Center for Cleft Lip and Palate Treatment, Plastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
Skin Res Technol. 2023 Jul;29(7):e13402. doi: 10.1111/srt.13402.
Age prediction powered by artificial intelligence (AI) can be used as an objective technique to assess the cosmetic effect of rejuvenation surgery. Existing age-estimation models are trained on public datasets with the Caucasian race as the main reference, thus they are impractical for clinical application in Chinese patients.
To develop and select an age-estimation model appropriate for Chinese patients receiving rejuvenation treatment, we obtained a face database of 10 529 images from 1821 patients from the author's hospital and selected two representative age-estimation algorithms for the model training. The prediction accuracies and the interpretability of calculation logic of these two facial age predictors were compared and analyzed.
The mean absolute error (MAE) of a traditional support vector machine-learning model was 10.185 years; the proportion of absolute error ≤6 years was 35.90% and 68.50% ≤12 years. The MAE of a deep-learning model based on the VGG-16 framework was 3.011 years; the proportion of absolute error ≤6 years was 90.20% and 100% ≤12 years. Compared with deep learning, traditional machine-learning models have clearer computational logic, which allows them to give clinicians more specific treatment recommendations.
Experimental results show that deep-learning exceeds traditional machine learning in the prediction of Chinese cosmetic patients' age. Although traditional machine learning model has better interpretability than deep-learning model, deep-learning is more accurate for clinical quantitative evaluation. Knowing the decision-making logic behind the accurate prediction of deep-learning is crucial for deeper clinical application, and requires further exploration.
人工智能（AI）驱动的年龄预测可作为评估年轻化手术美容效果的客观技术。现有的年龄估计模型是在以白种人为主要参考的公共数据集上进行训练的，因此对于接受年轻化治疗的中国患者的临床应用并不实用。
为了开发和选择适合接受年轻化治疗的中国患者的年龄估计模型，我们从作者医院的 1821 名患者中获取了 10529 张面部图像的面部数据库，并选择了两种具有代表性的年龄估计算法用于模型训练。比较和分析了这两种面部年龄预测器的预测准确性和计算逻辑的可解释性。
传统支持向量机学习模型的平均绝对误差（MAE）为 10.185 年；绝对误差≤6 年的比例为 35.90%，68.50%≤12 年。基于 VGG-16 框架的深度学习模型的 MAE 为 3.011 年；绝对误差≤6 年的比例为 90.20%，100%≤12 年。与深度学习相比，传统机器学习模型具有更清晰的计算逻辑，这使得它们能够为临床医生提供更具体的治疗建议。
实验结果表明，深度学习在预测中国美容患者年龄方面优于传统机器学习。虽然传统机器学习模型的可解释性优于深度学习模型，但深度学习模型在临床定量评估方面更准确。了解深度学习准确预测背后的决策逻辑对于更深入的临床应用至关重要，需要进一步探索。
