An Artificial Intelligence-Enabled Pipeline for Medical Domain: Malaysian Breast Cancer Survivorship Cohort as a Case Study.

Mogana Darshini Ganggayah,Elham Yousef Kalafi,Tania Islam,Sarinder Kaur Dhillon,Foad Kalhor,Nur Aishah Taib,Teh Chean Chiang

doi:10.3390/diagnostics11081492

Mogana Darshini Ganggayah, Elham Yousef Kalafi + Show 5 more

Open Access

https://doi.org/10.3390/diagnostics11081492

Copy DOI

Journal: Diagnostics	Publication Date: Aug 18, 2021
Citations: 3	License type: CC BY 4.0

Affiliation: University of Malaya

Abstract

Automated artificial intelligence (AI) systems enable the integration of different types of data from various sources for clinical decision-making. The aim of this study is to propose a pipeline to develop a fully automated clinician-friendly AI-enabled database platform for breast cancer survival prediction. A case study of breast cancer survival cohort from the University Malaya Medical Centre was used to develop and evaluate the pipeline. A relational database and a fully automated system were developed by integrating the database with analytical modules (machine learning, automated scoring for quality of life, and interactive visualization). The developed pipeline, iSurvive has helped in enhancing data management as well as to visualize important prognostic variables and survival rates. The embedded automated scoring module demonstrated quality of life of patients whereas the interactive visualizations could be used by clinicians to facilitate communication with patients. The pipeline proposed in this study is a one-stop center to manage data, to automate analytics using machine learning, to automate scoring and to produce explainable interactive visuals to enhance clinician-patient communication along the survivorship period to modify behaviours that relate to prognosis. The pipeline proposed can be modelled on any disease not limited to breast cancer.

Highlights

According to the 2020 GLOBOCAN estimates of cancer incidence and mortality, cancer is the first or second leading cause of death in 112 of 183 countries and ranks third or fourth in other 23 countries (Bray et al, 2020)
In order to demonstrate the pipeline, we developed iSurvive, a fully automated platform, which incorporates digitized questionnaires for data collection, database for data storage and management, automated machine learning analytics modules for survival prediction, and automated quality of life scoring and explainable interactive visualizations for clinician-patient communication during clinic consultations along the survivorship period to modify behaviors that relate to prognosis to improve the care of their patients
The results of the fully automated pipeline of iSurvive are presented in the order of digitized questionnaire, automated machine learning, automated quality of life scoring, interactive visualization and download module

Summary

Introduction

According to the 2020 GLOBOCAN estimates of cancer incidence and mortality, cancer is the first or second leading cause of death in 112 of 183 countries and ranks third or fourth in other 23 countries (Bray et al, 2020). Over the past two decades, the incidence of breast cancer has continued to escalate in most Asian countries [3,4]. The mortality rate of breast cancer is higher in developing countries despite the number of cases being lower compared to developed countries [5]. In Malaysia, 50–60% of breast cancer cases are detected at late stages, and the survival of the patients is one of the lowest in the region [6,7,8]. We need to explore other predictive factors such as Body Mass Index (BMI) and co-morbidities in building AI pipelines that could assist in clinical decision making and survivorship recommendations

Objectives

Methods

Results

Discussion

Conclusion