Felipe Magalhães Furtado
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Felipe Magalhães Furtado has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Maura Rosane Valerio Ikoma‐Colturato
43Flow Cytometry Laboratory, Hospital Amaral Carvalho, Jaú São Paulo, Brazil
2 shared publications - Miriam Perlingeiro Beltrame
Hospital Erasto Gaertner – Curitiba (PR), Brazil
2 shared publications Adamara Felício
Escola Superior de Agricultura Luiz de Queiroz Universidade de São Paulo Piracicaba Brazil
1 shared publication- Adriano de Moraes Arantes
Hospital Israelita Albert Einstein – São Paulo (SP), Brazil
1 shared publication Alan Carvalho Dias
Sabin Diagnostico e Saude Brasilia Brazil
1 shared publication- Ana Paula de Azambuja
Hospital de Clínicas, Universidade Federal do Paraná, Curitiba 80060-900, Brazil
1 shared publication
Latest Publications
- Open Access
- 3 November 2026
- Published by Wiley in Cytometry Part B: Clinical Cytometry
Artificial intelligence‐based screening of paroxysmal nocturnal hemoglobinuria clones: Development and comparative evaluation of machine learning models
The diagnosis of paroxysmal nocturnal hemoglobinuria (PNH) relies on detecting cells deficient in GPI‐anchored proteins and is currently based on manual, time‐consuming interpretation requiring specialized expertise. This study aimed to develop machine learning models to identify PNH clones in granulocytes and monocytes using flow cytometry data containing information on cell size, complexity, and expression of FLAER, CD15, CD45, CD64, and CD157. For training, 20 normal and 20 PNH samples were randomly selected; normal samples were used in full, whereas only PNH cells were retained from PNH samples. For analytical validation, 22 normal and 18 PNH samples were analyzed in their entirety. Samples were processed through a preprocessing pipeline and split into training (12 normal, 12 PNH), validation (4 normal, 4 PNH), and test (4 normal, 4 PNH) datasets. Two supervised models were developed: a Random Forest (RF) and an Artificial Neural Network (ANN). Validation samples underwent the same preprocessing, except for concatenation. Both models achieved specificity close to 100%, accuracy >93%, ROC‐AUC >0.99, and PR‐AUC >0.98; the ANN showed higher sensitivity (0.85 vs. 0.78) and F1‐score (0.92 vs. 0.87). In qualitative analysis, RF and ANN achieved 100% and 45% agreement with manual analysis, respectively, and quantitative analysis confirmed statistical equivalence between RF and manual results. RF repeatability was confirmed by identical triplicate results in 10 samples. In spiking experiments, RF identified >50 PNH cells in all samples spiked with 200 or 100 cells, in 3 of 5 samples spiked with 50 cells, and in none spiked with 25 cells. These results indicate that the RF model shows promise for PNH analysis; however, clinical implementation will require integration into immunophenotyping software and post‐deployment performance monitoring.
- 3 November 2026
- Published by Wiley in Cytometry Part B: Clinical Cytometry
Open AccessArtificial intelligence‐based screening of paroxysmal nocturnal hemoglobinuria clones: Development and comparative evaluation of machine learning models
The diagnosis of paroxysmal nocturnal hemoglobinuria (PNH) relies on detecting cells deficient in GPI‐anchored proteins and is currently based on manual, time‐consuming interpretation requiring specialized expertise. This study aimed to develop machine learning models to identify PNH clones in granulocytes and monocytes using flow cytometry data containing information on cell size, complexity, and expression of FLAER, CD15, CD45, CD64, and CD157. For training, 20 normal and 20 PNH samples were randomly selected; normal samples were used in full, whereas only PNH cells were retained from PNH samples. For analytical validation, 22 normal and 18 PNH samples were analyzed in their entirety. Samples were processed through a preprocessing pipeline and split into training (12 normal, 12 PNH), validation (4 normal, 4 PNH), and test (4 normal, 4 PNH) datasets. Two supervised models were developed: a Random Forest (RF) and an Artificial Neural Network (ANN). Validation samples underwent the same preprocessing, except for concatenation. Both models achieved specificity close to 100%, accuracy >93%, ROC‐AUC >0.99, and PR‐AUC >0.98; the ANN showed higher sensitivity (0.85 vs. 0.78) and F1‐score (0.92 vs. 0.87). In qualitative analysis, RF and ANN achieved 100% and 45% agreement with manual analysis, respectively, and quantitative analysis confirmed statistical equivalence between RF and manual results. RF repeatability was confirmed by identical triplicate results in 10 samples. In spiking experiments, RF identified >50 PNH cells in all samples spiked with 200 or 100 cells, in 3 of 5 samples spiked with 50 cells, and in none spiked with 25 cells. These results indicate that the RF model shows promise for PNH analysis; however, clinical implementation will require integration into immunophenotyping software and post‐deployment performance monitoring.
