Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring
Continuous glucose monitoring (CGM) devices could be useful for real-time management of diabetes therapy. In particular, CGM information could be used in real time to predict future glucose levels in order to prevent hypo-/hyperglycemic events. This article proposes a new online method for predictin...
Uložené v:
| Vydané v: | Diabetes technology & therapeutics Ročník 12; číslo 1; s. 81 |
|---|---|
| Hlavní autori: | , , , , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
United States
01.01.2010
|
| Predmet: | |
| ISSN: | 1557-8593, 1557-8593 |
| On-line prístup: | Zistit podrobnosti o prístupe |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Continuous glucose monitoring (CGM) devices could be useful for real-time management of diabetes therapy. In particular, CGM information could be used in real time to predict future glucose levels in order to prevent hypo-/hyperglycemic events. This article proposes a new online method for predicting future glucose concentration levels from CGM data.
The predictor is implemented with an artificial neural network model (NNM). The inputs of the NNM are the values provided by the CGM sensor during the preceding 20 min, while the output is the prediction of glucose concentration at the chosen prediction horizon (PH) time. The method performance is assessed using datasets from two different CGM systems (nine subjects using the Medtronic [Northridge, CA] Guardian and six subjects using the Abbott [Abbott Park, IL] Navigator. Three different PHs are used: 15, 30, and 45 min. The NNM accuracy has been estimated by using the root mean square error (RMSE) and prediction delay.
The RMSE is around 10, 18, and 27 mg/dL for 15, 30, and 45 min of PH, respectively. The prediction delay is around 4, 9, and 14 min for upward trends and 5, 15, and 26 min for downward trends, respectively. A comparison with a previously published technique, based on an autoregressive model (ARM), has been performed. The comparison shows that the proposed NNM is more accurate than the ARM, with no significant deterioration in the prediction delay.
The proposed NNM is a reliable solution for the online prediction of future glucose concentrations from CGM data. |
|---|---|
| AbstractList | Continuous glucose monitoring (CGM) devices could be useful for real-time management of diabetes therapy. In particular, CGM information could be used in real time to predict future glucose levels in order to prevent hypo-/hyperglycemic events. This article proposes a new online method for predicting future glucose concentration levels from CGM data.
The predictor is implemented with an artificial neural network model (NNM). The inputs of the NNM are the values provided by the CGM sensor during the preceding 20 min, while the output is the prediction of glucose concentration at the chosen prediction horizon (PH) time. The method performance is assessed using datasets from two different CGM systems (nine subjects using the Medtronic [Northridge, CA] Guardian and six subjects using the Abbott [Abbott Park, IL] Navigator. Three different PHs are used: 15, 30, and 45 min. The NNM accuracy has been estimated by using the root mean square error (RMSE) and prediction delay.
The RMSE is around 10, 18, and 27 mg/dL for 15, 30, and 45 min of PH, respectively. The prediction delay is around 4, 9, and 14 min for upward trends and 5, 15, and 26 min for downward trends, respectively. A comparison with a previously published technique, based on an autoregressive model (ARM), has been performed. The comparison shows that the proposed NNM is more accurate than the ARM, with no significant deterioration in the prediction delay.
