Introduction: Autogenous arteriovenous fistula (AVF) is the preferred vascular access in patients undergoing maintenance hemodialysis (MHD). However, complications such as thrombosis may occur. This study aimed to construct and validate a machine learning-based risk-prediction model for AVF thrombosis, hypothesizing that such a model can effectively predict occurrences, providing a foundation for early clinical intervention. Methods: The retrospective longitudinal study included a total of 270 patients who underwent MHD at the Hemodialysis Center of the Second Affiliated Hospital of Harbin Medical University between March 2021 and December 2022. During this study, baseline data and scale information of patients between March 2020 and December 2021 were collected. We recorded outcome indicators between March 2021 and December 2022 for subsequent analyses. Five machine learning models were developed (artificial neural network, logistic regression, ridge classification, random forest, and adaptive boosting). The sensitivity (recall), specificity, accuracy, and precision of each model were evaluated. The effect size of each variable was analyzed and ranked. Models were assessed using the area under the receiver-operating characteristic (AUROC) curve. Results: Among the 270 included patients, 105 had AVF thrombosis (55 male and 50 female patients; age range, 29–79 years; mean age, 56.72 years; standard deviation [SDs], ±13.10 years). Conversely, 165 patients did not have AVF thrombosis (99 male and 66 female patients; age range, 23–79 years; mean age, 53.58 years; SD, ± 13.33 years). During the observation period, approximately 52.6% of patients with AVF experienced long-term complications. The most common complications associated with AVF were thrombosis (105; 38.9%), aneurysm formation (27; 10%), and excessively high output flow (10; 3.7%). Fifty-four (20%) patients with AVF required intervention because of complications associated with vascular access. The AUROC curve of the testing set was between 0.858 and 0.903. Conclusion: In this study, we developed five machine learning models to predict the risk of AVF thrombosis, providing a reference for early clinical intervention.

1.
Wang
L
,
Xu
X
,
Zhang
M
.
Prevalence of chronic kidney disease in China: results from the sixth China chronic disease and risk factor surveillance JAMA
.
Intern Med
.
2023
Published online 20 February.
2.
Inker
L-A
,
Astor
B-C
,
Fox
C-H
,
Isakova
T
,
Lash
JP
,
Peralta
CA
, et al
.
KDOQI US commentary on the 2012 KDIGO clinical practice guideline for the evaluation and management of CKD
.
Am J Kidney Dis
.
2014
;
63
(
5
):
713
35
.
3.
Chen
X
,
Jie
F
,
Qin Yi the selection and effectiveness control of hemodialysis treatment methods for chronic uremia patients
.
Chin Med Guidel
.
2020
;
18
(
02
):
17
8
.
4.
Left force Expert consensus on the selection of blood purification mode
.
China Blood Purif
.
2019
;
18
(
07
):
442
72
.
5.
Wang
F
,
Yang
C
,
Long
J
,
Zhao
X
,
Tang
W
,
Zhang
D
, et al
.
Executive summary for the 2015 annual data report of the China Kidney Disease Network (CK NET)
.
Kidney Int
.
2019
;
95
(
3
):
501
5
.
6.
Yanqing
J
.
Chen jing interpretation of the key points of the expert consensus on clinical practice of safe injection in hemodialysis
.
Shanghai Nurs
.
2022
;
22
(
10
):
6
10
.
7.
Wang
Y
,
Ye
C
,
Jin
Q
.
Expert Consensus on Vascular Pathways for Hemodialysis in China (1st Edition)
.
China Blood Purif
.
2014
;
13
(
08
):
549
58
.
8.
Shiu
YT
,
Rotmans
JI
,
Geelhoed
WJ
.
Arteriovenous complications for hematology: now to better modulate the pathophysiological vacuum response to optimize vacuum access durability
.
Am J Phys Ren Phys
.
2019
;
316
(
5
):
F794
806
.
9.
Krzanowski
M
,
Janda
K
,
Chowaniec
E
,
Kuśnierz-Cabala
B
,
Sułowicz
W
.
[Types of hemodialysis vascular access in patients on renal replacement therapy and its complications during a one year observation period]
.
Przegl Lek
.
2011
;
68
(
7
):
343
7
.
10.
Quincer
KB
,
Friedman
T
.
Declosing the thrombosed access
.
Tech Vasc Interv Radio
.
2017
;
20
(
1
):
38
47
.
11.
Rana
S
,
Tran
T
,
Luo
W
,
Phung
D
,
Kennedy
RL
,
Venkatesh
S
.
Predictingunplannedreadmissionaftermyocardial infarction from routinely collected administrative hospital data
.
Aust Health Rev
.
2014
;
38
(
4
):
377
82
.
12.
Xiaoyan
W
,
Zhang
Q
,
Wang
M
.
Construction of a risk warning model for autologous arteriovenous fistula thrombosis in long-term hemodialysis patients
.
Shanghai Nurs
.
2023
;
23
(
10
):
29
32
.
13.
Kong
M
,
Ruohe
L
,
Wang
S
, et al
.
Risk factors for acute thrombosis of arteriovenous fistula in maintenance hemodialysis patients and the application value of nomograms
.
Chin J Integrated Traditional Chin West Med Nephrol
.
