# A Logic-Based Learning Approach to Explore Diabetes Patient Behaviors

## TL;DR

This paper introduces a logic-based learning method using Signal Temporal Logic to analyze and characterize behaviors of T1D patients, aiming to improve glycemic control through actionable insights.

## Contribution

It presents a novel STL-based approach to model and interpret T1D patient behaviors from real data, aiding clinical decision-making.

## Key findings

- Behavior patterns identified at individual and population levels
- Logical characterizations linked to glycemic control outcomes
- Potential feedback mechanisms for behavioral improvements

## Abstract

Type I Diabetes (T1D) is a chronic disease in which the body's ability to synthesize insulin is destroyed. It can be difficult for patients to manage their T1D, as they must control a variety of behavioral factors that affect glycemic control outcomes. In this paper, we explore T1D patient behaviors using a Signal Temporal Logic (STL) based learning approach. STL formulas learned from real patient data characterize behavior patterns that may result in varying glycemic control. Such logical characterizations can provide feedback to clinicians and their patients about behavioral changes that patients may implement to improve T1D control. We present both individual- and population-level behavior patterns learned from a clinical dataset of 21 T1D patients.