Clear Signal Health
The system behind the signal.
A patient-built platform for pattern awareness in neuroendocrine tumor care, designed to bring symptom trends, treatment timing, anatomy, food response, and longitudinal change into one usable view.
This synopsis is written for clinicians, technical reviewers, collaborators, and serious patients who want a clear picture of what the platform does, how it is structured, and how it is intended to evolve.
This platform starts with the problem patients actually live inside: making sense of what happens between appointments, not just recording what already happened.
Interpretation is shaped by surgical history, medication cycle, symptom baselines, and personal response patterns rather than generic averages alone.
The goal is not generic wellness advice. The goal is to help users better understand food, pacing, and symptom pressure in time to act on it.
The engine is built around biological context, temporal context, and patient-specific learning. Select a layer to see how each one contributes to the overall model.
The molecular layer focuses on rate of change rather than isolated values. Biomarkers such as Chromogranin A, 5-HIAA, or ctDNA become more informative when evaluated as trajectories across time.
This lets the engine treat worsening movement as signal, not just noise, and incorporate those changes into broader pattern awareness.
Surgical history changes how food, medications, and symptoms behave. Resection length, gallbladder status, and GI alterations are used to adjust baselines so the engine does not interpret normal-for-this-patient as abnormal.
This is especially important for food response logic and post-surgical symptom sensitivity.
Medication timing is not static. The platform models cycle phase, wear-off windows, and timing-dependent changes in symptom pressure so it can surface relevant context before a user simply feels blindsided.
In practice, that means treatment timing is part of the interpretation engine, not a separate log.
The system is intentionally flexible enough to capture what standard forms miss: unusual symptoms, personal triggers, functional capacity, and the way a patient actually describes their day.
This prevents the model from flattening a patient into only what the standard chart happens to collect.
The roadmap is built around safety, clarity, and progressive learning rather than complexity for its own sake.
Phase 1
Patient-safe rule logic provides immediate usefulness while establishing consistent data capture and stable interpretation.
Phase 2
Structured rules and machine learning work together so outputs stay grounded in domain logic while becoming more adaptive over time.
Phase 3
User-confirmed outcomes refine the model around individual offsets, letting the system become more useful for that specific patient.
“I built Clear Signal Health because I needed a way to understand what was happening between appointments. I approached it as both a patient and an architect: not to create another tracker, but to turn noise into something usable.”
Steve Petersen
Creator · Software Architect · Stage 4 NET Patient