机器学习模型的开发和多中心验证,用于高级结直肠瘤查模型
Mingqing Zhang1, Yongdan Zhang2, Lizhong Zhao3
1Department of Colorectal Surgery, Tianjin Union Medical Center, The First Affiliated Hospital of Nankai University, Tianjin, China; Tianjin Institute of Coloproctology, Tianjin, China; Nankai University School of Medicine, Nankai University, Tianjin, China; The Institute of Translational Medicine, Tianjin Union Medical Center of Nankai University, Tianjin, China.
一个新的机器学习模型,天津ML (TML),在结直肠癌查中有效地识别了患有晚期结直肠瘤 (ACN) 的高风险个体. 这种人工智能工具的性能优于传统方法,有助于早期干预和患者监测.
科学领域:
- 在瘤学瘤学.
- 医疗信息学 医疗信息学
- 医疗保健中的机器学习
背景情况:
- 准确识别高级结直肠瘤 (ACN) 高风险个体对于有效的结直肠癌 (CRC) 查至关重要.
- 早期干预和监测对于高风险患者至关重要.
研究的目的:
- 为ACN开发和验证基于机器学习 (ML) 的风险预测模型,用于早期识别高风险个体.
- 在CRC查计划中提高ACN风险分层的准确性.
主要方法:
- 利用天津CRC查计划 (2012-2022) 的数据,在12个医疗中心进行培训和验证.
- 使用LASSO和后勤回归来选择特征,然后构建和比较六个ML模型.
- 开发了一个堆叠集体学习模型 (S-TML),并使用SHAP值进行解释性分析.
主要成果:
- 天津ML (TML) 模型实现了0.690的AUC,超过了APCS和LR模型的性能.
- 堆叠组合模型 (S-TML) 进一步提高了性能,AUC为0.709.
- SHAP分析确定年龄,性别和便免疫化学测试是ACN的关键预测因素.
结论:
- 与传统方法相比,TML模型在预测ACN方面表现优越.
- 开发的ML模型可以作为一种有价值的查决策支持工具,用于识别高风险个体.
- 该研究强调了ML在提高CRC查计划的效率和准确性的潜力.
更多相关视频
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
相关概念视频
Mouse Models of Cancer Study
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
Mouse Models of Cancer Study
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
