Predicting extubation failure in intensive care is challenging due to complex data and the severe consequences of inaccurate predictions. Machine learning shows promise in improving clinical decision-making but often fails to account for temporal patient trajectories and model interpretability, highlighting the need for innovative solutions. This study aimed to develop an actionable, interpretable prediction system for extubation failure using temporal modelling approaches such as Long Short-Term Memory (LSTM) and Temporal Convolutional Networks (TCN). A retrospective cohort study of 4,701 mechanically ventilated patients from the MIMIC-IV database was conducted. Data from the 6 hours before extubation, including static and dynamic features, were processed through novel techniques addressing data inconsistency and synthetic data challenges. Feature selection was guided by clinical relevance and literature benchmarks. Iterative experimentation involved training LSTM, TCN, and LightGBM models. Initial results showed a strong bias toward predicting extubation success, despite advanced hyperparameter tuning and static data inclusion. Data was stratified by sampling frequency to reduce synthetic data impacts, leading to a fused decision system with improved performance. However, all architectures yielded modest predictive power (AUC-ROC ~0.6; F1 <0.5) with no clear advantage in incorporating static data or additional features. Ablation analysis indicated minimal impact of individual features on model performance. This thesis highlights the challenges of synthetic data in extubation failure prediction and introduces strategies to mitigate bias, including clinician-informed preprocessing and novel feature subsetting. While performance was limited, the study provides a foundation for future work, emphasising the need for reliable, interpretable models to optimise ICU outcomes.

翻译：预测重症监护中的拔管失败具有挑战性，原因在于数据复杂且预测不准确的后果严重。机器学习在改善临床决策方面显示出潜力，但往往未能考虑患者的时间轨迹和模型的可解释性，这凸显了对创新解决方案的需求。本研究旨在利用长短期记忆网络（LSTM）和时序卷积网络（TCN）等时序建模方法，开发一种可操作、可解释的拔管失败预测系统。研究对来自MIMIC-IV数据库的4,701名机械通气患者进行了回顾性队列研究。拔管前6小时的数据，包括静态和动态特征，通过处理数据不一致性和合成数据挑战的新技术进行处理。特征选择以临床相关性和文献基准为指导。迭代实验涉及训练LSTM、TCN和LightGBM模型。初步结果显示，尽管进行了高级超参数调优并纳入了静态数据，模型仍存在强烈偏向预测拔管成功的偏差。通过按采样频率对数据进行分层以减少合成数据的影响，最终形成了一个性能改进的融合决策系统。然而，所有架构的预测能力均有限（AUC-ROC ~0.6；F1 <0.5），且在纳入静态数据或额外特征方面无明显优势。消融分析表明，单个特征对模型性能的影响微乎其微。本论文强调了合成数据在拔管失败预测中的挑战，并介绍了减轻偏差的策略，包括基于临床知识的预处理和新的特征子集划分方法。尽管性能有限，但本研究为未来工作奠定了基础，强调了需要可靠、可解释的模型以优化重症监护室（ICU）的治疗结果。