TY - JOUR A1 - Fuchs, Andreas A1 - Hartmann, Stefan A1 - Ernestus, Karen A1 - Mutzbauer, Grit A1 - Linz, Christian A1 - Brands, Roman C. A1 - Kübler, Alexander C. A1 - Müller-Richter, Urs D. A. T1 - Mandibular intraosseous pseudocarcinomatous hyperplasia: a case report JF - Journal of Medical Case Reports N2 - Background Mandibular pseudocarcinomatous hyperplasia is a rare and generally benign pathology. We report on one of these rare cases. Case presentation The case history of a 73-year-old white man stated that he had a carcinoma of the oropharynx, which was primarily treated with radiotherapy and chemotherapy 4 years prior. As a result of radiotherapy he developed an osteoradionecrosis of his mandible and a consecutive pathological fracture of his left mandibular angle. Subsequent osteosynthesis was performed with a reconstruction plate. When we first saw him, his reconstruction plate was partially exposed with intraoral and extraoral fistulation. The resected bone of his defect-bordering jaw showed the typical pathohistological findings of an intraosseous mandibular pseudocarcinomatous hyperplasia. After a first reconstruction attempt with an iliac crest graft failed, definitive reconstruction of his mandible with a microvascular anastomosed fibula graft was achieved. Conclusions Intraosseous pseudocarcinomatous hyperplasia of the mandible is a rare differential diagnosis in maxillofacial surgery. Besides other benign epithelial neoplasms, such as calcifying epithelial odontogenic tumor, squamous odontogenic tumor, or different forms of ameloblastoma, the far more frequent invasive squamous cell carcinoma needs to be excluded. A misinterpretation of pseudocarcinomatous hyperplasia as squamous cell carcinoma must be avoided because it can lead to a massive overtreatment. KW - intraosseous KW - case report KW - pseudocarcinomatous hyperplasia KW - mandible Y1 - 2016 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-146873 VL - 16 IS - 268 ER - TY - JOUR A1 - Boschert, Verena A1 - Klenk, Nicola A1 - Abt, Alexander A1 - Raman, Sudha Janaki A1 - Fischer, Markus A1 - Brands, Roman C. A1 - Seher, Axel A1 - Linz, Christian A1 - Müller-Richter, Urs D. A. A1 - Bischler, Thorsten A1 - Hartmann, Stefan T1 - The influence of Met receptor level on HGF-induced glycolytic reprogramming in head and neck squamous cell carcinoma JF - International Journal of Molecular Sciences N2 - Head and neck squamous cell carcinoma (HNSCC) is known to overexpress a variety of receptor tyrosine kinases, such as the HGF receptor Met. Like other malignancies, HNSCC involves a mutual interaction between the tumor cells and surrounding tissues and cells. We hypothesized that activation of HGF/Met signaling in HNSCC influences glucose metabolism and therefore substantially changes the tumor microenvironment. To determine the effect of HGF, we submitted three established HNSCC cell lines to mRNA sequencing. Dynamic changes in glucose metabolism were measured in real time by an extracellular flux analyzer. As expected, the cell lines exhibited different levels of Met and responded differently to HGF stimulation. As confirmed by mRNA sequencing, the level of Met expression was associated with the number of upregulated HGF-dependent genes. Overall, Met stimulation by HGF leads to increased glycolysis, presumably mediated by higher expression of three key enzymes of glycolysis. These effects appear to be stronger in Met\(^{high}\)-expressing HNSCC cells. Collectively, our data support the hypothesized role of HGF/Met signaling in metabolic reprogramming of HNSCC. KW - HNSCC KW - head and neck cancer KW - HGF KW - Met KW - cancer metabolism Y1 - 2020 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-235995 SN - 1422-0067 VL - 21 IS - 2 ER - TY - JOUR A1 - Vollmer, Andreas A1 - Vollmer, Michael A1 - Lang, Gernot A1 - Straub, Anton A1 - Kübler, Alexander A1 - Gubik, Sebastian A1 - Brands, Roman C. A1 - Hartmann, Stefan A1 - Saravi, Babak T1 - Performance analysis of supervised machine learning algorithms for automatized radiographical classification of maxillary third molar impaction JF - Applied Sciences N2 - Background: Oro-antral communication (OAC) is a common complication following the extraction of upper molar teeth. The Archer and the Root Sinus (RS) systems can be used to classify impacted teeth in panoramic radiographs. The Archer classes B-D and the