Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only
In type 1 diabetes management, the availability of algorithms capable of accurately forecasting future blood glucose (BG) concentrations and hypoglycemic episodes could enable proactive therapeutic actions, e.g., the consumption of carbohydrates to mitigate, or even avoid, an impending critical even...
Gespeichert in:
| Veröffentlicht in: | Sensors (Basel, Switzerland) Jg. 21; H. 5; S. 1647 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Switzerland
MDPI AG
27.02.2021
MDPI |
| Schlagworte: | |
| ISSN: | 1424-8220, 1424-8220 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | In type 1 diabetes management, the availability of algorithms capable of accurately forecasting future blood glucose (BG) concentrations and hypoglycemic episodes could enable proactive therapeutic actions, e.g., the consumption of carbohydrates to mitigate, or even avoid, an impending critical event. The only input of this kind of algorithm is often continuous glucose monitoring (CGM) sensor data, because other signals (such as injected insulin, ingested carbs, and physical activity) are frequently unavailable. Several predictive algorithms fed by CGM data only have been proposed in the literature, but they were assessed using datasets originated by different experimental protocols, making a comparison of their relative merits difficult. The aim of the present work was to perform a head-to-head comparison of thirty different linear and nonlinear predictive algorithms using the same dataset, given by 124 CGM traces collected over 10 days with the newest Dexcom G6 sensor available on the market and considering a 30-min prediction horizon. We considered the state-of-the art methods, investigating, in particular, linear black-box methods (autoregressive; autoregressive moving-average; and autoregressive integrated moving-average, ARIMA) and nonlinear machine-learning methods (support vector regression, SVR; regression random forest; feed-forward neural network, fNN; and long short-term memory neural network). For each method, the prediction accuracy and hypoglycemia detection capabilities were assessed using either population or individualized model parameters. As far as prediction accuracy is concerned, the results show that the best linear algorithm (individualized ARIMA) provides accuracy comparable to that of the best nonlinear algorithm (individualized fNN), with root mean square errors of 22.15 and 21.52 mg/dL, respectively. As far as hypoglycemia detection is concerned, the best linear algorithm (individualized ARIMA) provided precision = 64%, recall = 82%, and one false alarm/day, comparable to the best nonlinear technique (population SVR): precision = 63%, recall = 69%, and 0.5 false alarms/day. In general, the head-to-head comparison of the thirty algorithms fed by CGM data only made using a wide dataset shows that individualized linear models are more effective than population ones, while no significant advantages seem to emerge when employing nonlinear methodologies. |
|---|---|
| AbstractList | In type 1 diabetes management, the availability of algorithms capable of accurately forecasting future blood glucose (BG) concentrations and hypoglycemic episodes could enable proactive therapeutic actions, e.g., the consumption of carbohydrates to mitigate, or even avoid, an impending critical event. The only input of this kind of algorithm is often continuous glucose monitoring (CGM) sensor data, because other signals (such as injected insulin, ingested carbs, and physical activity) are frequently unavailable. Several predictive algorithms fed by CGM data only have been proposed in the literature, but they were assessed using datasets originated by different experimental protocols, making a comparison of their relative merits difficult. The aim of