EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Differential diagnosis of bone marrow failure syndromes guided by machine learning

Fernanda Gutierrez-Rodrigues iD, Eric Munger, Xiaoyang Ma, Emma M Groarke iD, Youbao Tang, Bhavisha A Patel, Luiz Fernando B Catto iD, Diego V Clé iD, Marena R Niewisch iD, Raquel M Alves-Paiva iD, Flávia S Donaires iD, André Luiz Pinto iD und 26 weitere

Blood · 2022

DOI: 10.1182/blood.2022017518 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Blood, 2022. Verfasst von Fernanda Gutierrez-Rodrigues und 37 weiteren Autor:innen. Beteiligte Einrichtung: Hematology Branch, National Heart, Lung, and Blood Institute (NHLBI), National Institutes of Health (NIH), Bethesda, MD. Hauptthemen laut MEDLINE: Bone Marrow Diseases, Anemia, Aplastic, Pancytopenia. Die Arbeit wurde bisher 16-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The choice to postpone treatment while awaiting genetic testing can result in significant delay in definitive therapies in severely pancytopenic patients. Conversely, inherited bone marrow failure (BMF) misdiagnosis 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 two-step data-driven machine-learning model using 25 clinical and laboratory variables typically recorded at the initial clinical encounter. For model's development, patients were labeled as having acquired or inherited BMF depending on their genomic data. Datasets were unbiasedly clustered and an ensemble model was trained with cases from the largest cluster of the 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 was composed of underrepresented BMF phenotypes, and not included in the next step of data modeling due to small sample size. The ensemble model Cluster A-specific 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Bone Marrow DiseasesAnemia, AplasticPancytopeniaHumansDiagnosis, DifferentialBone Marrow Failure Disorders

Autor:innen und Institutionen

  • Hematology Branch, National Heart, Lung, and Blood Institute (NHLBI), National Institutes of Health (NIH), Bethesda, MD.
  • Department of Bioinformatics and Computational Biology, George Mason University, Fairfax, VA.
  • Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, NIH Clinical Center, Bethesda, MD.
  • Department of Medical Imaging, Hematology, and Oncology, Ribeirão Preto Medical School, University of São Paulo, São Paulo, Brazil.
  • Division of Cancer Epidemiology and Genetics, Clinical Genetics Branch, National Cancer Institute (NCI), NIH, Bethesda, MD.
  • Hemotherapy and Cell Therapy Branch, Albert Einstein Hospital, São Paulo, Brazil.

ORCID-Profile: Fernanda Gutierrez-Rodrigues, Emma M Groarke, Luiz Fernando B Catto, Diego V Clé, Marena R Niewisch, Raquel M Alves-Paiva, Flávia S Donaires, André Luiz Pinto, Lisa J McReynolds, Neelam Giri, Burak Altintas, Sachiko Kajigaya, Ronald M Summers, Paul Liu, Dennis D Hickstein, Elvira D R P Velloso, Blanche P Alter, Sharon A Savage, Carmem Bonfim, Rodrigo T Calado

Zitieren

APA

Gutierrez-Rodrigues, F., Munger, E., Ma, X., Groarke, E. M., Tang, Y., Patel, B. A., Catto, L. F. B., Clé, D. V., Niewisch, M. R., Alves-Paiva, R. M., Donaires, F. S., Pinto, A. L., Borges, G., Santana, B. A., McReynolds, L. J., Giri, N., Altintas, B., Fan, X., Shalhoub, R., …, & Young, N. S. (2022). Differential diagnosis of bone marrow failure syndromes guided by machine learning. Blood. https://doi.org/10.1182/blood.2022017518

Vancouver

Gutierrez-Rodrigues F, Munger E, Ma X, Groarke EM, Tang Y, Patel BA, et al. Differential diagnosis of bone marrow failure syndromes guided by machine learning. Blood. 2022. doi:10.1182/blood.2022017518

BibTeX
@article{GutierrezRodrigues2022,
  author = {Gutierrez-Rodrigues, Fernanda and Munger, Eric and Ma, Xiaoyang and Groarke, Emma M and Tang, Youbao and Patel, Bhavisha A and Catto, Luiz Fernando B and Clé, Diego V and Niewisch, Marena R and Alves-Paiva, Raquel M and Donaires, Flávia S and Pinto, André Luiz and Borges, Gustavo and Santana, Barbara A and McReynolds, Lisa J and Giri, Neelam and Altintas, Burak and Fan, Xing and Shalhoub, Ruba and Siwy, Christopher M and Diamond, Carrie and Raffo, Diego Quinones and Craft, Kathleen and Kajigaya, Sachiko and Summers, Ronald M and Liu, Paul and Cunningham, Lea and Hickstein, Dennis D and Dunbar, Cynthia E and Pasquini, Ricardo and De Oliveira, Michel Michels and Velloso, Elvira D R P and Alter, Blanche P and Savage, Sharon A and Bonfim, Carmem and Wu, Colin O and Calado, Rodrigo T and Young, Neal S},
  title = {Differential diagnosis of bone marrow failure syndromes guided by machine learning},
  journal = {Blood},
  year = {2022},
  doi = {10.1182/blood.2022017518}
}
Kostenlos starten →