Zakhar Grant, Hazime Samir, Eckert George, Wong Ariel, Badirli Sarkhan, Turkkahraman Hakan
Department of Orthodontics and Oral Facial Genetics, Indiana University School of Dentistry, Indianapolis, IN 46202, USA.
Indiana University School of Dentistry, Indianapolis, IN 46202, USA.
Diagnostics (Basel). 2023 Aug 21;13(16):2713. doi: 10.3390/diagnostics13162713.
The goal of this study was to create a novel machine learning (ML) model that can predict the magnitude and direction of pubertal mandibular growth in males with Class II malocclusion. Lateral cephalometric radiographs of 123 males at three time points (T1: 12; T2: 14; T3: 16 years old) were collected from an online database of longitudinal growth studies. Each radiograph was traced, and seven different ML models were trained using 38 data points obtained from 92 subjects. Thirty-one subjects were used as the test group to predict the post-pubertal mandibular length and -axis, using input data from T1 and T2 combined (2 year prediction), and T1 alone (4 year prediction). Mean absolute errors (MAEs) were used to evaluate the accuracy of each model. For all ML methods tested using the 2 year prediction, the MAEs for post-pubertal mandibular length ranged from 2.11-6.07 mm to 0.85-2.74° for the -axis. For all ML methods tested with 4 year prediction, the MAEs for post-pubertal mandibular length ranged from 2.32-5.28 mm to 1.25-1.72° for the -axis. Besides its initial length, the most predictive factors for mandibular length were found to be chronological age, upper and lower face heights, upper and lower incisor positions, and inclinations. For the -axis, the most predictive factors were found to be -axis at earlier time points, SN-MP, SN-Pog, SNB, and SNA. Although the potential of ML techniques to accurately forecast future mandibular growth in Class II cases is promising, a requirement for more substantial sample sizes exists to further enhance the precision of these predictions.
本研究的目的是创建一种新型机器学习（ML）模型，该模型能够预测Ⅱ类错颌男性青春期下颌生长的幅度和方向。从一个纵向生长研究的在线数据库中收集了123名男性在三个时间点（T1：12岁；T2：14岁；T3：16岁）的头颅侧位X线片。对每张X线片进行了描图，并使用从92名受试者获得的38个数据点训练了7种不同的ML模型。31名受试者被用作测试组，使用T1和T2组合的输入数据（2年预测）以及单独的T1数据（4年预测）来预测青春期后下颌长度和轴。平均绝对误差（MAE）用于评估每个模型的准确性。对于使用2年预测测试的所有ML方法，青春期后下颌长度的MAE范围为2.11 - 6.07毫米，轴的MAE范围为0.85 - 2.74°。对于使用4年预测测试的所有ML方法，青春期后下颌长度的MAE范围为2.32 - 5.28毫米，轴的MAE范围为1.25 - 1.72°。除了初始长度外，发现下颌长度的最具预测性的因素是实足年龄、上下面部高度、上下切牙位置和倾斜度。对于轴，最具预测性的因素是较早时间点的轴、SN - MP、SN - Pog、SNB和SNA。尽管ML技术在准确预测Ⅱ类病例未来下颌生长方面的潜力很有前景，但仍需要更大的样本量来进一步提高这些预测的精度。
