An explainable machine learning framework for lung cancer hospital length of stay prediction.

An explainable machine learning framework for lung cancer hospital length of stay prediction.
复制标题

DOI:
10.1038/s41598-021-04608-7
复制
发表时间:
2022-01-12
期刊:
影响因子:
4.6
通讯作者:
Darwish O
Darwish O
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Alsinglawi B;Alshari O;Alorjani M;Mubin O;Alnajjar F;Novoa M;Darwish O

文献摘要

参考文献

被引文献

相似文献

这项工作使用机器学习 (ML) 模型介绍了肺癌患者的预测住院时间 (LOS) 框架。该框架建议使用电子医疗记录(EHR)来处理基于分类的方法的不平衡数据集。我们利用 MIMIC-III 数据集,利用有监督的 ML 方法来预测 ICU 住院期间肺癌住院患者的 LOS。随机森林(RF)模型优于其他模型,并在三个框架阶段取得了预测结果。通过临床意义特征的选择,过采样方法(SMOTE 和 ADASYN)获得了最高的 AUC 结果(98%,CI 95%:分别为 95.3-100% 和 100%)。过采样和欠采样的组合取得了第二高的 AUC 结果(98%,CI 95%:95.3-100%;CI 95%:95.3-100%;SMOTE-Tomek 和 SMOTE-ENN 分别为 97%;CI 95%:93.7-100%)。欠采样方法报告了两者(ENN 和 Tomek-Links)最不重要的 AUC 结果(50%,CI 95%:40.2–59.8%)。使用称为 SHAP 的 ML 可解释技术,我们通过 SMOTE 类平衡技术解释了预测模型 (RF) 的结果,以了解有助于使用 RF 模型预测肺癌 LOS 的最重要的临床特征。我们前景广阔的框架使我们能够在医院临床信息系统中采用机器学习技术来预测肺癌入住 ICU 的情况。
This work introduces a predictive Length of Stay (LOS) framework for lung cancer patients using machine learning (ML) models. The framework proposed to deal with imbalanced datasets for classification-based approaches using electronic healthcare records (EHR). We have utilized supervised ML methods to predict lung cancer inpatients LOS during ICU hospitalization using the MIMIC-III dataset. Random Forest (RF) Model outperformed other models and achieved predicted results during the three framework phases. With clinical significance features selection, over-sampling methods (SMOTE and ADASYN) achieved the highest AUC results (98% with CI 95%: 95.3–100%, and 100% respectively). The combination of Over-sampling and under-sampling achieved the second-highest AUC results (98%, with CI 95%: 95.3–100%, and 97%, CI 95%: 93.7–100% SMOTE-Tomek, and SMOTE-ENN respectively). Under-sampling methods reported the least important AUC results (50%, with CI 95%: 40.2–59.8%) for both (ENN and Tomek- Links). Using ML explainable technique called SHAP, we explained the outcome of the predictive model (RF) with SMOTE class balancing technique to understand the most significant clinical features that contributed to predicting lung cancer LOS with the RF model. Our promising framework allows us to employ ML techniques in-hospital clinical information systems to predict lung cancer admissions into ICU.
DOI: 10.1109/access.2019.2934166
发表时间: 2019-01-01
期刊: IEEE ACCESS
影响因子: 3.9
作者:
Li, Chunling;Chen, Longyi;Xu, Weifeng
通讯作者: Xu, Weifeng
DOI: 10.1038/sdata.2016.35
发表时间: 2016-05-24
期刊: Scientific data
影响因子: 9.8
作者:
Johnson AE;Pollard TJ;Shen L;Lehman LW;Feng M;Ghassemi M;Moody B;Szolovits P;Celi LA;Mark RG
通讯作者: Mark RG
DOI: 10.1097/sla.0000000000004040
发表时间: 2022-05-01
期刊: ANNALS OF SURGERY
影响因子: 9
作者:
Best, Till D.;Mercaldo, Sarah F.;Fintelmann, Florian J.
通讯作者: Fintelmann, Florian J.
DOI: 10.1093/neuros/nyy343
发表时间: 2019-09-01
期刊: NEUROSURGERY
影响因子: 4.8
作者:
Muhlestein, Whitney E.;Akagi, Dallin S.;Chambless, Lola B.
通讯作者: Chambless, Lola B.
DOI: 10.1186/s12873-015-0067-9
发表时间: 2015-01-01
影响因子: 2.5
作者:
Blom, Mathias C.;Erwander, Karin;Ivarsson, Kjell
通讯作者: Ivarsson, Kjell