Machine Learning and Graph Signal Processing Applied to Healthcare: A Review

Abstract

Signal processing is a very useful field of study in the interpretation of signals in many everyday applications. In the case of applications with time-varying signals, one possibility is to consider them as graphs, so graph theory arises, which extends classical methods to the non-Euclidean domain. In addition, machine learning techniques have been widely used in pattern recognition activities in a wide variety of tasks, including health sciences. The objective of this work is to identify and analyze the papers in the literature that address the use of machine learning applied to graph signal processing in health sciences. A search was performed in four databases (Science Direct, IEEE Xplore, ACM, and MDPI), using search strings to identify papers that are in the scope of this review. Finally, 45 papers were included in the analysis, the first being published in 2015, which indicates an emerging area. Among the gaps found, we can mention the need for better clinical interpretability of the results obtained in the papers, that is not to restrict the results or conclusions simply to performance metrics. In addition, a possible research direction is the use of new transforms. It is also important to make new public datasets available that can be used to train the models.

Keywords: deep learning; graph signal processing; health; machine learning.

Figure 1

Organizational diagram of the paper.

Figure 2

Flowchart of the paper selection process for the review considering exclusion criteria.

Figure 3

Word cloud obtained from the titles of the 45 papers using the Iramuteq software.

Figure 4

Similitude analysis obtained from the titles of the 45 papers using the Iramuteq software (0.7 alpha 2).

Figure 5

Graph analysis considering the occurrence of keywords.

Figure 6

Country associated with the affiliation of the first author of the papers included in the review.

Figure 7

Continents associated with first author affiliation of the papers included in the review. The continents are separated by color and the numbers indicate the number of publications per continent.

Figure 8

Distribution of publications by year and medical specialty.

Figure 9

Tree map with the distribution of papers by medical specialty.

Figure 10

The five most cited papers according to the Web of Science database.

Figure 11

Most cited papers represented by the first author.

Figure 12

Graph network representation for bibliometric coupling analysis.

Figure 13

Diagram with the 5 most frequent performance measures in the works analyzed.

Figure 14

Graph showing the most frequently used databases in neurology.