Artificial intelligence in onco-anaesthesia: Current applications, challenges, and future directions

Figure 1 Artificial intelligence-augmented onco-anaesthesia: A conceptual framework for precision perioperative cancer care. The framework illustrates AI applications across the perioperative continuum: Preoperative risk stratification (green), intraoperative real-time optimization (orange), and postoperative outcome prediction (purple). The central element represents the onco-anaesthesia hypothesis linking anesthetic techniques to cancer outcomes. The lower panels depict implementation challenges (red) and future directions (blue), with core AI methodologies shown at the foundation. AI: Artificial intelligence; EHR: Electronic health record; NLP: Natural language processing; CLADS: Closed-loop anesthesia delivery systems; AUC: Area under curve; LMICs: Low- and middle-income countries; CNN: Convolutional neural network; RNN: Recurrent neural network; LSTM: Long short-term memory; SHAP: SHapley Additive exPlanations.