Development and Validation of a Machine Learning Model Predicting Arteriovenous Fistula Failure in a Large Network of Dialysis Clinics

Ricardo Peralta, Mario Garbelli, Francesco Bellocchio, Pedro Ponce, Stefano Stuard, Maddalena Lodigiani, João Fazendeiro Matos, Raquel Ribeiro, Milind Nikam, Max Botler, Erik Schumacher, Diego Brancaccio and Luca Neri
Additional contact information
Ricardo Peralta: NephroCare Portugal, Fresenius Medical Care Portugal, 1750-130 Lisboa, Portugal
Mario Garbelli: Clinical & Data Intelligence Systems-Advanced Analytics, Fresenius Medical Care, 26020 Vaiano Cremasco, Italy
Francesco Bellocchio: Clinical & Data Intelligence Systems-Advanced Analytics, Fresenius Medical Care, 26020 Vaiano Cremasco, Italy
Pedro Ponce: NephroCare Portugal, Fresenius Medical Care Portugal, 1750-130 Lisboa, Portugal
Stefano Stuard: Global Medical Office-Clinical & Therapeutic Governance Fresenius Medical Care, 61352 Bad Homburg, Germany
Maddalena Lodigiani: Clinical & Data Intelligence Systems-Advanced Analytics, Fresenius Medical Care, 26020 Vaiano Cremasco, Italy
João Fazendeiro Matos: NephroCare Portugal, Fresenius Medical Care Portugal, 1750-130 Lisboa, Portugal
Raquel Ribeiro: Nursing Care, Care Operations EMEA, 61352 Bad Homburg, Germany
Milind Nikam: Global Medical Office, Global Clinical Affairs, Medical Governance & Digital Health AP, Fresenius Medical Care, Singapore 307684, Singapore
Max Botler: Global Research & Development, Data Solutions, Fresenius Medical Care, 10117 Berlin, Germany
Erik Schumacher: Global Research & Development, Data Solutions, Fresenius Medical Care, 10117 Berlin, Germany
Diego Brancaccio: Global Medical Office-Clinical & Therapeutic Governance Fresenius Medical Care, 61352 Bad Homburg, Germany
Luca Neri: Clinical & Data Intelligence Systems-Advanced Analytics, Fresenius Medical Care, 26020 Vaiano Cremasco, Italy

IJERPH, 2021, vol. 18, issue 23, 1-12

Abstract: Background: Vascular access surveillance of dialysis patients is a challenging task for clinicians. We derived and validated an arteriovenous fistula failure model (AVF-FM) based on machine learning. Methods: The AVF-FM is an XG-Boost algorithm aimed at predicting AVF failure within three months among in-centre dialysis patients. The model was trained in the derivation set (70% of initial cohort) by exploiting the information routinely collected in the Nephrocare European Clinical Database (EuCliD ® ). Model performance was tested by concordance statistic and calibration charts in the remaining 30% of records. Features importance was computed using the SHAP method. Results: We included 13,369 patients, overall. The Area Under the ROC Curve (AUC-ROC) of AVF-FM was 0.80 (95% CI 0.79–0.81). Model calibration showed excellent representation of observed failure risk. Variables associated with the greatest impact on risk estimates were previous history of AVF complications, followed by access recirculation and other functional parameters including metrics describing temporal pattern of dialysis dose, blood flow, dynamic venous and arterial pressures. Conclusions: The AVF-FM achieved good discrimination and calibration properties by combining routinely collected clinical and sensor data that require no additional effort by healthcare staff. Therefore, it can potentially enable risk-based personalization of AVF surveillance strategies.

Keywords: machine learning; artificial intelligence; vascular access surveillance; arteriovenous fistula; end stage kidney disease; dialysis; kidney failure (search for similar items in EconPapers)
JEL-codes: I I1 I3 Q Q5 (search for similar items in EconPapers)
Date: 2021
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/1660-4601/18/23/12355/pdf (application/pdf)
https://www.mdpi.com/1660-4601/18/23/12355/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jijerp:v:18:y:2021:i:23:p:12355-:d:686824

Access Statistics for this article

IJERPH is currently edited by Ms. Jenna Liu

More articles in IJERPH from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().