Back

MaTiLDA: An Integrated Machine Learning and Topological Data Analysis Platform for Brain Network Dynamics

Prantzalos, K.; Upadhyaya, D. P.; Shafiabadi, N.; Gurski, N.; Fernandez-BacaVaca, G.; Yoshimoto, K.; Sivagnanam, S.; Majumdar, A.; Sahoo, S. S.

2023-06-12 health informatics
10.1101/2023.06.08.23290830 medRxiv
Show abstract

Topological data analysis (TDA) is a powerful approach for investigating complex relationships in brain networks; however, its application requires substantial domain knowledge in programming, mathematics, and data science, especially in the context of data-driven approaches like machine learning (ML). To address this educational barrier, we introduce MaTiLDA, a graphical user interface that enables exploration of common representations of TDA features and their efficacy in various classical machine learning models. This user-friendly tool is the first graphical user interface built to explore TDA representations in machine learning applications. MaTiLDA provides a user-centric method for characterizing complex neural relationships using TDA techniques. To demonstrate the utility of MaTiLDA in characterizing brain network dynamics, we apply this workflow to a cohort of 4 refractory epilepsy patients and evaluate the predictive performance of various TDA feature representations in a series of ML models. The MaTiLDA application can be accessed through https://bmhinformatics.case.edu/nic/MaTiLDA

Matching journals

The top 9 journals account for 50% of the predicted probability mass.

1
Scientific Reports
○ 3612 papers in training set
Top 0.4%
22.0%
Similar papers in this journal
2
Patterns
○ 78 papers in training set
Top 0.2%
5.6%
Similar papers in this journal
3
Informatics in Medicine Unlocked
○ 22 papers in training set
Top 0.2%
4.9%
Similar papers in this journal
4
Frontiers in Neuroscience
○ 256 papers in training set
Top 0.9%
4.1%
Similar papers in this journal
5
Biology Methods and Protocols
◐ 61 papers in training set
Top 0.2%
3.4%
Similar papers in this journal
6
Bioinformatics
◐ 1204 papers in training set
Top 5%
3.2%
7
PLOS Digital Health
● 106 papers in training set
Top 2%
3.1%
8
IEEE Journal of Biomedical and Health Informatics
● 37 papers in training set
Top 0.4%
2.8%
9
iScience
○ 1154 papers in training set
Top 9%
2.7%
50% of probability mass above
10
Computer Methods and Programs in Biomedicine
○ 28 papers in training set
Top 0.3%
2.5%
11
PLOS ONE
● 5266 papers in training set
Top 41%
2.4%
12
Scientific Data
○ 209 papers in training set
Top 1.0%
2.4%
13
PLOS Computational Biology
● 1863 papers in training set
Top 13%
2.1%
14
Journal of Medical Internet Research
◐ 87 papers in training set
Top 1%
2.1%
15
Computers in Biology and Medicine
○ 128 papers in training set
Top 2%
1.7%
16
Frontiers in Physiology
○ 106 papers in training set
Top 1%
1.7%
17
Journal of Visualized Experiments
● 34 papers in training set
Top 0.3%
1.7%
18
Frontiers in Bioinformatics
○ 49 papers in training set
Top 0.6%
1.5%
19
BMC Medical Research Methodology
○ 47 papers in training set
Top 0.8%
1.5%
20
Artificial Intelligence in Medicine
○ 17 papers in training set
Top 0.4%
1.5%
21
JAMIA Open
◐ 42 papers in training set
Top 1%
1.4%
22
Nature Computational Science
○ 55 papers in training set
Top 0.9%
1.3%
23
Neurophotonics
● 42 papers in training set
Top 0.4%
1.1%
24
Journal of Neural Engineering
○ 221 papers in training set
Top 2%
1.0%
25
BMC Bioinformatics
○ 457 papers in training set
Top 5%
1.0%
26
Briefings in Bioinformatics
◐ 354 papers in training set
Top 7%
0.8%
27
Expert Systems with Applications
○ 11 papers in training set
Top 0.4%
0.8%
28
BMC Medical Informatics and Decision Making
○ 43 papers in training set
Top 2%
0.8%
29
Frontiers in Digital Health
○ 24 papers in training set
Top 1%
0.8%
30
Frontiers in Neuroinformatics
○ 41 papers in training set
Top 0.7%
0.8%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.