AI-Powered Smartphone Diagnostics: A Game-Changer for Nystagmus Detection

Reviewed byNidhi Govil

4 Sources

Share

Researchers at Florida Atlantic University have developed an AI-based system that uses smartphone videos to diagnose nystagmus, offering a cost-effective and accessible alternative to traditional diagnostic methods.

Revolutionizing Nystagmus Diagnosis with AI and Smartphones

Researchers at Florida Atlantic University (FAU) have developed a groundbreaking artificial intelligence (AI) system that could transform the diagnosis of nystagmus, a condition characterized by involuntary eye movements often associated with vestibular or neurological disorders. This innovative approach leverages smartphone technology and deep learning to offer a cost-effective and accessible alternative to traditional diagnostic methods

1

2

3

4

.

The Challenge of Traditional Diagnostics

Conventional diagnostic tools for nystagmus, such as videonystagmography (VNG) and electronystagmography, while effective, come with significant drawbacks. These include:

  • High costs (VNG equipment often exceeding $100,000)
  • Bulky setups
  • Inconvenience for patients during testing

These limitations have long posed challenges for widespread accessibility, particularly in remote or underserved areas

1

2

3

4

.

AI-Powered Solution: How It Works

Source: Neuroscience News

Source: Neuroscience News

The FAU team's novel deep learning model offers a patient-friendly alternative for screening balance disorders and abnormal eye movements. Key features of the system include:

  1. Smartphone video recording of eye movements
  2. Secure upload to a cloud-based system
  3. Remote diagnostic analysis by vestibular and balance experts

At the core of this innovation is a deep learning framework that utilizes real-time facial landmark tracking. The AI system:

  • Automatically maps 468 facial landmarks
  • Evaluates slow-phase velocity (a crucial metric for identifying nystagmus intensity, duration, and direction)
  • Generates intuitive graphs and reports for clinician interpretation during virtual consultations

    1

    2

    3

    4

Promising Early Results

A pilot study involving 20 participants, published in Cureus, demonstrated that the AI system's assessments closely mirrored those obtained through traditional medical devices. This early success underscores the model's potential for clinical reliability

1

2

3

4

.

Technical Aspects and Development

The research team trained their algorithm on over 15,000 video frames, using a structured 70:20:10 split for training, testing, and validation. This rigorous approach ensures the model's robustness across varied patient populations. The AI also employs intelligent filtering to eliminate artifacts such as eye blinks, ensuring accurate and consistent readings

1

2

3

4

.

Broader Implications and Future Directions

Beyond diagnostics, the system is designed to streamline clinical workflows. Physicians and audiologists can access AI-generated reports via telehealth platforms, compare them with patients' electronic health records, and develop personalized treatment plans

1

2

3

4

.

In parallel, FAU researchers are experimenting with a wearable headset equipped with deep learning capabilities to detect nystagmus in real-time. While early tests in controlled environments have shown promise, further improvements are needed to address challenges such as sensor noise and individual user variability

1

2

3

4

.

Source: Medical Xpress

Source: Medical Xpress

Collaborative Effort and Next Steps

This interdisciplinary initiative involves collaborators from various FAU colleges and external partners. The team is working to enhance the model's accuracy, expand testing across diverse patient populations, and move toward FDA approval for broader clinical adoption

1

2

3

4

.

Source: News-Medical

Source: News-Medical

As telemedicine becomes increasingly integral to healthcare delivery, AI-powered diagnostic tools like this one have the potential to improve early detection, streamline specialist referrals, and reduce the burden on healthcare providers, ultimately promising better outcomes for patients regardless of their location

1

2

3

4

.

TheOutpost.ai

Your Daily Dose of Curated AI News

Don’t drown in AI news. We cut through the noise - filtering, ranking and summarizing the most important AI news, breakthroughs and research daily. Spend less time searching for the latest in AI and get straight to action.

© 2025 Triveous Technologies Private Limited
Instagram logo
LinkedIn logo