Zakia Hammal
Carnegie Mellon University, PA·Computer Science
Pain is usually measured by simply asking patients, through an interview or a visual analog scale where they mark their pain on a line. Self-reports can be hard to interpret, and sometimes patients cannot give them at all.
- Fields
Computer Science
Biomedical Engineering
Medicine & Clinical Research
- Topics
pain assessment
low back pain
chronic pain
- Grants
- 1 known grant, through Dec 2026
What they work on
- Develop automatic measures of whether pain is present and how intense it is in five types of low back pain, by training deep learning classifiers on tracked face, head and body movement from clinical exam videos.
- Validate the automated pain measures against patient and clinician visual analog scale ratings, the Brief Pain Inventory and continuous observer ratings, using MANOVA to compare face, head and body signals alone and combined.
- Identify factors linked to acute low back pain becoming chronic, using Ecological Momentary Assessment, repeated daily smartphone prompts over six months, to track pain and behavior in everyday life.
More about the research
This project asks whether computers can measure pain objectively from video of how people move their face, head and body. It focuses on low back pain (LBP), one of the most common and disabling pain conditions, and asks why acute back pain becomes chronic for some people.
Why it matters
Patients who cannot reliably report their pain, and clinicians who struggle to interpret those reports, could benefit from an automatic video-based pain measure. For people with low back pain, the work could also reveal early signs that acute pain will turn chronic, which could guide earlier intervention and better pain management.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Melvin McInnis
University of Michigan, MI·Medicine & Clinical Research
Test whether average levels of emotional valence and arousal, measured by phone self-ratings (EMA) and by the PRIORI speech algorithm, predict self-reported and clinician-rated mood severity in 160 adults with bipolar disorder.
Anna Kratz
University of Michigan, MI·Psychology·Early-career
Test whether smartphone-delivered ambulatory cognitive tests and real-time self-reports detect two-year changes in cognitive function in multiple sclerosis more sensitively than conventional clinic-based snapshot assessments.
Kevin Kuehn
University of California-San Diego, CA·Psychology·Early-career
Refine the personalized suicide prevention intervention PRECISE using a user-centered design approach and a case series with high-risk adults.
The school
Carnegie Mellon University: 28 labs on PI Pages, $505M a year on research, 346 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.