A Systematic Review of Machine Learning Techniques in Hematopoietic Stem Cell Transplantation (HSCT).

Sung Won Choi,Muneesh Tewari,Vibhuti Gupta,Mosharaf Chowdhury,Thomas M. Braun

doi:10.3390/s20216100

Abstract

Machine learning techniques are widely used nowadays in the healthcare domain for the diagnosis, prognosis, and treatment of diseases. These techniques have applications in the field of hematopoietic cell transplantation (HCT), which is a potentially curative therapy for hematological malignancies. Herein, a systematic review of the application of machine learning (ML) techniques in the HCT setting was conducted. We examined the type of data streams included, specific ML techniques used, and type of clinical outcomes measured. A systematic review of English articles using PubMed, Scopus, Web of Science, and IEEE Xplore databases was performed. Search terms included “hematopoietic cell transplantation (HCT),” “autologous HCT,” “allogeneic HCT,” “machine learning,” and “artificial intelligence.” Only full-text studies reported between January 2015 and July 2020 were included. Data were extracted by two authors using predefined data fields. Following PRISMA guidelines, a total of 242 studies were identified, of which 27 studies met the inclusion criteria. These studies were sub-categorized into three broad topics and the type of ML techniques used included ensemble learning (63%), regression (44%), Bayesian learning (30%), and support vector machine (30%). The majority of studies examined models to predict HCT outcomes (e.g., survival, relapse, graft-versus-host disease). Clinical and genetic data were the most commonly used predictors in the modeling process. Overall, this review provided a systematic review of ML techniques applied in the context of HCT. The evidence is not sufficiently robust to determine the optimal ML technique to use in the HCT setting and/or what minimal data variables are required.

Highlights

We examined the type of data streams included, specific machine learning (ML) techniques used, relevant predictors identified, and type of clinical outcomes measured
The workflow diagram for the systematic identification of scientific literature is shown in Figure 1 Search terms included different combinations of keywords related to “Hematopoietic Stem Cell Transplantation (HSCT)” and “machine learning” joined by Boolean operators “OR” and “AND”
We conducted a systematic review of ML techniques in the HSCT setting

Summary

Introduction

Machine learning is an application of artificial intelligence (AI) that provides machines the capability to automatically learn and improve from experience without being explicitly. It is a natural extension of traditional statistical approaches [3], focusing primarily on predictions, automatically identifying patterns within data, and performing tasks beyond human capabilities (i.e., classification of images) [4]. Applying machine learning (ML) algorithms on given data include building a model (i.e., learning relationship between the data features and outcome), validating (i.e., tuning the model parameters) and testing the model (i.e., applying the tuned model on a new testing dataset to make predictions and evaluations). The predictions improve with more experience (i.e., training data). The most important component for applying ML algorithms is data, which must be abundant to build robust and generalized predictive models

Objectives

Methods

Results

Discussion

Conclusion