SingHealth Polyclinics, SingHealth, 167, Jalan Bukit Merah, Connection One, Tower 5, #15-10, Singapore, P.O. 150167, Singapore.
Family Medicine Academic Clinical Programme, SingHealth-Duke NUS Academic Medical Centre, Singapore, Singapore.
BMC Med Inform Decis Mak. 2021 Jul 1;21(1):207. doi: 10.1186/s12911-021-01566-y.
Clinical risk prediction models (CRPMs) use patient characteristics to estimate the probability of having or developing a particular disease and/or outcome. While CRPMs are gaining in popularity, they have yet to be widely adopted in clinical practice. The lack of explainability and interpretability has limited their utility. Explainability is the extent of which a model's prediction process can be described. Interpretability is the degree to which a user can understand the predictions made by a model.
The study aimed to demonstrate utility of patient similarity analytics in developing an explainable and interpretable CRPM. Data was extracted from the electronic medical records of patients with type-2 diabetes mellitus, hypertension and dyslipidaemia in a Singapore public primary care clinic. We used modified K-nearest neighbour which incorporated expert input, to develop a patient similarity model on this real-world training dataset (n = 7,041) and validated it on a testing dataset (n = 3,018). The results were compared using logistic regression, random forest (RF) and support vector machine (SVM) models from the same dataset. The patient similarity model was then implemented in a prototype system to demonstrate the identification, explainability and interpretability of similar patients and the prediction process.
The patient similarity model (AUROC = 0.718) was comparable to the logistic regression (AUROC = 0.695), RF (AUROC = 0.764) and SVM models (AUROC = 0.766). We packaged the patient similarity model in a prototype web application. A proof of concept demonstrated how the application provided both quantitative and qualitative information, in the form of patient narratives. This information was used to better inform and influence clinical decision-making, such as getting a patient to agree to start insulin therapy.
Patient similarity analytics is a feasible approach to develop an explainable and interpretable CRPM. While the approach is generalizable, it can be used to develop locally relevant information, based on the database it searches. Ultimately, such an approach can generate a more informative CRPMs which can be deployed as part of clinical decision support tools to better facilitate shared decision-making in clinical practice.
临床风险预测模型（CRPMs）使用患者特征来估计患有或发展特定疾病和/或结局的概率。虽然 CRPMs 越来越受欢迎，但它们尚未在临床实践中广泛采用。缺乏可解释性和可解释性限制了它们的实用性。可解释性是模型预测过程可以描述的程度。可解释性是用户理解模型做出的预测的程度。
本研究旨在展示患者相似性分析在开发可解释和可解释的 CRPM 中的实用性。从新加坡一家公立初级保健诊所的 2 型糖尿病、高血压和血脂异常患者的电子病历中提取数据。我们使用改进的 K-最近邻法，结合专家输入，在这个真实的训练数据集（n=7041）上开发患者相似性模型，并在测试数据集（n=3018）上验证。使用来自同一数据集的逻辑回归、随机森林（RF）和支持向量机（SVM）模型比较结果。然后，将患者相似性模型实现到原型系统中，以演示相似患者的识别、可解释性和可解释性以及预测过程。
患者相似性模型（AUROC=0.718）与逻辑回归（AUROC=0.695）、RF（AUROC=0.764）和 SVM 模型（AUROC=0.766）相当。我们将患者相似性模型打包到一个原型 Web 应用程序中。一个概念验证演示了应用程序如何以患者叙述的形式提供定量和定性信息。该信息用于更好地告知和影响临床决策，例如让患者同意开始胰岛素治疗。
患者相似性分析是开发可解释和可解释的 CRPM 的可行方法。虽然该方法具有通用性，但它可以根据搜索的数据库来开发本地相关信息。最终，这种方法可以生成更具信息量的 CRPMs，作为临床决策支持工具的一部分部署，以更好地促进临床实践中的共同决策。
