Accurate artificial intelligence (AI) for disease diagnosis could lower healthcare workloads. However, when time or financial resources for gathering input data are limited, as in emergency and critical-care medicine, developing accurate AI models, which typically require inputs for many clinical variables, may be impractical. Here we report a model-agnostic cost-aware AI (CoAI) framework for the development of predictive models that optimize the trade-off between prediction performance and feature cost. By using three datasets, each including thousands of patients, we show that relative to clinical risk scores, CoAI substantially reduces the cost and improves the accuracy of predicting acute traumatic coagulopathy in a pre-hospital setting, mortality in intensive-care patients and mortality in outpatient settings. We also show that CoAI outperforms state-of-the-art cost-aware prediction strategies in terms of predictive performance, model cost, training time and robustness to feature-cost perturbations. CoAI uses axiomatic feature-attribution methods for the estimation of feature importance and decouples feature selection from model training, thus allowing for a faster and more flexible adaptation of AI models to new feature costs and prediction budgets.

用于疾病诊断的准确人工智能 (AI) 可以降低医疗保健工作量。然而，当用于收集输入数据的时间或财务资源有限时，例如在急救和重症监护医学中，开发准确的人工智能模型通常需要输入许多临床变量，这可能是不切实际的。在这里，我们报告了一个与模型无关的成本感知 AI (CoAI) 框架，用于开发预测模型，优化预测性能和特征成本之间的权衡。通过使用三个数据集，每个数据集包括数千名患者，我们表明，相对于临床风险评分，CoAI 大大降低了成本并提高了预测院前环境中急性创伤性凝血病、重症监护患者死亡率和门诊设置。我们还表明，CoAI 在预测性能、模型成本、​​训练时间和对特征成本扰动的稳健性方面优于最先进的成本感知预测策略。CoAI 使用公理化特征归因方法来估计特征重要性，并将特征选择与模型训练分离，从而允许 AI 模型更快、更灵活地适应新特征成本和预测预算。