 2004; 36(4): 505-513.
- 10Dispenzieri A, Gertz MA, Kyle RA, et al. Serum cardiac troponins and N-terminal pro-brain natriuretic peptide: a staging system for primary systemic amyloidosis. J Clin Oncol. 2004; 22(18): 3751-3757.
- 11Wechalekar AD, Schonland SO, Kastritis E, et al. A European collaborative study of treatment outcomes in 346 patients with cardiac stage III AL amyloidosis. Blood. 2013; 121(17): 3420-3427.
- 12Kumar S, Dispenzieri A, Lacy MQ, et al. Revised prognostic staging system for light chain amyloidosis incorporating cardiac biomarkers and serum free light chain measurements. J Clin Oncol. 2012; 30(9): 989-995.
- 13Lilleness B, Ruberg FL, Mussinelli R, Doros G, Sanchorawala V. Development and validation of a survival staging system incorporating BNP in patients with light chain amyloidosis. Blood. 2019; 133(3): 215-223.
- 14Cappelli F, Baldasseroni S, Bergesio F, et al. Echocardiographic and biohumoral characteristics in patients with AL and TTR amyloidosis at diagnosis. Clin Cardiol. 2015; 38(2): 69-75.
- 15Obici L, Perfetti V, Palladini G, Moratti R, Merlini G. Clinical aspects of systemic amyloid diseases. Biochim Biophys Acta. 2005; 1753(1): 11-22.
- 16Merlini G, Seldin DC, Gertz MA. Amyloidosis: pathogenesis and new therapeutic options. J Clin Oncol. 2011; 29(14): 1924-1933.
- 17Szalat R, Sarosiek S, Havasi A, Brauneis D, Sloan JM, Sanchorawala V. Organ responses after highdose melphalan and stemcell transplantation in AL amyloidosis. Leukemia. 2021; 35(3): 916-919.
- 18Angel-Korman A, Stern L, Sarosiek S, et al. Long-term outcome of kidney transplantation in AL amyloidosis. Kidney Int. 2019; 95(2): 405-411.
- 19Anand SK, Sanchorawala V, Verma A. Systemic amyloidosis and kidney transplantation: an update. Semin Nephrol. 2024; 44:151496.
- 20Leung N, Dispenzieri A, Fervenza FC, et al. Renal response after high-dose melphalan and stem cell transplantation is a favorable marker in patients with primary systemic amyloidosis. Am J Kidney Dis. 2005; 46(2): 270-277.
- 21Inney JH, Lachmann HJ, Bansi L. Outcome in renal Al amyloidosis after chemotherapy. J Clin Oncol. 2011; 29(6): 674-681.
- 22Leung N, Glavey SV, Kumar S, et al. A detailed evaluation of the current renal response criteria in AL amyloidosis: is it time for a revision? Haematologica. 2013; 98(6): 988-992.
- 23Palladini G, Hegenbart U, Milani P, et al. A staging system for renal outcome and early markers of renal response to chemotherapy in AL amyloidosis. J Am Soc Hematol. 2014; 124: 2325-2332.
- 24Havasi A, Stern L, Lo S, Sun F, Sanchorawala V. Validation of new renal staging system in AL amyloidosis treated with high dose melphalan and stem cell transplantation. Am J Hematol. 2016; 91(10): E458-E460.
- 25Shafqat A, Elmaleh H, Mushtaq A, et al. Renal AL amyloidosis: updates on diagnosis, staging, and management. J Clin Med. 2024; 13(6): 1744.
- 26Kastritis E, Gavriatopoulou M, Roussou M, et al. Renal outcomes in patients with AL amyloidosis: prognostic factors, renal response and the impact of therapy. Am J Hematol. 2017; 92(7): 632-639.
- 27Basset M, Milani P, Ferretti VV, et al. Prospective urinary albumin/creatinine ratio for diagnosis, staging, and organ response assessment in renal AL amyloidosis: results from a large cohort of patients. Clin Chem Lab Med. 2022; 60(3): 386-393.
- 28Kumar S, Dispenzieri A, Lacy MQ, et al. Serum uric acid: novel prognostic factor in primary systemic amyloidosis. Mayo Clin Proc. 2008; 83(3): 297-303.
- 29Muchtar E, Dispenzieri A, Lacy MQ, et al. Elevation of serum lactate dehydrogenase in AL amyloidosis reflects tissue damage and is an adverse prognostic marker in patients not eligible for stem cell transplantation. Br J Haematol. 2017; 178(6): 888-895.
- 30Dashtban A, Mizani MA, Pasea L, et al. Identifying subtypes of chronic kidney disease with machine learning: development, internal validation and prognostic validation using linked electronic health records in 350,067 individuals. EBioMedicine. 2023; 89:104489.
- 31Williams WW, Hogan JW, Ingelfinger JR. Time to eliminate health care disparities in the estimation of kidney function. N Engl J Med. 2021; 385(19): 1804-1806.
- 32van Buuren S, Groothuis-Oudshoorn K. Mice: multivariate imputation by chained equations in R. J Stat Softw. 2011; 45: 1-67.
- 33Monti S, Tamayo P, Mesirov J, Golub T. Consensus clustering: a resampling-based method for class discovery and visualization of gene expression microarray data. Mach Learn. 2003; 52(1): 91-118.
- 34Wilkerson MD, Hayes DN. ConsensusClusterPlus: a class discovery tool with confidence assessments and item tracking. Bioinformatics. 2010; 26(12): 1572-1573.
- 35Rand WM. Objective criteria for the evaluation of clustering methods. J Am Stat Assoc. 1971; 66(336): 846-850.
- 36Benjamini Y, Hochberg Y. Controlling the false discovery rate: a practical and powerful approach to multiple testing. J R Stat Soc. 1995; 57(1): 289-300.
10.1111/j.2517-6161.1995.tb02031.x Google Scholar
- 37Denz R, Klaaßen-Mielke R, Timmesfeld N. A comparison of different methods to adjust survival curves for confounders. Stat Med. 2023; 42(10): 1461-1479.
- 38Bergstra J, Yamins D, Cox D. Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures. Proceedings of the 30th International Conference on Machine Learning. Vol 28. PMLR; 2013: 115-123.
- 39Cohen J. A coefficient of agreement for nominal scales. Educ Psychol Meas. 1960; 20(1): 37-46.
- 40Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Adv Neural Inf Proces Syst. 2017; 4765-4774.
- 41Khwaja J, Ravichandran S, Bomsztyk J, et al. Limited utility of Mayo 2012 cardiac staging system for risk stratification of patients with advanced cardiac AL amyloidosis—analysis of a uniformly treated cohort of 1275 patients. Blood. 2023; 142(Supplement 1): 537.
10.1182/blood-2023-178243 Google Scholar
- 42Palladini G, Kastritis E, Maurer MS, et al. Daratumumab plus CyBorD for patients with newly diagnosed AL amyloidosis: safety run-in results of ANDROMEDA. Blood. 2020; 136(1): 71-80.
- 43Kastritis E, Palladini G, Minnema MC, et al. Daratumumab-based treatment for immunoglobulin light-chain amyloidosis. N Engl J Med. 2021; 385(1): 46-58.
- 44Wechalekar AD, Cibeira MT, Gibbs SD, et al. Guidelines for non-transplant chemotherapy for treatment of systemic AL amyloidosis: EHA-ISA working group. Amyloid. 2023; 30(1): 3-17.
Citing Literature
