Zhou Cong, Chase J Geoffrey, Knopp Jennifer, Sun Qianhui, Tawhai Merryn, Möller Knut, Heines Serge J, Bergmans Dennis C, Shaw Geoffrey M, Desaive Thomas
School of Civil Aviation, Northwestern Polytechnical University, China; Department of Mechanical Engineering, University of Canterbury, New Zealand.
Department of Mechanical Engineering, University of Canterbury, New Zealand.
Comput Methods Programs Biomed. 2021 Feb;199:105912. doi: 10.1016/j.cmpb.2020.105912. Epub 2020 Dec 22.
Mechanical ventilation (MV) is a core intensive care unit (ICU) therapy. Significant inter- and intra- patient variability in lung mechanics and condition makes managing MV difficult. Accurate prediction of patient-specific response to changes in MV settings would enable optimised, personalised, and more productive care, improving outcomes and reducing cost. This study develops a generalised digital clone model, or in-silico virtual patient, to accurately predict lung mechanics in response to changes in MV.
An identifiable, nonlinear hysteresis loop model (HLM) captures patient-specific lung dynamics identified from measured ventilator data. Identification and creation of the virtual patient model is fully automated using the hysteresis loop analysis (HLA) method to identify lung elastances from clinical data. Performance is evaluated using clinical data from 18 volume-control (VC) and 14 pressure-control (PC) ventilated patients who underwent step-wise recruitment maneuvers.
Patient-specific virtual patient models accurately predict lung response for changes in PEEP up to 12 cmHO for both volume and pressure control cohorts. R values for predicting peak inspiration pressure (PIP) and additional retained lung volume, V in VC, are R=0.86 and R=0.90 for 106 predictions over 18 patients. For 14 PC patients and 84 predictions, predicting peak inspiratory volume (PIV) and V yield R=0.86 and R=0.83. Absolute PIP, PIV and V errors are relatively small.
Overall results validate the accuracy and versatility of the virtual patient model for capturing and predicting nonlinear changes in patient-specific lung mechanics. Accurate response prediction enables mechanically and physiologically relevant virtual patients to guide personalised and optimised MV therapy.
机械通气（MV）是重症监护病房（ICU）的核心治疗手段。患者之间以及患者自身肺部力学和病情存在显著差异，这使得机械通气的管理变得困难。准确预测患者对机械通气设置变化的特异性反应，将有助于实现优化、个性化且更有效的治疗，改善治疗效果并降低成本。本研究开发了一种通用的数字克隆模型，即计算机模拟虚拟患者，以准确预测机械通气变化时的肺部力学情况。
一个可识别的非线性滞后环模型（HLM）可捕捉从测量得到的呼吸机数据中识别出的患者特异性肺动力学。使用滞后环分析（HLA）方法从临床数据中识别肺弹性，从而完全自动化地识别和创建虚拟患者模型。使用18例接受容量控制（VC）通气和14例接受压力控制（PC）通气且进行了逐步肺复张操作的患者的临床数据来评估模型性能。
针对容量控制组和压力控制组，患者特异性虚拟患者模型均可准确预测呼气末正压（PEEP）变化至12 cmH₂O时的肺部反应。对于18例患者的106次预测，预测吸气峰压（PIP）和容量控制中额外保留的肺容积V的R值分别为R = 0.86和R = 0.90。对于14例压力控制患者的84次预测，预测吸气峰容积（PIV）和V的R值分别为R = 0.86和R = 0.83。PIP、PIV和V的绝对误差相对较小。
总体结果验证了虚拟患者模型在捕捉和预测患者特异性肺力学非线性变化方面的准确性和通用性。准确的反应预测能够使具有机械和生理相关性的虚拟患者指导个性化和优化的机械通气治疗。
