SCOPE: predicting future diagnoses in office visits using electronic health records.
SCOPE: predicting future diagnoses in office visits using electronic health records.
复制标题
DOI：
10.1038/s41598-023-38257-9
复制
发表时间：
2023-07-07
影响因子：
4.6
通讯作者：
Gevaert, Olivier
中科院分区：
文献类型：
--
作者：
Mukherjee, Pritam;Humbert-Droz, Marie;Chen, Jonathan H. H.;Gevaert, Olivier
我们提出了一个可解释和可扩展的模型，以预测可能的诊断，在遇到基于过去的诊断和实验室结果。该模型旨在帮助医生与电子健康记录（EHR）进行交互。为了实现这一目标，我们回顾性地收集了2008年1月至2016年12月期间斯坦福大学医疗保健中心2，701，522名患者的EHR数据，并对其进行了去识别。选择了一个基于人群的患者样本，包括524，198例多次遇到至少一种常见诊断代码的患者（44%男性，56%女性）。开发了一个校准模型，以预测ICD-10诊断代码在遇到的基础上，过去的诊断和实验室结果，使用基于二进制相关性的多标签建模策略。逻辑回归和随机森林作为基础分类器进行了测试，并测试了几个时间窗口，以汇总过去的诊断和实验室。将这种建模方法与基于递归神经网络的深度学习方法进行了比较。最好的模型使用随机森林作为基本分类器，并集成人口统计特征，诊断代码和实验室结果。校准了最佳模型，其性能在各种指标方面与现有方法相当或更好，包括583种疾病的中位AUROC为0.904（IQR [0.838，0.954]）。当预测患者首次出现疾病标签时，最佳模型的中位AUROC为0.796（IQR [0.737，0.868]）。我们的建模方法与测试的深度学习方法相比表现出色，在AUROC方面优于它（p < 0.001），但在AUPRC方面表现不佳（p < 0.001）。对模型的解释表明，该模型使用了有意义的特征，并突出了诊断和实验室结果之间许多有趣的关联。我们的结论是，多标签模型与基于RNN的深度学习模型进行了融合，同时提供了简单性和潜在的上级可解释性。虽然该模型是根据从单一机构获得的数据进行训练和验证的，但其简单性、可解释性和性能使其成为一个有希望的部署候选者。
We propose an interpretable and scalable model to predict likely diagnoses at an encounter based on past diagnoses and lab results. This model is intended to aid physicians in their interaction with the electronic health records (EHR). To accomplish this, we retrospectively collected and de-identified EHR data of 2,701,522 patients at Stanford Healthcare over a time period from January 2008 to December 2016. A population-based sample of patients comprising 524,198 individuals (44% M, 56% F) with multiple encounters with at least one frequently occurring diagnosis codes were chosen. A calibrated model was developed to predict ICD-10 diagnosis codes at an encounter based on the past diagnoses and lab results, using a binary relevance based multi-label modeling strategy. Logistic regression and random forests were tested as the base classifier, and several time windows were tested for aggregating the past diagnoses and labs. This modeling approach was compared to a recurrent neural network based deep learning method. The best model used random forest as the base classifier and integrated demographic features, diagnosis codes, and lab results. The best model was calibrated and its performance was comparable or better than existing methods in terms of various metrics, including a median AUROC of 0.904 (IQR [0.838, 0.954]) over 583 diseases. When predicting the first occurrence of a disease label for a patient, the median AUROC with the best model was 0.796 (IQR [0.737, 0.868]). Our modeling approach performed comparably as the tested deep learning method, outperforming it in terms of AUROC (p < 0.001) but underperforming in terms of AUPRC (p < 0.001). Interpreting the model showed that the model uses meaningful features and highlights many interesting associations among diagnoses and lab results. We conclude that the multi-label model performs comparably with RNN based deep learning model while offering simplicity and potentially superior interpretability. While the model was trained and validated on data obtained from a single institution, its simplicity, interpretability and performance makes it a promising candidate for deployment.
登录
查看更多内容
DOI：
10.1111/j.1468-2850.2009.01164.x
发表时间：
2009-06
期刊：
Clinical psychology : a publication of the Division of Clinical Psychology of the American Psychological Association
影响因子：
--
作者：
Harvey AG;Talbot LS;Gershon A
通讯作者：
Gershon A
影响因子：
64.8
作者：
Harris CR;Millman KJ;van der Walt SJ;Gommers R;Virtanen P;Cournapeau D;Wieser E;Taylor J;Berg S;Smith NJ;Kern R;Picus M;Hoyer S;van Kerkwijk MH;Brett M;Haldane A;Del Río JF;Wiebe M;Peterson P;Gérard-Marchant P;Sheppard K;Reddy T;Weckesser W;Abbasi H;Gohlke C;Oliphant TE
通讯作者：
Oliphant TE
影响因子：
15.2
作者：
Hilton, C. Beau;Milinovich, Alex;Nazha, Aziz
通讯作者：
Nazha, Aziz
影响因子：
4.4
作者：
Arndt, Brian G.;Beasley, John W.;Gilchrist, Valerie J.
通讯作者：
Gilchrist, Valerie J.
影响因子：
1.7
作者：
CHAKRAVARTI, N
通讯作者：
CHAKRAVARTI, N