RESUMO
OBJECTIVES: The popularity of artificial intelligence (AI) in head and neck cancer (HNC) management is increasing, but postoperative complications remain prevalent and are the main factor that impact prognosis after surgery. Hence, recent studies aim to assess new AI models to evaluate their ability to predict free flap complications more effectively than traditional algorithms. This systematic review aims to summarize current evidence on the utilization of AI models to predict complications following reconstructive surgery for HNC. METHODS: A combination of MeSH terms and keywords was used to cover the following three subjects: "HNC," "artificial intelligence," and "free flap or reconstructive surgery." The electronic literature search was performed in three relevant databases: Medline (Ovid), Embase (Ovid), and Cochrane. Quality appraisal of the included study was conducted using the TRIPOD Statement. RESULTS: The review included a total of 5 manuscripts (n = 5) for a total of 7524 patients. Across studies, the highest area under the receiver operating characteristic (AUROC) value achieved was 0.824 by the Auto-WEKA model. However, only 20% of reported AUROCs exceeded 0.70. One study concluded that most AI models were comparable or inferior in performance to conventional logistic regression. The highest predictors of complications were flap type, smoking status, tumour location, and age. DISCUSSION: Some models showed promising results. Predictors identified across studies were different than those found in existing literature, showing the added value of AI models. However, the algorithms showed inconsistent results, underlying the need for better-powered studies with larger databases before clinical implementation.
RESUMO
We appreciate the comments made by Hornibrook (2024) [...].
RESUMO
Importance: Restoration of dental occlusion and oral rehabilitation is the ultimate goal of functional jaw reconstruction. Objective: To evaluate the prefabricated fibula flap (PFF) technique in occlusion-driven jaw reconstruction for benign or previously treated malignant disease. Design, Setting, and Participants: This cohort study was conducted from January 2000 to December 2019 at the University of Alberta Hospital and Institute of Reconstructive Sciences in Medicine in Edmonton, Alberta, Canada, among patients who underwent PFF or bone-driven and delayed osseointegrated implant installation (BDD). Patients were followed up for a minimum of 1 year after occlusal rehabilitation. Data were analyzed from July 2021 to June 2022. Exposures: Patients underwent BDD or PFF, which consists of osseointegrated dental implant installation and skin grafting of the fibular bone 3 to 6 months before jaw tumor resection or defect reconstruction. The implant osseointegration is completed at the time of jaw reconstruction, allowing for full reconstruction, loading, and restoration of the dental occlusion in the immediate postoperative period. Main outcomes and Measure: Safety, effectiveness, accuracy, timeliness of occlusal reconstruction, and aesthetic appeal were compared between PFF and BDD. Groups were compared for the following variables: postoperative complications, number of bony segments used, number of procedures needed, total operative time, time to occlusal rehabilitation, and number of implants installed, exposed, lost, and used (ie, exposed implants - lost implants). Aesthetic appeal was assessed using standardized full-face and profile digital photographs taken before and 6 to 12 months after the operation and analyzed by 3 naive raters. Results: Among 9 patients receiving PFF (mean [SD] age, 43.3 [13.0] years; 7 men [77.8%]) and 12 patients receiving BDD (mean [SD] age, 41.9 [18.0] years; 8 men [66.7%]), the overall complication rate was similar (4 patients [44.4%] vs 3 patients [25.0%], respectively; relative risk, 1.78 [95% CI, 0.52 to 6.04]). The number of patients with implant loss was similar between PFF and BDD groups (0 patients vs 3 patients [25.0%], respectively; difference, -25.0 percentage points [95% CI, -48.4 to 9.7 percentage points]). PFF had a clinically meaningful faster mean (SD) occlusal rehabilitation compared with BDD (12.1 [1.9] months vs 60.4 [23.1] months; difference, -48.3 months [95% CI, -64.5 to -32.0 months]). The mean (SD) difference in preoperative to postoperative aesthetic score was similar between PFF and BDD groups (-0.8 [1.5] vs -0.2 [0.8]; difference, -0.6 [95% CI, -1.6 to 0.4]). Conclusions and Relevance: This study found that PFF compared with BDD was a safe, effective, and aesthetic reconstructive option for patients with benign or previously treated jaw malignant tumors. This technique may provide rapid occlusal reconstruction and oral rehabilitation.