A reinforcement learning approach to effective forecasting of pediatric hypoglycemia in diabetes I patients using an extended de Bruijn graph

Abstract Pediatric diabetes I is an endemic and an especially difficult disease; indeed, at this point, there does not exist a cure, but only careful management that relies on anticipating hypoglycemia. The changing physiology of children producing unique blood glucose signatures, coupled with incon...

Full description

Saved in:
Bibliographic Details
Main Authors: Mert Onur Cakiroglu, Hasan Kurban, Lilia Aljihmani, Khalid Qaraqe, Goran Petrovski, Mehmet M. Dalkilic
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-82649-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846101200764665856
author Mert Onur Cakiroglu
Hasan Kurban
Lilia Aljihmani
Khalid Qaraqe
Goran Petrovski
Mehmet M. Dalkilic
author_facet Mert Onur Cakiroglu
Hasan Kurban
Lilia Aljihmani
Khalid Qaraqe
Goran Petrovski
Mehmet M. Dalkilic
author_sort Mert Onur Cakiroglu
collection DOAJ
description Abstract Pediatric diabetes I is an endemic and an especially difficult disease; indeed, at this point, there does not exist a cure, but only careful management that relies on anticipating hypoglycemia. The changing physiology of children producing unique blood glucose signatures, coupled with inconsistent activities, e.g., playing, eating, napping, makes “forecasting” elusive. While work has been done for adult diabetes I, this does not successfully translate for children. In the work presented here, we adopt a reinforcement approach by leveraging the de Bruijn graph that has had success in detecting patterns in sequences of symbols–most notably, genomics and proteomics. We translate a continuous signal of blood glucose levels into an alphabet that then can be used to build a de Bruijn, with some extensions, to determine blood glucose states. The graph allows us to “tune” its efficacy by computationally ignoring edges that provide either no information or are not related to entering a hypoglycemic episode. We can then use paths in the graph to anticipate hypoglycemia in advance of about 30 minutes sufficient for a clinical setting and additionally find actionable rules that accurate and effective. All the code developed for this study can be found at: https://github.com/KurbanIntelligenceLab/dBG-Hypoglycemia-Forecast .
format Article
id doaj-art-1f9d4293856548c0b03ed363aee60f2d
institution Kabale University
issn 2045-2322
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-1f9d4293856548c0b03ed363aee60f2d2024-12-29T12:25:13ZengNature PortfolioScientific Reports2045-23222024-12-0114111610.1038/s41598-024-82649-4A reinforcement learning approach to effective forecasting of pediatric hypoglycemia in diabetes I patients using an extended de Bruijn graphMert Onur Cakiroglu0Hasan Kurban1Lilia Aljihmani2Khalid Qaraqe3Goran Petrovski4Mehmet M. Dalkilic5Computer Science Department, Indiana UniversityCollege of Science and Engineering, Hamad Bin Khalifa UniversityElectrical and Computer Engineering, Texas A &M University at QatarCollege of Science and Engineering, Hamad Bin Khalifa UniversityWeill Cornell Medicine, Cornell UniversityComputer Science Department, Indiana UniversityAbstract Pediatric diabetes I is an endemic and an especially difficult disease; indeed, at this point, there does not exist a cure, but only careful management that relies on anticipating hypoglycemia. The changing physiology of children producing unique blood glucose signatures, coupled with inconsistent activities, e.g., playing, eating, napping, makes “forecasting” elusive. While work has been done for adult diabetes I, this does not successfully translate for children. In the work presented here, we adopt a reinforcement approach by leveraging the de Bruijn graph that has had success in detecting patterns in sequences of symbols–most notably, genomics and proteomics. We translate a continuous signal of blood glucose levels into an alphabet that then can be used to build a de Bruijn, with some extensions, to determine blood glucose states. The graph allows us to “tune” its efficacy by computationally ignoring edges that provide either no information or are not related to entering a hypoglycemic episode. We can then use paths in the graph to anticipate hypoglycemia in advance of about 30 minutes sufficient for a clinical setting and additionally find actionable rules that accurate and effective. All the code developed for this study can be found at: https://github.com/KurbanIntelligenceLab/dBG-Hypoglycemia-Forecast .https://doi.org/10.1038/s41598-024-82649-4
spellingShingle Mert Onur Cakiroglu
Hasan Kurban
Lilia Aljihmani
Khalid Qaraqe
Goran Petrovski
Mehmet M. Dalkilic
A reinforcement learning approach to effective forecasting of pediatric hypoglycemia in diabetes I patients using an extended de Bruijn graph
Scientific Reports
title A reinforcement learning approach to effective forecasting of pediatric hypoglycemia in diabetes I patients using an extended de Bruijn graph
title_full A reinforcement learning approach to effective forecasting of pediatric hypoglycemia in diabetes I patients using an extended de Bruijn graph
title_fullStr A reinforcement learning approach to effective forecasting of pediatric hypoglycemia in diabetes I patients using an extended de Bruijn graph
title_full_unstemmed A reinforcement learning approach to effective forecasting of pediatric hypoglycemia in diabetes I patients using an extended de Bruijn graph
title_short A reinforcement learning approach to effective forecasting of pediatric hypoglycemia in diabetes I patients using an extended de Bruijn graph
title_sort reinforcement learning approach to effective forecasting of pediatric hypoglycemia in diabetes i patients using an extended de bruijn graph
url https://doi.org/10.1038/s41598-024-82649-4
work_keys_str_mv AT mertonurcakiroglu areinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph
AT hasankurban areinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph
AT liliaaljihmani areinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph
AT khalidqaraqe areinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph
AT goranpetrovski areinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph
AT mehmetmdalkilic areinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph
AT mertonurcakiroglu reinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph
AT hasankurban reinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph
AT liliaaljihmani reinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph
AT khalidqaraqe reinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph
AT goranpetrovski reinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph
AT mehmetmdalkilic reinforcementlearningapproachtoeffectiveforecastingofpediatrichypoglycemiaindiabetesipatientsusinganextendeddebruijngraph