the present work was to perform a head-to-head comparison of thirty different linear and nonlinear predictive algorithms using the same dataset, given by 124 CGM traces collected over 10 days with the newest Dexcom G6 sensor available on the market and considering a 30-min prediction horizon. We considered the state-of-the art methods, investigating, in particular, linear black-box methods (autoregressive; autoregressive moving-average; and autoregressive integrated moving-average, ARIMA) and nonlinear machine-learning methods (support vector regression, SVR; regression random forest; feed-forward neural network, fNN; and long short-term memory neural network). For each method, the prediction accuracy and hypoglycemia detection capabilities were assessed using either population or individualized model parameters. As far as prediction accuracy is concerned, the results show that the best linear algorithm (individualized ARIMA) provides accuracy comparable to that of the best nonlinear algorithm (individualized fNN), with root mean square errors of 22.15 and 21.52 mg/dL, respectively. As far as hypoglycemia detection is concerned, the best linear algorithm (individualized ARIMA) provided precision = 64%, recall = 82%, and one false alarm/day, comparable to the best nonlinear technique (population SVR): precision = 63%, recall = 69%, and 0.5 false alarms/day. In general, the head-to-head comparison of the thirty algorithms fed by CGM data only made using a wide dataset shows that individualized linear models are more effective than population ones, while no significant advantages seem to emerge when employing nonlinear methodologies. In type 1 diabetes management, the availability of algorithms capable of accurately forecasting future blood glucose (BG) concentrations and hypoglycemic episodes could enable proactive therapeutic actions, e.g., the consumption of carbohydrates to mitigate, or even avoid, an impending critical event. The only input of this kind of algorithm is often continuous glucose monitoring (CGM) sensor data, because other signals (such as injected insulin, ingested carbs, and physical activity) are frequently unavailable. Several predictive algorithms fed by CGM data only have been proposed in the literature, but they were assessed using datasets originated by different experimental protocols, making a comparison of their relative merits difficult. The aim of the present work was to perform a head-to-head comparison of thirty different linear and nonlinear predictive algorithms using the same dataset, given by 124 CGM traces collected over 10 days with the newest Dexcom G6 sensor available on the market and considering a 30-min prediction horizon. We considered the state-of-the art methods, investigating, in particular, linear black-box methods (autoregressive; autoregressive moving-average; and autoregressive integrated moving-average, ARIMA) and nonlinear machine-learning methods (support vector regression, SVR; regression random forest; feed-forward neural network, fNN; and long short-term memory neural network). For each method, the prediction accuracy and hypoglycemia detection capabilities were assessed using either population or individualized model parameters. As far as prediction accuracy is concerned, the results show that the best linear algorithm (individualized ARIMA) provides accuracy comparable to that of the best nonlinear algorithm (individualized fNN), with root mean square errors of 22.15 and 21.52 mg/dL, respectively. As far as hypoglycemia detection is concerned, the best linear algorithm (individualized ARIMA) provided precision = 64%, recall = 82%, and one false alarm/day, comparable to the best nonlinear technique (population SVR): precision = 63%, recall = 69%, and 0.5 false alarms/day. In general, the head-to-head comparison of the thirty