Diagnostic algorithm for lower-risk myelodysplastic syndromes

Mufti, Ghulam J.; McLornan, Donal; Loosdrecht, Arjan A. van de; Germing, Ulrich

doi:10.1038/s41375-018-0173-2

Cited by 13 publications

(11 citation statements)

References 124 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although BM aspiration and biopsy examinations are essential to definite diagnosis, quantitative estimation of peripheral blood polymorphs including dysplastic features of granulocytes has been reported as a simple and valuable diagnostic tool in MDS 22 . Dysmorphic WBCs such as hypogranular neutrophils or pseudo-Pelger-Huet cells found in the PB are suggestive to differentiate hMDS from AA 23,24 .…”

Section: Discussionmentioning

confidence: 99%

A novel automated image analysis system using deep convolutional neural networks can assist to differentiate MDS and AA

Kimura

Tabe

et al. 2019

Sci Rep

View full text Add to dashboard Cite

Detection of dysmorphic cells in peripheral blood (PB) smears is essential in diagnostic screening of hematological diseases. Myelodysplastic syndromes (MDS) are hematopoietic neoplasms characterized by dysplastic and ineffective hematopoiesis, which diagnosis is mainly based on morphological findings of PB and bone marrow. We developed an automated diagnostic support system of MDS by combining an automated blood cell image-recognition system using a deep learning system (DLS) powered by convolutional neural networks (CNNs) with a decision-making system using extreme gradient boosting (XGBoost). The DLS of blood cell image-recognition has been trained using datasets consisting of 695,030 blood cell images taken from 3,261 PB smears including hematopoietic malignancies. The DLS simultaneously classified 17 blood cell types and 97 morphological features of such cells with >93.5% sensitivity and >96.0% specificity. The automated MDS diagnostic system successfully differentiated MDS from aplastic anemia (AA) with high accuracy; 96.2% of sensitivity and 100% of specificity (AUC 0.990). This is the first CNN-based automated initial diagnostic system for MDS using PB smears, which is applicable to develop new automated diagnostic systems for various hematological disorders.

show abstract

Section: Discussionmentioning

confidence: 99%

A novel automated image analysis system using deep convolutional neural networks can assist to differentiate MDS and AA

Kimura

Tabe

et al. 2019

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Increasing the availability of screening methods for somatic mutations will increasingly produce situations where the distinction between MDS and pre-MDS conditions like ICUS or CCUS is difficult. The use of mutational analysis is certainly recommended by guidelines [ 9 ], especially in low-risk MDS, but it is unclear to what extent the guidelines are followed in daily clinical practice. Data published by our group demonstrate that only a decade ago, alarmingly few elderly MDS patients were diagnosed according to the guidelines in Germany, mainly because cytogenetic analysis was omitted [ 10 ].…”

Section: Guidelines: the Key To Quality Care In Mdsmentioning

confidence: 99%

Guidelines for Myelodysplastic Syndromes: Converting Evidence into Action?

Kasprzak

Kaivers

Nachtkamp

et al. 2021

IJERPH

Self Cite

View full text Add to dashboard Cite

The heterogeneous group of myelodysplastic syndromes (MDS) needs an individualized and patient-tailored therapeutic approach. Consensus-based guidelines for diagnosis and treatment provide a basis for clinical decision making. MDS guidelines are issued by expert panels. Our main objective was to examine how guidelines influence patients’ adherence to expert recommendations and how they ensure healthcare quality. To approach this question, we reviewed the most common guidelines for diagnosing and treating MDS in adult patients. Furthermore, we critically looked at quality indicators for everyday practice and studied adherence in an everyday outpatient setting. Finally, we also paid close attention to patient-reported outcome measures and studied how they are used as endpoints in clinical trials. We can conclude that the combination of evidence-based diagnostic tools, standardized treatment recommendations, and patient-centered shared decision making will eventually lead to a healthcare standard that will significantly improve outcomes in adult patients with MDS.

show abstract

“…Myelodysplastic Syndrome (MDS) is a cluster of tumorous diseases originating from hematopoietic stem cells. It characterizes aberrant bone marrow hematopoiesis, abnormal blood cell development, manifested as refractory blood cell reduction, hematopoietic failure, and high risk of transforming to acute myeloid leukemia, once referred to as pre-leukemia [1][2]. Previous epidemiological studies have shown that the incidence of MDS in the United States, Europe, and Asia ranges from less than 2 to more than 68 per 100,000 people [3][4][5].…”

Section: Introductionmentioning

confidence: 99%

"Comprehensive Identification of Hub Genes and Signaling Pathways for Myelodysplastic Syndrome by Bioinformatics Analysis"

Guo

2021

BJSTR

View full text Add to dashboard Cite

Purpose: Myelodysplastic syndrome (MDS) is a group of tumor diseases derived from hematopoietic stem cells. It has a tendency to progress to acute myeloid leukemia (AML), but the mechanism is not clear due to complicated pathogenesis. Based on the integrated analysis of gene microarray data sets, the present study established a gene expression model related to the pathogenesis of MDS, and screened target molecules which have an impact on disease progression. Methods:We downloaded three gene microarray data sets (including 397 MDS patients and 45 normal controls) from Gene Expression Omnibus (GEO) database (http:// www.ncbi.nlm.nih.gov/geo). Then differential expressed genes (DEGs) from each data set was screened and integrated for obtaining co-expression DEGs. Enrichment analysis, network construction were performed to elucidate core genes and pathways related to the pathogenesis of MDS. Moreover, the DEGs were used to validate in extra data sets and for further exploration on online Gene Expression Profiling Interactive Analysis (GEPIA) tool (http://gepia.cancer-pku.cn/).Results: In our study, 325 co-expression DEGs including 141 up-regulated and 184 down-regulated were identified. And we found that these DEGs are enriched in interferonrelated signaling pathways, which also involve participation in antiviral responses. In addition, up-regulated hub genes such as IFIT3 and ITITM have been validated in extra data sets and had an important impact on the prognosis of patients with AML. Conclusion:Our findings will improve our understanding of the cause and underlying molecular events in MDS and may provide new research directions for treatment strategies.

show abstract

Diagnostic algorithm for lower-risk myelodysplastic syndromes

Cited by 13 publications

References 124 publications

A novel automated image analysis system using deep convolutional neural networks can assist to differentiate MDS and AA

A novel automated image analysis system using deep convolutional neural networks can assist to differentiate MDS and AA

Guidelines for Myelodysplastic Syndromes: Converting Evidence into Action?

"Comprehensive Identification of Hub Genes and Signaling Pathways for Myelodysplastic Syndrome by Bioinformatics Analysis"

Contact Info

Product

Resources

About