A Ready-to-Use Grading Tool for Facial Palsy Examiners—Automated Grading System in Facial Palsy Patients Made Easy

Abstract

Background: The grading process in facial palsy (FP) patients is crucial for time- and cost-effective therapy decision-making. The House-Brackmann scale (HBS) represents the most commonly used classification system in FP diagnostics. This study investigated the benefits of linking machine learning (ML) techniques with the HBS. Methods: Image datasets of 51 patients seen at the Department of Plastic, Hand, and Reconstructive Surgery at the University Hospital Regensburg, Germany, between June 2020 and May 2021, were used to build the neural network. A total of nine facial poses per patient were used to automatically determine the HBS. Results: The algorithm had an accuracy of 98%. The algorithm processed the real patient image series (i.e., nine images per patient) in 112 ms. For optimized accuracy, we found 30 training runs to be the most effective training length. Conclusion: We have developed an easy-to-use, time- and cost-efficient algorithm that provides highly accurate automated grading of FP patient images. In combination with our application, the algorithm may facilitate the FP surgeon’s clinical workflow.

Pure Wisdom or Potemkin Villages? A Comparison of ChatGPT 3.5 and ChatGPT 4 on USMLE Step 3 Style Questions: Quantitative Analysis

“…Artificial intelligence (AI)-supported tools have been proposed for a variety of medical scenarios, including preoperative outcome simulation, patient education, and automated disease grading [6][7][8][9]. Recently, chatbots such as ChatGPT have emerged as next-generation AI technology.…”

DeepSmile: Anomaly Detection Software for Facial Movement Assessment

“…Compared with other deep learning models that leverage on qualitative grading system to evaluate facial pathologies ( [59,60]), our LSTM model provides an objective assessment that exploits motion capture data. Furthermore, marker positions are more accurate than landmark positions because metric measurements are directly recorded rather than being estimated from the image space ( [22]).…”

An ACS-NSQIP Data Analysis of 30-Day Outcomes Following Surgery for Bell’s Palsy

“…The ACS-NSQIP database misses details on short-term (<30 days) complications, including hematoma and seroma, with the postoperative follow-up being limited to 30 days 48,49 . Thus, long-term complications and reoperations (such as brow ptosis correction, management of upper and lower eyelid dysfunction by weight placement and lateral tarsal strip procedure, respectively, tarsorrhaphy, and palpebral spring procedure) were not recorded 1,2,5,50–52 . Similarly, no data were available on long-term corrective procedures of the midface, including nasolabial fold modification, external nasal valve repair, or static facial suspension 53,54 .…”

“…48,49 Thus, long-term complications and reoperations (such as brow ptosis correction, management of upper and lower eyelid dysfunction by weight placement and lateral tarsal strip procedure, respectively, tarsorrhaphy, and palpebral spring procedure) were not recorded. 1,2,5,[50][51][52] Similarly, no data were available on long-term corrective procedures of the midface, including nasolabial fold modification, external nasal valve repair, or static facial suspension. 53,54 The outcomes of such procedures are only captured in long-term follow-up studies.…”