Root Sinus classes III, IV have been associated with an increased risk of OAC following tooth extraction in the upper molar region. In our previous study, we found that panoramic radiographs are not reliable for predicting OAC. This study aimed to (1) determine the feasibility of automating the classification (Archer/RS classes) of impacted teeth from panoramic radiographs, (2) determine the distribution of OAC stratified by classification system classes for the purposes of decision tree construction, and (3) determine the feasibility of automating the prediction of OAC utilizing the mentioned classification systems. Methods: We utilized multiple supervised pre-trained machine learning models (VGG16, ResNet50, Inceptionv3, EfficientNet, MobileNetV2), one custom-made convolutional neural network (CNN) model, and a Bag of Visual Words (BoVW) technique to evaluate the performance to predict the clinical classification systems RS and Archer from panoramic radiographs (Aim 1). We then used Chi-square Automatic Interaction Detectors (CHAID) to determine the distribution of OAC stratified by the Archer/RS classes to introduce a decision tree for simple use in clinics (Aim 2). Lastly, we tested the ability of a multilayer perceptron artificial neural network (MLP) and a radial basis function neural network (RBNN) to predict OAC based on the high-risk classes RS III, IV, and Archer B-D (Aim 3). Results: We achieved accuracies of up to 0.771 for EfficientNet and MobileNetV2 when examining the Archer classification. For the AUC, we obtained values of up to 0.902 for our custom-made CNN. In comparison, the detection of the RS classification achieved accuracies of up to 0.792 for the BoVW and an AUC of up to 0.716 for our custom-made CNN. Overall, the Archer classification was detected more reliably than the RS classification when considering all algorithms. CHAID predicted 77.4% correctness for the Archer classification and 81.4% for the RS classification. MLP (AUC: 0.590) and RBNN (AUC: 0.590) for the Archer classification as well as MLP 0.638) and RBNN (0.630) for the RS classification did not show sufficient predictive capability for OAC. Conclusions: The results reveal that impacted teeth can be classified using panoramic radiographs (best AUC: 0.902), and the classification systems can be stratified according to their relationship to OAC (81.4% correct for RS classification). However, the Archer and RS classes did not achieve satisfactory AUCs for predicting OAC (best AUC: 0.638). Additional research is needed to validate the results externally and to develop a reliable risk stratification tool based on the present findings. KW - oro-antral communication KW - oro-antral fistula KW - prediction KW - machine learning KW - teeth extraction KW - complications KW - classification KW - artificial intelligence Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-281662 SN - 2076-3417 VL - 12 IS - 13 ER - TY - JOUR A1 - Boschert, Verena A1 - Teusch, Jonas A1 - Müller-Richter, Urs D. A. A1 - Brands, Roman C. A1 - Hartmann, Stefan T1 - PKM2 modulation in head and neck squamous cell carcinoma JF - International Journal of Molecular Sciences N2 - The enzyme pyruvate kinase M2 (PKM2) plays a major role in the switch of tumor cells from oxidative phosphorylation to aerobic glycolysis, one of the hallmarks of cancer. Different allosteric inhibitors or activators and several posttranslational modifications regulate its activity. Head and neck squamous cell carcinoma (HNSCC) is a common disease with a high rate of recurrence. To find out more about PKM2 and its modulation in HNSCC, we examined a panel of HNSCC cells using real-time cell metabolic analysis and Western blotting with an emphasis on phosphorylation variant Tyr105 and two reagents known to impair PKM2 activity. Our results show that in HNSCC, PKM2 is commonly phosphorylated at Tyrosine 105. Its levels depended on tyrosine kinase activity, emphasizing the importance of growth factors such as EGF (epidermal growth factor) on HNSCC metabolism. Furthermore, its correlation with the expression of CD44 indicates a role in cancer stemness. Cells generally reacted with higher glycolysis to PKM2 activator DASA-58 and lower glycolysis to PKM2 inhibitor Compound 3k, but some were more susceptible to activation and others to inhibition. Our findings emphasize the need to further investigate the role of