In this paper, we study the surgery scheduling problem in the operating room theatre. The problem considers the sequencing of patients and calculation of their start times with splitting of surgeries into resource phases to facilitate the efficient use of different types of resources. We propose a dedicated two-layer heuristic to compose an operational patient and resource schedule. The first optimisation layer applies an evolutionary heuristic to devise patient schedules while considering the scheduling of the operating surgeons and rooms. This step employs a machine-learning mechanism predicting the feasibility of chromosomes, which improves the algorithm’s efficiency and effectiveness, and relies on novel local search operators to find high-quality solutions. The second layer devises the schedule of the other resources using a decomposition-based heuristic. Computational experiments are conducted to show the performance of the proposed two-layer heuristic and validate its design choices. We benchmark the proposed algorithm with other optimisation procedures and show the contribution of considering multiple resource phases for real-life decision-making.