Correlations between the clinical, histological and neurophysiological examinations in patients before and after parotid gland tumor surgery: verification of facial nerve transmission

Development of a Machine Learning Algorithm to Forecast the Likelihood of Postoperative Neurological Complications in Patients With Parotid Tumors

Objective: The objective of this study was to create and verify a machine learning-driven predictive model to forecast the likelihood of facial nerve impairment in patients with parotid tumors following surgery. Methods: We retrospectively collected data from patients with parotid tumors between 2013 and 2023 to develop a prediction model for postoperative facial nerve dysfunction using 5 ML techniques: Logistic Regression (Logit), Random Forest (RF), XGBoost (XGB), Artificial Neural Network (ANN), and Support Vector Machine (SVM). Predictor variables were screened using binomial-LASSO regression. Results: The study had a total of 403 participants, out of which 56 individuals encountered facial nerve damage after the surgery. By employing binomial-LASSO regression, we have successfully identified 8 crucial predictive variables: tumor kind, tumor pain, surgeon's experience, tumor volume, basophil percentage, red blood cell count, partial thromboplastin time, and prothrombin time. The models utilizing ANN and Logit achieved higher area under the curve (AUC) values, namely 0.829, which was significantly better than the SVM model that had an AUC of 0.724. There were no noticeable disparities in the AUC values between the ANN and Logit models, as well as between these models and other techniques like RF and XGB. Conclusion: Using machine learning, our prediction model accurately predicts the likelihood that patients with parotid tumors may experience facial nerve damage following surgery. By using this model, doctors can assess patients' risks more accurately before to surgery, and it may also help optimize postoperative treatment techniques. It is anticipated that this tool would enhance patients' quality of life and therapeutic outcomes.

Research trends and perspectives on immediate facial reanimation in radical parotidectomy (Review)

For patients diagnosed with advanced malignant parotid tumour, radical parotidectomy with facial nerve sacrifice is part of the treatment. Multiple surgical techniques have been developed to cure facial paralysis in order to restore the function and aesthetics of the face. Despite the large number of publications over time on facial nerve reanimation, a consensus on the timing of the procedure or the donor graft selection has remained to be established. Therefore, the aim of the present study was to conduct a bibliometric analysis to identify and analyse scientific publications on the reconstruction of the facial nerve of patients who underwent radical parotidectomy with facial nerve sacrifice. The analysis on the topic was conducted using the built-in tool of the Scopus database and VOSviewer software. The first 100 most cited articles were separately reviewed to address the aim of the study. No consensus was found regarding the recommended surgical techniques for facial nerve reanimation. The most used donor cranial nerves for transfer included the following: Masseteric branch of the V nerve, contralateral VII nerve with cross-face graft, the XI nerve and the XII nerve. The best timing of surgery is also controversial depending on pre-exiting pathology and degree of nerve degeneration. However, most of the clinical experience suggests facial nerve restoration immediately after the ablative procedure to reduce complications and improve patients' quality of life.

Prospective Assessment of Risk Factors Influencing Facial Nerve Paresis in Patients after Surgery for Parotid Gland Tumors

Background and objectives: Facial weakness is the most important complication of parotid gland tumor surgery. The aims of this study are as follows: (1) assessment of the prevalence of postparotidectomy facial nerve dysfunction; (2) clinical and electrophysiological assessment of the facial nerve function before parotidectomy and at 1 and 6 months postoperatively; (3) assessment of the association of postoperative facial palsy with selected risk factors; and (4) assessment of the correlation between the results of clinical and neurophysiological assessments of facial nerve function. Materials and Methods: This study comprised 50 patients (aged 24-75 years) who underwent parotidectomy at the Department of Otolaryngology and Laryngological Oncology in Zabrze, Poland between 2015 and 2017. The evaluation included neurological, clinical and electrophysiological assessments of the facial nerve prior to surgery and at 1 and 6 months postoperatively. Results: No facial palsy was found preoperatively or 6 months postoperatively. Facial nerve dysfunction was found in 74% of patients 1 month postoperatively. In most cases (54%), paresis was mild or moderate (House-Brackmann grades II and III). The results of electrophysiological tests before parotidectomy were either normal or showed some mild abnormalities. We found a statistically significant correlation between the clinical assessment of the facial nerve function (based on the House-Brackmann scale) one month postoperatively and the latency of the CMAP response from the orbicularis oculi and orbicularis oris muscles. In all three studies, a statistically significant correlation was found between the amplitude of the compound muscle action potential (CMAP) of the orbicularis oris muscle and the degree of facial nerve weakness. Conclusions: The factors that may influence the risk of postoperative facial nerve paralysis (prolonged surgical time and the size and location of the tumor other than in the superficial lobe only) may indirectly suggest that surgery-related difficulties and/or surgeon experience could be crucial to surgery safety.

