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

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.

Keywords: HSCT; artificial intelligence; hematopoietic stem cell transplantation; mHealth; machine learning; mobile health; sensors.

Figure 1

PRISMA Workflow for systematic identification of scientific literature.

Figure 2

Distribution of studies by publication year.

Figure 3

Schematic workflow of Roadmap 2.0. Firstly, (a) large volumes of wearable sensor (i.e., Fitbit) data stream (e.g., heart rate, sleep, activity/steps), Electronic health Records and physiological data streams will be captured in real-time in mHealth platform Roadmap 2.0. The captured multi-parameter data streams (b) will be stored in secure HIPPA compliant server. It will contain multivariate physiological signals and patient reported outcomes data (generated from patients’ response of survey questionnaires). (c) The stored data will be processed in data analytics pipeline. Here, firstly features will be extracted from all diverse types of data and then machine learning algorithms will be used to build a predictive model. This model will be applied to test set for predictions on the unseen data. Finally, the predictive model will be evaluated using AUC. Also, feature importance will be computed. (d) The final results will be stored in the secure server.