PKM2 in HNSCC, as it could aid understanding and treatment of the disease. KW - HNSCC KW - head and neck cancer KW - cancer metabolism KW - glycolysis KW - PKM2 KW - Warburg effect KW - CD44 KW - Compound 3k KW - DASA-58 KW - AMPK KW - TXNIP Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-284458 SN - 1422-0067 VL - 23 IS - 2 ER - TY - JOUR A1 - Vollmer, Andreas A1 - Saravi, Babak A1 - Vollmer, Michael A1 - Lang, Gernot Michael A1 - Straub, Anton A1 - Brands, Roman C. A1 - Kübler, Alexander A1 - Gubik, Sebastian A1 - Hartmann, Stefan T1 - Artificial intelligence-based prediction of oroantral communication after tooth extraction utilizing preoperative panoramic radiography JF - Diagnostics N2 - Oroantral communication (OAC) is a common complication after tooth extraction of upper molars. Profound preoperative panoramic radiography analysis might potentially help predict OAC following tooth extraction. In this exploratory study, we evaluated n = 300 consecutive cases (100 OAC and 200 controls) and trained five machine learning algorithms (VGG16, InceptionV3, MobileNetV2, EfficientNet, and ResNet50) to predict OAC versus non-OAC (binary classification task) from the input images. Further, four oral and maxillofacial experts evaluated the respective panoramic radiography and determined performance metrics (accuracy, area under the curve (AUC), precision, recall, F1-score, and receiver operating characteristics curve) of all diagnostic approaches. Cohen's kappa was used to evaluate the agreement between expert evaluations. The deep learning algorithms reached high specificity (highest specificity 100% for InceptionV3) but low sensitivity (highest sensitivity 42.86% for MobileNetV2). The AUCs from VGG16, InceptionV3, MobileNetV2, EfficientNet, and ResNet50 were 0.53, 0.60, 0.67, 0.51, and 0.56, respectively. Expert 1–4 reached an AUC of 0.550, 0.629, 0.500, and 0.579, respectively. The specificity of the expert evaluations ranged from 51.74% to 95.02%, whereas sensitivity ranged from 14.14% to 59.60%. Cohen's kappa revealed a poor agreement for the oral and maxillofacial expert evaluations (Cohen's kappa: 0.1285). Overall, present data indicate that OAC cannot be sufficiently predicted from preoperative panoramic radiography. The false-negative rate, i.e., the rate of positive cases (OAC) missed by the deep learning algorithms, ranged from 57.14% to 95.24%. Surgeons should not solely rely on panoramic radiography when evaluating the probability of OAC occurrence. Clinical testing of OAC is warranted after each upper-molar tooth extraction. KW - artificial intelligence KW - deep learning KW - X-ray KW - tooth extraction KW - oroantral fistula KW - operative planning Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-278814 SN - 2075-4418 VL - 12 IS - 6 ER - TY - JOUR A1 - Winter, Anna A1 - Schulz, Stefan M. A1 - Schmitter, Marc A1 - Brands, Roman C. A1 - Straub, Anton A1 - Kübler, Alexander A1 - Borgmann, Anna A1 - Hartmann, Stefan T1 - Oral-health-related quality of life in patients with medication-related osteonecrosis of the jaw: a prospective clinical study JF - International Journal of Environmental Research and Public Health N2 - Medication-related osteonecrosis of the jaw (MRONJ) represents an adverse side effect of antiresorptive and antiangiogenic medications. It is associated with impaired quality of life, oral health, and oral function and can be classified into various stages. The purpose of this prospective clinical study is to evaluate the impact of stages I and II MRONJ on oral-health-related quality of life (OHRQoL) and related parameters. Patients’ OHRQoL, satisfaction with life, oral discomfort, and oral health were assessed using the German version of the Oral Health Impact Profile (OHIP-G49), visual analog scales (VAS), and Satisfaction with Life Scale (SWLS) at baseline (T0), 10 days (T1), and 3 months after treatment (T2) in 36 patients. Data were analyzed using Kolmogorov–Smirnov test, two-way mixed ANOVAs, and follow-up Mann–Whitney U tests. The impact of treatment effects on the original seven OHIP domain structures and the recently introduced four-dimensional OHIP structure were evaluated using linear regression analysis. Thirty-six patients received surgical MRONJ treatment. Before treatment, patients’ perceived OHRQoL, oral discomfort, oral health, and satisfaction with life were negatively affected by