Survival Prediction of Children Undergoing Hematopoietic Stem Cell Transplantation Using Different Machine Learning Classifiers by Performing Chi-Square Test and Hyperparameter Optimization: A Retrospective Analysis

Abstract

Bone marrow transplant (BMT) is an effective surgical treatment for bone marrow-related disorders. However, several associated risk factors can impair long-term survival after BMT. Machine learning (ML) technologies have been proven useful in survival prediction of BMT receivers along with the influences that limit their resilience. In this study, an efficient classification model predicting the survival of children undergoing BMT is presented using a public dataset. Several supervised ML methods were investigated in this regard with an 80-20 train-test split ratio. To ensure prediction with minimal time and resources, only the top 11 out of the 59 dataset features were considered using Chi-square feature selection method. Furthermore, hyperparameter optimization (HPO) using the grid search cross-validation (GSCV) technique was adopted to increase the accuracy of prediction. Four experiments were conducted utilizing a combination of default and optimized hyperparameters on the original and reduced datasets. Our investigation revealed that the top 11 features of HPO had the same prediction accuracy (94.73%) as the entire dataset with default parameters, however, requiring minimal time and resources. Hence, the proposed approach may aid in the development of a computer-aided diagnostic system with satisfactory accuracy and minimal computation time by utilizing medical data records.

A Machine Learning based Investigative analysis for predicting critical temperature of superconductors

“…Machine learning has been a crucial aspect in numerous significant domains for researchers [45][46][47][48][49][50][51][52][53][54][55][56][57][58][59][60][61][62][63][64]. In recent years, there has been a surge of interest in using machine learning algorithms to predict the critical temperature of superconductors.…”

Analyzing Perceived Psychological and Social Stress of University Students: A Machine Learning Approach

“…However, most studies did not utilize ML and data mining techniques. These techniques are being applied in numerous research studies to construct automated healthcare assistance systems that help experts forecast and prescribe solutions early [ [21] , [22] , [23] , [24] , [25] ]. Some earlier studies presented stress prediction techniques based on machine learning and data mining techniques for various target users [ [26] , [27] , [28] ].…”

Implementation of Bio-inspired Algorithms in Designing Optimized PID controller for Cuk Converter for Enhanced Performance: A Software based Approach

“…An ample amount of literature exists on the successful executions of the Bio-Inspired Algorithms in the field of power converters professed by many researchers [11][12][13][14][15][16][17][18][19][20]. One of such promising instances of work has been witnessed with Machine learning (ML) algorithms [21][22][23][24][25][26][27][28][29], artificial intelligence [30][31][32][33][34][35][36][37][38][39], and different applications of ML in healthcare sectors [40][41][42][43][44][45][46][47][48][49], and so many other cases [50][51][52][53][54][55][56][57][58][...…”