Artificial intelligence–based image analysis in clinical testing: lessons from cervical cancer screening

作者：Didem Egemen, Rebecca B. Perkins, Li C. Cheung, Brian Befano, Ana Cecilia Rodríguez, Kanan Desai, Andréanne Lemay, Syed Rakin Ahmed, Sameer Antani, José Jerónimo, Nicolas Wentzensen, Jayashree Kalpathy–Cramer, Sílvia de Sanjosé, Mark Schiffman · 发表于：JNCI Journal of the National Cancer Institute · 年份：2023 · 被引用次数：56 · 研究领域：AI in cancer detection、Cervical Cancer and HPV Research、Radiomics and Machine Learning in Medical Imaging

Novel screening and diagnostic tests based on artificial intelligence (AI) image recognition algorithms are proliferating. Some initial reports claim outstanding accuracy followed by disappointing lack of confirmation, including our own early work on cervical screening. This is a presentation of lessons learned, organized as a conceptual step-by-step approach to bridge the gap between the creation of an AI algorithm and clinical efficacy. The first fundamental principle is specifying rigorously what the algorithm is designed to identify and what the test is intended to measure (eg, screening, diagnostic, or prognostic). Second, designing the AI algorithm to minimize the most clinically important errors. For example, many equivocal cervical images cannot yet be labeled because the borderline between cases and controls is blurred. To avoid a misclassified case-control dichotomy, we have isolated the equivocal cases and formally included an intermediate, indeterminate class (severity order of classes: case>indeterminate>control). The third principle is evaluating AI algorithms like any other test, using clinical epidemiologic criteria. Repeatability of the algorithm at the borderline, for indeterminate images, has proven extremely informative. Distinguishing between internal and external validation is also essential. Linking the AI algorithm results to clinical risk estimation is the fourth principle. Absolute risk (not relative) is the critical metric for translating a test res...