Machine learning can accurately predict pre-admission baseline hemoglobin and creatinine in intensive care patients.,npj Digital Medicine

当前位置： X-MOL 学术 › npj Digit. Med. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Machine learning can accurately predict pre-admission baseline hemoglobin and creatinine in intensive care patients.
npj Digital Medicine ( IF 12.4 ) Pub Date : 2019-11-29 , DOI: 10.1038/s41746-019-0192-z
Antonin Dauvin _{1,

2} , Carolina Donado ₃ , Patrik Bachtiger ₄ , Ke-Chun Huang ₁ , Christopher Martin Sauer _{1,

4} , Daniele Ramazzotti ₅ , Matteo Bonvini ₆ , Leo Anthony Celi _{1,

7} , Molly J Douglas ₈

Affiliation

Patients admitted to the intensive care unit frequently have anemia and impaired renal function, but often lack historical blood results to contextualize the acuteness of these findings. Using data available within two hours of ICU admission, we developed machine learning models that accurately (AUC 0.86-0.89) classify an individual patient's baseline hemoglobin and creatinine levels. Compared to assuming the baseline to be the same as the admission lab value, machine learning performed significantly better at classifying acute kidney injury regardless of initial creatinine value, and significantly better at predicting baseline hemoglobin value in patients with admission hemoglobin of <10 g/dl.

中文翻译：

机器学习可以准确预测重症监护患者入院前的基线血红蛋白和肌酐。

重症监护病房的患者经常患有贫血和肾功能受损，但通常缺乏历史性血液检查结果来说明这些发现的严重性。利用ICU入院后两个小时内的可用数据，我们开发了机器学习模型，该模型可以准确地（AUC 0.86-0.89）对单个患者的基线血红蛋白和肌酐水平进行分类。与假设基线与入院实验室值相同相比，无论初始肌酐值如何，机器学习在对急性肾损伤进行分类中均表现出明显更好的效果，并且在入院血红蛋白<10 g / dl的患者中，机器学习在预测基线血红蛋白值方面显着更好。

更新日期：2019-11-30

点击分享查看原文

点击收藏

公开下载

阅读更多本刊最新论文