Burnett Bruce, Zhou Shang-Ming, Brophy Sinead, Davies Phil, Ellis Paul, Kennedy Jonathan, Bandyopadhyay Amrita, Parker Michael, Lyons Ronan A
Swansea University Medical School, Swansea SA2 8PP, UK.
Faculty of Health, University of Plymouth, Plymouth PL4 8AA, UK.
Diagnostics (Basel). 2023 Jan 13;13(2):301. doi: 10.3390/diagnostics13020301.
The inclusion of machine-learning-derived models in systematic reviews of risk prediction models for colorectal cancer is rare. Whilst such reviews have highlighted methodological issues and limited performance of the models included, it is unclear why machine-learning-derived models are absent and whether such models suffer similar methodological problems. This scoping review aims to identify machine-learning models, assess their methodology, and compare their performance with that found in previous reviews. A literature search of four databases was performed for colorectal cancer prediction and prognosis model publications that included at least one machine-learning model. A total of 14 publications were identified for inclusion in the scoping review. Data was extracted using an adapted CHARM checklist against which the models were benchmarked. The review found similar methodological problems with machine-learning models to that observed in systematic reviews for non-machine-learning models, although model performance was better. The inclusion of machine-learning models in systematic reviews is required, as they offer improved performance despite similar methodological omissions; however, to achieve this the methodological issues that affect many prediction models need to be addressed.
在结直肠癌风险预测模型的系统评价中纳入机器学习衍生模型的情况很少见。虽然此类评价突出了所纳入模型的方法学问题和有限的性能，但尚不清楚为何缺少机器学习衍生模型，以及此类模型是否存在类似的方法学问题。本范围综述旨在识别机器学习模型，评估其方法，并将其性能与以往评价中的模型进行比较。对四个数据库进行了文献检索，以查找包含至少一个机器学习模型的结直肠癌预测和预后模型出版物。共确定了14篇出版物纳入范围综述。使用改编后的CHARM清单提取数据，并以此为基准对模型进行评估。该综述发现，机器学习模型存在与非机器学习模型系统评价中观察到的类似方法学问题，尽管模型性能更好。需要将机器学习模型纳入系统评价，因为尽管存在类似的方法学遗漏，但它们的性能有所提高；然而，要做到这一点，需要解决影响许多预测模型的方法学问题。