2022
;
23
(
05
):
432
5
.
14.
Wu
A
,
Huang
X
.
Progress in the application of ultrasound in autologous arteriovenous fistula thrombosis
.
Anhui Med J
.
2018
;
39
(
12
):
1532
4
.
15.
Jiang Huili Development of a self-management scale for autologous arteriovenous fistula in maintenance hemodialysis patients
.
Shandong University
,
2019
.
16.
Nattino
G
,
Finazzi
S
,
Bertolini
G
.
A new calibration test and a reappraisal of the calibration belt for the assessment of prediction models based on dichotomous outcomes
.
Stat Med
.
2014
;
33
(
14
):
2390
407
.
17.
Gerds
TA
,
van de Wiel
MA
.
Confidence scores for prediction models
.
Biom J
.
2011
;
53
(
2
):
259
74
.
18.
Steyerberg
EW
,
Vickers
AJ
,
Cook
NR
,
Gerds
T
,
Gonen
M
,
Obuchowski
N
, et al
.
Assessing the performance of prediction models: a framework for traditional and novel measures
.
Epidemiology
.
2010
;
21
(
1
):
128
38
.
19.
Ma
P
,
Wu
Y
,
Huang
F
.
Factors influencing late stage dysfunction of arteriovenous fistula in hemodialysis patients and their predictive efficacy
.
Shandong Med J
.
2021
;
61
(
12
):
81
4
.
20.
Cheung
AK
,
Imrey
PB
,
Alpers
CE
,
Robbin
ML
,
Radeva
M
,
Larive
B
, et al
.
Intimal hyperplasia, stenosis, and arteriovenous fistula maturation failure in the hemodialysis fistula maturation study
.
J Am Soc Nephrol
.
2017
;
28
(
10
):
3005
13
.
21.
Zhang
Y
,
Yan
M
,
Peng
Y
.
Meta analysis of risk factors for thrombosis in autologous arteriovenous fistula
.
Chin J Blood Purif
.
2021
;
20
(
02
):
126
9
.
22.
Huan-Sheng
C
,
Yeong-Chang
C
,
Ming-Hsing
H
,
Fan-Lieh
T
,
Chu-Cheng
L
,
Tsai-Kun
W
, et al
.
Application of bioimpedance spectroscopy in Asian Dialysis patients (ABISAD-III): a randomized controlled trial for clinical outcomes
.
Int Urol Nephrol
.
2016
;
48
(
11
):
1897
1909
.
23.
Takashima T
,
Matsumoto K
,
Takeshita
C
.
Restoration of autologous arteriovenous fistula by removal of the occluded short venous part and venovenous end-to-end anastomosis in a hemodialysis patient
.
Ann Vasc Surg
.
2018
;
52
:
313
.
24.
Zhang
Y
,
Peng
Y
,
Congshan
P
.
Research progress on risk factors and prevention strategies for autologous arteriovenous fistula thrombosis
.
Nurs Res
.
2021
;
35
(
15
):
2698
701
.
25.
Miaomiao
L
,
Bin
Z
,
Gao
J
.
Self-care status and influencing factors of autologous arteriovenous fistula in hemodialysis patients
.
Nurs Res
.
2021
;
35
(
19
):
3534
7
.
26.
Deng
J
,
Wang
L
.
Research progress on the effect of different puncture methods on intimal hyperplasia of autologous arteriovenous fistula vessels
.
Nurs Res
.
2023
;
37
(
04
):
668
70
.
27.
Xiuming
Z
,
Niu
H
,
Liu
J
.
Analysis of influencing factors on intimal hyperplasia in patients with arteriovenous fistula undergoing buttonhole puncture during hemodialysis
.
Chin J Blood Purif
.
2023
;
22
(
09
):
710
4
.
28.
Moreira
CL
,
Castro
A
,
Silva
F
,
Almeida
P
,
de Matos
AN
,
Sousa
CN
, et al
.
Stenosis and thrombosis-unveiled complications of buttonhole cannulation
.
Hemodial Int
.
2019
;
23
(
3
):
E90
2
.
29.
Qin
HY
,
Jia
P
,
Liu
H
.
Nursing strategies for patients with chronic renal failure undergoing maintenance hemodialysis treatment by arteriovenous fistula
.
Iran J Public Health
.
2016
;
45
(
10
):
1270
5
.
30.
Kong
X
,
Xiao
D
,
Xu
J
.
The relationship between plasma ADAMTS-13 changes and arteriovenous fistula thrombosis in uremic hemodialysis patients
.
Zhejiang J Integrated Traditional Chin West Med
.
2021
;
31
(
07
):
621
5
.
31.
Zhong
X
,
Yang
F
,
Zhong
X
.
Study on the relationship between CD62P, CD63, average platelet volume, and arteriovenous fistula thrombosis
.
Chin Foreign Med J
.
2021
;
40
(
29
):
31
4
.
32.
Peralta
R
,
Garbelli
M
,
Bellocchio
F
,
Ponce
P
,
Stuard
S
,
Lodigiani
M
, et al
.
Development and validation of a machine learning model predicting arteriovenous fistula failure in a large network of dialysis clinics
.
Int J Environ Res Public Health
.
2021
;
18
(
23
):
12355
.
You do not currently have access to this content.