Automated analysis of spontaneous eye blinking in patients with acute facial palsy or facial synkinesis

Lukas Schuhmann, Tim Büchner, Martin Heinrich, Gerd Fabian Volk, Joachim Denzler, Orlando Guntinas‐LichiusScientific 2024 · DOI

TL;DR

This paper introduces an automated, smartphone-based system for analyzing spontaneous eye blinking in patients with facial palsy. The system objectively quantifies blinking impairments, revealing reduced blink frequency and prolonged blink duration in affected individuals, which are not adequately captured by current patient-reported outcome measures.

What Problem Does This Paper Address?

Eye blinking is a crucial protective mechanism for the eyes, but it's often compromised in individuals with facial palsy, leading to visual impairment and reduced quality of life. Current clinical assessments of facial palsy don't typically include objective measures of eye blinking. While patient-reported outcome measures (PROMs) like the FaCE and FDI exist, they don't specifically address blinking issues. This study aims to bridge this gap by developing and validating an automated tool to objectively quantify spontaneous eye blinking in patients with acute facial palsy and facial synkinesis, comparing them to healthy controls.

Methods

The core of this research is the "Jena Facial Palsy Toolbox" (JeFaPaTo), a custom computer program designed for automated blinking analysis. The process involves:

  • Video Recording: 20-minute resting videos of participants' faces were captured using a smartphone.
  • Automated Face and Landmark Detection: The program utilizes the MediaPipe library to detect faces and extract 468 facial landmarks.
  • Eye Aspect Ratio (EAR) Calculation: From the eye landmarks, the Eye Aspect Ratio (EAR) is computed. EAR is a measure of eye openness, decreasing as the eye closes. This allows for detailed tracking of eyelid movement during blinking.
  • Blink Detection and Quantification: The software automatically detects and counts blinks, and quantifies their frequency and duration.
  • Patient-Reported Outcomes: Participants also completed the Facial Clinimetric Evaluation (FaCE) and Facial Disability Index (FDI) questionnaires to assess their quality of life.

Datasets

The study involved two groups:

  • Patients: 30 individuals with facial palsy (6 with acute palsy, 24 with facial synkinesis).
  • Healthy Controls: 30 age- and gender-matched healthy individuals.

The data collected consisted of 20-minute smartphone video recordings of spontaneous eye blinking at rest for each participant.

Key Insights and Ideas

  • Objective Blinking Metrics are Crucial: The study highlights that standard clinical assessments and PROMs fall short in capturing the nuances of blinking impairments in facial palsy. Automated analysis provides objective, quantifiable data.
  • Facial Synkinesis Also Impairs Blinking: Beyond acute facial palsy, the research demonstrates that facial synkinesis also significantly impacts spontaneous eye blinking, a finding not extensively studied before.
  • Contralateral Eye Compensation: In patients with facial synkinesis, there's a suggestion that the contralateral eye might actively open more, potentially as a compensatory mechanism.
  • PROMs Don't Capture Blinking: A significant finding is the lack of correlation between the objective blinking parameters and the scores from established PROMs (FaCE and FDI). This underscores the need for dedicated blinking assessment tools.

Key Results

  • Reduced Blink Frequency: Patients with both acute facial palsy and facial synkinesis exhibited significantly lower blink frequencies on the affected (paretic) side compared to healthy controls.
  • Prolonged Blink Duration: Conversely, blink duration was significantly longer in both patient groups compared to healthy controls.
  • Impaired Eye Closure: The minimal EAR (indicating the degree of eye closure) was significantly higher on the paretic side in patients with acute facial palsy, signifying less complete eye closure.
  • No Correlation with Quality of Life: Despite the objective impairments, the study found no significant correlation between blinking parameters and the FaCE or FDI scores, suggesting these PROMs do not adequately reflect blinking-related quality of life issues.

Limitations and Future Work

  • Small Sample Size for Acute Palsy: The group with acute facial palsy was particularly small (N=6), limiting the statistical power for this specific subgroup.
  • Focus on Spontaneous Blinking at Rest: The study only analyzed spontaneous blinking at rest. Future work could investigate voluntary blinking, reflex blinking, and blinking during daily activities (e.g., talking, smiling).
  • Limited Blink Parameter Scope: While EAR, frequency, and duration were analyzed, other blink parameters like peak velocity and amplitude, which are also affected in facial palsy, are not yet implemented in the tool.
  • Asymmetry Not Analyzed: The asymmetry of blinking between the two eyes was not assessed but is suggested as an important future addition.
  • Future Directions: The authors propose expanding the software to include more blink parameters, analyzing blinking during various activities, and applying the tool to other oculofacial conditions like hemifacial spasm, blepharospasm, and Parkinson's disease. They also envision using the tool for home-based video recordings and potentially integrating it into clinical routine grading.

Summary updated

Abstract

Although patients with facial palsy often complain of disturbed eye blinking which may lead to visual impairment, a blinking analysis is not part of routine grading of facial palsy. Twenty minutes of spontaneous eye blinking at rest of 30 patients with facial palsy (6 with acute palsy; 24 patients with facial synkinesis; median age: 58 years, 67% female), and 30 matched healthy probands (median age: 57 years; 67% female) was smart phone video recorded. A custom computer program automatically extracted eye measures and determined the eye closure rate (eye aspect ratio [EAR]), blink frequency, and blink duration. Facial Clinimetric Evaluation (FaCE), Facial Disability Index (FDI) were assessed as patient-reported outcome measures. The minimal EAR, i.e., minimal visible eye surface during blinking, was significantly higher on the paretic side in patients with acute facial palsy than in patients with synkinesis or in healthy controls. The blinking frequency on the affected side was significantly lower in both patient groups compared to healthy controls. Vice versa, blink duration was longer in both patient groups. There was no clear correlation between the blinking values and FaCE and FDI. Blinking parameters are easy to estimate automatically and add a functionally important parameter to facial grading.
BibTeX
@inproceedings{schuhmann2024automated,
  author = {Lukas Schuhmann and Tim Büchner and Martin Heinrich and Gerd Fabian Volk and Joachim Denzler and Orlando Guntinas‐Lichius},
  title = {{Automated analysis of spontaneous eye blinking in patients with acute facial palsy or facial synkinesis}},
  booktitle = {Scientific},
  year = {2024},
  doi = {10.1038/s41598-024-68707-x},
}
Figure