Predicting Chronic Wound Healing Time Using Machine Learning
Predicting Chronic Wound Healing Time Using Machine Learning
复制标题
DOI：
10.1089/wound.2021.0073
复制
发表时间：
2022-03-24
影响因子：
4.9
通讯作者：
Hayes D
中科院分区：
文献类型：
--
作者：
Berezo M;Budman J;Deutscher D;Hess CT;Smith K;Hayes D
在美国，慢性伤口已经上升到流行病的程度，并且可能对患者造成情感、身体和经济损失。通过利用电子健康记录（EHR）中的数据，机器学习模型提供了一个机会，可以帮助更早地识别处于不愈合或异常长时间后愈合风险的伤口，这可能会改善治疗决策和患者结局。本研究中的机器学习模型用于预测慢性伤口愈合时间。使用EHR数据开发了机器学习模型，以预测患者在治疗开始后4周、8周和12周内伤口无法愈合的风险。这些模型是在1，220，576个伤口的三个数据集上训练的，包括描述患者人口统计学、合并症和伤口特征的187个协变量。使用受试者工作特征曲线下面积（AUC）评估模型的准确性。Shapley加法解释（SHAP）用于分析变量在预测中的重要性，并增强临床解释。4周、8周和12周梯度提升决策树模型分别实现了0.854、0.855和0.853的AUC。治疗天数、伤口深度和位置以及伤口面积是伤口不愈合风险的最有影响力的预测因素。机器学习模型可以使用EHR数据准确预测慢性伤口愈合时间。SHAP值可以深入了解患者特定变量如何影响预测。识别慢性伤口无愈合或愈合缓慢风险患者的准确模型是可行的，可以纳入常规伤口护理。
Chronic wounds have risen to epidemic proportions in the United States and can have an emotional, physical, and financial toll on patients. By leveraging data within the electronic health record (EHR), machine learning models offer the opportunity to facilitate earlier identification of wounds at risk of not healing or healing after an abnormally long time, which may improve treatment decisions and patient outcomes. Machine learning models in this study were built to predict chronic wound healing time. Machine learning models were developed using EHR data to predict patients at risk of having wounds not heal within 4, 8, and 12 weeks from the start of treatment. The models were trained on three data sets of 1,220,576 wounds, including 187 covariates describing patient demographics, comorbidities, and wound characteristics. The area under the receiver operating characteristic curve (AUC) was used to assess the accuracy of the models. Shapley Additive Explanations (SHAP) were used to analyze variable importance in predictions and enhance clinical interpretations. The 4-, 8-, and 12-week gradient-boosted decision tree models achieved AUC's of 0.854, 0.855, and 0.853, respectively. Days in treatment, wound depth and location, and wound area were the most influential predictors of wounds at risk of not healing. Machine learning models can accurately predict chronic wound healing time using EHR data. SHAP values can give insight into how patient-specific variables influenced predictions. Accurate models identifying patients with chronic wounds at risk of non or slow healing are feasible and can be incorporated into routine wound care.
登录
查看更多内容
影响因子：
4.9
作者：
Fife, Caroline E.;Horn, Susan D.;Thomson, Brett
通讯作者：
Thomson, Brett
影响因子：
2.9
作者：
Jung, Kenneth;Covington, Scott;Shah, Nigam H.
通讯作者：
Shah, Nigam H.
影响因子：
3.7
作者：
Lin, Chunmei;Liu, Jinhao;Sun, Hu
通讯作者：
Sun, Hu
影响因子：
2.9
作者：
Ennis, William J.;Hoffman, Rachel A.;Gordon, Hanna M.
通讯作者：
Gordon, Hanna M.
影响因子：
2.1
作者：
Pollard, Tom J.;Johnson, Alistair E. W.;Mark, Roger G.
通讯作者：
Mark, Roger G.