METHOD: In this study, the MNSI data were collected from the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials. Two different datasets with different MNSI variable combinations based on the results from the eXtreme Gradient Boosting feature ranking technique were used to analyze the performance of eight different conventional ML algorithms.
RESULTS: The random forest (RF) classifier outperformed other ML models for both datasets. However, all ML models showed almost perfect reliability based on Kappa statistics and a high correlation between the predicted output and actual class of the EDIC patients when all six MNSI variables were considered as inputs.
CONCLUSIONS: This study suggests that the RF algorithm-based classifier using all MNSI variables can help to predict the DSPN severity which will help to enhance the medical facilities for diabetic patients.
MATERIALS AND METHODS: An electronic search was performed in PubMed, SCOPUS, and Web of Science using a combination of relevant keywords: digital workflow, digital designing, computer-assisted design-computer aided manufacturing, 3D printing, maxillectomy, and mandibulectomy. The Joanna Briggs Institute Critical Appraisal Tool was used to assess the quality of evidence in the studies reviewed.
RESULTS: From a total of 542 references, 33 articles were selected, including 25 on maxillary prostheses and 8 on mandibular prostheses. The use of digital workflows was limited to one or two steps of the fabrication of the prostheses, and only four studies described a complete digital workflow. The most preferred method for data acquisition was intraoral scanning with or without a cone beam computed tomography combination.
CONCLUSION: Currently, the fabrication process of maxillofacial prostheses requires combining digital and conventional methods. Simplifying the data acquisition methods and providing user-friendly and affordable software may encourage clinicians to use the digital workflow more frequently for patients requiring maxillofacial prostheses.