Smartphone Neck-Vein Waveform Analysis

ISEF Category: Translational Medical Science

Subcategory: Disease Detection and Diagnosis  ·  Difficulty: Advanced  ·  Setup: University Lab  ·  Time: Full Year

The Hook

A tiny pulse in your neck can reveal how hard your heart is working. Doctors read that signal by eye, but video can turn it into data. With the right analysis, your phone may capture a waveform that tracks fluid buildup and heart strain.

What Is It?

Jugular venous pressure, or JVP, describes the pressure in the veins in your neck. When the right side of the heart struggles, that pressure can rise, and the vein pulse can change shape. Think of it like a soft hose connected to a pump, if the pump backs up, the hose swells and the pressure waves look different.

Eulerian video magnification is a computer method that amplifies tiny changes in a video. It can make small skin motions or color shifts easier to see. In this project, you would analyze neck videos to see whether the visible vein pulse contains patterns linked to heart failure risk. You would not diagnose patients. You would test whether the signal can be measured cleanly and whether waveform features match known bedside markers.

Why This Is a Good Topic

This topic is testable because you can measure video quality, signal strength, and waveform features without building a wet-lab setup. It connects to a real clinical need, since fast, contact-free screening could help flag people who need urgent care. You can learn computer vision, signal processing, and medical data analysis in one project.

Research Questions

• How does Eulerian video magnification affect the detectability of jugular venous waveform features in smartphone footage?
• What is the effect of recording angle on the signal-to-noise ratio of neck-vein pulse measurements?
• Does skin tone or lighting condition change the accuracy of waveform feature extraction from smartphone video?
• To what extent do waveform morphology features from public bedside-camera datasets separate decompensated heart-failure cases from control cases?
• Which video preprocessing method gives the most stable peak timing across repeated neck recordings?
• What is the effect of frame rate on the reliability of jugular venous pressure waveform measurement?

Basic Materials

• Smartphone with a rear camera that can record high-frame-rate video.
• Tripod or phone stand.
• Plain background cloth or wall space.
• Small ruler or calibration marker.
• Consent form and human-subjects protocol materials if you record people.
• Laptop with enough storage for large video files.
• Spreadsheet software for organizing measurements.

Advanced Materials

• Access to public bedside-camera or clinical video datasets.
• High-frame-rate camera or smartphone with manual recording settings.
• Controlled lighting setup with soft, even illumination.
• Reference pulse sensor or synchronized physiological signal source if available.
• MATLAB, Python, or similar environment for video and signal analysis.
• Secure storage for de-identified human data.
• Institutional review board or school human-subjects paperwork if new recordings are collected.

Software & Tools

• ImageJ: Measures frame-by-frame changes and helps inspect motion and contrast in neck videos.
• Python: Runs preprocessing, feature extraction, and statistical comparisons across recordings.
• OpenCV: Detects regions of interest, tracks motion, and handles video frames.
• NumPy and SciPy: Support signal filtering, peak finding, and basic statistics.
• Jupyter Notebook: Keeps your analysis steps organized and easy to revise.

Experiment Steps

1. Define the exact signal feature you want to measure, such as peak timing, waveform shape, or motion amplitude.
2. Choose one recording setup and lock it down so your comparisons stay fair.
3. Plan how you will isolate the neck region and remove obvious noise from camera motion, lighting changes, and background movement.
4. Build a comparison method that turns video changes into numeric features you can test against reference labels or known clinical groupings.
5. Decide on controls that check whether the signal comes from the vein pulse, not from breathing, swallowing, or head motion.
6. Pre-plan your statistics so you can compare methods, report uncertainty, and test whether any effect survives repeat trials.

Common Pitfalls

• Recording with a moving phone, which creates fake motion signals that can overwhelm the neck pulse.
• Using inconsistent lighting, which changes color and contrast enough to distort magnified features.
• Picking the wrong region of interest, which captures throat motion or skin texture instead of the jugular area.
• Treating every visible pulse as a vein signal, which can confuse arterial motion, swallowing, and muscle twitches with JVP.
• Comparing results across people without handling placement and anatomy differences, which can make the classifier look better than it really is.

What Makes This Competitive

A strong version of this project does more than make videos look clearer. It tests whether the extracted waveform is repeatable, whether the signal survives across lighting and pose changes, and whether the features actually separate clinical groups. A more competitive entry also compares methods, such as raw motion, color change, and magnification, then uses careful statistics to show which one adds real value.

Project Variations

• Analyze neck-vein videos from healthy volunteers instead of clinical datasets, then test which preprocessing pipeline gives the cleanest waveform.
• Compare Eulerian magnification with simple optical-flow tracking to see which method captures venous pulse shape more reliably.
• Focus on one feature, such as peak-to-trough timing, and test whether it correlates with a separate heart-rate or respiration measure.

Learn More

• PubMed: Search review articles on jugular venous pressure, heart failure screening, and remote monitoring.
• NIH PubMed Central: Find free full-text papers on video-based physiological signal extraction.
• NASA Open Courseware or MIT OpenCourseWare: Look for free signal processing and image analysis lectures and notes.
• OpenCV Documentation: Read the official guides for video frame handling and motion analysis.
• US National Library of Medicine MedlinePlus: Review background on heart failure and related symptoms in clear patient-facing language.