Scholarlink

<p>Acute kidney injury (AKI) is a common hospital complication with substantial morbidity and mortality. Deep learning models for AKI prediction show strong development-cohort performance, but single-point evaluation fails to capture behaviour under continuous monitoring. We conducted a multi-centre retrospective study using electronic health records from three cohorts (<i>n</i> = 157,323 admissions): National Health Insurance Service Ilsan Hospital (development), Chuncheon Sacred Heart Hospital, and MIMIC-IV (external validation). Three deep learning architectures (LSTM-Attention, Masked CNN, ITE-Transformer) and two baselines (XGBoost, logistic regression) were developed across 0-, 48-, and 72-h horizons, with an online simulation framework generating predictions at 12-h intervals before onset. Deep learning substantially outperformed baselines externally (AUROC 0.956–0.963 vs. 0.630–0.686). Online simulation revealed that 0-h models exhibited “clinical faithfulness”—consistent AUROC improvement as onset approached (Mann–Kendall significant in 15/15 combinations)—whereas longer horizons showed unstable trajectories. Notably, the highest single-point AUROC model (Masked CNN, 0.961) had the worst deployment profile (NNE 17.6–564), while ITE-Transformer (AUROC 0.924) achieved the most favourable alert burden (NNE 1.5–2.4). Deployment-oriented evaluation should complement conventional metrics for continuous monitoring models.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep learning models for acute kidney injury prediction: multi-center external validation and evaluation under simulated continuous monitoring conditions

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月8日

查看全文
  • Kyung Hyun Lee,
  • Donghwee Yoon,
  • Hyunsun Lim,
  • Ki-Byung Lee,
  • Yong Kyu Lee

摘要

Acute kidney injury (AKI) is a common hospital complication with substantial morbidity and mortality. Deep learning models for AKI prediction show strong development-cohort performance, but single-point evaluation fails to capture behaviour under continuous monitoring. We conducted a multi-centre retrospective study using electronic health records from three cohorts (n = 157,323 admissions): National Health Insurance Service Ilsan Hospital (development), Chuncheon Sacred Heart Hospital, and MIMIC-IV (external validation). Three deep learning architectures (LSTM-Attention, Masked CNN, ITE-Transformer) and two baselines (XGBoost, logistic regression) were developed across 0-, 48-, and 72-h horizons, with an online simulation framework generating predictions at 12-h intervals before onset. Deep learning substantially outperformed baselines externally (AUROC 0.956–0.963 vs. 0.630–0.686). Online simulation revealed that 0-h models exhibited “clinical faithfulness”—consistent AUROC improvement as onset approached (Mann–Kendall significant in 15/15 combinations)—whereas longer horizons showed unstable trajectories. Notably, the highest single-point AUROC model (Masked CNN, 0.961) had the worst deployment profile (NNE 17.6–564), while ITE-Transformer (AUROC 0.924) achieved the most favourable alert burden (NNE 1.5–2.4). Deployment-oriented evaluation should complement conventional metrics for continuous monitoring models.