algorithms fed by CGM data only made using a wide dataset shows that individualized linear models are more effective than population ones, while no significant advantages seem to emerge when employing nonlinear methodologies.In type 1 diabetes management, the availability of algorithms capable of accurately forecasting future blood glucose (BG) concentrations and hypoglycemic episodes could enable proactive therapeutic actions, e.g., the consumption of carbohydrates to mitigate, or even avoid, an impending critical event. The only input of this kind of algorithm is often continuous glucose monitoring (CGM) sensor data, because other signals (such as injected insulin, ingested carbs, and physical activity) are frequently unavailable. Several predictive algorithms fed by CGM data only have been proposed in the literature, but they were assessed using datasets originated by different experimental protocols, making a comparison of their relative merits difficult. The aim of the present work was to perform a head-to-head comparison of thirty different linear and nonlinear predictive algorithms using the same dataset, given by 124 CGM traces collected over 10 days with the newest Dexcom G6 sensor available on the market and considering a 30-min prediction horizon. We considered the state-of-the art methods, investigating, in particular, linear black-box methods (autoregressive; autoregressive moving-average; and autoregressive integrated moving-average, ARIMA) and nonlinear machine-learning methods (support vector regression, SVR; regression random forest; feed-forward neural network, fNN; and long short-term memory neural network). For each method, the prediction accuracy and hypoglycemia detection capabilities were assessed using either population or individualized model parameters. As far as prediction accuracy is concerned, the results show that the best linear algorithm (individualized ARIMA) provides accuracy comparable to that of the best nonlinear algorithm (individualized fNN), with root mean square errors of 22.15 and 21.52 mg/dL, respectively. As far as hypoglycemia detection is concerned, the best linear algorithm (individualized ARIMA) provided precision = 64%, recall = 82%, and one false alarm/day, comparable to the best nonlinear technique (population SVR): precision = 63%, recall = 69%, and 0.5 false alarms/day. In general, the head-to-head comparison of the thirty algorithms fed by CGM data only made using a wide dataset shows that individualized linear models are more effective than population ones, while no significant advantages seem to emerge when employing nonlinear methodologies. |
| Author | Prendin, Francesco Vettoretti, Martina Sparacino, Giovanni Facchinetti, Andrea Del Favero, Simone |
| AuthorAffiliation | Department of Information Engineering, University of Padova, 35131 Padova, Italy; prendinf@dei.unipd.it (F.P.); vettore1@dei.unipd.it (M.V.); gianni@dei.unipd.it (G.S.); facchine@dei.unipd.it (A.F.) |
| AuthorAffiliation_xml | – name: Department of Information Engineering, University of Padova, 35131 Padova, Italy; prendinf@dei.unipd.it (F.P.); vettore1@dei.unipd.it (M.V.); gianni@dei.unipd.it (G.S.); facchine@dei.unipd.it (A.F.) |
| Author_xml | – sequence: 1 givenname: Francesco surname: Prendin fullname: Prendin, Francesco – sequence: 2 givenname: Simone orcidid: 0000-0002-8214-2752 surname: Del Favero fullname: Del Favero, Simone – sequence: 3 givenname: Martina surname: Vettoretti fullname: Vettoretti, Martina – sequence: 4 givenname: Giovanni orcidid: 0000-0002-3248-1393 surname: Sparacino fullname: Sparacino, Giovanni – sequence: 5 givenname: Andrea orcidid: 0000-0001-8041-2280 surname: Facchinetti fullname: Facchinetti, Andrea |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/33673415$$D View this record in MEDLINE/PubMed |
