Ítem


Negative results for the prediction of postprandial hypoglycemias from insulin intakes and carbohydrates: analysis and comparison with simulated data

Comunicació de congrés presentada a: Workshop on Artificial Intelligence for Diabetes (2nd: 2017: Viena, Àustria). Aquest workshop ha rebut finançament del programa d’investigació i innovació EU Horizon 2020 sota el núm. d’ajut 689810

Diabetic patients usually take insulin bolus right before eating a meal. A wrong dosage of insulin may lead to a hypoglycemia. Being able to anticipate such insulin-induced, postprandial hypoglycemias would enable warning of the patients about the risk associated with the quantity of insulin they are planning to take. In this work, we explore the feasibility of predicting these postprandial hypoglycemias by using information available at pre-meal time, such as glucose levels, planned insulin intakes and carbohydrates estimations. First, an experiment has been done on a dataset acquired on real patients, for which several classes of machine learning algorithms have been tried. The obtained results do not offer predictions that are useful enough to consider any usage in real-life applications. These kinds of datasets - acquired on real patients - suffer heavily from missing data and incorrect carbohydrates estimations though. In order to analyse the impact of these flaws on the obtained results, the same experiment has been run on a simulated dataset. Results support that even with the simulated dataset, which does not have missing data and which has precise carbohydrates intake, these features alone are not able to predict postprandial hypoglycemia. Therefore, improving the quality of patients annotations is not enough to solve the problem, and using these features without further features engineering does not offer good results

© Herrero, P., López, B., Martin, C.(eds). (2017). AID 2017: Proceedings of the 2nd International Workshop on Artificial Intelligence for Diabetes held in conjunction with the 16th Conference on Artificial Intelligence in Medicine (AIME): Vienna, Austria: 24th June 2017, p. 25-29

Artificial Intelligence for Diabetes (AID), Artificial Intelligence in Medicine (AIME), PEPPER

Autor: Dubosson, Fabien
Mordvanyuk, Natalia
López Ibáñez, Beatriz
Schumacher, Michael
Data: 2017
Resum: Comunicació de congrés presentada a: Workshop on Artificial Intelligence for Diabetes (2nd: 2017: Viena, Àustria). Aquest workshop ha rebut finançament del programa d’investigació i innovació EU Horizon 2020 sota el núm. d’ajut 689810
Diabetic patients usually take insulin bolus right before eating a meal. A wrong dosage of insulin may lead to a hypoglycemia. Being able to anticipate such insulin-induced, postprandial hypoglycemias would enable warning of the patients about the risk associated with the quantity of insulin they are planning to take. In this work, we explore the feasibility of predicting these postprandial hypoglycemias by using information available at pre-meal time, such as glucose levels, planned insulin intakes and carbohydrates estimations. First, an experiment has been done on a dataset acquired on real patients, for which several classes of machine learning algorithms have been tried. The obtained results do not offer predictions that are useful enough to consider any usage in real-life applications. These kinds of datasets - acquired on real patients - suffer heavily from missing data and incorrect carbohydrates estimations though. In order to analyse the impact of these flaws on the obtained results, the same experiment has been run on a simulated dataset. Results support that even with the simulated dataset, which does not have missing data and which has precise carbohydrates intake, these features alone are not able to predict postprandial hypoglycemia. Therefore, improving the quality of patients annotations is not enough to solve the problem, and using these features without further features engineering does not offer good results
Format: application/pdf
Accés al document: http://hdl.handle.net/10256/14859
Llenguatge: eng
Editor: Artificial Intelligence for Diabetes (AID), Artificial Intelligence in Medicine (AIME), PEPPER
Col·lecció: Reproducció digital del document publicat a: http://sots.brookes.ac.uk/~p0042050/aid2017/assets/files/AIME_AID_2017_proceedings.pdf
Articles publicats (D-EEEiA)
info:eu-repo/grantAgreement/EC/H2020/689810
És part de: © Herrero, P., López, B., Martin, C.(eds). (2017). AID 2017: Proceedings of the 2nd International Workshop on Artificial Intelligence for Diabetes held in conjunction with the 16th Conference on Artificial Intelligence in Medicine (AIME): Vienna, Austria: 24th June 2017, p. 25-29
Drets: Tots els drets reservats
Matèria: Diabetis
Diabetes
Hipoglucèmia
Hypoglycemia
Insulina
Insuline
Hidrats de carboni
Carbohydrates
Intel·ligència artificial -- Aplicacions a la medicina
Artificial intelligence -- Medical applications
Títol: Negative results for the prediction of postprandial hypoglycemias from insulin intakes and carbohydrates: analysis and comparison with simulated data
Tipus: info:eu-repo/semantics/article
Repositori: DUGiDocs

Matèries

Autors