Graduate Research Lead – Digital Neurocognition & Expectancy Modeling
Description
Focus: Multimodal Expectancy Measurement, Placebo Dilution Modeling, and Clinical Protocol Integration
1. Executive Summary & Clinical Context
In clinical trials and real-world behavioral management (e.g., dementia and CNS care), treatment response heterogeneity is often obscured by averaging high- and low-expectancy individuals. This dilution conceals true therapeutic signals and inflates non-specific or transient placebo responses.
As part of the AI-COPE clinical development program (focused on treatment-response validation, early inadequate-response detection, and response sustainability), InnoNext is recruiting an MSc-level Graduate Research Lead. The candidate will design, build, and pilot a lightweight, multimodal test inspired by the Stimulus Expectancy Assessment Tool (SEAT) to quantify stimulus/response expectancy and model placebo dilution.
2. Core Responsibilities & Scope
- Test Customization & Digital Adaptation:
- Adapt the 6-item visual stimulus battery (evaluating agents like pills, powders, drinks, bars, injections, and devices across cognitive/performance domains) into a low-burden, 1- to 3-minute digital micro-assessment.
- Build on the unidimensional Tendency to Believe in Positive Effects (TTBPE) framework, extending it from binary metrics to granular, continuous confidence scales.
- Multimodal Sensor Integration:
- Integrate behavioral capture (response latency, touch kinetics, tablet pupillometry/gaze, or vocal micro-markers during stimulus presentation) to corroborate explicit expectancy ratings.
- Feed expectancy scores into the AI-COPE Response Confidence Score and Response Concordance Index to separate transient placebo effects from sustained clinical response.
- Study Design & Data Collection:
- Lead end-to-end data collection across pilot cohorts (Stage 0 signal characterization; N≈40).
- Implement statistical validation pipelines: Confirmatory Factor Analysis (CFA), logistic response modeling for dilution curves, and subgroup invariance testing (e.g., baseline belief profiles).
- Protocol & Regulatory Alignment:
- Ensure data collection adheres to GCP/ICH, remote digital health technologies (DHT) guidelines, and AI lifecycle standards for model locking before prospective validation.
Skills
Sign in to read and join the discussion.