| BookMark | eNptkstu1DAUhiNURC-w4AWQJTawCPUtTswCqUwvU2mgG1hHJ44z9cixp3Yy0rwUz4gzU0Ztxer48v2__nN0TrMj553OsvcEf2FM4vNICS6I4OWr7IRwyvOKUnz05Hycnca4wpgyxqo32TFjomScFCfZn2sftII4GLdEvkM3dlQ-arTQG20jAtei-Xbtl3ardG8UutpoN8SvaK6hzQefTxXNfL-GYKJ3k8XCOA1hJ_3pnd3fLmGA_DKYJEcXdumDGe77iL5D1C1Kupl3KcLox3iI8MM7MyQwBZvU6M7Z7dvsdQc26neP9Sz7fX31azbPF3c3t7OLRa64kEPOKIUO45JWbQeilYUmjWoaRmVTaaU0F4ypkqhWEkE6IKzilCnKQRUCKqHYWXa79209rOp1MD2Ebe3B1LsHH5Y1hMEoq2tKKMOEEC0UcAKlJLqUtALBO1GRCievb3uv9dj0ulVpgAHsM9PnP87c10u_qUtZCI5FMvj0aBD8w6jjUPcmKm0tOJ0GVlMuq4IQuUM_vkBXfgwujWqiSpoalyxRH54mOkT5txYJ-LwHVPAxBt0dEILraeXqw8ol9vwFq8wAg_FTM8b-R_EXM0zYxQ |
| CitedBy_id | crossref_primary_10_1016_j_procs_2024_05_194 crossref_primary_10_1186_s12911_025_02856_5 crossref_primary_10_1016_j_ifacol_2025_06_015 crossref_primary_10_1186_s13098_022_00969_9 crossref_primary_10_3389_fpubh_2023_1044059 crossref_primary_10_1016_j_bspc_2023_105167 crossref_primary_10_3390_s22228682 crossref_primary_10_1038_s41598_024_82649_4 crossref_primary_10_2196_47833 crossref_primary_10_3389_fnut_2022_855223 crossref_primary_10_1177_19322968221093665 crossref_primary_10_3390_s23198269 crossref_primary_10_1002_idm2_12069 crossref_primary_10_1016_j_compbiomed_2025_110015 crossref_primary_10_1371_journal_pone_0310801 crossref_primary_10_3389_fbioe_2022_876672 crossref_primary_10_1016_j_bios_2023_115103 crossref_primary_10_7717_peerj_cs_1619 crossref_primary_10_1016_j_bspc_2025_108589 crossref_primary_10_1016_j_cmpb_2024_108179 crossref_primary_10_1109_ACCESS_2023_3237992 crossref_primary_10_1111_dom_14783 crossref_primary_10_3390_s25134038 crossref_primary_10_1177_19322968221147570 crossref_primary_10_1038_s41598_025_14599_4 crossref_primary_10_7717_peerj_cs_3001 crossref_primary_10_1016_S0140_6736_23_00223_4 crossref_primary_10_1109_JIOT_2022_3143375 crossref_primary_10_1177_19322968241267818 |
| Cites_doi | 10.1109/JBHI.2018.2823763 10.1371/journal.pone.0118432 10.15439/2019F159 10.1016/j.automatica.2014.01.001 10.1016/j.cmpb.2013.09.016 10.1109/ICMLA.2018.00227 10.1109/JBHI.2019.2908488 10.3390/s20236925 10.1109/EMBC.2019.8856940 10.1109/JBHI.2018.2887067 10.1080/02664760903002667 10.1089/dia.2018.0150 10.1089/dia.2019.0139 10.1016/j.diabres.2017.08.005 10.1089/dia.2012.0285 10.1089/dia.2005.7.3 10.1007/s10916-017-0788-2 10.3182/20110828-6-IT-1002.01929 10.1109/TBME.2015.2470521 10.1177/193229681300700314 10.1016/j.bios.2018.03.039 10.1177/193229681300700324 10.1089/dia.2010.0151 10.3390/s19040800 10.1109/JBHI.2018.2840690 10.1109/ACCESS.2019.2919184 10.1021/ci034160g 10.2337/dc09-1487 10.1109/TBME.2006.889774 10.1038/s41598-017-06478-4 10.1177/193229681200600519 10.1016/j.ecl.2019.10.006 10.3390/s19204482 10.1081/DDC-120018209 10.1109/NEUREL.2018.8586990 10.3390/diagnostics9010031 10.1177/193229680700100505 10.1007/s11517-015-1320-9 10.2337/dc09-2303 10.2337/dc12-0736 10.1089/dia.2009.0076 10.1109/TITB.2009.2034141 10.1177/1932296816654161 10.1109/ICMLA.2013.30 10.1177/193229681000400106 10.1016/j.ecl.2019.10.009 10.4093/dmj.2019.0121 10.1002/cnm.2833 10.1016/S0925-2312(02)00632-X |
| ContentType | Journal Article |
| Copyright | 2021. This work is licensed under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2021 by the authors. 2021 |
| Copyright_xml | – notice: 2021. This work is licensed under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2021 by the authors. 2021 |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 3V. 7X7 7XB 88E 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA GHDGH K9. M0S M1P PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM DOA |
