Cross-validation for triplets of HRV and BPV indices based on ordinal patterns in differentiating OSA patients from healthy controls

Results of cross-validation for triplets of HRV and BPV indices based on ordinal patterns, as described in the paper “Differentiating patients with obstructive sleep apnea from healthy controls based on heart rate–blood pressure coupling quantified by entropy-based indices” by P. Pilarczyk, G. Graff, J.M. Amigó, K. Tessmer, K. Narkiewicz, B. Graff.
The paper was published in Chaos 33 (2023), 103140. DOI: 10.1063/5.0158923. See also arXiv:2311.10752.
If you use this data in your research, please, cite the paper.
Columns in the CSV file contain the following data:1. The consecutive number of a triplet of indices for which the cross-validation was carried out.2. Mean AUC obtained in five repetitions of a threefold cross-validation test for a non-linear SVM classifier.3. The standard deviation of the 15 AUCs obtained in the tests.4. The minimum value of the mean AUC obtained among the five repetitions of the cross-validation test.5. The maximum value of the mean AUC obtained among the five repetitions of the cross-validation test.6. A comma-separated list of the indices in the triplet.The rows are sorted in a descending order according to the value of mean AUC (the second column).
This research was supported by the National Science Centre, Poland, within the following grants: SHENG 2018/30/Q/ST1/00228 (G. Graff), OPUS 2021/41/B/ST1/00405 (P. Pilarczyk), and MAESTRO 2011/02/A/NZ5/00329 (B. Graff and K. Narkiewicz). J. M. Amigó was financially supported by Agencia Estatal de Investigación, Spain, Grant No. PID2019-108654GB-I00/AEI/10.13039/501100011033 and by Generalitat Valenciana, Spain, Grant PROMETEO/2021/063. G. Graff and K. Tessmer were also supported by Gdańsk University of Technology grant Neptunium Excellence Initiative—Research University, DEC−2/2021/IDUB/II. Computations were carried out using the computers of Centre of Informatics Tricity Academic Supercomputer and Network.