> ## Documentation Index
> Fetch the complete documentation index at: https://docs.medera.info/llms.txt
> Use this file to discover all available pages before exploring further.
# Neurobehavioral Construct Computer
> 15 named neurobehavioral constructs across 5 domains.
`NeurobehavioralConstructComputer.compute_all_constructs(facial_features, vocal_features, assessments, context)` returns an `NeurobehavioralActivationProfile` containing 15 `ConstructActivation` objects — one per construct — across 5 neurobehavioral domains.
## Domain map
`acute_threat_fear` · `potential_threat_anxiety` · `sustained_threat`
`reward_responsiveness` · `reward_anticipation` · `reward_satiation`
`attention` · `working_memory` · `executive_function`
`social_communication` · `affiliation_attachment`
`arousal` · `arousal_regulation` · `circadian_rhythms` · `sleep_wakefulness`
***
## ConstructActivation \`\`\`python
@dataclass
class ConstructActivation: name: str # e.g. "potential\_threat\_anxiety" score: float # 0–1 activation confidence: float # 0–1 calibrated contributors: List\[Dict] # \[{feature, value, contribution}] interpretation: str # clinical text domain: str # neurobehavioral domain low\_threshold: float = 0.3 high\_threshold: float = 0.7 def get\_severity(self) -> str: # "low"
\| "moderate" | "high" |
````Severity bands: theme={"system"}
| Score | Severity |
| :--- | :--- |
| `< 0.3` | low |
| `0.3 – 0.7` | moderate |
| `≥ 0.7` | high |
## Profile schema ```json
{ "constructs": [ { "name": "potential_threat_anxiety", "domain": "negative_valence", "score": 0.74, "confidence": 0.81, "severity": "high", "interpretation": "Elevated anxiety markers across vocal F0, jitter, and facial stress.", "contributors": [ {"feature": "f0_mean", "value": 218.0, "contribution": 0.31}, {"feature": "jitter", "value": 1.4, "contribution": 0.22}, {"feature": "vocal_anxiety_index", "value": 0.66, "contribution": 0.18}, {"feature": "stress_index", "value": 62.0, "contribution": 0.15}, {"feature": "hrv_lf_hf_ratio", "value": 2.1, "contribution": 0.14} ] } ]
}
````
## Endpoint \`\`\`
POST /api/multimodal-therapy/analyze-session
\`\`\` The neurobehavioral profile is included in the canonical payload at `payload.rdoc.constructs`.
***
## What's next
Vocal features that drive constructs.
Facial features that drive constructs.
Pipeline deep dive.
Agent-level documentation.