MRONJ. Surgical treatment significantly improved OHRQoL and related parameters (all p ≤ 0.012). This improvement was greater in patients with higher impairment at T0. OHRQoL and oral restrictions were still impaired after treatment in patients who needed prosthetic treatment. The four-dimensional structure revealed valuable information beyond the standard seven OHIP domains. Increased awareness of MRONJ risks and an interdisciplinary treatment approach for MRONJ patients are needed. KW - oral-health-related quality of life KW - satisfaction with life KW - oral health KW - medication-related osteonecrosis of the jaw KW - treatment benefit KW - OHIP-49 KW - SWLS Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-288141 SN - 1660-4601 VL - 19 IS - 18 ER - TY - JOUR A1 - Straub, Anton A1 - Stapf, Maximilian A1 - Fischer, Markus A1 - Vollmer, Andreas A1 - Linz, Christian A1 - Lâm, Thiên-Trí A1 - Kübler, Alexander A1 - Brands, Roman C. A1 - Scherf-Clavel, Oliver A1 - Hartmann, Stefan T1 - Bone concentration of ampicillin/sulbactam: a pilot study in patients with osteonecrosis of the jaw JF - International Journal of Environmental Research and Public Health N2 - Osteonecrosis of the jaw (ONJ) occurs typically after irradiation of the head and neck area or after the intake of antiresorptive agents. Both interventions can lead to compromised bone perfusion and can ultimately result in infection and necrosis. Treatment usually consists of surgical necrosectomy and prolonged antibiotic therapy, usually through beta-lactams such as ampicillin/sulbactam. The poor blood supply in particular raises the question as to whether this form of antibiosis can achieve sufficient concentrations in the bone. Therefore, we investigated the antibiotic concentration in plasma and bone samples in a prospective study. Bone samples were collected from the necrosis core and in the vital surrounding bone. The measured concentrations in plasma for ampicillin and sulbactam were 126.3 ± 77.6 and 60.2 ± 35.0 µg/mL, respectively. In vital bone and necrotic bone samples, the ampicillin/sulbactam concentrations were 6.3 ± 7.8/1.8 ± 2.0 µg/g and 4.9 ± 7.0/1.7 ± 1.7 µg/g, respectively. These concentrations are substantially lower than described in the literature. However, the concentration seems sufficient to kill most bacteria, such as Streptococci and Staphylococci, which are mostly present in the biofilm of ONJ. We, therefore, conclude that intravenous administration of ampicillin/sulbactam remains a valuable treatment in the therapy of ONJ. Nevertheless, increasing resistance of Escherichia coli towards beta-lactam antibiotics have been reported and should be considered. KW - osteonecrosis of the jaw KW - ARONJ KW - MRONJ KW - ONJ KW - osteoradionecrosis KW - antibiotic bone concentration KW - jaw bone KW - beta-lactam KW - ampicillin Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-297413 SN - 1660-4601 VL - 19 IS - 22 ER - TY - JOUR A1 - Vollmer, Andreas A1 - Vollmer, Michael A1 - Lang, Gernot A1 - Straub, Anton A1 - Kübler, Alexander A1 - Gubik, Sebastian A1 - Brands, Roman C. A1 - Hartmann, Stefan A1 - Saravi, Babak T1 - Automated assessment of radiographic bone loss in the posterior maxilla utilizing a multi-object detection artificial intelligence algorithm JF - Applied Sciences N2 - Periodontitis is one of the most prevalent diseases worldwide. The degree of radiographic bone loss can be used to assess the course of therapy or the severity of the disease. Since automated bone loss detection has many benefits, our goal was to develop a multi-object detection algorithm based on artificial intelligence that would be able to detect and quantify radiographic bone loss using standard two-dimensional radiographic images in the maxillary posterior region. This study was conducted by combining three recent online databases and validating the results using an external validation dataset from our organization. There were 1414 images for training and testing and 341 for external validation in the final dataset. We applied a Keypoint RCNN with a ResNet-50-FPN backbone network for both boundary box and keypoint detection. The intersection over union (IoU) and the object keypoint similarity (OKS) were used for model evaluation. The evaluation of the boundary box metrics showed a moderate overlapping with the ground truth, revealing an average precision of up to 