Prospective Assessment of Intraoperative Facial Nerve Monitoring in Patients Undergoing Partial Parotidectomy

The most significant complication of parotid gland tumor surgery is facial weakness. This study compares the occurrence of transient facial palsy in patients with parotid gland tumors who underwent surgery without monitoring to those who underwent surgery with monitoring. The study’s aim was to investigate facial nerve function in patients undergoing parotidectomy as well as the effect of intraoperative facial nerve monitoring and the effect of certain risk factors on the surgery and onset of postoperative facial palsy. This prospective study included 100 patients who underwent parotidectomy. The study cohort was divided into two groups. Group I included 50 patients who underwent surgery without neuromonitoring and group II included 50 patients who underwent surgery with neuromonitoring. The neurological assessment was conducted using the House–Brackmann scale. Preoperatively and one month postoperatively, electroneuronography (ENoG) and blink reflex tests were done. The analyses showed a significant reduction of the compound muscle action potential (CMAP) amplitude of the orbicularis oculi and orbicularis oris muscles and prolonged R1 and R2 blink reflex latencies 1 month after surgery. On neurological and electrophysiological studies, the rate of postoperative transient facial nerve dysfunction was significantly different between the groups. Significantly more patients, operated with use of facial nerve monitoring, presented postoperatively normal nerve function (i.e., House–Brackmann grade I) compared to those who underwent surgery without monitoring (78% and 26%, respectively; $p<0.001$ ). Monitoring had a statistically significant impact on the prevalence of facial nerve conduction disorders in patients who underwent surgery, according to the blink reflex and ENoG studies. The duration of the surgical procedure was not affected by monitoring in any way. The clinical evaluation of facial nerve function (House–Brackmann scale) and some ENoG results 1 month after surgery were found to have a significant correlation. To summarize, using monitoring considerably reduced the negative impact of local factors and the prevalence of transient facial nerve palsy.

The Offprint of an Abnormal Pre-Parotidectomy Electrodiagnostic Finding in a Normally Functioning Facial Nerve: Correlation with Intraoperative Findings, Histology and Postoperative Facial Nerve Function

The aim of this study was to search for associations between an electrodiagnostically abnormal but clinically normal facial nerve before parotidectomy and the intraoperative findings, as well as the postoperative facial nerve function. The records of all patients treated for parotid tumors between 2002 and 2021 with a preoperative House–Brackmann score of grade I but an abnormal electrophysiologic finding were studied retrospectively. A total of 285 patients were included in this study, and 222 patients had a benign lesion (77.9%), whereas 63 cases had a malignant tumor (22.1%). Electroneurographic facial nerve involvement was associated with nerve displacement in 185 cases (64.9%) and infiltration in 17 cases (6%). In 83 cases (29.1%), no tumor–nerve interface could be detected intraoperatively. An electroneurographic signal was absent despite supramaximal stimulation in 6/17 cases with nerve infiltration and in 17/268 cases without nerve infiltration (p < 0.001). The electrophysiologic involvement of a normal facial nerve is not pathognomonic for a malignancy (22%), but it presents a rather rare (~6%) sign of a “true” nerve infiltration and could also appear in tumors without any contact with the facial nerve (~29%). Of our cases, two thirds of those with an anatomic nerve preservation and facial palsy had already directly and postoperatively recovered to a major extent in the midterm.