Chronic Kidney Disease as a Cardiovascular Disorder-Tonometry Data Analyses

Mateusz Twardawa, Piotr Formanowicz, Dorota Formanowicz, Mateusz Twardawa, Piotr Formanowicz, Dorota Formanowicz

Abstract

Tonometry is commonly used to provide efficient and good diagnostics for cardiovascular disease (CVD). There are many advantages of this method, including low cost, non-invasiveness and little time to perform. In this study, the effort was undertaken to check whether tonometry data hides valuable information associated with different stages of chronic kidney disease (CKD) and end-stage renal disease (ESRD) treatment. For this purpose, six groups containing patients at different stages of CKD following different ways of dialysis treatment, as well as patients without CKD but with CVD and healthy volunteers were assessed. It was revealed that each of the studied groups had a unique profile. Only the type of dialysis was indistinguishable a from tonometric perspective (hemodialysis vs. peritoneal dialysis). Several techniques were used to build profiles that independently gave the same outcome: analysis of variance, network correlation structure analysis, multinomial logistic regression, and discrimination analysis. Moreover, to evaluate the classification potential of the discriminatory model, all mentioned techniques were later compared and treated as feature selection methods. Although the results are promising, it could be difficult to express differences as simple mathematical relations. This study shows that artificial intelligence can differentiate between different stages of CKD and patients without CKD. Potential future machine learning models will be able to determine kidney health with high accuracy and thereby classify patients. ClinicalTrials.gov Identifier: NCT05214872.

Keywords: cardiovascular disease; chronic kidney disease; tonometry.

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Division into groups selected for this study.
Figure 2
Figure 2
Dialysis duration and mortality within the groups: (A) the boxplot illustrating dialysis treatment duration with distinction of hemodialyzed (HD) and peritoneal dialyzed (PD) patients; (B) the barplot depicting the percent of deceased patients in every group with 2 year follow up; (C) the scatterplot presenting relation of age and number of months survived for dead patients, additional regression line was added to clarify the image and show lack of correlation (Spearman ρ = −0.075, p = 0.7194).
Figure 3
Figure 3
Visualization of differences between the groups made for the 39 cardiovascular parameters analyzed in this study. For each variable, values in the control group were standardized. Then, for each group, mean value transformation into a z-score according to standardization made for the control group was performed (each dot represents the z-scored average within a group). Each dot shows how much the mean parameter value calculated for the group was away from the healthy control average. The goal of the picture was to build intuition behind the direction and the magnitude of differences and similarities between the groups.
Figure 4
Figure 4
Correlation graphs representing only strong correlations between the parameters (Spearman ρ≥0.7 and p<0.01).
Figure 5
Figure 5
Kernel Fisher Discrimination Analysis results. Local clusters of patients from the same group are visible.
Figure 6
Figure 6
Original tonometric mean parameters values. The values for each individual parameter were standardized according to the scalar created for the whole patient population (n = 252) and normalized to fall between 0 and 1 values afterward. The radar plots consist of 39 tonometry parameters and show where the means inside every group lie (after scaling). The lowest values are in the circle center, and the highest touch the circumference. The white lines are provided to easily track values calculated for each parameter according to the label outside the circle.
Figure 7
Figure 7
Selected tonometric mean parameters values. The values for each individual parameter were standardized according to the scalar created for the whole patient population (n = 252) and normalized to fall between 0 and 1 values afterward. The radar plots consist of 23 tonometry parameters and show where the means inside every group lie (after scaling). The lowest values are in the circle center, and the highest touch the circumference. The white lines are provided to easily track values calculated for each parameter according to the label outside the circle.
Figure 8
Figure 8
Radar charts for Kernel Fisher Discrimination Analysis results. Each chart represents distinct profiles of the analyzed groups drawn for the mean values of 5 components extracted during dimensionality reduction. The values for each individual component were standardized according to the scalar created for the whole patient population (n = 252) and normalized to fall between 0 and 1 values afterward. The lowest values are in the circle center, and the highest touch the circumference. The white lines are provided to easily track values calculated for each component according to the label outside the circle.

