Scholarlink

Background <p>Intraoperative hypotension (IOH) is a frequent and clinically important complication associated with adverse postoperative outcomes. Early prediction may facilitate timely intervention, although existing models have limitations in integrating multimodal physiological data and patient-specific characteristics.</p> Methods <p>We developed Hypotension Hybrid Forecast (HypoBridCast), a hybrid architecture integrating 1D Convolutional Layer (Conv1D) and Transformer (TF) modules. The model integrates intraoperative waveform data (arterial pressure, electrocardiogram, photoplethysmogram, and capnography) with preoperative clinical variables (including demographic characteristics, medical history, laboratory results, and surgical and anesthetic variables). Data from the VitalDB database (<i>n</i> = 3,369) were used for model development and internal evaluation, and an independent cohort from Zhongda Hospital (<i>n</i> = 437) was used for external evaluation. Model performance for predicting IOH (MAP ≤ 65&#xa0;mmHg for ≥ 1&#xa0;min) 5, 10, and 15&#xa0;min in advance was assessed using AUROC, AUPRC, and calibration metrics.</p> Results <p>HypoBridCast achieved strong discriminative performance across prediction horizons in both internal and external evaluations (e.g., internal 5-min AUROC 0.9442 [95% CI 0.9427–0.9456] and AUPRC 0.9387 [0.9376–0.9398]). Compared with Mono-ART models, performance was improved, whereas differences versus multi-channel waveform models were modest. The addition of preoperative variables provided limited and inconsistent gains across datasets. In contrast, performance gains over simple MAP-based baseline models were more pronounced. Calibration was acceptable overall, with some reduction observed in the external cohort, particularly at longer prediction horizons.</p> Conclusions <p>The proposed hybrid deep learning framework achieved strong performance for short-term prediction of intraoperative hypotension using routinely collected clinical data. Multimodal integration and preoperative variables provide incremental improvements. Further work is needed to improve generalizability and calibration before clinical deployment.</p> Trial registration <p>ChiCTR2500099041</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

Early prediction of intraoperative hypotension: development and validation of the HypoBridCast hybrid deep learning model

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月13日

查看全文
  • Youran Wang,
  • Xian Zeng,
  • Lingjue Chen,
  • Bin Li,
  • Kaiqiang Shen,
  • Jun Xu,
  • Jie Sun

摘要

Background

Intraoperative hypotension (IOH) is a frequent and clinically important complication associated with adverse postoperative outcomes. Early prediction may facilitate timely intervention, although existing models have limitations in integrating multimodal physiological data and patient-specific characteristics.

Methods

We developed Hypotension Hybrid Forecast (HypoBridCast), a hybrid architecture integrating 1D Convolutional Layer (Conv1D) and Transformer (TF) modules. The model integrates intraoperative waveform data (arterial pressure, electrocardiogram, photoplethysmogram, and capnography) with preoperative clinical variables (including demographic characteristics, medical history, laboratory results, and surgical and anesthetic variables). Data from the VitalDB database (n = 3,369) were used for model development and internal evaluation, and an independent cohort from Zhongda Hospital (n = 437) was used for external evaluation. Model performance for predicting IOH (MAP ≤ 65 mmHg for ≥ 1 min) 5, 10, and 15 min in advance was assessed using AUROC, AUPRC, and calibration metrics.

Results

HypoBridCast achieved strong discriminative performance across prediction horizons in both internal and external evaluations (e.g., internal 5-min AUROC 0.9442 [95% CI 0.9427–0.9456] and AUPRC 0.9387 [0.9376–0.9398]). Compared with Mono-ART models, performance was improved, whereas differences versus multi-channel waveform models were modest. The addition of preoperative variables provided limited and inconsistent gains across datasets. In contrast, performance gains over simple MAP-based baseline models were more pronounced. Calibration was acceptable overall, with some reduction observed in the external cohort, particularly at longer prediction horizons.

Conclusions

The proposed hybrid deep learning framework achieved strong performance for short-term prediction of intraoperative hypotension using routinely collected clinical data. Multimodal integration and preoperative variables provide incremental improvements. Further work is needed to improve generalizability and calibration before clinical deployment.

Trial registration

ChiCTR2500099041