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

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.

Overfitting, Model Tuning, and Evaluation of Prediction Performance

The overfitting phenomenon happens when a statistical machine learning model learns very well about the noise as well as the signal that is present in the training data. On the other hand, an underfitted phenomenon occurs when only a few predictors are included in the statistical machine learning model that represents the complete structure of the data pattern poorly. This problem also arises when the training data set is too small and thus an underfitted model does a poor job of fitting the training data and unsatisfactorily predicts new data points. This chapter describes the importance of the trade-off between prediction accuracy and model interpretability, as well as the difference between explanatory and predictive modeling: Explanatory modeling minimizes bias, whereas predictive modeling seeks to minimize the combination of bias and estimation variance. We assess the importance and different methods of cross-validation as well as the importance and strategies of tuning that are key to the successful use of some statistical machine learning methods. We explain the most important metrics for evaluating the prediction performance for continuous, binary, categorical, and count response variables.

The Prediction of Essential Medicines Demand: A Machine Learning Approach Using Consumption Data in Rwanda

Today’s global business trends are causing a significant and complex data revolution in the healthcare industry, culminating in the use of artificial intelligence and predictive modeling to improve health outcomes and performance. The dataset, which was referred to is based on consumption data from 2015 to 2019, included approximately 500 goods. Based on a series of data pre-processing activities, the top ten (10) essential medicines most used were chosen, namely cotrimoxazole 480 mg, amoxicillin 250 mg, paracetamol 500 mg, oral rehydration salts (O.R.S) sachet 20.5 g, chlorpheniramine 4 mg, nevirapine 200 mg, aminophylline 100 mg, artemether 20 mg + lumefantrine (AL) 120 mg, Cromoglycate ophthalmic. Our study concentrated on the application of machine learning (ML) to forecast future trends in the demand for essential drugs in Rwanda. The following models were created and applied: linear regression, artificial neural network, and random forest. The random forest was able to predict 10 selected medicines with an accuracy of 88 percent with the train set and 76 percent with the test set, and it can thus be used to forecast future demand based on past consumption data by inputting a month, year, district, and medicine name. According to our findings, the random Forest model performed well as a forecasting model for the demand for essential medicines. Finally, data-driven predictive modeling with machine learning (ML) could become the cornerstone of health supply chain planning and operational management.