We suggest that deep learning can be used for pre-screening cancer by analyzing demographic and anthropometric information of patients, as well as biological markers obtained from routine blood samples and relative risks obtained from meta-analysis and international databases. We applied feature selection algorithms to a database of 116 women, including 52 healthy women and 64 women diagnosed with breast cancer, to identify the best pre-screening predictors of cancer. We utilized the best predictors to perform k-fold Monte Carlo cross-validation experiments that compare deep learning against traditional machine learning algorithms. Our results indicate that a deep learning model with an input-layer architecture that is fine-tuned using feature selection can effectively distinguish between patients with and without cancer. Additionally, compared to machine learning, deep learning has the lowest uncertainty in its predictions. These findings suggest that deep learning algorithms applied to cancer pre-screening offer a radiation-free, non-invasive, and affordable complement to screening methods based on imagery. The implementation of deep learning algorithms in cancer pre-screening offer opportunities to identify individuals who may require imaging-based screening, can encourage self-examination, and decrease the psychological externalities associated with false positives in cancer screening. The integration of deep learning algorithms for both screening and pre-screening will ultimately lead to earlier detection of malignancy, reducing the healthcare and societal burden associated to cancer treatment.
翻译:我们建议,通过分析病人的人口和人体测量信息,以及从常规血液样本和元分析及国际数据库中获得的相对风险中获得的生物标记,可以将深度学习用于癌症预检前的预测。我们把特征选择算法应用到116名妇女的数据库中,其中包括52名健康妇女和64名被诊断患有乳腺癌的妇女,以确定癌症的最佳预检预测者。我们利用最佳预测者进行与传统机器学习算法相比的对蒙特卡洛的深度学习交叉校验试验。我们的结果表明,一个具有投入层结构的深度学习模型,使用特征选择进行微调,可以有效地区分癌症患者和无癌症患者。此外,与机器学习相比,深层学习算法在预测中具有最低的不确定性。这些发现表明,癌症预检前的深层学习算法提供了无辐射、无侵扰和负担得起的对基于图像的筛查方法的补充。在癌症预检中采用深层学习算算法,为确定哪些人可能需要基于成像的筛查,可以鼓励自我检查,并减少与癌症患者的心理内核反应。在早期癌症检查中进行不实的检查,将减少与癌症前的癌症检查相关的社会研究。