Development and validation of AI-based triage support algorithms for prevention of intradialytic hypotension.

Artificial intelligence End stage kidney disease Intradialytic hypotension Personalized medicine

Journal

Journal of nephrology
ISSN: 1724-6059
Titre abrégé: J Nephrol
Pays: Italy
ID NLM: 9012268

Informations de publication

Date de publication:
Sep 2023
Historique:
received: 15 02 2023
accepted: 19 07 2023
pubmed: 14 9 2023
medline: 14 9 2023
entrez: 14 9 2023
Statut: ppublish

Résumé

Intradialytic hypotension remains one of the most recurrent complications of dialysis sessions. Inadequate management can lead to adverse outcomes, highlighting the need to develop personalized approaches for the prevention of intradialytic hypotension. Here, we sought to develop and validate two AI-based risk models predicting the occurrence of symptomatic intradialytic hypotension at different time points. The models were built using the XGBoost algorithm and they predict the occurrence of intradialytic hypotension in the next dialysis session and in the next month. The initial dataset, obtained from routinely collected data in the EuCliD The final dataset included 1,249,813 dialysis sessions, and the incidence rate of intradialytic hypotension was 10.07% (95% CI 10.02-10.13). Our models retained good discrimination (AUC around 0.8) and a suitable calibration yielding to the selection of three classification thresholds identifying four distinct risk groups. Variables providing the most significant impact on risk estimates were blood pressure dynamics and other metrics mirroring hemodynamic instability over time. Recurrent symptomatic intradialytic hypotension could be reliably and accurately predicted using routinely collected data during dialysis treatment and standard clinical care. Clinical application of these prediction models would allow for personalized risk-based interventions for preventing and managing intradialytic hypotension.

Sections du résumé

BACKGROUND BACKGROUND
Intradialytic hypotension remains one of the most recurrent complications of dialysis sessions. Inadequate management can lead to adverse outcomes, highlighting the need to develop personalized approaches for the prevention of intradialytic hypotension. Here, we sought to develop and validate two AI-based risk models predicting the occurrence of symptomatic intradialytic hypotension at different time points.
METHODS METHODS
The models were built using the XGBoost algorithm and they predict the occurrence of intradialytic hypotension in the next dialysis session and in the next month. The initial dataset, obtained from routinely collected data in the EuCliD
RESULTS RESULTS
The final dataset included 1,249,813 dialysis sessions, and the incidence rate of intradialytic hypotension was 10.07% (95% CI 10.02-10.13). Our models retained good discrimination (AUC around 0.8) and a suitable calibration yielding to the selection of three classification thresholds identifying four distinct risk groups. Variables providing the most significant impact on risk estimates were blood pressure dynamics and other metrics mirroring hemodynamic instability over time.
CONCLUSIONS CONCLUSIONS
Recurrent symptomatic intradialytic hypotension could be reliably and accurately predicted using routinely collected data during dialysis treatment and standard clinical care. Clinical application of these prediction models would allow for personalized risk-based interventions for preventing and managing intradialytic hypotension.

Identifiants

pubmed: 37707692
doi: 10.1007/s40620-023-01741-6
pii: 10.1007/s40620-023-01741-6
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

2001-2011

Informations de copyright

© 2023. The Author(s) under exclusive licence to Italian Society of Nephrology.

