利用透析前特征预测透析中低血压:基于深度学习的人工智能模型
研究纳入7所大学医院2007例患者共943220次血液透析 sessions,开发深度学习人工智能模型利用透析前特征预测透析中低血压(IDH),并与逻辑回归、随机森林和XGBoost三种机器学习模型比较。IDH发生在5.39%的透析 sessions 中。仅用单次 session 数据时各模型性能相似,但结合前三次 session 数据后深度学习模型预测性能提升并优于其他模型。
要点
- IDH发生在5.39%的血液透析 sessions 中。
- IDH sessions 的透析前血压更低、超滤目标率和透析间体重增长更高,且既往 session 中 IDH 发生更频繁。
- 结合前三次 session 数据后深度学习模型预测性能优于逻辑回归、随机森林和XGBoost。
核心结论
- 人工智能模型能准确预测IDH,可作为血液透析治疗的可靠工具。
研究设计与样本
- 研究使用7所大学医院2007例患者共943220次血液透析 session 的数据,开发基于深度学习的人工智能模型,并与逻辑回归、随机森林和XGBoost三种机器学习模型比较性能。
主要发现
- IDH发生在所有研究的血液透析 sessions 的5.39%中。
- IDH sessions 相比非IDH sessions 表现为透析前血压更低、超滤目标率更高、透析间体重增长更高,且既往 session 中 IDH 发生更频繁。
- 仅用单次 session 数据开发时,逻辑回归、随机森林、XGBoost和深度学习模型的 Matthews 相关系数和宏平均 F1 分数相似。
- 结合前三次 session 数据后,深度学习模型的预测性能提升并优于其他模型。
- IDH预测的常见排名最高特征为前一次 session 的平均收缩压、超滤目标率、透析前收缩压和前一次 session 的 IDH 经历。
关键数值与推荐
- 研究采用 Matthews 相关系数和宏平均 F1 分数评估阳性和阴性预测性能。
临床怎么用
- 原文未据此给出临床推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Intradialytic hypotension (IDH) is a serious complication of hemodialysis (HD) that is associated with increased risks of cardiovascular morbidity and mortality. However, its accurate prediction remains a clinical challenge. The aim of this study was to develop a deep learning-based artificial intelligence (AI) model to predict IDH using pre-dialysis features. METHODS: Data from 2007 patients with 943 220 HD sessions at seven university hospitals were used. The performance of the deep learning model was compared with three machine learning models (logistic regression, random forest and XGBoost). RESULTS: IDH occurred in 5.39% of all studied HD sessions. A lower pre-dialysis blood pressure (BP), and a higher ultrafiltration (UF) target rate and interdialytic weight gain in IDH sessions compared with non-IDH sessions, and the occurrence of IDH in previous sessions was more frequent among IDH sessions compared with non-IDH sessions. Matthews correlation coefficient and macro-averaged F1 score were used to evaluate both positive and negative prediction performances. Both values were similar in logistic regression, random forest, XGBoost and deep learning models, developed with data from a single session. When combining data from the previous three sessions, the prediction performance of the deep learning model improved and became superior to that of other models. The common top-ranked features for IDH prediction were mean systolic BP (SBP) during the previous session, UF target rate, pre-dialysis SBP, and IDH experience during the previous session. CONCLUSIONS: Our AI model predicts IDH accurately, suggesting it as a reliable tool for HD treatment.
引用
- Lee H, Moon SJ, Kim SW, et al. Prediction of intradialytic hypotension using pre-dialysis features-a deep learning-based artificial intelligence model. Nephrol Dial Transplant. 2023. PMID: 37019834. doi:10.1093/ndt/gfad064
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。