Behavioral endpoints carry weight in non-human primate (NHP) drug development, especially when a therapeutic effect does not show up in biochemical or structural readouts. Locomotion, posture, gait, spontaneous activity, scratching, facial responses: a shift in any of these can be functional evidence of disease progression or treatment response.

NHP behavior is continuous and highly multidimensional, while conventional assessment leans on manual observation, video review, or predefined scoring systems. Those methods work, but they consume time and carry inter-observer variability, which matters most when the change you want to quantify is subtle or slow to develop.
Computer vision and AI offer another route: ordinary multi-view video turned into structured three-dimensional behavioral data. Markerless tracking converts movement into quantitative kinematic and ethological endpoints, so a video no longer has to be a record someone sits through.
The open question for NHP translational work is whether video-derived measurements become scientifically meaningful endpoints for characterizing disease and evaluating pharmacology.
From Video to 3D Pose: How Markerless Tracking Works
Markerless 3D behavioral analysis pairs synchronized multi-view video acquisition with computer vision and deep-learning-based pose estimation.
The animal carries no reflective markers or sensors. The system identifies anatomical key points directly from the video frames, and multiple camera views fill in each other's blind spots, which eases the occlusion and perspective problems that plague single-view 2D analysis. Posture and movement can then be reconstructed in three dimensions. Prisys' AI-based NHP behavior analysis system tracks more than 21 anatomical key points, enough to characterize whole-body movement and joint-related kinematics quantitatively.
The pipeline runs from multi-view video capture through 3D pose reconstruction and behavioral segmentation to parameter extraction, and ends at a pharmacological endpoint.
Pose estimation is a means to that endpoint. Its value lies in turning thousands or millions of individual movement observations into behavioral features an investigator can interpret.
What Can Be Quantified from NHP Movement?
Once 3D pose data exist, a whole layer of parameters opens up.
Kinematics first: position, velocity, movement trajectory, posture, gait characteristics, limb coordination, joint-related movement patterns. Behavior follows, with movement sequences segmented into recognizable behavioral states and analyzed over defined observation windows. Prisys' platform documentation describes automated decomposition of behavioral sequences with temporal precision down to the scale of seconds, which moves a study past isolated behavioral scores toward continuous behavioral profiles.
A written note that an animal "showed increased activity" records only the conclusion. Tracking data record when activity rose, how long it held, which movement patterns drove the change, and whether the timing lined up with dosing. That is a finer-grained picture of phenotype and treatment response.
Why Markerless Analysis Matters in NHP Studies
Markerless tracking collects behavioral data without attaching anything to the animal.
Marker-based motion capture gives detailed movement information, but attaching markers or sensors means extra handling, and the hardware can interfere with the very movement being measured. Markerless capture sidesteps that, which matters most when spontaneous behavior is itself the endpoint of interest. Prisys' technical framework combines markerless tracking with synchronized multi-view acquisition and deep-learning-based analysis, automating key-point tracking and behavioral analysis while trimming occlusion and perspective limits.
Markerless tracking removes the markers, not the requirement for validation. AI-derived behavioral endpoints still need model-specific validation, and the webinar recap made this point directly: algorithmic outputs should be checked against suitable human-reviewed references and read in the context of the animal model, the study design, and the research question. That requirement is stronger when behavioral classification serves as a pharmacodynamic endpoint rather than exploratory observation.
From Movement to Pharmacological Endpoints
Movement data become translational when they are tied to a specific biological or pharmacological question.
In an efficacy study, the endpoint is not movement itself but whether treatment reduces a pathological behavior, restores motor function, or changes the trajectory of disease progression.
Three application areas from the Prisys and Bayone NHP BehaviorAtlas webinar show what that looks like.
Pain and Pruritus
Scratching is a good candidate for objective quantification.
Pruritus studies need scratching frequency, duration, temporal distribution, and movement characteristics. Manual scoring works but becomes punishing when observations repeat over hours or days. 3D tracking characterizes scratching as a structured movement sequence rather than a count of visible events, and trajectory, posture, and spatial relationships help separate scratching from grooming or routine limb movement.
At Prisys, this analysis slots into NHP pruritus studies, including the IL-31-induced cynomolgus macaque model, which produces measurable scratching behavior and inflammatory responses for evaluating anti-pruritic and related therapeutic strategies. The behavioral measurements sit alongside clinical observations, inflammatory biomarkers, and pathological assessments as complementary pharmacodynamic endpoints.
Neurological and Motor Function
Motor phenotypes are the other natural fit.
