This repository presents a dual-architecture machine learning system for early detection of clinical deterioration in intensive care unit (ICU) patients. The system compares gradient-boosted decision trees (LightGBM) with temporal convolutional networks (TCN) to model complementary aspects of physiological risk using routinely collected clinical observations. Three NEWS2-derived deterioration outcomes are considered: maximum risk level attained during the ICU stay (max_risk), median sustained risk level across the stay (median_risk), and the proportion of time spent in a high-risk state (pct_time_high). Models are trained and evaluated using the PhysioNet MIMIC-IV Clinical Demo v2.2 dataset via two distinct feature-engineering pipelines. The TCN operates on high-resolution timestamp-level temporal features (96-hour windows, 171 features) to capture short-term physiological instability, while the LightGBM model uses patient-level aggregated tabular features (40 features) to characterise longer-term exposure to risk. Comparative evaluation indicates complementary performance profiles: LightGBM exhibits superior calibration and regression fidelity for sustained risk estimation, while TCNs show stronger sensitivity and discrimination for acute deterioration events. Performance is assessed using ROC-AUC, Brier score, and R², alongside interpretability analyses based on SHAP values and saliency methods. The end-to-end pipeline includes clinically validated NEWS2 preprocessing (including CO₂ retainer logic, Glasgow Coma Scale mapping, and supplemental oxygen protocols), comprehensive feature engineering, model training with hyperparameter optimisation, robust metric evaluation, and a command-line inference interface supporting batch prediction and per-patient lookup. Overall, the system demonstrates physiologically plausible predictive behaviour, clinically meaningful interpretability, and a reproducible workflow suitable for extension to full clinical datasets or downstream deployment contexts. This repository contains code and documentation only; no patient-level clinical data are redistributed. Users must obtain the MIMIC-IV dataset directly from PhysioNet and comply with its data use requirements. The work is intended for research and educational use. Target Outcome Best-Performing Model Key Metric(s) Notes max_risk TCN ROC-AUC = 0.923; Strong acute deterioration detection median_risk LightGBM ROC-AUC = 0.872; Brier Score = 0.065 Superior sustained risk calibration pct_time_high LightGBM R² = 0.793; RMSE = 0.038 Higher fidelity estimation of high-risk exposure