A targeted and timely treatment can be a beneficial tool for patients with hematological emergencies (particularly acute leukemias). The key challenges in the early diagnosis of leukemias and related hematological disorders are their symptom-sharing nature and prolonged turnaround time as well as the expertise needed in reporting confirmatory tests. The present study made use of the potential morphological and immature fraction-related parameters (research items or cell population data) generated during complete blood cell count (CBC), through artificial intelligence (AI)/machine learning (ML) predictive modeling for early (at the pre-microscopic level) differentiation of various types of leukemias: acute from chronic as well as myeloid from lymphoid. The routine CBC parameters along with research CBC items from a hematology analyzer in the diagnosis of 1577 study subjects with hematological neoplasms were collected. The statistical and data visualization tools, including heat-map and principal component analysis (PCA,) helped in the evaluation of the predictive capacity of research CBC items. Next, research CBC parameter-driven artificial neural network (ANN) predictive modeling was developed to use the hidden trend (disease’s signature) by increasing the auguring accuracy of these potential morphometric parameters in differentiation of leukemias. The classical statistics for routine and research CBC parameters showed that as a whole, all study items are significantly deviated among various types of leukemias (study groups). The CPD parameter-driven heat-map gave clustering (separation) of myeloid from lymphoid leukemias, followed by the segregation (nodding) of the acute from the chronic class of that particular lineage. Furthermore, acute promyelocytic leukemia (APML) was also well individuated from other types of acute myeloid leukemia (AML). The PCA plot guided by research CBC items at notable variance vindicated the aforementioned findings of the CPD-driven heat-map. Through training of ANN predictive modeling, the CPD parameters successfully differentiate the chronic myeloid leukemia (CML), AML, APML, acute lymphoid leukemia (ALL), chronic lymphoid leukemia (CLL), and other related hematological neoplasms with AUC values of 0.937, 0.905, 0.805, 0.829, 0.870, and 0.789, respectively, at an agreeably significant (10.6%) false prediction rate. Overall practical results of using our ANN model were found quite satisfactory with values of 83.1% and 89.4.7% for training and testing datasets, respectively. We proposed that research CBC parameters could potentially be used for early differentiation of leukemias in the hematology–oncology unit. The CPD-driven ANN modeling is a novel practice that substantially strengthens the predictive potential of CPD items, allowing the clinicians to be confident about the typical trend of the “disease fingerprint” shown by these automated potential morphometric items.
A targeted and timely offered treatment can be a benefitting tool for patients with acute promyelocytic leukemia (APML). Current round of study made use of potential morphological and immature fraction-related parameters (cell population data) generated during complete blood cell count (CBC), through artificial neural network (ANN) predictive modeling for early flagging of APML cases. We collected classical CBC items along with cell population data (CPD) from hematology analyzer at diagnosis of 1067 study subjects with hematological neoplasms. For morphological assessment, peripheral blood films were examined. Statistical and machine learning tools including principal component analysis (PCA) helped in the evaluation of predictive capacity of routine and CPD items. Then selected CBC item-driven ANN predictive modeling was developed to smartly use the hidden trend by increasing the auguring accuracy of these parameters in differentiation of APML cases. We found a characteristic triad based on lower (53.73) platelet count (PLT) with decreased/normal (4.72) immature fraction of platelet (IPF) with addition of significantly higher value (65.5) of DNA/RNA content-related neutrophil (NE-SFL) parameter in patients with APML against other hematological neoplasm's groups. On PCA, APML showed exceptionally significant variance for PLT, IPF, and NE-SFL. Through training of ANN predictive modeling, our selected CBC items successfully classify the APML group from non-APML groups at highly significant (0.894) AUC value with lower (2.3 percent) false prediction rate. Practical results of using our ANN model were found acceptable with value of 95.7% and 97.7% for training and testing data sets, respectively. We proposed that PLT, IPF, and NE-SFL could potentially be used for early flagging of APML cases in the hematology-oncology unit. CBC item-driven ANN modeling is a novel approach that substantially strengthen the predictive potential of CBC items, allowing the clinicians to be confident by the typical trend raised by these studied parameters.