| DOI | 10.3390/s21051647 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) Medical Database (Alumni Edition) Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One ProQuest Central Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) Health & Medical Collection (Alumni Edition) PML(ProQuest Medical Library) ProQuest Central Premium ProQuest One Academic ProQuest - Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Central China ProQuest Central ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea Health & Medical Research Collection ProQuest Central (New) ProQuest Medical Library (Alumni) ProQuest One Academic Eastern Edition ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest Medical Library ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | CrossRef MEDLINE - Academic MEDLINE Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1424-8220 |
| ExternalDocumentID | oai_doaj_org_article_21230111e6ca41a791e7928a64f68180 PMC7956406 33673415 10_3390_s21051647 |
| Genre | Journal Article |
| GrantInformation_xml | – fundername: Ministero dell'Istruzione, dell'Università e della Ricerca grantid: RBSI14JYM2 |
| GroupedDBID | --- 123 2WC 53G 5VS 7X7 88E 8FE 8FG 8FI 8FJ AADQD AAHBH AAYXX ABDBF ABUWG ACUHS ADBBV ADMLS AENEX AFFHD AFKRA AFZYC ALMA_UNASSIGNED_HOLDINGS BENPR BPHCQ BVXVI CCPQU CITATION CS3 D1I DU5 E3Z EBD ESX F5P FYUFA GROUPED_DOAJ GX1 HH5 HMCUK HYE IAO ITC KQ8 L6V M1P M48 MODMG M~E OK1 OVT P2P P62 PHGZM PHGZT PIMPY PJZUB PPXIY PQQKQ PROAC PSQYO RNS RPM TUS UKHRP XSB ~8M 3V. ABJCF ALIPV ARAPS CGR CUY CVF ECM EIF HCIFZ KB. M7S NPM PDBOC 7XB 8FK AZQEC DWQXO K9. PKEHL PQEST PQUKI PRINS 7X8 PUEGO 5PM |
| ID | FETCH-LOGICAL-c469t-322af00728dfa6d95e1bcbb329b8ecce4633c71cd9161fa138423c24ac56a86c3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 37 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000628579100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1424-8220 |
| IngestDate | Fri Oct 03 12:52:32 EDT 2025 Tue Nov 04 01:58:59 EST 2025 Fri Sep 05 10:32:52 EDT 2025 Tue Oct 07 07:34:47 EDT 2025 Wed Feb 19 02:29:12 EST 2025 Sat Nov 29 07:11:50 EST 2025 Tue Nov 18 22:38:32 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| Keywords | time series glucose sensor signal processing data-driven modeling |
| Language | English |
| License | Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c469t-322af00728dfa6d95e1bcbb329b8ecce4633c71cd9161fa138423c24ac56a86c3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-3248-1393 0000-0002-8214-2752 0000-0001-8041-2280 |
| OpenAccessLink | https://doaj.org/article/21230111e6ca41a791e7928a64f68180 |
| PMID | 33673415 |
| PQID | 2497246393 |
| PQPubID | 2032333 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_21230111e6ca41a791e7928a64f68180 pubmedcentral_primary_oai_pubmedcentral_nih_gov_7956406 proquest_miscellaneous_2498511906 proquest_journals_2497246393 pubmed_primary_33673415 crossref_primary_10_3390_s21051647 crossref_citationtrail_10_3390_s21051647 |
| PublicationCentury | 2000 |
| PublicationDate | 20210227 |
| PublicationDateYYYYMMDD | 2021-02-27 |
| PublicationDate_xml | – month: 2 year: 2021 text: 20210227 day: 27 |
| PublicationDecade | 2020 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland – name: Basel |
| PublicationTitle | Sensors (Basel, Switzerland) |
| PublicationTitleAlternate | Sensors (Basel) |
| PublicationYear | 2021 |
| Publisher | MDPI AG MDPI |
| Publisher_xml | – name: MDPI AG – name: MDPI |
| References | Camerlingo (ref_10) 2019; 21 ref_50 Zecchin (ref_17) 2014; 113 Cappon (ref_9) 2019; 43 Buckingham (ref_25) 2010; 33 Frandes (ref_28) 2017; 7 Pillonetto (ref_32) 2014; 50 Pillonetto (ref_36) 2011; 44 Allen (ref_22) 2019; 9 ref_55 ref_52 ref_51 Klonoff (ref_4) 2017; 133 ref_16 ref_15 Svetnik (ref_47) 2003; 43 Tang (ref_6) 2020; 20 Hidalgo (ref_18) 2017; 41 Zarkogianni (ref_27) 2015; 53 Facchinetti (ref_34) 2013; 36 Daskalaki (ref_54) 2013; 7 Sparacino (ref_33) 2007; 54 Georga (ref_39) 2013; 15 Zarkogianni (ref_23) 2015; 62 ref_29 Shivers (ref_7) 2013; 7 Ullah (ref_3) 2018; 110 Palerm (ref_13) 2007; 1 Cameron (ref_37) 2012; 6 Chatzigiannakis (ref_41) 2019; 19 Gani (ref_45) 2010; 37 Facchinetti (ref_42) 2010; 12 ref_31 ref_30 Dovc (ref_2) 2020; 49 Li (ref_21) 2019; 24 Sun (ref_11) 2018; 23 Palerm (ref_12) 2005; 7 Wadwa (ref_53) 2018; 20 Gadaleta (ref_38) 2018; 23 Oviedo (ref_19) 2017; 33 Mobashsher (ref_5) 2019; 19 Sathe (ref_48) 2003; 29 ref_44 Kravarusic (ref_1) 2020; 49 Zecchin (ref_20) 2016; 10 ref_40 Wang (ref_46) 2003; 55 Yang (ref_14) 2018; 23 Gani (ref_24) 2009; 14 ref_49 ref_8 Aliberti (ref_43) 2019; 7 Facchinetti (ref_35) 2011; 13 Dassau (ref_26) 2010; 33 |
