Wound Monitoring Platform / Tabby

NIH R43 Phase I sensing program with prototype-to-grant-deliverable execution in approximately 1 year.

Device/study metrics: 40 mAh battery, 20 subjects, 172 six-minute logs, and 7 days hourly use per charge.

Reusable encapsulated electronics plus disposable replaceable adhesive sensing interface.

BLE/NFC data-transfer workflow to tablet/cloud.

Sensing stack: thermal actuator, thermistor array, humidity sensor, and temperature sensor.

Raw temperature, humidity, and thermal-response signals were converted into analyzable features.

Built thermal-transfer simulation and thermal diffusivity back-calculation from transient and steady-state parameters.

Built a linear regression model from 10 control and 10 diabetic mouse subjects and evaluated it with 5-fold cross-validation.

Wound-healing feature set included peripheral temperature rise, humidity dynamics, and maximum heater derivative with IQR normalization.

Why I built it

The program needed a fast path from sensor concept to preclinical study device and grant deliverables in about one year.

What I built

Sensor selection, adhesive fabrication, product design, testing, thermal-transfer simulation, diffusivity back-calculation, preclinical data collection, and multimodal analysis workflows.

What worked

Thermal response, humidity dynamics, and peripheral temperature features created a quantitative path from raw patch signals to wound-healing progression.

What failed

Wound physiology is noisy: exudate, perfusion, epidermal thickening, movement, tissue composition, and animal-to-animal variation all affect the signal.

What I learned

The best sensing platforms are built with the study workflow and feature model from the beginning, not after hardware is finished.