Shao Huiling, Chan Wing Chi Lawrence, Du Heng, Chen Xiangyan Fiona, Ma Qilin, Shao Zhiyu
Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong.
Department of Neurology, The First Affiliated Hospital of Xiamen University, Xiamen, China.
Digit Health. 2023 Jan 3;9:20552076221149528. doi: 10.1177/20552076221149528. eCollection 2023 Jan-Dec.
Thrombolysis is the first-line treatment for patients with acute ischemic stroke. Previous studies leveraged machine learning to assist neurologists in selecting patients who could benefit the most from thrombolysis. However, when designing the algorithm, most of the previous algorithms traded interpretability for predictive power, making the algorithms hard to be trusted by neurologists and be used in real clinical practice.
Our proposed algorithm is an advanced version of classical k-nearest neighbors classification algorithm (KNN). We achieved high interpretability by changing the isotropy in feature space of classical KNN. We leveraged a cohort of patients to prove that our algorithm maintains the interpretability of previous models while in the meantime improving the predictive power when compared with the existing algorithms. The predictive powers of models were assessed by area under the receiver operating characteristic curve (AUC).
In terms of interpretability, only onset time, diabetes, and baseline National Institutes of Health Stroke Scale (NIHSS) were statistically significant and their contributions to the final prediction were forced to be proportional to their feature importance values by the rescaling formula we defined. In terms of predictive power, our advanced KNN (AUC 0.88) outperformed the classical KNN (AUC 0.75, ).
Our preliminary results show that the advanced KNN achieved high AUC and identified consistent significant clinical features as previous clinical trials/observational studies did. This model shows the potential to assist in thrombolysis patient selection for improving the successful rate of thrombolysis.
溶栓是急性缺血性脑卒中患者的一线治疗方法。以往的研究利用机器学习来协助神经科医生选择最能从溶栓治疗中获益的患者。然而，在设计算法时，大多数先前的算法为了预测能力而牺牲了可解释性，导致神经科医生难以信任这些算法，也无法在实际临床实践中应用。
我们提出的算法是经典k近邻分类算法（KNN）的改进版本。我们通过改变经典KNN特征空间的各向同性实现了高可解释性。我们利用一组患者来证明，与现有算法相比，我们的算法在保持先前模型可解释性的同时提高了预测能力。模型的预测能力通过受试者操作特征曲线下面积（AUC）进行评估。
在可解释性方面，只有发病时间、糖尿病和基线美国国立卫生研究院卒中量表（NIHSS）具有统计学意义，并且根据我们定义的重新缩放公式，它们对最终预测的贡献被迫与它们的特征重要性值成比例。在预测能力方面，我们改进的KNN（AUC 0.88）优于经典KNN（AUC 0.75， ）。
我们的初步结果表明，改进的KNN实现了高AUC，并识别出与先前临床试验/观察性研究一致的显著临床特征。该模型显示了协助选择溶栓患者以提高溶栓成功率的潜力。
