Clinical & Technical Synopsis — Clear Signal Health

Executive Summary

NET Tracker is a high-density clinical intelligence platform built by a patient to turn white noise into a clear signal. The system utilizes a native SwiftData persistence layer to map the multi-dimensional complexity of NET management.

Technical Deep Dive: Persistence Layer

Select a data pillar to explore each layer..

Molecular Velocity

Maps serum levels against time-series data to identify kinetic trends. This entity allows the engine to predict flares by calculating the first-order rate of change in biomarkers like Signatera or 5-HIAA.

Surgical Baselines

Encodes 18 anatomical markers to establish physiological constants. This data layer adjusts engine sensitivity based on individual surgical history and primary site location.

Temporal Logic

The 28-day cycle engine. It mathematically identifies vulnerability windows by tracking medication degradation over time, providing foresight into recurring symptom patterns.

Flexible Patient Voice

A 25-slot dynamic schema. This allows subjective lived experiences to be promoted to first-class data entities, ensuring the "unthought-of" symptoms are weighted equally in the Machine Learning model.

Next Phase: Clinical Evolution

Phase 1

Heuristic Baseline

100% hard-coded clinical logic for immediate safety and reliability.

Phase 2

Hybrid Inference

Integrating Machine Learning-driven predictive scoring alongside clinical rules.

Phase 3

Personalized Machine Learning

Full ensemble learning optimized to individual patient offsets.

The Architect's Perspective

"I built NET Tracker because I needed it—and what I needed didn’t exist... I approached this as an architect to finally give us a way to turn that noise into a clear, predictable signal."

Steve Petersen

Creator · Software Architect · Stage 4 NET Patient