Eriksson Mikael, Czene Kamila, Vachon Celine, Conant Emily F, Hall Per
Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, 171 65 Stockholm, Sweden.
Centre for Cancer Genetic Epidemiology, Department of Public Health and Primary Care, University of Cambridge, Cambridge CB1 8RN, UK.
Cancers (Basel). 2023 Jun 19;15(12):3246. doi: 10.3390/cancers15123246.
Image-derived artificial intelligence (AI) risk models have shown promise in identifying high-risk women in the short term. The long-term performance of image-derived risk models expanded with clinical factors has not been investigated.
We performed a case-cohort study of 8110 women aged 40-74 randomly selected from a Swedish mammography screening cohort initiated in 2010 together with 1661 incident BCs diagnosed before January 2022. The imaging-only AI risk model extracted mammographic features and age at screening. Additional lifestyle/familial risk factors were incorporated into the lifestyle/familial-expanded AI model. Absolute risks were calculated using the two models and the clinical Tyrer-Cuzick v8 model. Age-adjusted model performances were compared across the 10-year follow-up.
The AUCs of the lifestyle/familial-expanded AI risk model ranged from 0.75 (95%CI: 0.70-0.80) to 0.68 (95%CI: 0.66-0.69) 1-10 years after study entry. Corresponding AUCs were 0.72 (95%CI: 0.66-0.78) to 0.65 (95%CI: 0.63-0.66) for the imaging-only model and 0.62 (95%CI: 0.55-0.68) to 0.60 (95%CI: 0.58-0.61) for Tyrer-Cuzick v8. The increased performances were observed in multiple risk subgroups and cancer subtypes. Among the 5% of women at highest risk, the PPV was 5.8% using the lifestyle/familial-expanded model compared with 5.3% using the imaging-only model, < 0.01, and 4.6% for Tyrer-Cuzick, < 0.01.
The lifestyle/familial-expanded AI risk model showed higher performance for both long-term and short-term risk assessment compared with imaging-only and Tyrer-Cuzick models.
基于图像的人工智能（AI）风险模型在短期内识别高风险女性方面已显示出前景。尚未对结合临床因素的基于图像的风险模型的长期性能进行研究。
我们对2010年启动的瑞典乳腺X线筛查队列中随机选取的8110名40 - 74岁女性以及2022年1月前诊断出的1661例新发乳腺癌进行了病例队列研究。仅基于影像的AI风险模型提取了乳腺X线特征和筛查时的年龄。其他生活方式/家族风险因素被纳入生活方式/家族扩展AI模型。使用这两种模型以及临床Tyrer-Cuzick v8模型计算绝对风险。在10年随访期间比较了年龄调整后的模型性能。
在研究入组后1 - 10年，生活方式/家族扩展AI风险模型的AUC范围为0.75（95%CI：0.70 - 0.80）至0.68（95%CI：0.66 - 0.69）。仅基于影像模型的相应AUC为0.72（95%CI：0.66 - 0.78）至0.65（95%CI：0.63 - 0.66），Tyrer-Cuzick v8模型为0.62（95%CI：0.55 - 0.68）至0.60（95%CI：0.58 - 0.61）。在多个风险亚组和癌症亚型中观察到性能有所提高。在风险最高的5%女性中，使用生活方式/家族扩展模型的阳性预测值为5.8%，仅基于影像模型为5.3%，P < 0.01，Tyrer-Cuzick模型为4.6%，P < 0.01。
与仅基于影像和Tyrer-Cuzick模型相比，生活方式/家族扩展AI风险模型在长期和短期风险评估中均表现出更高的性能。
