Novel evaluation method for facial nerve palsy using 3D facial recognition system in iPhone.

OBJECTIVE: While subjective methods like the Yanagihara system and the House-Brackmann system are standard in evaluating facial paralysis, they are limited by intra- and inter-observer variability. Meanwhile, quantitative objective methods such as electroneurography and electromyography are time-consuming. Our aim was to introduce a swift, objective, and quantitative method for evaluating facial movements. METHODS: We developed an application software (app) that utilizes the facial recognition functionality of the iPhone (Apple Inc., Cupertino, USA) for facial movement evaluation. This app leverages the phone's front camera, infrared radiation, and infrared camera to provide detailed three-dimensional facial topology. It quantitatively compares left and right facial movements by region and displays the movement ratio of the affected side to the opposite side. Evaluations using the app were conducted on both normal and facial palsy subjects and were compared with conventional methods. RESULTS: Our app provided an intuitive user experience, completing evaluations in under a minute, and thus proving practical for regular use. Its evaluation scores correlated highly with the Yanagihara system, the House-Brackmann system, and electromyography. Furthermore, the app outperformed conventional methods in assessing detailed facial movements. CONCLUSION: Our novel iPhone app offers a valuable tool for the comprehensive and efficient evaluation of facial palsy.

Impact of Changing Surgical Strategies on Clinical Outcomes in Patients with Parotid Carcinoma: A 53-Year Single-Institution Experience.

Background and Objectives: We investigated the clinical outcomes of patients who underwent surgery for parotid carcinoma in a single institution during a 53-year period. This study aimed to estimate the impact of changing the surgical approach to parotid carcinoma on clinical outcomes including the incidence rate of the facial nerve palsy. Materials and Methods: Sixty-seven patients with parotid carcinoma who underwent surgery between 1966 and 2018 were retrospectively reviewed. Group A consisted of 29 patients who underwent surgery from 1966 to 2002, and Group B consisted of 38 patients from 2002 to 2018. Treatment outcomes were estimated. Additionally, candidate prognostic factors of Group B, the current surgical approach group, were evaluated. Results: Partial parotidectomy and total parotidectomy were performed in 35 and 32 patients, respectively. Partial parotidectomy was performed in 4 patients in Group A and 31 patients in Group B, with a predominant increase in Group B. The facial nerve was preserved in 43 patients, among whom 8 in Group A (8/17; 47.1%) and 7 in Group B (7/26; 26.9%) had temporary postoperative facial nerve palsy. Postoperative radiotherapy was performed on 35 patients. The 5-year OS, DSS, and DFS rates for Group A were 77.1%, 79.9%, and 71.5%, respectively. The 5-year OS, DSS, and DFS rates for Group B were 77.1%, 77.1%, and 72.4%, respectively. Clinical T4 stage, clinical N+ stage, stage IV disease, and tumor invasion of the facial nerve were independent prognostic factors in Group B. Conclusions: The incidence of facial nerve palsy in the current surgical approach group decreased compared with that in the previous surgical approach group. The current surgical management and treatment policies for parotid carcinoma have led to improved outcomes.

Objective Assessment of Pathological Voice Using Artificial Intelligence Based on the GRBAS Scale.

OBJECTIVES: The validity and reliability of the psychological assessment of auditory perceptions, as typified by the grade, roughness, breathiness, asthenia, and strain (GRBAS) scale, have been widely recognized. However, due to their subjective nature, inter- and intra-examiner reliability are unavoidable. In this study, we aimed to add objectivity to the GRBAS scale using artificial intelligence and to compare the accuracy of two methods-one based on Google's TensorFlow and another based on Apple's Core ML. METHODS: The GRBAS scale of 1,377 vowel samples was evaluated and used as training data to create a machine learning model. We used TensorFlow and Apple's Create ML to create two machine learning models and examined the difference in their accuracies for classifying the severity of pathological Voice data based on the GRBAS scale. RESULTS: Absolute comparisons are difficult to make because of the difference in methods; however, both training models could objectively evaluate GRBAS scales and were statistically correlated in G and B. CONCLUSION: While TensorFlow requires creation of a training model from scratch, Create ML is a relatively easy way to create a training model for voice by adding training data for GRBAS scales to an existing training model for sounds. Although the data handling and learning methods are different, both models performed well. Findings from this study could be used for medical screening purposes, and there is the potential to change the clinical approach to voice diagnostics in the future.