- Open Access
- 8 January 2026
- Published by Journal of Bone Marrow Transplantation and Cellular Therapy in JOURNAL OF BONE MARROW TRANSPLANTATION AND CELLULAR THERAPY
- Vol. 7 (1)
Hematopoietic stem cell transplantation for acute myeloid leukemia: Brazilian Society of Cell Therapy and Bone Marrow Transplantation Consensus
This document updates the 2023 Brazilian Society of Cell Therapy and Bone Marrow Transplantation (SBTMO) consensus on allogeneic hematopoietic stem cell transplantation (HSCT) for acute myeloid leukemia (AML), incorporating the 2022 and 2024 European LeukemiaNet (ELN) risk classifications, the 2025 ELN-DAVID measurable residual disease (MRD) recommendations, recent induction trials, and the 2025 European Society for Blood and Marrow Transplantation (EBMT) transplant indications. MRD monitoring, assessed by quantitative polymerase chain reaaction, next-generation sequencing, or multiparameter flow cytometry, now guides transplant timing alongside ELN risk category, refining decisions in intermediate-risk patients and informing pre- and post-transplant management. Allogeneic HSCT remains indicated for adverse-risk AML and second complete remission regardless of MRD status, while favorable-risk patients generally avoid transplant unless MRD persists after consolidation. For elderly patients, chronological age alone should not exclude HSCT candidacy; comprehensive geriatric assessment and alternative donor sources have expanded access, supported by Brazilian regulatory changes raising the eligibility age to 75. Conditioning strategy, graft-versus-host disease prophylaxis with post-transplant cyclophosphamide, stem cell source selection, and donor immunogenetic screening are addressed, alongside emerging post-transplant maintenance therapies for high-risk molecular subgroups. Novel cellular therapies— CAR-T and CAR-NK cells—remain investigational, limited by antigen escape and short persistence, requiring consolidation with allogeneic HSCT. This consensus provides evidence-graded recommendations to standardize transplant decisionmaking for AML across Brazilian centers, reflecting the rapidly evolving therapeutic and diagnostic landscape.
- 8 January 2026
- Published by Journal of Bone Marrow Transplantation and Cellular Therapy in JOURNAL OF BONE MARROW TRANSPLANTATION AND CELLULAR THERAPY
- Vol. 7 (1)
Open AccessHematopoietic stem cell transplantation for acute myeloid leukemia: Brazilian Society of Cell Therapy and Bone Marrow Transplantation Consensus
This document updates the 2023 Brazilian Society of Cell Therapy and Bone Marrow Transplantation (SBTMO) consensus on allogeneic hematopoietic stem cell transplantation (HSCT) for acute myeloid leukemia (AML), incorporating the 2022 and 2024 European LeukemiaNet (ELN) risk classifications, the 2025 ELN-DAVID measurable residual disease (MRD) recommendations, recent induction trials, and the 2025 European Society for Blood and Marrow Transplantation (EBMT) transplant indications. MRD monitoring, assessed by quantitative polymerase chain reaaction, next-generation sequencing, or multiparameter flow cytometry, now guides transplant timing alongside ELN risk category, refining decisions in intermediate-risk patients and informing pre- and post-transplant management. Allogeneic HSCT remains indicated for adverse-risk AML and second complete remission regardless of MRD status, while favorable-risk patients generally avoid transplant unless MRD persists after consolidation. For elderly patients, chronological age alone should not exclude HSCT candidacy; comprehensive geriatric assessment and alternative donor sources have expanded access, supported by Brazilian regulatory changes raising the eligibility age to 75. Conditioning strategy, graft-versus-host disease prophylaxis with post-transplant cyclophosphamide, stem cell source selection, and donor immunogenetic screening are addressed, alongside emerging post-transplant maintenance therapies for high-risk molecular subgroups. Novel cellular therapies— CAR-T and CAR-NK cells—remain investigational, limited by antigen escape and short persistence, requiring consolidation with allogeneic HSCT. This consensus provides evidence-graded recommendations to standardize transplant decisionmaking for AML across Brazilian centers, reflecting the rapidly evolving therapeutic and diagnostic landscape.
- Open Access
- 21 November 2020
- Published by Elsevier in Hematology, Transfusion and Cell Therapy
- Vol. 43 (3) , 332-340
Minimal residual disease assessment in acute lymphoblastic leukemia by 4-color flow cytometry: Recommendations from the MRD Working Group of the Brazilian Society of Bone Marrow Transplantation
- 21 November 2020
- Published by Elsevier in Hematology, Transfusion and Cell Therapy
- Vol. 43 (3) , 332-340
Open AccessMinimal residual disease assessment in acute lymphoblastic leukemia by 4-color flow cytometry: Recommendations from the MRD Working Group of the Brazilian Society of Bone Marrow Transplantation