0.758. The average precision and recall over all five folds were 0.694 and 0.611, respectively. Mean average precision and recall for the keypoint detection were 0.632 and 0.579, respectively. Despite only using a small and heterogeneous set of images for training, our results indicate that the algorithm is able to learn the objects of interest, although without sufficient accuracy due to the limited number of images and a large amount of information available in panoramic radiographs. Considering the widespread availability of panoramic radiographs as well as the increasing use of online databases, the presented model can be further improved in the future to facilitate its implementation in clinics. KW - radiographic bone loss KW - alveolar bone loss KW - maxillofacial surgery KW - deep learning KW - classification KW - artificial intelligence KW - object detection Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-305050 SN - 2076-3417 VL - 13 IS - 3 ER - TY - JOUR A1 - Straub, Anton A1 - Vollmer, Andreas A1 - Lâm, Thiên-Trí A1 - Brands, Roman C. A1 - Stapf, Maximilian A1 - Scherf-Clavel, Oliver A1 - Bittrich, Max A1 - Fuchs, Andreas A1 - Kübler, Alexander C. A1 - Hartmann, Stefan T1 - Evaluation of advanced platelet-rich fibrin (PRF) as a bio-carrier for ampicillin/sulbactam JF - Clinical Oral Investigations N2 - Objectives Mechanisms of wound healing are often impaired in patients with osteonecrosis of the jaw (ONJ). According to the guidelines for the treatment of this disease, early surgical intervention is indicated. However, surgery often faces complications such as wound healing disorders. The application of platelet-rich fibrin (PRF) after necrosectomy between bone and mucosa may constitute a promising approach to improve surgical results. An aspect that was not investigated until now is that PRF acts as a “bio-carrier” for antibiotics previously applied intravenously. Materials and methods We investigated the antimicrobial properties of PRF in 24 patients presenting ONJ undergoing systemic antibiosis with ampicillin/sulbactam. We measured the concentration of ampicillin/sulbactam in plasma and PRF and performed agar diffusion tests. Ampicillin/sulbactam was applied intravenously to the patient 10 minutes for blood sampling for PRF. No further incorporation of patients’ blood or PRF product with antibiotic drugs was obtained. Four healthy patients served as controls. Results Our results revealed that PRF is highly enriched with ampicillin/sulbactam that is released to the environment. The antibiotic concentration in PRF was comparable to the plasma concentration of ampicillin/sulbactam. The inhibition zone (IZ) of PRF was comparable to the standard ampicillin/sulbactam discs used in sensitivity testing. Conclusions The results of our study demonstrated that PRF is a reliable bio-carrier for systemic applied antibiotics and exhibits a large antimicrobial effect. Clinical relevance We describe a clinically useful feature of PRF as a bio-carrier for antibiotics. Especially when applied to poorly perfused tissues and bone such as in ONJ, the local release of antibiotics can reduce wound healing disorders like infections. KW - osteonecrosis of the jaw KW - osteoradionecrosis KW - antiresorptive drug-related osteonecrosis of the jaw KW - ARONJ KW - oral microbiome KW - agar diffusion test Y1 - 2022 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-324515 VL - 26 IS - 12 ER - TY - JOUR A1 - Linz, Christian A1 - Brands, Roman C. A1 - Kertels, Olivia A1 - Dierks, Alexander A1 - Brumberg, Joachim A1 - Gerhard-Hartmann, Elena A1 - Hartmann, Stefan A1 - Schirbel, Andreas A1 - Serfling, Sebastian A1 - Zhi, Yingjun A1 - Buck, Andreas K. A1 - Kübler, Alexander A1 - Hohm, Julian A1 - Lapa, Constantin A1 - Kircher, Malte T1 - Targeting fibroblast activation protein in newly diagnosed squamous cell carcinoma of the oral cavity – initial experience and comparison to [\(^{18}\)F]FDG PET/CT and MRI JF - European Journal of Nuclear Medicine and Molecular Imaging N2 - Purpose While [\(^{18}\)F]-fluorodeoxyglucose ([\(^{18}\)F]FDG) is the standard for positron emission tomography/computed tomography (PET/CT) imaging of oral squamous cell carcinoma (OSCC), diagnostic specificity is hampered by uptake in inflammatory cells such as neutrophils or macrophages. Recently, molecular imaging probes targeting fibroblast activation protein α (FAP), which