arXiv 2011.073962020-11-14cs.LGcs.CY

成本敏感的机器学习分类用于大规模结核病口头筛查

Cost-Sensitive Machine Learning Classification for Mass Tuberculosis Verbal Screening

Inovasi Sehat Indonesia（印度尼西亚健康创新）；University of Indonesia（印度尼西亚大学）；Oxford University（牛津大学）

Ali Akbar Septiandri, Aditiawarman, Roy Tjiong, Erlina Burhan, Anuraj Shankar

备注：: Machine Learning for Health (ML4H) at NeurIPS 2020 - Extended Abstract

摘要：

基于分数的结核病（TB）口头筛查算法表现不佳，导致错误分类，导致漏诊病例和不必要的昂贵的假阳性实验室检测。我们将临床医生定义的基于评分的分类与SVM-RBF、逻辑回归和XGBoost等机器学习分类进行了比较。我们限制我们的分析，从成年人的数据，受结核病影响最大的人口，并调查未调整和未加权分类器的成本敏感的差异。将预测值与相应的GeneXpert MTB/Rif结果进行比较。将XGBoost的阳性类别权重调整为40后，我们获得了96.64%的灵敏度和35.06%的特异性。因此，与我们的临床医生定义的传统基于评分的方法相比，我们的标识符的灵敏度增加了1.26%，而特异性的绝对值增加了13.19%。我们的方法进一步证明，只有2000个数据点就足以使模型收敛。结果表明，即使数据有限，我们实际上也可以设计出一种更好的方法来识别结核病嫌疑人。

英文摘要：

Score-based algorithms for tuberculosis (TB) verbal screening perform poorly, causing misclassification that leads to missed cases and unnecessary costly laboratory tests for false positives. We compared score-based classification defined by clinicians to machine learning classification such as SVM-RBF, logistic regression, and XGBoost. We restricted our analyses to data from adults, the population most affected by TB, and investigated the difference between untuned and unweighted classifiers to the cost-sensitive ones. Predictions were compared with the corresponding GeneXpert MTB/Rif results. After adjusting the weight of the positive class to 40 for XGBoost, we achieved 96.64% sensitivity and 35.06% specificity. As such, the sensitivity of our identifier increased by 1.26% while specificity increased by 13.19% in absolute value compared to the traditional score-based method defined by our clinicians. Our approach further demonstrated that only 2000 data points were sufficient to enable the model to converge. The results indicate that even with limited data we can actually devise a better method to identify TB suspects from verbal screening.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

摘要：

英文摘要：

相关论文