Turku Bioscience Centre, University of Turku and Åbo Akademi University, Turku, Finland.
Department of Oncology, Turku University Hospital and FICAN West, Turku, Finland.
Cancer Med. 2022 Feb;11(3):654-663. doi: 10.1002/cam4.4465. Epub 2021 Dec 3.
The existing risk prediction models for chemotherapy-induced febrile neutropenia (FN) do not necessarily apply to real-life patients in different healthcare systems and the external validation of these models are often lacking. Our study evaluates whether a machine learning-based risk prediction model could outperform the previously introduced models, especially when validated against real-world patient data from another institution not used for model training.
Using Turku University Hospital electronic medical records, we identified all patients who received chemotherapy for non-hematological cancer between the years 2010 and 2017 (N = 5879). An experimental surrogate endpoint was first-cycle neutropenic infection (NI), defined as grade IV neutropenia with serum C-reactive protein >10 mg/l. For predicting the risk of NI, a penalized regression model (Lasso) was developed. The model was externally validated in an independent dataset (N = 4594) from Tampere University Hospital.
Lasso model accurately predicted NI risk with good accuracy (AUROC 0.84). In the validation cohort, the Lasso model outperformed two previously introduced, widely approved models, with AUROC 0.75. The variables selected by Lasso included granulocyte colony-stimulating factor (G-CSF) use, cancer type, pre-treatment neutrophil and thrombocyte count, intravenous treatment regimen, and the planned dose intensity. The same model predicted also FN, with AUROC 0.77, supporting the validity of NI as an endpoint.
Our study demonstrates that real-world NI risk prediction can be improved with machine learning and that every difference in patient or treatment characteristics can have a significant impact on model performance. Here we outline a novel, externally validated approach which may hold potential to facilitate more targeted use of G-CSFs in the future.
现有的化疗引起的发热性中性粒细胞减少症（FN）风险预测模型不一定适用于不同医疗体系中的实际患者，并且这些模型的外部验证往往缺乏。我们的研究评估了基于机器学习的风险预测模型是否可以优于先前介绍的模型，尤其是当针对来自另一个未用于模型训练的机构的真实患者数据进行验证时。
我们使用图尔库大学医院的电子病历，确定了 2010 年至 2017 年间接受非血液系统癌症化疗的所有患者（N=5879）。首次周期中性粒细胞减少性感染（NI）被定义为血清 C 反应蛋白>10mg/L 的 IV 级中性粒细胞减少症，作为实验替代终点。为了预测 NI 风险，我们开发了一个惩罚回归模型（Lasso）。该模型在坦佩雷大学医院的独立数据集（N=4594）中进行了外部验证。
Lasso 模型能够准确预测 NI 风险，具有良好的准确性（AUROC 0.84）。在验证队列中，Lasso 模型优于两个先前介绍的、广泛认可的模型，AUROC 为 0.75。Lasso 选择的变量包括粒细胞集落刺激因子（G-CSF）的使用、癌症类型、治疗前中性粒细胞和血小板计数、静脉治疗方案以及计划的剂量强度。同一个模型也预测了 FN，AUROC 为 0.77，支持 NI 作为终点的有效性。
我们的研究表明，基于机器学习可以提高真实世界中 NI 风险预测的准确性，并且患者或治疗特征的每一个差异都可能对模型性能产生重大影响。在这里，我们概述了一种新的、经过外部验证的方法，该方法可能有潜力在未来促进更有针对性地使用 G-CSF。
