Machine Learning Algorithms as a Computer-Assisted Decision Tool for Oral Cancer Prognosis and Management Decisions: A Systematic Review.

INTRODUCTION: Despite multiple prognostic indicators described for oral cavity squamous cell carcinoma (OCSCC), its management still continues to be a matter of debate. Machine learning is a subset of artificial intelligence that enables computers to learn from historical data, gather insights, and make predictions about new data using the model learned. Therefore, it can be a potential tool in the field of head and neck cancer. METHODS: We conducted a systematic review. RESULTS: A total of 81 manuscripts were revised, and 46 studies met the inclusion criteria. Of these, 38 were excluded for the following reasons: use of a classical statistical method (N = 16), nonspecific for OCSCC (N = 15), and not being related to OCSCC survival (N = 7). In total, 8 studies were included in the final analysis. CONCLUSIONS: ML has the potential to significantly advance research in the field of OCSCC. Advantages are related to the use and training of ML models because of their capability to continue training continuously when more data become available. Future ML research will allow us to improve and democratize the application of algorithms to improve the prediction of cancer prognosis and its management worldwide.

Complications after Functional Neck Dissection in Head and Neck Cancer Patients: An Observational, Retrospective, Single-Centre Study.

INTRODUCTION: Functional neck dissection (FND) represents a surgical procedure usually associated with less morbidity. METHODS: An observational, retrospective, analysis of patients diagnosed with any type of head and neck malignancy was designed to summarize and report the incidence of postoperative complications in patients undergoing FND including just those levels described for selective neck dissections in a tertiary university hospital between June 2016 and June 2019. RESULTS: 131 patients met the inclusion criteria. The total number of sides studied was 200. 40.5% of the patients suffer a complication in the postoperative period, being the spinal accessory nerve (SAN) injury the most common complication (10%). We did not find any statistical -correlation between the previous organ-preservation treatments and surgical complications (p = 0.207). An advanced T stage (p = 0.009) and the need of bilateral FND (p = 0.034) were significantly correlated with a higher risk of surgical complications. CONCLUSION: FND represents a useful technique. In this study, 40.5% of the patients suffer a complication in the postoperative period, being the SAN injury the most common complication. However, these data contribute to increasing our knowledge about surgical complications related to FND.

Facial nerve palsy following parotid gland surgery: A machine learning prediction outcome approach.

Introduction: Machine learning (ML)-based facial nerve injury (FNI) forecasting grounded on multicentric data has not been released up to now. Three distinct ML models, random forest (RF), K-nearest neighbor, and artificial neural network (ANN), for the prediction of FNI were evaluated in this mode. Methods: A retrospective, longitudinal, multicentric study was performed, including patients who went through parotid gland surgery for benign tumors at three different university hospitals. Results: Seven hundred and thirty-six patients were included. The most compelling aspects related to risk escalation of FNI were as follows: (1) location, in the mid-portion of the gland, near to or above the main trunk of the facial nerve and at the top part, over the frontal or the orbital branch of the facial nerve; (2) tumor volume in the anteroposterior axis; (3) the necessity to simultaneously dissect more than one level; and (4) the requirement of an extended resection compared to a lesser extended resection. By contrast, in accordance with the ML analysis, the size of the tumor (>3 cm), as well as gender and age did not result in a determining favor in relation to the risk of FNI. Discussion: The findings of this research conclude that ML models such as RF and ANN may serve evidence-based predictions from multicentric data regarding the risk of FNI. Conclusion: Along with the advent of ML technology, an improvement of the information regarding the potential risks of FNI associated with patients before each procedure may be achieved with the implementation of clinical, radiological, histological, and/or cytological data.

Impact of lymph node ratio and number of lymph node metastases on survival and recurrence in laryngeal squamous cell carcinoma.

INTRODUCTION: The aim of this study is to assess the impact of lymph node ratio (LNR) and number of positive lymph nodes (NPLN) on mortality and recurrence rates in patients with laryngeal squamous cell carcinoma. MATERIALS AND METHODS: We conducted a retrospective multicenter international study involving 24 Otorhinolaryngology-Head and Neck Surgery divisions. Disease-specific survival (DSS) and disease-free survival (DFS) were evaluated as the main outcomes. The curves for DSS and DFS according to NPLN and LNR were analyzed to identify significant variations and establish specific cut-off values. RESULTS: 2507 patients met the inclusion criteria. DSS and DFS were significantly different in the groups of patients stratified according to LNR and NPLN. The 5-year DSS and DFS based on LNR and NPLN demonstrated an improved ability to stratify patients when compared to pN staging. CONCLUSION: Our data demonstrate the potential prognostic value of NPLN and LNR in laryngeal squamous cell carcinoma.

A Novel Computer-Aided Design/Computer-Aided Manufacturing (CAD/CAM) 3D Printing Method for Nasal Framework Reconstruction Using Microvascular Free Flaps.

The need for a total or subtotal nose resection represents a dramatic situation for any patient and a challenge for the reconstructive surgeon. Because even in the most skillful hands, an optimal result may be difficult to achieve. In this way, sometimes a free flap reconstruction is needed. A subtotal nasal reconstruction is presented using a fasciocutaneous free flap supported by computer-aided design (CAD), computer-aided manufacturing (CAM), and novel 3D printed guide to recreate the nasal cartilage framework. A successfully free flap reconstruction of the nasal framework was achieved supported by the CAD/CAM 3D printed template. We present a novel approach for nasal total or subtotal reconstruction using a CAD/CAM 3D printed model to create the nasal framework, based on the anatomical and radiological evaluation of the patient.

Stapler-Assisted Pharyngeal Closure After Total Laryngectomy: A Systematic Review and Meta-Analysis.

