Interpretable Machine Learning Text Classification for Clinical Computed Tomography Reports – a Case Study of Temporal Bone Fracture

•Random forest classifier achieves 0.93 F1-score in classifying temporal bone fracture texts.•Word frequency score reveals differences between fracture texts and non-fracture texts.•Local interpretable model explanations visualizes the word-level contribution to classification results.•The interpretable model provides physicians with accessible evidence for clinical diagnosis.