Using NLP to Analyze CBCT Reports

In recent years, dentistry has seen an upsurge in using artificial intelligence. The demand for automatic diagnosis in oral and maxillofacial surgery and other medical fields is increasing. Natural language processing (NLP) is a branch of artificial intelligence that can process free text reports. Extraction of the mandibular third molar requires surgical planning during preoperative diagnosis. The present study aimed to predict the extraction difficulty of the mandibular third molar based on free-text oral and maxillofacial radiology reports. This prediction is made by processing in two steps: pre-processing and processing. The pre-processing step makes the data suitable for data analysis. The primary information extraction step is the processing step. The information required to classify the reports was extracted using rule-based natural language processing methods. Finally, a machine learning algorithm was used to classify the reports. The precision, recall, and f1-score for classification of extraction difficulty were respectively 0.97, 0.89, and 0.92 for the validation set. The results showed that the proposed approach is promising. To our knowledge, this is the first study to apply NLP technology in dental CBCT reports.