Artificial Intelligence based Models for Screening of Hematologic Malignancies using Cell Population Data

Abstract

Cell Population Data (CPD) provides various blood cell parameters that can be used for differential diagnosis. Data analytics using Machine Learning (ML) have been playing a pivotal role in revolutionizing medical diagnostics. This research presents a novel approach of using ML algorithms for screening hematologic malignancies using CPD. The data collection was done at Konkuk University Medical Center, Seoul. A total of (882 cases: 457 hematologic malignancy and 425 hematologic nonmalignancy) were used for analysis. In our study, seven machine learning models, i.e., SGD, SVM, RF, DT, Linear model, Logistic regression, and ANN, were used. In order to measure the performance of our ML models, stratified 10-fold cross validation was performed, and metrics, such as accuracy, precision, recall, and AUC were used. We observed outstanding performance by the ANN model as compared to other ML models. The diagnostic ability of ANN achieved the highest accuracy, precision, recall, and AUC ± Standard Deviation as follows: 82.8%, 82.8%, 84.9%, and 93.5% ± 2.6 respectively. ANN algorithm based on CPD appeared to be an efficient aid for clinical laboratory screening of hematologic malignancies. Our results encourage further work of applying ML to wider field of clinical practice.

Beyond the In-Practice CBC: The Research CBC Parameters-Driven Machine Learning Predictive Modeling for Early Differentiation among Leukemias

“…In another study by Virk et al, the clinical utility of the CPD parameters, scatter grams, and flags by generating statistical equations for screening of AML cases was published [ 34 ]. Here, an exception is found in studies conducted by Shabbir et al [ 35 ] and our work (Haider et al) [ 36 ], wherein ML tools were challenged for discernment between just two study groups (hematologic vs. non-hematologic malignancies and acute promyelocytic leukemia vs. other hematologic malignancies, respectively).…”

“…Here, an exception is found in studies conducted by Shabbir et al [35] and our work (Haider et al) [36], wherein ML tools were challenged for discernment between just two study groups (hematologic vs. non-hematologic malignancies and acute promyelocytic leukemia vs. other hematologic malignancies, respectively).…”

Artificial Intelligence in Surveillance, Diagnosis, Drug Discovery and Vaccine Development against COVID-19

“…Generally, routine blood exams data in numerical form such as Whole Blood Cells count, blood sugar level, Hemoglobin, etc., can be used as a feature set to build classification and regression models. Combining blood tests with advanced AI-based methods can significantly improve the sensitivity and accuracy of diagnosis [ 105 , 106 , 107 ]. In the recent past, several studies have been published which show the applicability of these techniques in predicting common diseases [ 107 , 108 ].…”

Assessing the risk of dengue severity using demographic information and laboratory test results with machine learning

“…Artificial intelligence has recently attracted much attention in various fields of health and medicine. Different artificial intelligence and machine learning (ML) methods have been applied for various purposes, including image recognition, patient phenotyping, and outcome prediction for diseases such as cancer [15][16][17][18][19], cardiac arrest [20], Alzheimer's disease [21][22][23], respiratory diseases [24,25], rheumatic diseases [26], cornea and retinal diseases [27,28], gastrointestinal diseases [29,30], and infectious diseases [31][32][33][34][35]. These studies revealed that artificial intelligence has the capacity to assist clinicians in the disease diagnosis with high efficiency and accuracy.…”