Références

Sands JJ et al (2014) Intradialytic hypotension: frequency, sources of variation and correlation with clinical outcome. Hemodial Int 18(2):415–422. https://doi.org/10.1111/hdi.12138
doi: 10.1111/hdi.12138 pubmed: 24467830
Kuipers J et al (2019) The prevalence of intradialytic hypotension in patients on conventional hemodialysis: a systematic review with meta-analysis. Am J Nephrol 49(6):497–506. https://doi.org/10.1159/000500877
doi: 10.1159/000500877 pubmed: 31129661
Flythe JE, Xue H, Lynch KE et al (2015) Association of mortality risk with various definitions of intradialytic hypotension. J Am Soc Nephrol 26(3):724–734. https://doi.org/10.1681/ASN.2014020222
doi: 10.1681/ASN.2014020222 pubmed: 25270068
Silversides JA et al (2014) Fluid balance, intradialytic hypotension, and outcomes in critically ill patients undergoing renal replacement therapy: a cohort study. Crit Care. https://doi.org/10.1186/s13054-014-0624-8
doi: 10.1186/s13054-014-0624-8 pubmed: 25407408 pmcid: 4255668
Sars B, Van Der Sande FM, Kooman JP (2020) Intradialytic hypotension: mechanisms and outcome. Blood Purif 49(1–2):158–167. https://doi.org/10.1159/000503776
doi: 10.1159/000503776 pubmed: 31851975
Larkin JW, Reviriego-Mendoza MM, Usvyat LA et al (2017) To cool, or too cool: Is reducing dialysate temperature the optimal approach to preventing intradialytic hypotension? Semin Dial 30(6):501–508. https://doi.org/10.1111/sdi.12628
doi: 10.1111/sdi.12628 pubmed: 28666073
Ronco C, Brendolan A, Milan M et al (2000) Impact of biofeedback-induced cardiovascular stability on hemodialysis tolerance and efficiency. Kidney Int 58(2):800–808. https://doi.org/10.1046/j.1523-1755.2000.00229.x
doi: 10.1046/j.1523-1755.2000.00229.x pubmed: 10916105
Chang TI et al (2011) Intradialytic hypotension and vascular access thrombosis. J Am Soc Nephrol 22(8):1526–1533. https://doi.org/10.1681/ASN.2010101119
doi: 10.1681/ASN.2010101119 pubmed: 21803971 pmcid: 3148707
Shoji T et al (2004) Hemodialysis-associated hypotension as an independent risk factor for two-year mortality in hemodialysis patients. Kidney Int 66(3):1212–1220. https://doi.org/10.1111/j.1523-1755.2004.00812.x
doi: 10.1111/j.1523-1755.2004.00812.x pubmed: 15327420
Chou JA, Kalantar-Zadeh K, Mathew AT (2017) A brief review of intradialytic hypotension with a focus on survival. Semin Dial 30(6):473–480. https://doi.org/10.1111/SDI.12627
doi: 10.1111/SDI.12627 pubmed: 28661565 pmcid: 5738929
Mancini E et al (2007) Prevention of dialysis hypotension episodes using fuzzy logic control system. Nephrol Dial Transplant 22(5):1420–1427. https://doi.org/10.1093/NDT/GFL799
doi: 10.1093/NDT/GFL799 pubmed: 17299006
Lee H et al (2021) Deep learning model for real-time prediction of intradialytic hypotension. Clin J Am Soc Nephrol. https://doi.org/10.2215/cjn.09280620
doi: 10.2215/cjn.09280620 pubmed: 34362786 pmcid: 8092068
Kim HW et al (2022) Deep learning model for predicting intradialytic hypotension without privacy infringement: a retrospective two-center study. Front Med J. https://doi.org/10.3389/fmed.2022.878858
doi: 10.3389/fmed.2022.878858
Steil H et al (2004) EuCliD®—a medical registry. Methods Inf Med 43(01):83–88. https://doi.org/10.1055/s-0038-1633841
doi: 10.1055/s-0038-1633841 pubmed: 15026844
Marcelli D (2001) EuCliD (European Clinical Database): a database comparing different realities. J Nephrol 14(4 SUPPL):S94–S100. Available: http://www.ncbi.nlm.nih.gov/pubmed/11798154
MerelloGodino JI, Rentero R, Orlandini G et al (2002) Results from EuCliD® (European Clinical Dialysis Database): impact of shifting treatment modality. Int J Artif Organs 25(11):1049–1060. https://doi.org/10.1177/039139880202501103
doi: 10.1177/039139880202501103
Sherman RA (2002) Intradialytic hypotension: an overview of recent, unresolved and overlooked issues. Semin Dial 15(3):141–143. https://doi.org/10.1046/j.1525-139X.2002.00002.x
doi: 10.1046/j.1525-139X.2002.00002.x pubmed: 12100450
Park S et al (2019) Predicting intradialytic hypotension using heart rate variability. Sci Rep. https://doi.org/10.1038/s41598-019-39295-y
doi: 10.1038/s41598-019-39295-y pubmed: 31892695 pmcid: 6938486
Assimon MM, Flythe JE (2017) Definitions of intradialytic hypotension. Semin Dial 30(6):464–472. https://doi.org/10.1111/sdi.12626
doi: 10.1111/sdi.12626 pubmed: 28691195 pmcid: 5668149
Kooman J et al (2007) EBPG guideline on haemodynamic instability. Nephrol Dial Transplant 22(Suppl 2):785–794. https://doi.org/10.1093/NDT/GFM019
doi: 10.1093/NDT/GFM019
Kuipers J et al (2016) Prevalence of intradialytic hypotension, clinical symptoms and nursing interventions—a three-months, prospective study of 3818 haemodialysis sessions Dialysis and Transplantation. BMC Nephrol 17(1):1–11. https://doi.org/10.1186/s12882-016-0231-9
doi: 10.1186/s12882-016-0231-9
(2005) K/DOQI clinical practice guidelines for cardiovascular disease in dialysis patients. Am J Kidney Dis 45(Suppl 3):16–153. https://doi.org/10.1053/J.AJKD.2005.01.019
Barbieri C et al (2019) Development of an artificial intelligence model to guide the management of blood pressure, fluid volume, and dialysis dose in end-stage kidney disease patients: proof of concept and first clinical assessment. Kidney Dis 5(1):28–33. https://doi.org/10.1159/000493479
doi: 10.1159/000493479
Lin CJ et al (2018) Intelligent system to predict intradialytic hypotension in chronic hemodialysis. J Formos Med Assoc 117(10):888–893. https://doi.org/10.1016/J.JFMA.2018.05.023
doi: 10.1016/J.JFMA.2018.05.023 pubmed: 29941330
Kuipers J et al (2019) Association between quality of life and various aspects of intradialytic hypotension including patient-reported intradialytic symptom score. BMC Nephrol 20(1):1–8. https://doi.org/10.1186/S12882-019-1366-2/TABLES/2
doi: 10.1186/S12882-019-1366-2/TABLES/2
McCausland FR et al (2020) Intradialytic hypotension and cardiac arrhythmias in patients undergoing maintenance hemodialysis: results from the monitoring in dialysis study. Clin J Am Soc Nephrol 15(6):805–812. https://doi.org/10.2215/CJN.06810619
doi: 10.2215/CJN.06810619
Matsuura R et al (2019) Intradialytic hypotension is an important risk factor for critical limb ischemia in patients on hemodialysis. BMC Nephrol 20(1):1–8. https://doi.org/10.1186/S12882-019-1662-X
doi: 10.1186/S12882-019-1662-X
Cedeño S et al (2021) Intradialytic hypotension and relationship with cognitive function and brain morphometry. Clin Kidney J 14(4):1156–1164. https://doi.org/10.1093/CKJ/SFAA070
doi: 10.1093/CKJ/SFAA070 pubmed: 33841861