The proposed NNM is a reliable solution for the online prediction of future glucose concentrations from CGM data. Continuous glucose monitoring (CGM) devices could be useful for real-time management of diabetes therapy. In particular, CGM information could be used in real time to predict future glucose levels in order to prevent hypo-/hyperglycemic events. This article proposes a new online method for predicting future glucose concentration levels from CGM data.BACKGROUND AND AIMSContinuous glucose monitoring (CGM) devices could be useful for real-time management of diabetes therapy. In particular, CGM information could be used in real time to predict future glucose levels in order to prevent hypo-/hyperglycemic events. This article proposes a new online method for predicting future glucose concentration levels from CGM data.The predictor is implemented with an artificial neural network model (NNM). The inputs of the NNM are the values provided by the CGM sensor during the preceding 20 min, while the output is the prediction of glucose concentration at the chosen prediction horizon (PH) time. The method performance is assessed using datasets from two different CGM systems (nine subjects using the Medtronic [Northridge, CA] Guardian and six subjects using the Abbott [Abbott Park, IL] Navigator. Three different PHs are used: 15, 30, and 45 min. The NNM accuracy has been estimated by using the root mean square error (RMSE) and prediction delay.METHODSThe predictor is implemented with an artificial neural network model (NNM). The inputs of the NNM are the values provided by the CGM sensor during the preceding 20 min, while the output is the prediction of glucose concentration at the chosen prediction horizon (PH) time. The method performance is assessed using datasets from two different CGM systems (nine subjects using the Medtronic [Northridge, CA] Guardian and six subjects using the Abbott [Abbott Park, IL] Navigator. Three different PHs are used: 15, 30, and 45 min. The NNM accuracy has been estimated by using the root mean square error (RMSE) and prediction delay.The RMSE is around 10, 18, and 27 mg/dL for 15, 30, and 45 min of PH, respectively. The prediction delay is around 4, 9, and 14 min for upward trends and 5, 15, and 26 min for downward trends, respectively. A comparison with a previously published technique, based on an autoregressive model (ARM), has been performed. The comparison shows that the proposed NNM is more accurate than the ARM, with no significant deterioration in the prediction delay.RESULTSThe RMSE is around 10, 18, and 27 mg/dL for 15, 30, and 45 min of PH, respectively. The prediction delay is around 4, 9, and 14 min for upward trends and 5, 15, and 26 min for downward trends, respectively. A comparison with a previously published technique, based on an autoregressive model (ARM), has been performed. The comparison shows that the proposed NNM is more accurate than the ARM, with no significant deterioration in the prediction delay.The proposed NNM is a reliable solution for the online prediction of future glucose concentrations from CGM data.CONCLUSIONSThe proposed NNM is a reliable solution for the online prediction of future glucose concentrations from CGM data. |
| Author | Gómez, E J Sparacino, G Rigla, M Facchinetti, A de Leiva, A Pérez-Gandía, C Hernando, M E Cobelli, C |