References

    1. Jankowski J., Floege J., Fliser D., Böhm M., Marx N. Cardiovascular Disease in Chronic Kidney Disease. Circulation. 2021;143:1157–1172. doi: 10.1161/CIRCULATIONAHA.120.050686.
    1. Podkowińska A., Formanowicz D. Chronic Kidney Disease as Oxidative Stress- and Inflammatory-Mediated Cardiovascular Disease. Antioxidants. 2020;9:752. doi: 10.3390/antiox9080752.
    1. Formanowicz D., Formanowicz P. Transferrin changes in haemodialysed patients. Int. Urol. Nephrol. 2012;44:907–919. doi: 10.1007/s11255-011-9947-4.
    1. Formanowicz D., Sackmann A., Kozak A., Błażewicz J., Formanowicz P. Some aspects of the anemia of chronic disorders modeled and analyzed by petri net based approach. Bioprocess. Biosyst. Eng. 2011;34:581–595. doi: 10.1007/s00449-010-0507-6.
    1. Segall L., Nistor I., Covic A. Heart Failure in Patients with Chronic Kidney Disease: A Systematic Integrative Review. BioMed Res. Int. 2014;2014:937398. doi: 10.1155/2014/937398.
    1. Kasprzak Ł., Twardawa M., Formanowicz P., Formanowicz D. The Mutual Contribution of 3-NT, IL-18, Albumin, and Phosphate Foreshadows Death of Hemodialyzed Patients in a 2-Year Follow-Up. Antioxidants. 2022;11:355. doi: 10.3390/antiox11020355.
    1. Pugh D., Gallacher P., Dhaun N. Management of Hypertension in Chronic Kidney Disease. Drugs. 2019;79:365–379. doi: 10.1007/s40265-019-1064-1.
    1. Sharman J.E., Marwick T.H., Gilroy D., Otahal P., Abhayaratna W.P., Stowasser M. Randomized Trial of Guiding Hypertension Management Using Central Aortic Blood Pressure Compared With Best-Practice Care. Hypertension. 2013;62:1138–1145. doi: 10.1161/HYPERTENSIONAHA.113.02001.
    1. Carlsen R.K., Peters C.D., Khatir D.S., Laugesen E., Bøtker H.E., Winther S., Buus N.H. Estimated aortic blood pressure based on radial artery tonometry underestimates directly measured aortic blood pressure in patients with advancing chronic kidney disease staging and increasing arterial stiffness. Kidney Int. 2016;90:869–877. doi: 10.1016/j.kint.2016.05.014.
    1. Boutouyrie P., London G.M., Sharman J.E. Estimating central blood pressure in the extreme vascular phenotype of advanced kidney disease. Kidney Int. 2016;90:736–739. doi: 10.1016/j.kint.2016.06.039.
    1. Mika S., Ratsch G., Weston J., Scholkopf B., Mullers K. Fisher discriminant analysis with kernels; Proceedings of the Neural Networks for Signal Processing IX: 1999 IEEE Signal Processing Society Workshop; Madison, WI, USA. 25 August 1999; pp. 41–48.
    1. Ghojogh B., Karray F., Crowley M. Fisher and Kernel Fisher Discriminant Analysis: Tutorial. arXiv. 20191906.09436
    1. Virtanen P., Gommers R., Oliphant T.E., Haberland M., Reddy T., Cournapeau D., Burovski E., Peterson P., Weckesser W., Bright J., et al. SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python. Nat. Methods. 2020;17:261–272. doi: 10.1038/s41592-019-0686-2.
    1. Hagberg A., Swart P., Chult D.S. Exploring Network Structure, Dynamics, and Function Using NetworkX. Los Alamos National Lab. (LANL); Los Alamos, NM, USA: 2008. Technical Report.
    1. Venables W.N., Ripley B.D. Modern Applied Statistics with S. 4th ed. Springer; New York, NY, USA: 2002.
    1. Wickham H., Averick M., Bryan J., Chang W., McGowan L.D., François R., Grolemund G., Hayes A., Henry L., Hester J., et al. Welcome to the tidyverse. J. Open Source Softw. 2019;4:1686. doi: 10.21105/joss.01686.
    1. Nikomborirak K. Kernel FDA (0.1.1) [(accessed on 3 February 2022)]. Available online: .
    1. Harris C.R., Millman K.J., van der Walt S.J., Gommers R., Virtanen P., Cournapeau D., Wieser E., Taylor J., Berg S., Smith N.J., et al. Array programming with NumPy. Nature. 2020;585:357–362. doi: 10.1038/s41586-020-2649-2.
    1. Pandas Development Team Pandas-Dev/Pandas: Pandas, 2020. [(accessed on 3 February 2022)]. Available online:
    1. McKinney W. Data Structures for Statistical Computing in Python. In: van der Walt S., Jarrod M., editors. Proceedings of the 9th Python in Science Conference; Austin, TX, USA. 28 June–3 July 2010; pp. 56–61.
    1. Hunter J.D. Matplotlib: A 2D graphics environment. Comput. Sci. Eng. 2007;9:90–95. doi: 10.1109/MCSE.2007.55.
    1. Caswell T.A., Droettboom M., Lee A., Hunter J., Firing E., Stansby D., Klymak J., de Andrade E.S., Hoffmann T., Nielsen J.H., et al. Matplotlib/Matplotlib v3.1.2. 2019. [(accessed on 3 February 2022)]. Available online:
