机器学习模型预测复杂头颈部手术的住院时间和出院去向。
Machine learning models to predict length of stay and discharge destination in complex head and neck surgery.
机构信息
Department of Otolaryngology-Head and Neck Surgery, University of California, Irvine, California, USA.
Department of Biomedical Engineering, University of California, Irvine, California, USA.
出版信息
Head Neck. 2021 Mar;43(3):788-797. doi: 10.1002/hed.26528. Epub 2020 Nov 3.
BACKGROUND
This study develops machine learning (ML) algorithms that use preoperative-only features to predict discharge-to-nonhome-facility (DNHF) and length-of-stay (LOS) following complex head and neck surgeries.
METHODS
Patients undergoing laryngectomy or composite tissue excision followed by free tissue transfer were extracted from the 2005 to 2017 NSQIP database.
RESULTS
Among the 2786 included patients, DNHF and mean LOS were 421 (15.1%) and 11.7 ± 8.8 days. Four classification models for predicting DNHF with high specificities (range, 0.80-0.84) were developed. The generalized linear and gradient boosting machine models performed best with receiver operating characteristic (ROC), accuracy, and negative predictive value (NPV) of 0.72-0.73, 0.75-0.76, and 0.88-0.89. Four regression models for predicting LOS in days were developed, where all performed similarly with mean absolute error and root mean-squared errors of 3.95-3.98 and 5.14-5.16. Both models were developed into an encrypted web-based interface: https://uci-ent.shinyapps.io/head-neck/.
CONCLUSION
Novel and proof-of-concept ML models to predict DNHF and LOS were developed and published as web-based interfaces.
背景
本研究开发了机器学习 (ML) 算法，这些算法仅使用术前特征来预测复杂头颈部手术后的非家庭设施出院 (DNHF) 和住院时间 (LOS)。
方法
从 2005 年至 2017 年的 NSQIP 数据库中提取行喉切除术或复合组织切除后行游离组织转移的患者。
结果
在 2786 名纳入患者中，DNHF 和平均 LOS 分别为 421（15.1%）和 11.7±8.8 天。开发了四个用于预测 DNHF 的分类模型，其特异性均较高（范围为 0.80-0.84）。广义线性和梯度提升机模型的表现最佳，其接收者操作特征（ROC）、准确性和阴性预测值（NPV）分别为 0.72-0.73、0.75-0.76 和 0.88-0.89。开发了四个用于预测 LOS 的回归模型，所有模型的平均绝对误差和均方根误差均相似，分别为 3.95-3.98 和 5.14-5.16。这两个模型都被开发成一个加密的基于网络的界面：https://uci-ent.shinyapps.io/head-neck/。
结论
开发并发布了用于预测 DNHF 和 LOS 的新型概念验证 ML 模型，作为基于网络的界面。
Zotero 插件