A trusted tool with practical limits
The goniometer is a fixture of the clinic for good reason — it's simple, inexpensive, and familiar. But measuring joint range of motion by hand has well-known friction: aligning the device with anatomical landmarks takes care, results vary between clinicians, and capturing a full picture of a moving joint one angle at a time is slow. A classic review of goniometry found its reliability depends on the instrument and procedure, the joint and motion being measured, and whether the same or different testers take the measurements — and urged clinicians to adopt standardized methods (Gajdosik and Bohannon, 1987). In a busy schedule, measurements get estimated or skipped.
How markerless capture measures motion
Computer-vision methods identify joint positions directly from video, which means a joint's angle can be derived throughout an entire movement rather than at a single static endpoint. Instead of reading one number off a protractor, a clinician can capture how the joint moves across its whole range — and do it the same way every time, without manual alignment.
Repeatability is the practical win
The biggest day-to-day advantage is repeatability. Because the method doesn't depend on how a clinician holds a device, the same movement tends to produce the same measurement, which is exactly what's needed to track change over time. In one reliability study of an AI-driven markerless system, between-session agreement for sagittal-plane joint angles was high, while frontal- and transverse-plane angles were less consistent (Schoenwether et al., 2025). Accuracy also varies by joint and plane: a 2022 scoping review concluded that markerless joint-center and joint-angle estimates were not yet accurate enough for clinical use across the board, even as spatiotemporal measures looked equivalent to marker-based systems (Wade et al., 2022). So it matters which joints, motions, and planes a tool has been validated for. Our validation page summarizes that evidence. That consistency makes progress easier to demonstrate and documentation easier to defend.
Fitting into the workflow
Objective range-of-motion capture isn't about discarding decades of clinical practice — it's about removing the manual friction that keeps a useful measurement from being taken consistently. Read alongside clinical judgment, faster and more repeatable range-of-motion data lets clinicians measure more often, compare more confidently, and spend less of the visit wrestling with a protractor.
References
- Gajdosik RL, Bohannon RW. Clinical measurement of range of motion: review of goniometry emphasizing reliability and validity. Physical Therapy. 1987;67(12):1867-1872. doi:10.1093/ptj/67.12.1867
- Schoenwether B, Ripic Z, Nienhuis M, Signorile JF, Best TM, Eltoukhy M. Reliability of artificial intelligence-driven markerless motion capture in gait analyses of healthy adults. PLOS ONE. 2025;20(1):e0316119. doi:10.1371/journal.pone.0316119
- Wade L, Needham L, McGuigan P, Bilzon J. Applications and limitations of current markerless motion capture methods for clinical gait biomechanics. PeerJ. 2022;10:e12995. doi:10.7717/peerj.12995