Artificial intelligence outperforms experienced nephrologists to assess dry weight in pediatric patients on chronic hemodialysis
Dry weight is the lowest weight patients on hemodialysis can tolerate; correct dry weight estimation is necessary to minimize morbi-mortality, but is difficult to achieve. Here, we used artificial intelligence to improve the accuracy of dry weight assessment in hemodialysis patients.
We designed a neural network which used bio-impedancemetry, blood volume monitoring, and blood pressure values as inputs; output was artificial intelligence dry weight. Fourteen pediatric patients were switched from nephrologist to artificial intelligence dry weight. Artificial intelligence dry weight was higher (28.6%), lower (50%), or identical to nephrologist dry weight. Mean difference between artificial intelligence and nephrologist dry weights was 0.497 kg (− 1.33 to + 1.29 kg). In patients for whom artificial intelligence dry weight was lower than nephrologist dry weight, systolic blood pressure significantly decreased after dry weight decrease to artificial intelligence dry weight (77th to 60th percentile, p = 0.022); anti-hypertensive treatments were successfully decreased or discontinued in 28.7% of cases. In patients for whom artificial intelligence dry weight was higher than nephrologist dry weight, no hypertension was observed after dry weight increase to artificial intelligence dry weight; when present, symptoms of dry weight underestimation receded.
Neural network predictions outperformed those of experienced nephrologists in most cases, proving artificial intelligence is a powerful tool for predicting dry weight in hemodialysis patients.
KeywordsArtificial intelligence Hemodialysis Dry weight Blood pressure Neural network Bio-impedancemetry
The authors would like to thank the nurses at Robert Debré Pediatric Nephrology Department for their help in assessing dialysis parameters during this study.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Informed consent was obtained from all individual participants included in the study.
- 3.Peng W, Li Z, Xu H, Xia C, Guo Y, Zhang J, Liu K, Li Y, Pu J, Zhang H, Cui T (2018) Assessment of right ventricular dysfunction in end-stage renal disease patients on maintenance haemodialysis by cardiac magnetic resonance imaging. Eur J Radiol 102:89–94. https://doi.org/10.1016/j.ejrad.2018.02.036 CrossRefPubMedGoogle Scholar
- 5.Gotta V, Marsenic O, Pfister M (2018) Age- and weight-based differences in haemodialysis prescription and delivery in children, adolescents and young adults. Nephrol Dial Transplant. https://doi.org/10.1093/ndt/gfy067
- 7.Heerspink HJL, Ninomiya T, Zoungas S, de Zeeuw D, Grobbee DE, Jardine MJ, Gallagher M, Roberts MA, Cass A, Neal B, Perkovic V (2009) Effect of lowering blood pressure on cardiovascular events and mortality in patients on dialysis: a systematic review and meta-analysis of randomised controlled trials. Lancet 373:1009–1015. https://doi.org/10.1016/S0140-6736(09)60212-9 CrossRefPubMedPubMedCentralGoogle Scholar
- 11.Torterüe X, Dehoux L, Macher MA, Niel O, Kwon T, Deschênes G, Hogan J (2017) Fluid status evaluation by inferior vena cava diameter and bioimpedance spectroscopy in pediatric chronic hemodialysis. BMC Nephrol 18:373. https://doi.org/10.1186/s12882-017-0793-1 CrossRefPubMedPubMedCentralGoogle Scholar
- 13.Srisuwan K, Hongsawong N, Lumpaopong A, Thirakhupt P, Chulamokha Y (2015) Blood volume monitoring to assess dry weight in pediatric chronic hemodialysis patients. J Med Assoc Thail 98:1089–1096Google Scholar
- 14.Nielsen MA (2015) Neural Networks. Neural Networks and Deep Learning, Determination PressGoogle Scholar