| Author_xml | – sequence: 1 givenname: C surname: Pérez-Gandía fullname: Pérez-Gandía, C email: cperez@gbt.tfo.upm.es organization: Networking Research Center on Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN), Madrid, Spain. cperez@gbt.tfo.upm.es – sequence: 2 givenname: A surname: Facchinetti fullname: Facchinetti, A – sequence: 3 givenname: G surname: Sparacino fullname: Sparacino, G – sequence: 4 givenname: C surname: Cobelli fullname: Cobelli, C – sequence: 5 givenname: E J surname: Gómez fullname: Gómez, E J – sequence: 6 givenname: M surname: Rigla fullname: Rigla, M – sequence: 7 givenname: A surname: de Leiva fullname: de Leiva, A – sequence: 8 givenname: M E surname: Hernando fullname: Hernando, M E |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/20082589$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkD1PwzAYhC1UREthZEXemFIcJ_4aq4ovqRILzJFjvy6GxC6OI8S_J4KCmO6G506nO0WzEAMgdFGSVUmkurZeryghakWI4EdoUTImCslUNfvn5-h0GF7JhFS0PEHzKSApk2qB7Dpl77zxusMBxvQt-SOmN6y7XUw-v_TYxYRj6HwAvOtGEwfA-wTWm-xjwC7FHpsYsg9jHIc_pI_B56kh7M7QsdPdAOcHXaLn25unzX2xfbx72Ky3halUnQsA0_IapGPOcSda4UxLwTgtadkqzYXmUjBgtbW0NUo542RteW215loIRZfo6qd3n-L7CENuej8Y6DodYFrWiKpShAleTuTlgRzbHmyzT77X6bP5PYZ-Ae64avc |
| CitedBy_id | crossref_primary_10_3390_app10124381 crossref_primary_10_1049_iet_syb_2017_0036 crossref_primary_10_1186_s12911_025_02856_5 crossref_primary_10_1002_jctb_4591 crossref_primary_10_1016_j_cmpb_2013_09_016 crossref_primary_10_1016_j_cmpb_2020_105523 crossref_primary_10_1007_s11517_015_1263_1 crossref_primary_10_1017_cts_2020_545 crossref_primary_10_1016_j_bios_2022_114348 crossref_primary_10_1016_j_ifacol_2017_08_268 crossref_primary_10_1109_TITB_2012_2219876 crossref_primary_10_1002_dmrr_3348 crossref_primary_10_1177_1932296820922622 crossref_primary_10_1109_JBHI_2022_3233486 crossref_primary_10_2196_10775 crossref_primary_10_1016_j_bbe_2018_02_005 crossref_primary_10_1038_s41746_022_00626_5 crossref_primary_10_1155_2022_7902418 crossref_primary_10_2196_18660 crossref_primary_10_1016_j_chemolab_2018_01_010 crossref_primary_10_1016_j_bbe_2020_10_004 crossref_primary_10_1007_s41666_019_00059_y crossref_primary_10_1007_s00521_020_05248_0 crossref_primary_10_1007_s10916_015_0377_1 crossref_primary_10_1109_JBHI_2019_2931842 crossref_primary_10_3390_electronics12030756 crossref_primary_10_1016_j_compbiomed_2021_104865 crossref_primary_10_1007_s10916_014_0166_2 crossref_primary_10_1016_j_bspc_2023_105077 crossref_primary_10_3390_s21093188 crossref_primary_10_1016_j_bspc_2025_108468 crossref_primary_10_1371_journal_pone_0307136 crossref_primary_10_1109_TBME_2023_3276193 crossref_primary_10_1016_j_jnca_2018_06_007 crossref_primary_10_1007_s10710_024_09500_7 crossref_primary_10_1089_dia_2011_0093 crossref_primary_10_1177_19322968221100839 crossref_primary_10_1007_s40747_021_00360_7 crossref_primary_10_1093_bib_bbac324 crossref_primary_10_1108_LHT_08_2019_0171 crossref_primary_10_1080_13102818_2024_2371354 crossref_primary_10_1109_JBHI_2019_2908488 crossref_primary_10_1109_TBME_2012_2185234 crossref_primary_10_1177_193229681100500109 crossref_primary_10_1177_19322968211018246 crossref_primary_10_1016_j_patrec_2019_06_005 crossref_primary_10_1016_j_artmed_2019_07_007 crossref_primary_10_1002_aisy_202400822 crossref_primary_10_1177_1932296816654161 crossref_primary_10_2196_mhealth_9236 crossref_primary_10_1016_j_biosystems_2010_09_012 crossref_primary_10_3390_s20113214 crossref_primary_10_1016_j_heliyon_2024_e41199 crossref_primary_10_1177_19322968221103561 crossref_primary_10_1109_RBME_2023_3331297 crossref_primary_10_1016_j_conengprac_2023_105498 crossref_primary_10_1016_j_yofte_2022_102822 crossref_primary_10_1177_193229681200600317 crossref_primary_10_1371_journal_pone_0069475 crossref_primary_10_1007_s11517_021_02433_8 crossref_primary_10_1016_j_eswa_2021_115367 crossref_primary_10_1177_0959651819870328 crossref_primary_10_3390_s121013753 crossref_primary_10_3390_s19204538 crossref_primary_10_1007_s11517_018_1859_3 crossref_primary_10_3390_s20226460 