is overexpressed in a variety of cancer-associated fibroblasts, have become available and might constitute a feasible alternative to FDG PET/CT. Methods Ten consecutive, treatment-naïve patients (8 males, 2 females; mean age, 62 ± 9 years) with biopsy-proven OSCC underwent both whole-body [\(^{18}\)F]FDG and [\(^{68}\)Ga]FAPI-04 (FAP-directed) PET/CT for primary staging prior to tumor resection and cervical lymph node dissection. Detection of the primary tumor, as well as the presence and number of lymph node and distant metastases was analysed. Intensity of tracer accumulation was assessed by means of maximum (SUV\(_{max}\)) and peak (SUV\(_{peak}\) standardized uptake values. Histological work-up including immunohistochemical staining for FAP served as standard of reference. Results [\(^{18}\)F]FDG and FAP-directed PET/CT detected all primary tumors with a SUVmax of 25.5 ± 13.2 (FDG) and 20.5 ± 6.4 (FAP-directed) and a SUVpeak of 16.1 ± 10.3 ([\(^{18}\)F]FDG) and 13.8 ± 3.9 (FAP-directed), respectively. Regarding cervical lymph node metastases, FAP-directed PET/CT demonstrated comparable sensitivity (81.3% vs. 87.5%; P = 0.32) and specificity (93.3% vs. 81.3%; P = 0.16) to [\(^{18}\)F]FDG PET/CT. FAP expression on the cell surface of cancer-associated fibroblasts in both primary lesions as well as lymph nodes metastases was confirmed in all samples. Conclusion FAP-directed PET/CT in OSCC seems feasible. Future research to investigate its potential to improve patient staging is highly warranted. KW - molecular imaging KW - fibroblast activation protein KW - head and neck cancer KW - PET Y1 - 2021 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-307246 SN - 1619-7070 SN - 1619-7089 VL - 48 IS - 12 ER - TY - JOUR A1 - Vollmer, Andreas A1 - Nagler, Simon A1 - Hörner, Marius A1 - Hartmann, Stefan A1 - Brands, Roman C. A1 - Breitenbücher, Niko A1 - Straub, Anton A1 - Kübler, Alexander A1 - Vollmer, Michael A1 - Gubik, Sebastian A1 - Lang, Gernot A1 - Wollborn, Jakob A1 - Saravi, Babak T1 - Performance of artificial intelligence-based algorithms to predict prolonged length of stay after head and neck cancer surgery JF - Heliyon N2 - Background Medical resource management can be improved by assessing the likelihood of prolonged length of stay (LOS) for head and neck cancer surgery patients. The objective of this study was to develop predictive models that could be used to determine whether a patient's LOS after cancer surgery falls within the normal range of the cohort. Methods We conducted a retrospective analysis of a dataset consisting of 300 consecutive patients who underwent head and neck cancer surgery between 2017 and 2022 at a single university medical center. Prolonged LOS was defined as LOS exceeding the 75th percentile of the cohort. Feature importance analysis was performed to evaluate the most important predictors for prolonged LOS. We then constructed 7 machine learning and deep learning algorithms for the prediction modeling of prolonged LOS. Results The algorithms reached accuracy values of 75.40 (radial basis function neural network) to 97.92 (Random Trees) for the training set and 64.90 (multilayer perceptron neural network) to 84.14 (Random Trees) for the testing set. The leading parameters predicting prolonged LOS were operation time, ischemia time, the graft used, the ASA score, the intensive care stay, and the pathological stages. The results revealed that patients who had a higher number of harvested lymph nodes (LN) had a lower probability of recurrence but also a greater LOS. However, patients with prolonged LOS were also at greater risk of recurrence, particularly when fewer (LN) were extracted. Further, LOS was more strongly correlated with the overall number of extracted lymph nodes than with the number of positive lymph nodes or the ratio of positive to overall extracted lymph nodes, indicating that particularly unnecessary lymph node extraction might be associated with prolonged LOS. Conclusions The results emphasize the need for a closer follow-up of patients who experience prolonged LOS. Prospective trials are warranted to validate the present results. KW - prediction KW - head and neck cancer KW - machine learning KW - deep learning KW - artificial intelligence KW - length of stay KW - cancer Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:20-opus-350416 SN - 2405-8440 VL - 9 IS - 11 ER -