Auteurs

Federica Gervasoni (F)

Fresenius Medical Care Italia SpA, Palazzo Pignano, Italy.

Francesco Bellocchio (F)

Fresenius Medical Care Italia SpA, Palazzo Pignano, Italy.

Jaroslav Rosenberger (J)

FMC-Dialysis Services Slovakia, Kosice, Slovakia.
Medical Faculty, University of PJ Safarik, Kosice, Slovakia.

Otto Arkossy (O)

Fresenius Medical Care Deutschland GmbH, Bad Homburg, Germany.

Jasmine Ion Titapiccolo (J)

Fresenius Medical Care Italia SpA, Palazzo Pignano, Italy.

Vratislava Kovarova (V)

Fresenius Medical Care Deutschland GmbH, Bad Homburg, Germany.

John Larkin (J)

Fresenius Medical Care, Waltham, MA, USA.

Milind Nikam (M)

Fresenius Medical Care, Singapore, 307684, Singapore.

Stefano Stuard (S)

Fresenius Medical Care Deutschland GmbH, Bad Homburg, Germany.

Giovanni Luigi Tripepi (GL)

Institute of Clinical Physiology (IFC-CNR) of Reggio Calabria, Reggio Calabria, Italy.

Len A Usvyat (LA)

Fresenius Medical Care, Waltham, MA, USA.

Anke Winter (A)

Fresenius Medical Care Deutschland GmbH, Bad Homburg, Germany.

Luca Neri (L)

Fresenius Medical Care Italia SpA, Palazzo Pignano, Italy. luca.neri@fmc-ag.com.

Carmine Zoccali (C)

Renal Research Institute, New York, USA.
Associazione Ipertensione Nefrologia e Trapianto Renale (IPNET) c/o Nefrologia e CNR, Grande Ospedale Metropolitano, Reggio Calabria, Italy.
Biologia E Genetica Molecolare (BIOGEM) Research Center, Ariano Irpino, Avellino, Italy.

Classifications MeSH