Article
A Personalized Medical Decision Support System Based on
Explainable Machine Learning Algorithms and ECC
Features: Data from the Real World
Dongxiao Gu
1,2,
* , Wang Zhao
1,2
, Yi Xie
1,2
, Xiaoyu Wang
3
, Kaixiang Su
1,2
and Oleg V. Zolotarev
4
Citation: Gu, D.; Zhao, W.; Xie, Y.;
Wang, X.; Su, K.; Zolotarev, O.V. A
Personalized Medical Decision
Support System Based on Explainable
Machine Learning Algorithms and
ECC Features: Data from the Real
World. Diagnostics 2021, 11, 1677.
https://doi.org/10.3390/
diagnostics11091677
Academic Editor: Keun Ho Ryu
Received: 17 August 2021
Accepted: 10 September 2021
Published: 14 September 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
1
The School of Management, Hefei University of Technology, Hefei 230009, China;
2019110768@mail.hfut.edu.cn (W.Z.); yixie928@163.com (Y.X.); 2018110745@mail.hfut.edu.cn (K.S.)
2
Key Laboratory of Process Optimization and Intelligent Decision-Making of Ministry of Education,
Hefei 230009, China
3
The 1st Affiliated Hospital, Anhui University of Traditional Chinese Medicine, Hefei 230009, China;
xywang0551@163.com
4
The Department of Information Systems in Economics and Management, Russian New University,
105005 Moscow, Russia; ol-zolot@yandex.ru
* Correspondence: dongxiaogu@yeah.net; Tel.: +86-152-8967-9200
Abstract:
Artificial intelligence can help physicians improve the accuracy of breast cancer diagnosis.
However, the effectiveness of AI applications is limited by doctors’ adoption of the results recom-
mended by the personalized medical decision support system. Our primary purpose is to study
the impact of external case characteristics (ECC) on the effectiveness of the personalized medical
decision support system for breast cancer assisted diagnosis (PMDSS-BCAD) in making accurate rec-
ommendations. Therefore, we designed a novel comprehensive framework for case-based reasoning
(CBR) that takes the impact of external features of cases into account, made use of the naive Bayes
and k-nearest neighbor (KNN) algorithms (CBR-ECC), and developed a PMDSS-BCAD system by
using the CBR-ECC model and external features as system components. Under the new case-based
reasoning framework, the accuracy of the combined model of naive Bayes and KNN with an optimal
K value of 2 is 99.40%. Moreover, in a real hospital scenario, users rated the PMDSS-BCAD system,
which takes into account the external characteristics of the case, better than the original personalized
system. These results suggest that PMDSS-BCD can not only provide doctors with more personalized
and accurate results for auxiliary diagnosis, but also improve doctors’ trust in the results, so as to
encourage doctors to adopt the results recommended by the personalized system.
Keywords:
case-based reasoning; personalized recommendations; machine learning; external fea-
tures of cases; physician adoption
1. Introduction
The International Agency for Research on Cancer of the World Health Organization
has released the latest global cancer data for 2020, and there were about 2.3 million new
cases of breast cancer worldwide in 2020, accounting for nearly 12% of all cancer cases,
surpassing lung cancer as the most prevalent cancer type worldwide for the first time [
1
].
With the improvement of living standards, the accelerated pace of life, and the increase in
life pressures and stress, the incidence of breast diseases, especially breast cancer, is also
increasing, and the age of affected individuals is getting younger [
2
]. It is predicted that
by 2030, cancer incidence will affect more than half of the population. Moreover, while
survival rates are 89% in the United States and 76% in Europe, in developing countries
survival rates are dropping [
3
]. Thus, the management of breast cancer remains one of the
most problematic healthcare issues [4].
In this context, machine learning represents a great opportunity for:
Diagnostics 2021, 11, 1677. https://doi.org/10.3390/diagnostics11091677 https://www.mdpi.com/journal/diagnostics
