Ontology Driven Temporal Event Annotator mHealth Application Framework

How can we efficiently collect gold-standard temporal event annotations from patients — the critical training data needed for clinical ML models?

Proceedings of the 28th Annual International Conference on Computer Science and Software Engineering (CASCON 2018)

ACM · 2018

Read Paper
mHealthOntologyAnnotationMachine LearningAndroidClinical Data

Life Sciences Research Day 2018

Carleton University · 2018

The Gap

There is a need for a framework to facilitate the collection of gold standard temporal event annotation data in the context of developing effective systems for predicting temporal events, such as real-time detection of clinical events from physiologic signals. Recording such data using pen and paper is tedious and error-prone, and the reusability of most apps for other domains is limited due to tight binding of application UI to the domain.

which led us to ask
?The Question

How can we efficiently collect gold-standard temporal event annotations from patients — the critical training data needed for clinical ML models?

The Approach

We developed the Temporal Event Annotator (TEA) framework that aids the process of annotation of clinical events that can be used as gold standard labels for a time series dataset gathered from medical instruments and sensors in a clinical study. The TEA Framework provides a user-centric method to produce a tailored native mobile application (TEA Fabric), a web management client (TEA Central), and a secure API service for seamless data handling and persistence.

The Transformation

The TEA Framework has been used to successfully deploy event annotation apps for three studies: NICU Patient Monitoring, SAANS estimation during VR therapy, and the quantification of patient experience during emergency transport. TEA Fabric was demonstrated to aid the process of gathering reliable gold-standard temporal event annotations for all the studies.