Differential diagnosis of bone marrow failure syndromes guided by machine learning

Nenhuma Miniatura disponível
Citações na Scopus
9
Tipo de produção
article
Data de publicação
2023
DOI
Scopus
Web of Science
PubMed
Título da Revista
ISSN da Revista
Título do Volume
Editora
AMER SOC HEMATOLOGY
Autores
GUTIERREZ-RODRIGUES, Fernanda
MUNGER, Eric
MA, Xiaoyang
GROARKE, Emma M.
TANG, Youbao
PATEL, Bhavisha A.
CATTO, Luiz Fernando B.
CLE, Diego V.
NIEWISCH, Marena R.
ALVES-PAIVA, Raquel M.
Citação
BLOOD, v.141, n.17, p.2100-2113, 2023
Projetos de Pesquisa
Unidades Organizacionais
Fascículo
Resumo
The choice to postpone treatment while awaiting genetic testing can result in significant delay in definitive therapies in patients with severe pancytopenia. Conversely, the misdiagnosis of inherited bone marrow failure (BMF) can expose patients to ineffectual and expensive therapies, toxic transplant conditioning regimens, and inappropriate use of an affected family member as a stem cell donor. To predict the likelihood of patients having acquired or inherited BMF, we developed a 2-step data-driven machine-learning model using 25 clinical and laboratory variables typically recorded at the initial clinical encounter. For model development, patients were labeled as having acquired or inherited BMF depending on their genomic data. Data sets were unbiasedly clustered, and an ensemble model was trained with cases from the largest cluster of a training cohort (n = 359) and validated with an independent cohort (n = 127). Cluster A, the largest group, was mostly immune or inherited aplastic anemia, whereas cluster B comprised underrepresented BMF phenotypes and was not included in the next step of data modeling because of a small sample size. The ensemble cluster A-specific model was accurate (89%) to predict BMF etiology, correctly predicting inherited and likely immune BMF in 79% and 92% of cases, respectively. Our model represents a practical guide for BMF diagnosis and highlights the importance of clinical and laboratory variables in the initial evaluation, particularly telomere length. Our tool can be potentially used by general hematologists and health care providers not specialized in BMF, and in under-resourced centers, to prioritize patients for genetic testing or for expeditious treatment.
Palavras-chave
URI
https://observatorio.fm.usp.br/handle/OPI/53810
Referências
  1. Abelson S, 2018, NATURE, V559, P400, DOI 10.1038/s41586-018-0317-6
  2. Bluteau O, 2018, BLOOD, V131, P717, DOI 10.1182/blood-2017-09-806489
  3. Calado RT, 2009, NEW ENGL J MED, V361, P2353, DOI 10.1056/NEJMra0903373
  4. Calinski T., 1974, COMMUN STAT, V3, P1, DOI 10.1080/03610927408827101
  5. DeZern AE, 2014, EUR J HAEMATOL, V92, P467, DOI 10.1111/ejh.12299
  6. Ghemlas I, 2015, J MED GENET, V52, P575, DOI 10.1136/jmedgenet-2015-103270
  7. Grinfeld J, 2018, NEW ENGL J MED, V379, P1416, DOI 10.1056/NEJMoa1716614
  8. Guncar G, 2018, SCI REP-UK, V8, DOI 10.1038/s41598-017-18564-8
  9. Gutierrez-Rodrigues F, 2014, PLOS ONE, V9, DOI 10.1371/journal.pone.0113747
  10. Hastie T., 2001, SPRINGER SERIES STAT
  11. Libbrecht MW, 2015, NAT REV GENET, V16, P321, DOI 10.1038/nrg3920
  12. Munger E, 2020, J AM ACAD DERMATOL, V83, P1647, DOI 10.1016/j.jaad.2019.10.060
  13. Nagata Y, 2020, BLOOD, V136, P2249, DOI 10.1182/blood.2020005488
  14. Nykamp K, 2017, GENET MED, V19, P1105, DOI 10.1038/gim.2017.37
  15. Radakovich N, 2020, LANCET HAEMATOL, V7, pE541, DOI 10.1016/S2352-3026(20)30121-6
  16. Rajkomar A, 2019, NEW ENGL J MED, V380, P1347, DOI 10.1056/NEJMra1814259
  17. Rajkomar A, 2018, NPJ DIGIT MED, V1, DOI 10.1038/s41746-018-0029-1
  18. Richards S, 2015, GENET MED, V17, P405, DOI 10.1038/gim.2015.30
  19. Robnik-Sikonja M, 2003, MACH LEARN, V53, P23, DOI 10.1023/A:1025667309714
  20. Sachdev V, 2021, BRIT J HAEMATOL, V192, P932, DOI 10.1111/bjh.17342
  21. Shah YB, 2021, BLOOD ADV, V5, P3216, DOI 10.1182/bloodadvances.2021004201
  22. Shouval R, 2021, BRIT J HAEMATOL, V192, P239, DOI 10.1111/bjh.16915
  23. Townsley DM, 2017, NEW ENGL J MED, V376, P1540, DOI 10.1056/NEJMoa1613878
  24. Townsley DM, 2014, BLOOD, V124, P2775, DOI 10.1182/blood-2014-05-526285
  25. van der Ploeg T, 2014, BMC MED RES METHODOL, V14, DOI 10.1186/1471-2288-14-137
  26. Vulliamy TJ, 2011, PLOS ONE, V6, DOI 10.1371/journal.pone.0024383
  27. Wegman-Ostrosky T, 2017, BRIT J HAEMATOL, V177, P526, DOI 10.1111/bjh.14535
  28. Young NS, 2018, NEW ENGL J MED, V379, P1643, DOI 10.1056/NEJMra1413485
  29. Zhang MY, 2015, HAEMATOLOGICA, V100, P42, DOI 10.3324/haematol.2014.113456

Coleções
Artigos e Materiais de Revistas Científicas - FM/MCM
Artigos e Materiais de Revistas Científicas - LIM/31