PDF(Pubmed)
Abstract：
Secondary muscle weakness in critically ill patients like intensive care unit (ICU)-associated weakness is frequently noted in patients with prolonged mechanical ventilation and ICU stay. It can be a result of critical illness, myopathy, or neuropathy. Although ICU-acquired weakness (ICU-AW) has been known for a while, there is still no effective treatment for it. Therefore, prevention of ICU-AW becomes the utmost priority, and knowing the risk factors is crucial. Nevertheless, the pathophysiology and the attributing causes are complex for ICU-AW, and proper delineation and formulation of a preventive strategy from such vast, multifaceted data are challenging. Artificial intelligence has recently helped healthcare professionals understand and analyze such intricate data through deep machine learning. Hence, using such a strategy also helps in knowing the risk factors and their weight as contributors, applying them in formulating a preventive path for ICU-AW worth trials.
摘要：
重症患者的继发性肌肉无力，如重症监护病房（ICU）相关的无力，在长期机械通气和ICU住院的患者中经常注意到。这可能是严重疾病的结果，肌病,或者神经病。尽管ICU获得性虚弱（ICU-AW）已经知道了一段时间，仍然没有有效的治疗方法。因此,预防ICU-AW成为当务之急，了解风险因素至关重要。然而，ICU-AW的病理生理学和归因是复杂的，并从如此广泛的范围内适当划分和制定预防策略，多方面的数据具有挑战性。人工智能最近通过深度机器学习帮助医疗保健专业人员理解和分析这些复杂的数据。因此，使用这种策略还有助于了解风险因素及其作为贡献者的权重，将它们应用于制定ICU-AW值得试验的预防路径。
