Todd B S, Stamper R
Programming Research Group, Oxford University Computing Laboratory, UK.
Med Inform (Lond). 1993 Jul-Sep;18(3):255-70. doi: 10.3109/14639239309025314.
This paper explores the limits to computer-aided medical diagnosis. A specific application area (the diagnosis of abdominal pain of suspected gynaecological origin) is chosen, and the factors limiting the accuracy of computer programs are investigated by means of a simulation model which has been shown previously to generate realistic cases. The model is used to generate arbitrarily large training and test sets. The results suggest that, while statistical dependencies exist amongst symptoms and signs, there is little to be gained by taking interactions into account. However, failure to record all possible observations does limit diagnostic accuracy significantly. The results suggest that near-optimal diagnostic accuracy (75-80%) can be obtained with a training set size of 10(5) cases simply by applying Bayes' theorem with the usual assumption of conditional independence.
本文探讨了计算机辅助医学诊断的局限性。选择了一个特定的应用领域（疑似妇科起源的腹痛诊断），并通过一个先前已证明能生成真实病例的模拟模型来研究限制计算机程序准确性的因素。该模型用于生成任意大小的训练集和测试集。结果表明，虽然症状和体征之间存在统计相关性，但考虑相互作用并不能带来太多收获。然而，未能记录所有可能的观察结果确实会显著限制诊断准确性。结果表明，只需在条件独立性的通常假设下应用贝叶斯定理，训练集大小为10⁵个病例时就能获得接近最优的诊断准确性（75 - 80%）。