crossref_primary_10_1177_1932296814524080 crossref_primary_10_1038_s41598_017_06478_4 crossref_primary_10_1109_JBHI_2018_2823763 crossref_primary_10_1109_JSSC_2014_2384037 crossref_primary_10_1089_dia_2019_0435 crossref_primary_10_1186_s12911_021_01403_2 crossref_primary_10_1016_j_ifacol_2025_06_003 crossref_primary_10_1109_TBME_2024_3424665 crossref_primary_10_1007_s41666_020_00068_2 crossref_primary_10_1109_JBHI_2023_3348334 crossref_primary_10_1109_TBME_2014_2387293 crossref_primary_10_1002_cnm_2833 crossref_primary_10_1155_2011_681786 crossref_primary_10_3390_pharmaceutics17060777 crossref_primary_10_3390_s20143896 crossref_primary_10_1177_193229681300700116 crossref_primary_10_1109_TCST_2018_2843785 crossref_primary_10_1111_dom_14783 crossref_primary_10_1177_19322968211042621 crossref_primary_10_1016_j_smhl_2021_100193 crossref_primary_10_1016_j_ijmedinf_2021_104472 crossref_primary_10_1016_j_neunet_2012_05_004 crossref_primary_10_1007_s11517_023_02866_3 crossref_primary_10_3390_s19040800 crossref_primary_10_1177_1932296818761457 crossref_primary_10_1007_s11042_024_19766_9 crossref_primary_10_1016_j_iot_2023_100945 crossref_primary_10_1007_s11428_022_00966_6 crossref_primary_10_1109_JIOT_2022_3143375 crossref_primary_10_1016_j_conengprac_2017_10_013 crossref_primary_10_1109_TBME_2012_2188893 crossref_primary_10_1089_dia_2012_0208 crossref_primary_10_1089_dia_2010_0151 crossref_primary_10_7554_eLife_58820 crossref_primary_10_3390_sym11091164 crossref_primary_10_1177_193229681300700126 crossref_primary_10_1177_193229681300700522 crossref_primary_10_1016_j_bspc_2023_105167 crossref_primary_10_1016_j_mehy_2011_08_042 crossref_primary_10_1089_dia_2012_0285 crossref_primary_10_3390_s22228682 crossref_primary_10_1088_1757_899X_803_1_012012 crossref_primary_10_21307_ijssis_2017_878 crossref_primary_10_1177_1932296817710475 crossref_primary_10_1016_j_heliyon_2022_e11648 crossref_primary_10_1186_s12911_019_0943_4 crossref_primary_10_1016_j_asoc_2019_01_020 crossref_primary_10_1109_ACCESS_2021_3059858 crossref_primary_10_1007_s00449_012_0750_0 crossref_primary_10_1111_aor_13104 crossref_primary_10_1109_JBHI_2020_3014556 crossref_primary_10_3390_s100706751 crossref_primary_10_3390_s22051843 crossref_primary_10_1002_idm2_12069 crossref_primary_10_1155_2022_7511806 crossref_primary_10_1109_ACCESS_2021_3059343 crossref_primary_10_1109_TBME_2012_2227256 crossref_primary_10_1016_j_bspc_2020_101923 crossref_primary_10_2196_26909 crossref_primary_10_1016_j_cmpb_2021_106424 crossref_primary_10_4316_AECE_2011_04010 crossref_primary_10_1002_aisy_202500235 crossref_primary_10_3390_healthcare11060779 crossref_primary_10_3390_s20143870 crossref_primary_10_2337_dc12_0736 crossref_primary_10_1007_s11517_015_1320_9 crossref_primary_10_1089_dia_2020_0061 crossref_primary_10_1109_ACCESS_2019_2919184 crossref_primary_10_1109_ACCESS_2023_3244712 crossref_primary_10_1177_19322968211008442 crossref_primary_10_1109_TITB_2011_2177469 crossref_primary_10_1016_j_bspc_2024_107204 crossref_primary_10_1088_2632_2153_ae023f crossref_primary_10_3390_nu12020302 crossref_primary_10_1186_s12911_021_01462_5 crossref_primary_10_1002_dmrr_1023 crossref_primary_10_1109_JBHI_2019_2956704 crossref_primary_10_1007_s11517_018_1872_6 crossref_primary_10_1002_aic_15983 crossref_primary_10_2196_47833 crossref_primary_10_2196_40524 crossref_primary_10_1109_JSEN_2021_3070706 crossref_primary_10_3390_s21051647 crossref_primary_10_3389_fbioe_2023_1280233 crossref_primary_10_1007_s42979_024_03318_x crossref_primary_10_1016_j_bbe_2018_06_005 crossref_primary_10_1089_dia_2010_0104 crossref_primary_10_1089_dia_2013_0229 crossref_primary_10_1177_193229681300700314 crossref_primary_10_1109_JBHI_2018_2840690 crossref_primary_10_1088_1757_899X_646_1_012018 crossref_primary_10_1186_s12902_019_0456_2 |
