Machine learning prediction of 1-year thrombosis risk in membranous nephropathy: integration of renal pathology and early longitudinal trajectories
Abstract
IntroductionPatients with membranous nephropathy (MN) have an increased risk of thrombotic events. Existing prediction approaches primarily use clinical and laboratory measurements obtained at a single time point and rarely incorporate renal pathology or early longitudinal changes. This study integrated multiple types of information to predict the occurrence of thrombosis from 4 weeks after discharge to 1 year after being diagnosed with MN.MethodThis single-center retrospective cohort study included 1,070 patients with MN. Patient characteristics, laboratory findings, renal pathological features, and follow-up data were collected. Patients were randomly divided into training and validation sets at an 8:2 ratio. Latent class trajectory modeling identified longitudinal classes from measurements obtained during the index hospitalization for MN diagnosis and at 2 and 4 weeks after discharge. Predictors were selected using LASSO regression. Seven machine learning algorithms were used, including logistic boosting, adaptive boosting, generalized linear model, weighted k-nearest neighbors (kknn), naive Bayes, random forest, and support vector machine.ResultThrombotic events occurred in 150 patients (14.0%). LASSO selected 10 predictors: hypertension history, stroke or myocardial infarction history, erythrocyte sedimentation rate, D-dimer, cystatin C, estimated glomerular filtration rate, 24-hour urinary protein excretion, interstitial fibrosis and tubular atrophy score, neutrophil trajectory class, and serum albumin trajectory class. Among all models, kknn showed relatively balanced performance between the training and validation sets. The full kknn model achieved a validation AUC of 0.810 (95% CI: 0.725–0.896), sensitivity of 0.800, specificity of 0.663, and F1 score of 0.414.ConclusionIntegrating clinical, laboratory, renal pathological, and early longitudinal trajectory information enabled prediction of 1-year thrombotic events in MN. The kknn model may support early risk stratification and individualized antithrombotic strategy.
Related
- Multimodal longitudinal prediction of alcohol-use trajectories in adolescents and young adults: Social context, real-life social affective benefit, and fronto-striatal involvement
- High definition longitudinal spatial atlas of psoriasis reveals SPRR2F+ keratinocytes and distinct tissue-resolution trajectories under IL-17 and IL-23 inhibition
- Cerebral Artery Stenosis, Glymphatic Dysfunction, and Cognitive Trajectories: A Longitudinal Cohort Study of Community-Dwelling Older Adults.
- Longitudinal fMRI reveals altered developmental trajectories of functional network organisation associated with adolescent cannabis use
- Longitudinal trajectories and persistence of frequent emergency department use: A two-year individual-level cohort study
BibTeX
@article{shi2026machine,
title = {{Machine learning prediction of 1-year thrombosis risk in membranous nephropathy: integration of renal pathology and early longitudinal trajectories}},
author = {Yueyi Shi and Zheng Lin and Xianfa Li and Yue Sun and Riyang Lin and Hongliang Fang and Jiazhen Yin and Caifeng Zhu and Ziyang Bao},
journal = {Frontiers in Immunology},
year = {2026},
month = nov,
doi = {10.3389/fimmu.2026.1987864},
url = {https://www.frontiersin.org/articles/10.3389/fimmu.2026.1987864},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Machine learning prediction of 1-year thrombosis risk in membranous nephropathy: integration of renal pathology and early longitudinal trajectories
AU - Yueyi Shi
AU - Zheng Lin
AU - Xianfa Li
AU - Yue Sun
AU - Riyang Lin
AU - Hongliang Fang
AU - Jiazhen Yin
AU - Caifeng Zhu
AU - Ziyang Bao
PY - 2026
DA - 2026/11/05
JO - Frontiers in Immunology
DO - 10.3389/fimmu.2026.1987864
UR - https://www.frontiersin.org/articles/10.3389/fimmu.2026.1987864
AB - IntroductionPatients with membranous nephropathy (MN) have an increased risk of thrombotic events. Existing prediction approaches primarily use clinical and laboratory measurements obtained at a single time point and rarely incorporate renal pathology or early longitudinal changes. This study integrated multiple types of information to predict the occurrence of thrombosis from 4 weeks after discharge to 1 year after being diagnosed with MN.MethodThis single-center retrospective cohort study included 1,070 patients with MN. Patient characteristics, laboratory findings, renal pathological features, and follow-up data were collected. Patients were randomly divided into training and validation sets at an 8:2 ratio. Latent class trajectory modeling identified longitudinal classes from measurements obtained during the index hospitalization for MN diagnosis and at 2 and 4 weeks after discharge. Predictors were selected using LASSO regression. Seven machine learning algorithms were used, including logistic boosting, adaptive boosting, generalized linear model, weighted k-nearest neighbors (kknn), naive Bayes, random forest, and support vector machine.ResultThrombotic events occurred in 150 patients (14.0%). LASSO selected 10 predictors: hypertension history, stroke or myocardial infarction history, erythrocyte sedimentation rate, D-dimer, cystatin C, estimated glomerular filtration rate, 24-hour urinary protein excretion, interstitial fibrosis and tubular atrophy score, neutrophil trajectory class, and serum albumin trajectory class. Among all models, kknn showed relatively balanced performance between the training and validation sets. The full kknn model achieved a validation AUC of 0.810 (95% CI: 0.725–0.896), sensitivity of 0.800, specificity of 0.663, and F1 score of 0.414.ConclusionIntegrating clinical, laboratory, renal pathological, and early longitudinal trajectory information enabled prediction of 1-year thrombotic events in MN. The kknn model may support early risk stratification and individualized antithrombotic strategy.
SN - 1664-3224
ER -