用概率混合提升罕见术中并发症检测准确率
Feature Mixing Approach for Detecting Intraoperative Adverse Events in Laparoscopic Roux-en-Y Gastric Bypass Surgery
- 基于贝塔分布混合样本，将严重程度转为连续值增强小样本
- 在140例手术数据上实现0.76加权F1和0.81召回率
- 适合需要精准评估手术风险的临床医生使用
术中不良事件（IAEs）如出血或热损伤若未被及时发现，可能导致严重术后并发症。然而其发生率低导致数据极度不平衡，给AI检测与严重程度量化带来挑战。我们提出BetaMixer，一种基于贝塔分布混合方法的深度学习模型，将离散的IAE严重程度评分（0-5级）转化为连续值进行精确回归。通过贝塔分布采样增强少数类，并对中间特征进行正则化以保持结构化特征空间。生成式方法使特征空间与采样严重程度对齐，借助变换器实现鲁棒分类与严重程度回归。在我们扩展了IAE标签的MultiBypass140数据集上，BetaMixer达到加权F1分数0.76、召回率0.81、阳性预测值0.73、阴性预测值0.84，展现出在不平衡数据上的优异性能。通过融合贝塔采样、特征混合与生成建模，BetaMixer为临床环境中的IAE检测与量化提供了稳健解决方案。
原文摘要 · Abstract (English)
Intraoperative adverse events (IAEs), such as bleeding or thermal injury, can lead to severe postoperative complications if undetected. However, their rarity results in highly imbalanced datasets, posing challenges for AI-based detection and severity quantification. We propose BetaMixer, a novel deep learning model that addresses these challenges through a Beta distribution-based mixing approach, converting discrete IAE severity scores into continuous values for precise severity regression (0-5 scale). BetaMixer employs Beta distribution-based sampling to enhance underrepresented classes and regularizes intermediate embeddings to maintain a structured feature space. A generative approach aligns the feature space with sampled IAE severity, enabling robust classification and severity regression via a transformer. Evaluated on the MultiBypass140 dataset, which we extended with IAE labels, BetaMixer achieves a weighted F1 score of 0.76, recall of 0.81, PPV of 0.73, and NPV of 0.84, demonstrating strong performance on imbalanced data. By integrating Beta distribution-based sampling, feature mixing, and generative modeling, BetaMixer offers a robust solution for IAE detection and quantification in clinical settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。