# Automated Neuromuscular Assessment: Machine-Learning-Based Facial Palsy Classification Using Surface Electromyography

## TL;DR

A machine learning approach using surface EMG data can classify facial palsy severity with high accuracy, offering a non-invasive alternative to traditional methods.

## Contribution

Ensemble machine learning models achieve reliable classification of facial palsy grades using surface EMG data.

## Key findings

- Time-domain EMG features during facial movements reflect facial nerve dysfunction effectively.
- Ensemble ML models achieved up to ~84.8% accuracy in automated HB classification from EMG data.
- Random forest and decision tree ensembles were most effective for classifying facial palsy severity.

## Abstract

What are the main findings?
Time-domain EMG features during facial movements effectively reflect facial nerve dysfunction.Ensemble ML models achieved up to ~84.8% accuracy in automated HB classification from EMG data in facial palsy.

Time-domain EMG features during facial movements effectively reflect facial nerve dysfunction.

Ensemble ML models achieved up to ~84.8% accuracy in automated HB classification from EMG data in facial palsy.

What are the implications of the main findings?
EMG-based ML enables objective, non-invasive assessment of facial palsy severity.This method can enhance diagnostic consistency and enable longitudinal monitoring in both clinical practice and research settings.

EMG-based ML enables objective, non-invasive assessment of facial palsy severity.

This method can enhance diagnostic consistency and enable longitudinal monitoring in both clinical practice and research settings.

Facial palsy (FP) impairs voluntary control of facial muscles, resulting in facial asymmetry and difficulties in emotional expression. Traditional assessment methods to define the severity of FP (e.g., House–Brackmann score, HB) rely on visual examinations and, therefore, are highly examiner-dependent. This study proposes an alternative approach using facial surface electromyography (EMG) for automated HB prediction. Time-domain EMG features were extracted during different facial movements (i.e., smile, close eyes, and raise forehead) and analyzed through nine different machine learning (ML) models in 58 subjects (51.98 ± 1.67 years, 20 male) with variable facial nerve function (HB 1: n = 16, HB 2–3: n = 32; HB 4–6: n = 10). Model performances were evaluated based on accuracy, precision, recall, and F1-score. Among the evaluated models, ensemble-based approaches—particularly a random forest model with 100 trees and a decision tree ensemble—proved to be the most effective with classification accuracies ranging from 81.7 to 84.8% and from 81.7 to 84.7%, depending on the evaluated facial movement. The results indicate that ensemble-based ML models can reliably distinguish between different FP grades using non-invasive EMG data. The approach offers a robust alternative to subjective clinical scoring, potentially improving diagnostic consistency and supporting longitudinal monitoring in clinical and research applications.