Cost-sensitive test strategies

In medical diagnosis doctors must often determine what medical tests (e.g., X-ray, blood tests) should be ordered for a patient to minimize the total cost of medical tests and misdiagnosis. In this paper, we design cost-sensitive machine learning algorithms to model this learning and diagnosis process. Medical tests are like attributes in machine learning whose values may be obtained at cost (attribute cost), and misdiagnoses are like misclassifications which may also incur a cost (misclassification cost). We first propose an improved decision tree learning algorithm that minimizes the sum of attribute costs and misclassification costs. Then we design several novel "test strategies" that may request to obtain values of unknown attributes at cost (similar to doctors' ordering of medical tests at cost) in order to minimize the total cost for test examples (new patients). We empirically evaluate and compare these test strategies, and show that they are effective and that they outperform previous methods. A case study on heart disease is given.