Machine learning algorithms for the detection of spurious white blood cell differentials due to erythrocyte lysis resistance

Bigorra, Laura; Larriba, Iciar; Gutiérrez-Gallego, Ricardo

doi:10.1136/jclinpath-2019-205820

Cited by 11 publications

(21 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…25 The ultimate goal of the lymphocytosis diagnosis approach is to classify the encounter as benign or neoplastic 2,3,5 ; moreover, we included the spurious category, as it was previously reported that erythrocyte-lysis resistance phenomenon may lead to spurious lymphocytosis when using the DxH 800 analyzer. 17 The model validation revealed global, weighted, validation accuracy for the different diagnostic categories, corresponding to 95.8%, and a 91.0% accuracy in the POC. An accuracy above 90% is remarkable in view of the difficult diagnostic problem achieving, or even outperforming, the human-level performance reported by the EQA schemes.…”

Section: Discussionmentioning

confidence: 94%

“…12 Machine learning (ML) is a tool that uses information from different sources, finding patterns from training data and allowing predictions to be made with classification purposes. 13,14 Building on prior experiences using ML and CPD to address lymphocytosis diagnosis in benign or neoplastic categories, 15,16 excluding spurious lymphocytosis, 17 The goal was to develop a CPD-based ML model as an aid to the lymphocytosis diagnosis approach and evaluate its feasibility, standardization, and benefit-cost ratio. Moreover, as it is expected that this ML model would be integrated into the general routine workflow, a proof of concept (POC) was also designed to evaluate its daily-basis performance.…”

mentioning

confidence: 99%

“…[10][11][12] These parameters have specific mean and standard deviation values for normal cells and any variation point to a particular pathology 12. Machine learning (ML) is a tool that uses information from different sources, finding patterns from training data and allowing predictions to be made with classification purposes.13,14 Building on prior experiences using ML and CPD to address lymphocytosis diagnosis in benign or neoplastic categories,15,16 excluding spurious lymphocytosis,17 the current work increases the diagnostic complexity by combining (1) 3 benign causes of lymphocytosis (viral infection [VI], persistent polyclonal B-cell lymphocytosis [PPBL], and postsplenectomy lymphocytosis), (2) 4 different types of neoplastic lymphocytosis (chronic lymphocytic leukemia [CLL], monoclonal B-cell lymphocytosis [MBL] CLL-like, and peripheral expression of follicular lymphoma [FL] and splenic marginal zone lymphoma [SMZL]), and (3) 2 spurious categories with lymphocytosis due to erythrocyte-lysis resistance (anemia and liver disease)-which…”

mentioning

confidence: 99%

See 2 more Smart Citations

A Physician-in-the-Loop Approach by Means of Machine Learning for the Diagnosis of Lymphocytosis in the Clinical Laboratory

Bigorra

Larriba²,

Gutiérrez-Gallego

2021

Archives of Pathology &Amp; Laboratory Medicine

Self Cite

View full text Add to dashboard Cite

Context.— The goal of the lymphocytosis diagnosis approach is its classification into benign or neoplastic categories. Nevertheless, a nonnegligible percentage of laboratories fail in that classification. Objective.— To design and develop a machine learning model by using objective data from the DxH 800 analyzer, including cell population data, leukocyte and absolute lymphoid counts, hemoglobin concentration, and platelet counts, besides age and sex, with classification purposes for lymphocytosis diagnosis. Design.— A total of 1565 samples were included from 10 different lymphoid categories grouped into 4 diagnostic categories: normal controls (458), benign causes of lymphocytosis (567), neoplastic lymphocytosis (399), and spurious causes of lymphocytosis (141). The data set was distributed in a 60-20-20 scheme for training, testing, and validation stages. Six machine learning models were built and compared, and the selection of the final model was based on the minimum generalization error and 10-fold cross validation accuracy. Results.— The selected neural network classifier rendered a global 10-class classification validation accuracy corresponding to 89.9%, which, considering the aforementioned 4 diagnostic categories, presented a diagnostic impact accuracy corresponding to 95.8%. Finally, a prospective proof of concept was performed with 100 new cases with a global diagnostic accuracy corresponding to 91%. Conclusions.— The proposed machine learning model was feasible, with a high benefit-cost ratio, as the results were obtained within the complete blood count with differential. Finally, the diagnostic impact with high accuracies in both model validation and proof of concept encourages exploration of the model for real-world application on a daily basis.

show abstract

Section: Discussionmentioning

confidence: 94%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

A Physician-in-the-Loop Approach by Means of Machine Learning for the Diagnosis of Lymphocytosis in the Clinical Laboratory

Bigorra

Larriba²,

Gutiérrez-Gallego

2021

Archives of Pathology &Amp; Laboratory Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…Blood was collected from mice by using a retro-orbital puncture. The numbers of Red blood cell (RBC), white blood cell (WBC), and Platelet (PLT) in the blood were detected and analyzed by an automatic cellular analyzers (DXH-800, Beckman Coulter) ( Bigorra et al., 2019 ).…”

Section: Methodsmentioning

confidence: 99%

Properties and Roles of γδT Cells in Plasmodium yoelii nigeriensis NSM Infected C57BL/6 Mice

Xie

Wang

et al. 2022

Front. Cell. Infect. Microbiol.

