Nuances of Morphology in Myelodysplastic Diseases in the Age of Molecular Diagnostics

Single-cell data combined with phenotypes improves variant interpretation

BACKGROUND

Whole genome sequencing offers significant potential to improve the diagnosis and treatment of rare diseases by enabling the identification of thousands of rare, potentially pathogenic variants. Existing variant prioritisation tools can be complemented by approaches that incorporate phenotype specificity and provide contextual biological information, such as tissue or cell-type specificity. We hypothesised that integrating single-cell gene expression data into phenotype-specific models would improve the accuracy and interpretability of pathogenic variant prioritisation.

METHODS

To test this hypothesis, we developed IMPPROVE, a new tool that constructs phenotype-specific ensemble models integrating CADD scores with bulk and single-cell gene expression data. We constructed a total of 1,866 Random Forest models for individual HPO terms, incorporating both bulk and single cell expression data.

RESULTS

Our phenotype-specific models utilising expression data can better predict pathogenic variants in 90% of the phenotypes (HPO terms) considered. Using single-cell expression data instead of bulk benefited the models, significantly shifting the proportion of pathogenic variants that were correctly identified at a fixed false positive rate ( p < 10 - 30 , using an approximate Wilcoxon signed rank test). We found 57 phenotypes' models exhibited a large performance difference, depending on the dataset used. Further analysis revealed biological links between the pathology and the tissues or cell-types used by these 57 models.

CONCLUSIONS

Phenotype-specific models that integrate gene expression data with CADD scores show great promise in improving variant prioritisation. In addition to improving diagnostic accuracy, these models offer insights into the underlying biological mechanisms of rare diseases. Enriching existing pathogenicity-related scores with gene expression datasets has the potential to advance personalised medicine through more accurate and interpretable variant prioritisation.

Application of Pathomic Features for Differentiating Dysplastic Cells in Patients with Myelodysplastic Syndrome

Myelodysplastic syndromes (MDSs) are a group of hematologic neoplasms accompanied by dysplasia of bone marrow (BM) hematopoietic cells with cytopenia. Recently, digitalized pathology and pathomics using computerized feature analysis have been actively researched for classifying and predicting prognosis in various tumors of hematopoietic tissues. This study analyzed the pathomic features of hematopoietic cells in BM aspiration smears of patients with MDS according to each hematopoietic cell lineage and dysplasia. We included 24 patients with an MDS and 21 with normal BM. The 12,360 hematopoietic cells utilized were to be classified into seven types: normal erythrocytes, normal granulocytes, normal megakaryocytes, dysplastic erythrocytes, dysplastic granulocytes, dysplastic megakaryocytes, and others. Four hundred seventy-six pathomic features quantifying cell intensity, shape, and texture were extracted from each segmented cell. After comparing the combination of feature selection and machine learning classifier methods using 5-fold cross-validation area under the receiver operating characteristic curve (AUROC), the quadratic discriminant analysis (QDA) with gradient boosting decision tree (AUROC = 0.63) and QDA with eXtreme gradient boosting (XGB) (AUROC = 0.64) showed a high AUROC combination. Through a feature selection process, 30 characteristics were further analyzed. Dysplastic erythrocytes and granulocytes showed lower median values on heatmap analysis compared to that of normal erythrocytes and granulocytes. The data suggest that pathomic features could be applied to cell differentiation in hematologic malignancies. It could be used as a new biomarker with an auxiliary role for more accurate diagnosis. Further studies including prediction survival and prognosis with larger cohort of patients are needed.

Patterns of Diagnostic Evaluation and Determinants of Treatment in Older Patients With Non-transfusion Dependent Myelodysplastic Syndromes

BACKGROUND

Older patients with myelodysplastic syndromes (MDS), particularly those with no or one cytopenia and no transfusion dependence, typically have an indolent course. Approximately, half of these receive the recommended diagnostic evaluation (DE) for MDS. We explored factors determining DE in these patients and its impact on subsequent treatment and outcomes.

PATIENTS AND METHODS

We used 2011-2014 Medicare data to identify patients ≥66 years of age diagnosed with MDS. We used Classification and Regression Tree (CART) analysis to identify combinations of factors associated with DE and its impact on subsequent treatment. Variables examined included demographics, comorbidities, nursing home status, and investigative procedures performed. We conducted a logistic regression analysis to identify correlates associated with receipt of DE and treatment.

RESULTS

Of 16 851 patients with MDS, 51% underwent DE. patients with MDS with no cytopenia (n = 3908) had the lowest uptake of DE (34.7%). Compared to patients with no cytopenia, those with any cytopenia had nearly 3 times higher odds of receiving DE [adjusted odds ratio (AOR), 2.81: 95% CI, 2.60-3.04] and the odds were higher for men than for women [AOR, 1.39: 95%CI, 1.30-1.48] and for Non-Hispanic Whites [vs. everyone else (AOR, 1.17: 95% CI, 1.06-1.29)]. The CART showed DE as the principal discriminating node, followed by the presence of any cytopenia for receiving MDS treatment. The lowest percentage of treatment was observed in patients without DE, at 14.6%.

CONCLUSION

In this select older patients with MDS, we identified disparities in accurate diagnosis by demographic and clinical factors. Receipt of DE influenced subsequent treatment but not survival.

A geno-clinical decision model for the diagnosis of myelodysplastic syndromes

We developed a machine learning–based model to assist in the differential diagnosis of myeloid malignancies.

Our work also describes genotype-phenotype correlations in different myeloid malignancies.

The differential diagnosis of myeloid malignancies is challenging and subject to interobserver variability. We used clinical and next-generation sequencing (NGS) data to develop a machine learning model for the diagnosis of myeloid malignancies independent of bone marrow biopsy data based on a 3-institution, international cohort of patients. The model achieves high performance, with model interpretations indicating that it relies on factors similar to those used by clinicians. In addition, we describe associations between NGS findings and clinically important phenotypes and introduce the use of machine learning algorithms to elucidate clinicogenomic relationships.

Inter-observer variance and the need for standardization in the morphological classification of myelodysplastic syndrome

In this era of genome medicine, the sub-classification of myeloid neoplasms, including myelodysplastic syndrome (MDS), is now supported by genetic testing in selected cases. However, as the initial suspicion and primary diagnosis of the disease still largely relies on morphological features and numbers of hematopoietic cells, the establishment of a uniform diagnostic basis, especially for cell morphology, is essential. In this study, we collected nearly 100,000 hematopoietic cell images from 499 peripheral blood smear specimens from patients with MDS and used these to evaluate the standardization of morphological classification by medical technologists. The observers in this study ranged between two to eleven for each image, and the images were classified according to MDS criteria through a web-based system. We found considerable inter-observer variance in the assessment of dysplastic features. Observers did not recognize cytoplasmic hypo-granularity unless almost all granules in neutrophils were absent. Pseudo Pelger-Huët anomalies were also often overlooked, except for cells with a very typical "pince-nez" appearance. Taken together, this study suggests a requirement for further standardization in terms of morphological cell classification, and a need for the development of automatic cell classification-supporting devices for the accurate diagnosis of MDS.