| ContentType | Journal Article |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1089/dia.2009.0076 |
| DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1557-8593 |
| ExternalDocumentID | 20082589 |
| Genre | Research Support, Non-U.S. Gov't Journal Article |
| GroupedDBID | --- 0R~ 29F 34G 39C 4.4 53G 6PF AAWTL ABBKN ABJNI ACGFS ADBBV AENEX AHMBA ALMA_UNASSIGNED_HOLDINGS BNQNF CAG CGR COF CS3 CUY CVF DU5 EBS ECM EIF EJD F5P IAO IER IHR IM4 INH INR ITC MV1 NPM NQHIM O9- PQQKQ RIG RML UE5 7X8 J8X SAUOL SCNPE SFC |
| ID | FETCH-LOGICAL-c394t-eecb64e8f5ff6f7b7fcb2ecfa821b9a67a6875e54dd2bc99fcf84d64daa6a7792 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 207 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000273676100010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1557-8593 |
| IngestDate | Sun Nov 09 12:13:48 EST 2025 Thu Jan 02 22:06:47 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c394t-eecb64e8f5ff6f7b7fcb2ecfa821b9a67a6875e54dd2bc99fcf84d64daa6a7792 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| PMID | 20082589 |
| PQID | 733905761 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_733905761 pubmed_primary_20082589 |
| PublicationCentury | 2000 |
| PublicationDate | 2010-Jan 20100101 |
| PublicationDateYYYYMMDD | 2010-01-01 |
| PublicationDate_xml | – month: 01 year: 2010 text: 2010-Jan |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Diabetes technology & therapeutics |
| PublicationTitleAlternate | Diabetes Technol Ther |
| PublicationYear | 2010 |
| SSID | ssj0007321 |
| Score | 2.406739 |
| Snippet | Continuous glucose monitoring (CGM) devices could be useful for real-time management of diabetes therapy. In particular, CGM information could be used in real... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | 81 |
| SubjectTerms | Algorithms Biosensing Techniques Blood Glucose - analysis Equipment Design Humans Hydrogen-Ion Concentration Monitoring, Ambulatory - instrumentation Monitoring, Ambulatory - methods Neural Networks (Computer) Predictive Value of Tests |
| Title | Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/20082589 https://www.proquest.com/docview/733905761 |
| Volume | 12 |
| WOSCitedRecordID | wos000273676100010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV05T8MwFLaAIsTCXSiXPLBGTeJ7QghRMdCqA6BulU-oRNPSg9-P7bhlQgwsyeDEsp6dl-9d3wPgBjvKDJcoC7aFN1AKlSmn84wTrxmdwJLECu_XJ9br8cFA9FNuzjylVa50YlTUZqKDj7zNkLfOPTgubqefWWgaFYKrqYPGJmggj2RCRhcb_JCFM1SXXRHiFTERKFFs5ly0vexXXJWM_g4u40-ms__P5R2AvYQu4V19HA7Bhq2OwE43xc-PgQkjNWcEDEyW8RbzwKH8ePMTLt7H0MNYWBNowJTQDqezMEXYQxjqUWBIcB9Vy8lyvn5kHJVD8BKegJfOw_P9Y5b6LGQaCbzIrNWKYssdcY46ppjTqrTaSV4WSkjKJPVWjSXYmFJpIZx2HBuKjZRUMibKJtiqJpU9AzAnfsjlqqSKYYmxUIU0SCAcoYyWLQBX4hv6cxyCE7KyfrXDtQBb4LTeguG05tuInTJLwsX53y9fgN06vB98JJeg4fw3bK_Atv5ajOaz63g-_LXX734D6b_IZw |
| linkProvider | ProQuest |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Artificial+neural+network+algorithm+for+online+glucose+prediction+from+continuous+glucose+monitoring&rft.jtitle=Diabetes+technology+%26+therapeutics&rft.au=P%C3%A9rez-Gand%C3%ADa%2C+C&rft.au=Facchinetti%2C+A&rft.au=Sparacino%2C+G&rft.au=Cobelli%2C+C&rft.date=2010-01-01&rft.eissn=1557-8593&rft.volume=12&rft.issue=1&rft.spage=81&rft_id=info:doi/10.1089%2Fdia.2009.0076&rft_id=info%3Apmid%2F20082589&rft_id=info%3Apmid%2F20082589&rft.externalDocID=20082589 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1557-8593&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1557-8593&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1557-8593&client=summon |