View full text Add to dashboard Cite

BackgroundMany kinds of immune cells are involved in malaria infection. γδT cells represent a special type of immune cell between natural and adaptive immune cells that play critical roles in anti-parasite infection.MethodsIn this study, malaria infection model was constructed. Distribution of γδT cells in various immune organs and dynamic changes of γδT cells in the spleens of C57BL/6 mice after infection were detected by flow cytometry. And activation status of γδT cells was detected by flow cytometry. Then γδT cells in naive and infected mice were sorted and performed single-cell RNA sequencing (scRNA-seq). Finally, γδTCR KO mice model was constructed and the effect of γδT cell depletion on mouse T and B cell immunity against Plasmodium infection was explored.ResultsHere, splenic γδT cells were found to increase significantly on day 14 after Plasmodium yoelii nigeriensis NSM infection in C57BL/6 mice. Higher level of CD69, ICOS and PD-1, lower level of CD62L, and decreased IFN-γ producing after stimulation by PMA and ionomycin were found in γδT cells from infected mice, compared with naive mice. Moreover, 11 clusters were identified in γδT cells by scRNA-seq based t-SNE analysis. Cluster 4, 5, and 7 in γδT cells from infected mice were found the expression of numerous genes involved in immune response. In the same time, the GO enrichment analysis revealed that the marker genes in the infection group were involved in innate and adaptive immunity, pathway enrichment analysis identified the marker genes in the infected group shared many key signalling molecules with other cells or against pathogen infection. Furthermore, increased parasitaemia, decreased numbers of RBC and PLT, and increased numbers of WBC were found in the peripheral blood from γδTCR KO mice. Finally, lower IFN-γ and CD69 expressing CD4+ and CD8+ T cells, lower B cell percentage and numbers, and less CD69 expressing B cells were found in the spleen from γδTCR KO infected mice, and lower levels of IgG and IgM antibodies in the serum were also observed than WT mice.ConclusionsOverall, this study demonstrates the diversity of γδT cells in the spleen of Plasmodium yoelii nigeriensis NSM infected C57BL/6 mice at both the protein and RNA levels, and suggests that the expansion of γδT cells in cluster 4, 5 and 7 could promote both cellular and humoral immune responses.

show abstract

“…Bigorra et al [ 34 ] investigated the use of ML to build a model that can use cell population data parameters to improve the detection of liver disease and anemia in samples with abnormal scattergrams. Multiple algorithms have been used, including random forests, naive Bayes classifiers, k -NN, neural networks, and SVM.…”

Section: And DL In the Diagnosis Of Hematological Diseasesmentioning

confidence: 99%

Machine Learning Applications in the Diagnosis of Benign and Malignant Hematological Diseases

Muhsen¹,

Shyr²,

Sung³

et al. 2020

CHI

View full text Add to dashboard Cite

The use of machine learning (ML) and deep learning (DL) methods in hematology includes diagnostic, prognostic, and therapeutic applications. This increase is due to the improved access to ML and DL tools and the expansion of medical data. The utilization of ML remains limited in clinical practice, with some disciplines further along in their adoption, such as radiology and histopathology. In this review, we discuss the current uses of ML in diagnosis in the field of hematology, including image-recognition, laboratory, and genomics-based diagnosis. Additionally, we provide an introduction to the fields of ML and DL, highlighting current trends, limitations, and possible areas of improvement.

show abstract

Machine learning algorithms for the detection of spurious white blood cell differentials due to erythrocyte lysis resistance

Cited by 11 publications

References 16 publications

A Physician-in-the-Loop Approach by Means of Machine Learning for the Diagnosis of Lymphocytosis in the Clinical Laboratory

A Physician-in-the-Loop Approach by Means of Machine Learning for the Diagnosis of Lymphocytosis in the Clinical Laboratory

Properties and Roles of γδT Cells in Plasmodium yoelii nigeriensis NSM Infected C57BL/6 Mice

Machine Learning Applications in the Diagnosis of Benign and Malignant Hematological Diseases

Contact Info

Product

Resources

About