In NHP models of Parkinson's disease, stroke, and other neurological disorders, the functional changes show up in gait, posture, spontaneous activity, limb use, coordination, or movement velocity. A single observational score struggles to capture all of that. 3D tracking represents movement as a time-dependent dataset, so behavioral features can be compared longitudinally before and after disease induction or treatment. Gait symmetry, movement velocity, posture transitions, and limb coordination get evaluated together instead of as isolated notes.
That matters in efficacy studies where functional recovery builds progressively rather than arriving as a clean yes or no.
Facial Expression and Pain-Related Responses
Phenotyping extends beyond whole-body movement.
The webinar covered 3D facial modeling and expression analysis as a way to catch subtle responses associated with pain or discomfort, quantifying changes in facial geometry and movement instead of leaning on subjective visual interpretation. This is still an emerging application. It should be read alongside established clinical observations, physiological measurements, and other study endpoints, with annotation, model-specific characterization, and validation in place before facial features serve as a formal pharmacodynamic endpoint.
Why Continuous Behavioral Data Improves Study Interpretation
Conventional assessment samples behavior at fixed time points, so a treatment-related behavioral change that happens between observation windows goes undetected. Continuous or repeated automated monitoring fills in a denser temporal record.
Timing matters in pharmacology because a behavioral effect is often tied to drug exposure. Drug administration leads to exposure, then to a pharmacodynamic response, then to a behavioral change.
Collected alongside PK/PD data, behavioral measurements can answer whether behavior changed inside the expected pharmacological window and whether the size of the response tracks with exposure. The behavioral endpoint becomes one component of a broader translational dataset instead of an isolated observation.
Integrating Behavioral Phenotyping with NHP Translational Research
Behavioral analysis is most useful when it runs alongside the other modalities.
At Prisys, phenotyping folds into broader NHP studies with disease models, PK/PD assessment, in vivo imaging, pathology, and biomarker analysis. It adds a functional layer that connects molecular and physiological change to observable phenotype, and it sits beside established endpoints rather than replacing them.
The workflow runs from behavior to PK/PD, imaging, pathology, and biomarkers.
Each piece answers a different question. Behavior gives function, PK/PD gives exposure and pharmacological response, imaging gives longitudinal anatomical or functional information, pathology gives tissue-level effects, biomarkers give underlying mechanism. The combination counts most when a treatment produces subtle functional change that no single molecular or structural endpoint fully reflects.
From Video Recording to Digital Behavioral Phenotyping
The larger shift is that video stops being an observational record and becomes a quantitative data source.
Hours of footage hold hours of behavioral information, but pulling it out by hand is slow and inconsistent. Markerless 3D tracking turns the same footage into structured datasets containing pose, movement, behavioral sequences, and temporal patterns, which is the foundation of digital behavioral phenotyping in NHP research.
Digital phenotyping is not an automation exercise. The science holds up only if the extracted parameters are biologically relevant, reproducible, and validated for the question at hand. In practice that means selecting behavioral endpoints before analysis begins, defining reference behaviors, establishing validation procedures, and interpreting AI-derived measurements alongside conventional pharmacology and disease endpoints.
What This Means for Future NHP Drug Development
As preclinical research leans harder on quantitative, longitudinal endpoints, behavioral analysis will sit closer to pharmacology, imaging, and biomarker strategies. Markerless 3D tracking, automated behavioral classification, and multimodal translational datasets let a team read treatment response at several levels, from drug exposure and biological activity to functional phenotype.
For CNS, pain, pruritus, and other indications where behavior is a core part of the disease phenotype, this gives functional outcomes a more objective measuring stick.
The opportunity lies in better-defined behavioral endpoints that connect to pharmacological mechanisms and translational questions, which is a harder problem than collecting more data.
Revisit the NHP BehaviorAtlas Webinar
This article builds on the Prisys and Bayone webinar, "NHP BehaviorAtlas: High-Fidelity 3D NHP Behavioral Tracking for Drug Development," which covered multi-view 3D tracking, markerless pose estimation, behavioral kinematics, automated behavior classification, and facial expression analysis in NHP research.
For the fuller discussion, both pages are worth a read:
- Original Webinar: NHP BehaviorAtlas Webinar | 3D NHP Behavioral Tracking For Drug Development
- Webinar Recap: Webinar Recap: Advancing Translational NHP Research Through Digital Behavioral Phenotyping
The recap goes deeper on pain, pruritus, neurological disease models, facial expression analysis, and the integration of behavioral endpoints with PK/PD, imaging, pathology, and biomarkers.
For researchers planning NHP efficacy or translational studies, the practical question is whether a tracking dataset converts into validated, biologically meaningful endpoints that sharpen how treatment response is read.