INTRODUCTION: Pharyngocutaneous fistula (PCF) remains the most frequent complication following total laryngectomy (TL). Pharyngeal closure with a surgical stapler (SAPC) has been proposed as an effective closure technique that decreases the rate of PCF, reduces surgical time, decreases the length of hospital stay, and shortens the time required before safely initiating oral feeding. METHODS: This study involved a systematic review and meta-analysis of patients with laryngeal cancer who underwent TL and with subsequent stapler pharyngeal closure, in order to analyse the current literature regarding the role of SAPC after TL. RESULTS: The incidence of PCF in the stapler-assisted suture group (SASG) was 9.5% (95% CI 8.2-15.9%), with a mean absolute deviation of 1.12, while in the hand-suture group (HSG) group the incidence was 23.4% (95% CI 23-26.1%), with a mean absolute deviation of 5.71 (p = 0.01). CONCLUSIONS: SAPC may decrease the risk of PCF in patients following TL. Based on the current data, SAPC appears to shorten the surgical time and the length of hospital stay. Nevertheless, prospective randomized trials are required to validate these findings.

Pedicled Supraclavicular Artery Island Flap Versus Free Radial Forearm Flap: Perioperative Outcomes in Head and Neck Reconstruction.

INTRODUCTION: Radial forearm free flap (RFFF) and supraclavicular artery island flap (SCAIF) are some of the most common fasciocutaneous flaps used for head and neck (H&N) reconstruction. MATERIAL AND METHODS: A retrospective analysis of clinical data and outcomes of 31 consecutive patients who underwent H&N reconstruction using either SCAIF or RFFF over a three-year period, aiming to compare the surgical outcomes of the SCAIF and the RFFF in H&N reconstruction. RESULTS: Thirty-two flaps were performed in 31 patients (17 SCAIFs and 15 RFFFs). There was no difference in patient demographics between both groups. Hospital stay was longer in the SCAIF group (30.7 ± 18.2 days (min: 9/max: 60) versus 19.2 ± 15.8 days (min: 7/max: 72). Patients who underwent reconstruction with a SCAIF had shorter reconstructive procedure time; 74.4 min (min: 60/max: 93) versus 147.8 min (min: 140/max: 187). Overall morbidity was not significantly different (SCAIF 52.7% vs RFFF 39.9%, p = NS). Global flap survival was higher without statistical significance in the RFFF group (100%) versus the SCAIF group (70.7%). CONCLUSION: Despite the advantages related to the use of SCAIF like regarding the time spent in the reconstructive procedure. In our experience, the RFFF continues to be the most successful technique with similar perioperative outcomes and fewer complication rates. In this vein, both techniques can be reasonably used to reconstruct post-ablative H&N defects. However, in our experience, the use of SCAIF may lengthen hospital length of stay probably due to the augmented risk of flap failure.

Artificial Neural Network as a Tool to Predict Facial Nerve Palsy in Parotid Gland Surgery for Benign Tumors.

(1) Background: Despite the increasing use of intraoperative facial nerve monitoring during parotid gland surgery or the improvement in the preoperative radiological assessment, facial nerve injury (FNI) continues to be the most feared complication; (2) Methods: patients who underwent parotid gland surgery for benign tumors between June 2010 and June 2019 were included in this study aiming to make a proof of concept about the reliability of an artificial neural networks (AAN) algorithm for prediction of FNI and compared with a multivariate linear regression (MLR); (3) Results: Concerning prediction accuracy and performance, the ANN achieved the highest sensitivity (86.53% vs 46.23%), specificity (95.67% vs 92.59%), PPV (87.28% vs 66.94%), NPV (95.68% vs 83.37%), ROC-AUC (0.960 vs 0.769) and accuracy (93.42 vs 80.42) than MLR; and (4) Conclusions: ANN prediction models can be useful for otolaryngologists-head and neck surgeons-and patients to provide evidence-based predictions about the risk of FNI. As an advantage, the possibility to develop a calculator using clinical, radiological and histological or cytological information can improve our ability to generate patients counselling before surgery.

Systematic review of international guidelines for tracheostomy in COVID-19 patients.

At this moment, the world lives under the SARS-CoV-2 outbreak pandemic. As Otolaryngologists - Head & Neck Surgeons, we need to perform and participate in examinations and procedures within the head and neck region and airway that carry a particularly high risk of exposure and infection because of aerosol and droplet contamination. One of those surgical procedures in demand at this moment is tracheostomy due the increasing ICU admissions. This review of international guidelines for tracheostomy in COVID-19 infected patients, aims to summarize in a systematic way the available recommendations: indications, timing, technique and safety measures for tracheostomy, from all over the world.

CO2 Transoral Laser Microsurgery in Benign, Premalignant and Malignant (Tis, T1, T2) Lesion of the Glottis. A Literature Review.

Carbon Dioxide transoral laser microsurgery represents a reliable option for the treatment of early glottic carcinoma (Tis-T2), with good functional and oncological outcomes, nowadays representing one of the main options in larynx preservation protocols. The development and improvement of laser devices means surgeons are able to use more precise instruments compared with classic cold dissection in laser-assisted phonosurgery. Secondary effects on voice, swallowing, or quality of life as well as complications have been well documented. Also, with the introduction of a new proposal for staging systems following the principle of the three-dimensional map of isoprognostic zones, the use of narrow-band imaging in clinical evaluation and intraoperative, and the implementation of diffusion-weighted magnetic resonance during preoperative evaluation, the development of new tools to improve surgical quality and preliminary reports regarding the use of carbon dioxide laser in transoral robotic surgery suggests an exciting future for this technique.