Patient diabetes monitoring system with clustering of unsupervised daily CGM profiles (or insulin profiles) and method thereof

US10575790B2 · kind B2 · utility

Assignee

• Roche Diabetes Care, Inc. · US

Inventors

• David L. Duke · Fishers, US
• Bernd Steiger · Brohl, DE
• Chinmay Uday Manohar · Rochester, US

Key dates

• Filing date: Mar 2, 2016
• Grant date: Mar 3, 2020
• Expiry date: Nov 15, 2038

Classification

• Technology area (CPC G): Physics
• CPC primary: G06F2218/00
• WIPO field: Medical technology
• WIPO sector: Instruments

Abstract

A patient diabetes monitoring system with an efficient unsupervised daily monitoring profile clustering algorithm, a method, and a computer product thereof are disclosed. The system may include a physiological data input device or sensor which receives a plurality of physiological measurements to generate a dataset, a memory which stores a clustering algorithm, and a processor. The clustering algorithm when executed by the processor, causes the processor to automatically pre-process the dataset to control an amount of bias/aggressiveness from the collected unsupervised daily monitoring profiles, thereby generating a pre-processed dataset, build a similarity matrix from the pre-processed dataset, and output an optimum number of similarity clusters found by the processor from the similarity matrix.