1 January 2020 in Revista de Investigación Clínica
The hematology analyzer, Sysmex XN-1000, generates white blood cell count with varying scattering intensities during a complete blood count (CBC) analysis. The objectives of the study were to study the predictive role of median and coefficient of variation of neutrophil scattering items in blood samples for differentiation of leukemic subjects. We evaluated six neutrophil scattering parameters: neutrophil side scatter mean intensity, neutrophil side fluorescence light (SFL) mean intensity, neutrophil forward scatter mean intensity, neutrophil side scatter area distribution width (NE-WX), neutrophil SFL area distribution width (NE-WY), and neutrophil forward scatter area distribution width (NE-WZ), measured in white blood cell differential scattergram generated by the hematology analyzer (Sysmex XN-1000) at an academic medical center. We collected 433 blood samples from acute myeloid leukemia (AML) and acute lymphoid leukemia (ALL) cases and normal controls. AML group showed highly significant differences in the mean values compared with the control group. Out of six neutrophil scattering items, NE-WX, NE-WY, and NE-WZ showed high efficiency, with area under the curve (AUC) values of 0.764, 0.748, and 0.757, respectively, to differentiate AML from ALL cases and control groups. When comparing combined acute leukemia cases (AML plus ALL) with the control group, NE-WX, NE-WY, and NE-WZ generated highly significant AUC values (0.840, 0.884, and 0.801, respectively). The neutrophil scattering parameters generated during CBC analysis provide a new tool for the prediction of acute leukemia and its lineage.
Leucocytes, especially neutrophils featuring pro- and anti-cancerous characteristics, are involved in nearly every stage of tumorigenesis. Phenotypic and functional differences among mature and immature neutrophil fractions are well reported, and their correlation with tumor progression and therapy has emerging implications in modern oncology practices. Technological advancements enabled modern hematology analyzers to generate extended information (research parameters) during complete blood cell count (CBC) analysis. We hypothesized that neutrophil and lymphocyte fractions-related extended differential leucocytes count (DLC) parameters hold superior diagnostic utility over routine modalities. The present study was carried out over a four-and-a-half-year period wherein extended neutrophil (immature granulocyte [IG] and mature neutrophil [NEUT#&]), and lymphocyte (activated/high fluorescence lymphocyte count [HFLC] and resting lymphocyte [LYMP#&]) parameters were challenged over routine neutrophil [NEUT#] and lymphocyte [LYMP#] items in a study population of 1067 hematological neoplasm patients. Extending the classical statistical approaches, machine-learning-backed data visualization was used to explore trends in the study parameters. As a whole, extended neutrophil and lymphocyte count outperformed and was diagnostically more relevant than routine neutrophil and lymphocyte parameters by showing the least difference from their respective (gold-standard) manual DLC counts. The mature neutrophil count was compared to IG, and resting lymphocyte count was compared to HFLC by calling the function ‘correlation’ as a ‘clustering function’ for heatmap based visualization. The aforementioned study parameters displayed close clustering (rearrangement) for their respective study items by presenting distinct trends of equally valuable weights (deviated values), advocating fractions-based extended DLC reporting. Importantly, using a Bland and Altman analysis analogously to a manual neutrophil count, the mature neutrophil count [NEUT#&] remained unbiased since a routine neutrophil count [NEUT#] was found to be a negatively biased. The extended DLC-parameter-driven fractions-based reporting has superior diagnostic utility over classical routine approaches; this finding can largely minimize labor-intensive manual DLC practices, especially in hematology–oncology departments.
1 February 2021 in International Journal of Laboratory Hematology
Background: The diagnosis and classification of dysplasia associated hematological neoplasms is dominated by morphology. Current round of study made use of potential ‘fingerprints’ among routinely generated diagnostic data particularly morphological and immature fraction-related (morphometric) parameters produced during routine complete blood count (CBC) testing in hemat-oncology department through artificial intelligence predictive modeling.Methods: Along conventional statistics, neural network models were trained on anonymized demographical, clinical and diagnostic data of total 1624 individuals with common hematological neoplasms. In addition, validation conducted on independent dataset. The frameworks were trained to differentiate hematological malignancies cases with various sub-entities of Dysplasia against Non-dysplastic group as a control cohort.Results: Our predictive model attained greater precisions; percent incorrect prediction were remained 10.3 and 4.6 for training and testing phases, respectively along with a 95.4% negative predictive value (NPV). Moreover, higher accuracy (93.1%) was obtained during prospective validation in challenge of independent dataset. Model’s performance related metrics: the gain and lift chart, predictive-pseudo probability chart, and receiver operative curve (ROC) curve were noted as persuasive. Considering the sensitivity and specificity, area under the curve (AUC) values were also noted quite convincing; 0.954 for Non-dysplasia group while 0.994 for acute myeloid leukemia with dysplasia (AML-Dys) followed by 0.992, 0.988, 0.986, 0.984, 0.973, and 0.962 for chronic myelo-monocytic leukemia (CMML), refractory anemia with excess blast-I (RAEB-I), refractory anemia with excess blast-II (RAEB-II), refractory anemia with multi-lineage dysplasia (RCMD), Hypoplastic myelodysplastic syndrome (H-MDS), and refractory anemia with uni-lineage dysplasia (RCUD) respectively.Conclusion: The negative predictive efficiency of our framework advocates its utility as a screening tool for the rapid expulsion of Dysplasia associated hematological neoplasms in hemat-oncology sections, aiding prompt care decisions.