使用机器学习方法预测堕胎风险:一项比较研究
Zhenning Zhu1, Na Wei1, Junjie Guo2
1The Second Affiliated Hospital of Shaanxi University of Chinese Medicine, Gynecology Department, Xianyang, 712000, China.
BMC pregnancy and childbirth
|August 30, 2025
概括
机器学习模型可以使用常规血液检测预测流产的威胁, 改善早期发现和干预这种常见的妊娠并发症. 这种方法提供了比目前的诊断方法更快,更准确的替代方案.
科学领域:
- 产科和妇科
- 医疗信息学
- 计算生物学
背景情况:
- 由于非特异性症状和与其他早期妊娠出血重叠的原因,很难预测堕胎的威胁.
- 目前的诊断方法,如串行超声波和临床监测,耗时且缺乏及时的早期干预.
- 需要先进的分析工具来改善堕胎威胁的早期发现和风险分层.
研究的目的:
- 开发和评估机器学习 (ML) 模型,使用常规血液测试数据预测可能发生的流产.
- 为了比较八种不同的ML算法在识别堕胎的性能.
- 确定最有影响力预测流产威胁的关键血液指标.
主要方法:
- 收集了1764名受威胁堕胎患者和1489名对照患者的医疗记录 (2022年1月至2024年3月).
- 在血液常规指标上应用Z-score正常化,并使用"class_weight="balanced"来优化超参数.
- 训练并测试了八种ML算法 (LR,RF,SVM,GBM,XGB,DNN,DT,NB),使用AUC,精度,特异性,灵敏度和F1评分来评估性能.
主要成果:
- 深度神经网络 (DNN) 模型以96. 76%的AUC实现了最高的预测性能.
- DNN模型表现出极好的指标:准确度 (91.88%),特异性 (91.62%),灵敏度 (92.11%) 和F1得分 (92.48%).
- SHAP分析确定了RDW-SD,PDW,MPV,RDW-CV,BAS#,PLT,MCHC和LYM作为重要的预测特征.
结论:
- 使用常规血液检测的机器学习模型显示出早期发现堕胎威胁的巨大潜力.
- 开发的ML模型可以帮助医疗保健提供者更早地进行干预,从而减少堕胎发生率.
- 在临床实施ML模型之前,需要进行进一步的广泛验证研究.
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
6.9K
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.3K
相关概念视频
01:18Steps in Outbreak Investigation
188
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
188
01:52Regression Toward the Mean
6.5K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.5K