    1. Waskom M.L. Seaborn: Statistical data visualization. J. Open Source Softw. 2021;6:3021. doi: 10.21105/joss.03021.
    1. Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., et al. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 2011;12:2825–2830.
    1. Leng L., Li M., Kim C., Bi X. Dual-source discrimination power analysis for multi-instance contactless palmprint recognition. Multimed. Tools Appl. 2017;76:333–354. doi: 10.1007/s11042-015-3058-7.
    1. Tam J.C.W., Ko C.H., Koon C.M., Cheng Z., Lok W.H., Lau C.P., Leung P.C., Fung K.P., Chan W.Y., Lau C.B.S. Identification of Target Genes Involved in Wound Healing Angiogenesis of Endothelial Cells with the Treatment of a Chinese 2-Herb Formula. PLoS ONE. 2015;10:e0139342. doi: 10.1371/journal.pone.0139342.
    1. Wang W., Guan X., Zhang X. Profiling program and user behaviors for anomaly intrusion detection based on non-negative matrix factorization; Proceedings of the 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601); Nassau, Bahamas. 14–17 December 2004; pp. 99–104.
    1. Kobak D., Berens P. The art of using t-SNE for single-cell transcriptomics. Nat. Commun. 2019;10:5416. doi: 10.1038/s41467-019-13056-x.
    1. Tian Q., Zou J., Tang J., Fan S. Multi-distance based spectral embedding fusion for clustering single-cell methylation data; Proceedings of the 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB); Melbourne, Australia. 13–15 October 2021; pp. 1–8.
    1. Kublanov V.S., Dolganov A., Beloand D., Gamboa H. Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics. Appl. Bionics Biomech. 2017;2017:5985479. doi: 10.1155/2017/5985479.
    1. Jones G., Parr J., Nithiarasu P., Pant S. Machine learning for detection of stenoses and aneurysms: Application in a physiologically realistic virtual patient database. Biomech. Model. Mechanobiol. 2021;20:2097–2146. doi: 10.1007/s10237-021-01497-7.
    1. Garcia-Carretero R., Vigil-Medina L., Barquero-Perez O., Ramos-Lopez J. Pulse Wave Velocity and Machine Learning to Predict Cardiovascular Outcomes in Prediabetic and Diabetic Populations. J. Med. Syst. 2020;44:1573–1689. doi: 10.1007/s10916-019-1479-y.
    1. Almeida V.G., Vieira J., Santos P., Pereira T., Pereira H.C., Correia C., Pego M., Cardoso J. Machine Learning Techniques for Arterial Pressure Waveform Analysis. J. Pers. Med. 2013;3:82–101. doi: 10.3390/jpm3020082.
    1. Nabeel P., Vinay C., Kiran V.R., Jayaraj J., Mohanasankar S. Deep Learning for Blood Pressure Estimation: An Approach using Local Measure of Arterial Dual Diameter Waveforms; Proceedings of the 2019 IEEE International Symposium on Medical Measurements and Applications (MeMeA); Istanbul, Turkey. 26–28 June 2019; pp. 1–6.
    1. Chen S., Ji Z., Wu H., Xu Y. A Non-Invasive Continuous Blood Pressure Estimation Approach Based on Machine Learning. Sensors. 2019;19:2585. doi: 10.3390/s19112585.
    1. Johnson A.E., Pollard T.J., Shen L., Lehman L.W.H., Feng M., Ghassemi M., Moody B., Szolovits P., Anthony Celi L., Mark R.G. MIMIC-III, a freely accessible critical care database. Sci. Data. 2016;3:2052–4463. doi: 10.1038/sdata.2016.35.
    1. Athaya T., Choi S. A Review of Noninvasive Methodologies to Estimate the Blood Pressure Waveform. Sensors. 2022;22:3953. doi: 10.3390/s22103953.
    1. Inserra F., Forcada P., Castellaro A., Castellaro C. Chronic Kidney Disease and Arterial Stiffness: A Two-Way Path. Front. Med. 2021;8:1958. doi: 10.3389/fmed.2021.765924.
    1. Wu Y., Luttrell I., Feng S., Chen P.P., Spaide T., Lee A.Y., Wen J.C. Development and validation of a machine learning, smartphone-based tonometer. Br. J. Ophthalmol. 2020;104:1394–1398. doi: 10.1136/bjophthalmol-2019-315446.
    1. Bodington R., Kassianides X., Bhandari S. Point-of-care testing technologies for the home in chronic kidney disease: A narrative review. Clin. Kidney J. 2021;14:2316–2331. doi: 10.1093/ckj/sfab080.
    1. Polańczyk A., Strzelecki M., Woźniak T., Szubert W., Stefańczyk L. 3D Blood Vessels Reconstruction Based on Segmented CT Data for Further Simulations of Hemodynamic in Human Artery Branches. Found. Comput. Decis. Sci. 2017;42:359–371. doi: 10.1515/fcds-2017-0018.
    1. Jha V., Garcia-Garcia G., Iseki K., Li Z., Naicker S., Plattner B., Saran R., Wang A.Y.M., Yang C.W. Chronic kidney disease: Global dimension and perspectives. Lancet. 2013;382:260–272. doi: 10.1016/S0140-6736(13)60687-X.

Source: PubMed

스폰서 및 공동 작업자

건강 상태

약물 개입

3
구독하다