Nathan, John

Abstract Objective The aim of this study is to determine if supervised machine learning algorithms can accurately predict cancelled and self-intercepted computerized physician order entry in oral and maxillofacial surgery inpatients. Methods Data from Electronic Medical Record included patient demographics, comorbidities, procedures, vital signs, laboratory values, and medication orders were retrospectively collected. Predictor variables included patient demographics, comorbidities, procedures, vital signs, and laboratory values. Outcome of interest is if a medication order was voided or not. Data was cleaned and pro1cessed using Microsoft Excel and Python v3.12. Gradient Boosted Decision Trees, Random Forest, K-Nearest Neighbor, and Naïve Bayes were trained, validated, and tested for accuracy of the prediction of voided medication orders. Results 37,546 medication orders from 1,204 patient admissions over 5 years were used for this study included 3,892 (10.4%) medication orders that were voided. Gradient Boosted Decision Trees, Random Forest, K-Nearest Neighbor, and Naïve Bayes had an Area Under the Receiver Operating Curve of 0.802 802 with 95% CI [0.787, 0.825], 0.746 with 95% CI [0.722, 0.765], 0.685 with 95% CI [0.667, 0.699], and 0.505 with 95% CI [0.489, 0.539], respectively. Area Under the Precision Recall Curve was 0.684 with 95% CI [0.679, 0.702], 0.647 with 95% CI [0.638, 0.664], 0.429 with 95% CI [0.417, 0.434], and 0.551 with 95% CI [0.551, 0.552], respectively. Conclusion Gradient Boosted Decision Trees is the best model of the supervised machine learning algorithms with satisfactory performance in validation cohort for predicting voided Computerized Physician Order Entry in Oral and Maxillofacial Surgery inpatients.

Background Small recalcitrant defects of the mandible and maxilla may be secondary to tumor, trauma, infection, and congenital origin. Vascularized bone grafting has been shown to effectively manage these defects; however, donor sites are limited. The vascularized medial femoral condyle (MFC) provides adequate cortical cancellous bone with the option of a skin island, consistent anatomy, and minimal donor site morbidity. This article outlines the use of the MFC flap for maxillomandibular reconstruction. Methods A retrospective chart review of patients who required segmental maxillomandibular reconstruction with the MFC flap was conducted. A total of 9 patients (5 men and 5 women) with an average age of 45.3 years were identified. The etiology of the defects, flap sizes, and postoperative outcomes were recorded. Results Three patients had osteoradionecrosis of the neomandible after irradiation of the free fibula reconstruction, 3 patients had defects after cancer extirpation (1 mandible, 2 maxillary), 1 patient had a maxillary defect from trauma, and 2 patients had a residual cleft palate defect. All defects failed initial treatment with nonvascularized bone grafts. The average dimensions of the MFC flaps were 1.2 × 2.5 × 4 cm. Two of 9 flaps included a skin island. Eight flaps survived completely, but 1 patient suffered from flap failure requiring debridement and resulted in an oroantral fistula. Four patients received endosseous dental implants. Average time to union was 6.7 months, and average time to implant was 6.75 months. The average follow-up time was 24.9 months. Conclusions The MFC flap is useful in the reconstruction of small segmental maxillomandibular defects and for the salvage of a neomandible after osteoradionecrosis. The MFC flap provides a reliable platform for endosseous dental implants and serves as an alternative source of vascularized bone reconstruction in the head and neck.