Research nurse AI
Will prepare and share source notes using only authorized information.
RESEARCH PROJECT · 001
Agentic AI & Temporal Neuro-Symbolic Reasoning for Clinical Trials
TENSYM investigates how errors spread across AI agents and whether independent temporal rules can verify their decisions in a fully simulated clinical trial.
01 / THE RESEARCH QUESTION
Information can describe an event that has already occurred yet still be unavailable when an agent makes a decision. Across multiple agents, documents and corrections, this becomes a question of causality, provenance and auditability.
What did the agent know? When? Which source and version did it use? Which rule applied?
02 / THE EXPERIMENTAL SETTING
An initial cohort of ten entirely fictional participants and forty visits has been generated. The agent roles and scenarios below describe the intended experimental design; there are no multi-agent results at this stage.
03 / THE EXPERIMENT
The proposed experimental setup will have AI agents work with synthetic source documents and eCRF data. Independent temporal verification remains a hypothesis to test, not an observed result.
The cohort and synthetic source documents have been generated; their temporal availability will be examined in future experiments.
Will prepare and share source notes using only authorized information.
Will transcribe information into the eCRF and address queries.
Will review accessible data and may raise clarification queries.
Proposed component for independently checking rules, evidence availability, access permissions and provenance, without relying solely on model-generated explanations.
The design calls for logging agent actions and their supporting evidence for independent evaluation.
In the planned experimental design, the three roles are consolidated in single-agent conditions. Rules will be active only in configurations that enable them.
04 / WHAT THE PROJECT WILL TEST
Each proposed scenario will compare observed decisions against synthetic reference facts hidden from the agents.
Measure false alerts and unnecessary blocking.
Test whether incorrect transcription hides a visit outside the Day 12–16 window.
Observe whether a wrongly transcribed measurement spreads or is detected.
Check whether a clarification and simulated human review are triggered.
Test denial of access to information that is not yet available.
COMPARATIVE DESIGN
One independent scorer must assess all four conditions against the same criteria. No experimental results have been published yet.
| # | Agent organization | Verification during simulation |
|---|---|---|
| A | 1 agent · 3 combined roles | No active rule engine |
| B | 1 agent · 3 combined roles | Rule engine enabled |
| C | 3 specialized agents | No active rule engine |
| D | 3 specialized agents | Rule engine enabled |
06 / RESEARCH IN PROGRESS
The initial SYN-HTA-001 cohort is available: 10 fictional participants, 40 visits and 120 sets of systolic/diastolic blood pressure and pulse measurements. The generator underwent technical coherence and reproducibility testing, including 10,000 synthetic cohorts. This does not constitute clinical validation.
07 / RESEARCH JOURNAL
Each note reports a tangible research milestone, the decisions behind it, the checks performed and the limitations. Unfinished experiments are never presented as results.
SPRINT-derived statistical references, longitudinal data generation, technical tests, ten fictional participants and an eCRF documentary environment.
Read the research articleSCOPE & TRANSPARENCY
TENSYM is a research simulation built exclusively on synthetic data: no real patients, no real clinical trial, and no claim of eCRF certification or regulatory compliance. It does not assess treatment efficacy or make autonomous medical decisions.
ABOUT THE RESEARCHER
I’m Aurélien Vannieuwenhuyze, an AI Research Engineer working on temporal medical data, neuro-symbolic reasoning and agentic AI systems. I’m open to new opportunities in R&D and Applied AI, especially in healthcare and pharma — through permanent roles, consulting assignments or research collaborations.
View my CV ↗