使用深度神经网络方法预测血液透析患者中SARS-CoV-2感染
Lihao Xiao1, Hanjie Zhang2, Juntao Duan1
1Department of Statistics and Applied Probability, University of California, Santa Barbara, CA, USA.
Scientific reports
|October 9, 2024
概括
深度学习模型在化期间准确地预测透析患者的COVID-19. 这些模型,包括长期短期记忆 (LSTM) 和卷积神经网络 (CNN),优于早期感染检测和改善患者结果的传统方法.
科学领域:
- 传染性疾病 传染性疾病
- 医疗保健中的人工智能
- 腎臟病學 (nephrology) 是一種醫學專業.
背景情况:
- 透析患者面临更高的COVID-19发病率和死亡率风险.
- 早期识别SARS-CoV-2感染对于在透析中心实施控制措施至关重要.
- 现有的预测模型通常需要复杂的特征工程,并且在性能上显示出局限性.
研究的目的:
- 开发和评估深度学习模型,用于预测严重急性呼吸系统综合征冠状病毒2 (SARS-CoV-2) 感染在潜伏期内透析患者.
- 将深度学习模型的预测精度与传统机器学习方法进行比较.
- 在这个弱势群体中确定早期COVID-19诊断的关键预测特征.
主要方法:
- 收集了各种数据:人口统计,临床,治疗,实验室,疫苗接种,社会经济状况和COVID-19监测.
- 开发和实施深度学习模型,特别是循环神经网络 (RNN),卷积神经网络 (CNN) 和长短期记忆 (LSTM).
- 将深度学习模型与逻辑回归,支持矢量机 (SVM) 和XGBoost等传统方法进行比较,重点关注准确性和特征工程要求.
主要成果:
- 与传统模型相比,深度学习模型,特别是LSTM和CNN在预测SARS-CoV-2感染方面表现出卓越的准确性.
- LSTM模型实现了曲线下的面积 (AUC) 超过0.80,达到0.91,显著超过XGBoost.
- 在20%的虚假阳性率下,LSTM和CNN分别发现了66%和64%的阳性病例,而XGBoost则为42%.
结论:
- 深度神经网络,特别是LSTM和CNN,提供了一个更准确,更有效的方法来预测COVID-19在浸泡期间透析患者.
- 深度学习模型需要最小的特征工程,简化其实现.
- 通过这些先进模型的早期检测可以导致及时的干预,可能减少透析患者的严重后果.
相关概念视频
01:27Dialysis
274
Renal failure occurs when the kidneys lose their ability to filter waste products from the blood effectively. It can be classified into two types: acute renal failure (ARF) and chronic renal failure (CRF).
Acute kidney injury develops suddenly and can be caused by pre-renal causes (e.g., hypovolemia, shock), intrinsic renal causes (e.g., acute tubular necrosis), or post-renal causes (e.g., urinary obstruction). In contrast, chronic renal failure progresses gradually over time and is often...
Acute kidney injury develops suddenly and can be caused by pre-renal causes (e.g., hypovolemia, shock), intrinsic renal causes (e.g., acute tubular necrosis), or post-renal causes (e.g., urinary obstruction). In contrast, chronic renal failure progresses gradually over time and is often...
274
01:25Hemodialysis III: Nursing Management
2
The nursing management of a patient undergoing hemodialysis includes several critical steps, starting with a thorough assessment before the procedure.Before the Hemodialysis ProcedureFirst, record the patient's vital signs—blood pressure, heart rate, respiratory rate, and temperature—to establish a baseline. This baseline is essential for detecting conditions such as hypotension that could impact the patient's response to dialysis. Document the patient's pre-dialysis weight, as this...
2
01:24Hemodialysis II: Procedure and Complications
2
DialyzersA hemodialysis (HD) dialyzer is a plastic cartridge containing thousands of parallel hollow fibers, which serve as semipermeable membranes. These fibers are typically made from cellulose-based or other synthetic materials. During HD, blood is pumped into the top of the cartridge and distributed among these fibers. Simultaneously, dialysis fluid, known as dialysate, is introduced into the bottom of the cartridge, bathing the outside of the fibers. Across the semipermeable membrane,...
2