Artificial Intelligence with CBC based Morphometric Parameters aimed toward effective diagnostic practices for Dysplasia associated Hematological Malignancies
Zeeshan Haider, Ikram Uddin Ujjan, Dr Najeed Ahmed Khan, Muhammad Umer Farooq, Waseemullah Nazir, Eloísa Urrechaga, Rafiq Khanani · Research Square · 2022
Abstract 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.