| References_xml | – ident: ref_55 – volume: 23 start-page: 650 year: 2018 ident: ref_38 article-title: Prediction of adverse glycemic events from continuous glucose monitoring signal publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2018.2823763 – ident: ref_52 doi: 10.1371/journal.pone.0118432 – ident: ref_44 doi: 10.15439/2019F159 – volume: 50 start-page: 657 year: 2014 ident: ref_32 article-title: Kernel methods in system identification, machine learning and function estimation: A survey publication-title: Automatica doi: 10.1016/j.automatica.2014.01.001 – volume: 113 start-page: 144 year: 2014 ident: ref_17 article-title: Jump neural network for online short-time prediction of blood glucose from continuous monitoring sensors and meal information publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2013.09.016 – ident: ref_49 doi: 10.1109/ICMLA.2018.00227 – volume: 24 start-page: 603 year: 2019 ident: ref_21 article-title: Convolutional recurrent neural networks for glucose prediction publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2019.2908488 – volume: 20 start-page: 6925 year: 2020 ident: ref_6 article-title: Non-Invasive Blood Glucose Monitoring Technology: A Review publication-title: Sensors doi: 10.3390/s20236925 – ident: ref_51 doi: 10.1109/EMBC.2019.8856940 – volume: 23 start-page: 2633 year: 2018 ident: ref_11 article-title: A dual mode adaptive basal-bolus advisor based on reinforcement learning publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2018.2887067 – volume: 37 start-page: 309 year: 2010 ident: ref_45 article-title: Support vector regression based residual control charts publication-title: J. Appl. Stat. doi: 10.1080/02664760903002667 – volume: 20 start-page: 395 year: 2018 ident: ref_53 article-title: Accuracy of a factory-calibrated, real-time continuous glucose monitoring system during 10 days of use in youth and adults with diabetes publication-title: Diabetes Technol. Ther. doi: 10.1089/dia.2018.0150 – volume: 21 start-page: 644 year: 2019 ident: ref_10 article-title: A Real-Time Continuous Glucose Monitoring–Based Algorithm to Trigger Hypotreatments to Prevent/Mitigate Hypoglycemic Events publication-title: Diabetes Technol. Ther. doi: 10.1089/dia.2019.0139 – ident: ref_31 – volume: 133 start-page: 178 year: 2017 ident: ref_4 article-title: Continuous glucose monitoring: A review of the technology and clinical use publication-title: Diabetes Res. Clin. Pract. doi: 10.1016/j.diabres.2017.08.005 – volume: 15 start-page: 634 year: 2013 ident: ref_39 article-title: A glucose model based on support vector regression for the prediction of hypoglycemic events under free-living conditions publication-title: Diabetes Technol. Ther. doi: 10.1089/dia.2012.0285 – volume: 7 start-page: 3 year: 2005 ident: ref_12 article-title: Hypoglycemia prediction and detection using optimal estimation publication-title: Diabetes Technol. Ther. doi: 10.1089/dia.2005.7.3 – volume: 41 start-page: 142 year: 2017 ident: ref_18 article-title: Data based prediction of blood glucose concentrations using evolutionary methods publication-title: J. Med. Syst. doi: 10.1007/s10916-017-0788-2 – volume: 44 start-page: 8340 year: 2011 ident: ref_36 article-title: A novel nonparametric approach for the identification of the glucose-insulin system in Type 1 diabetic patients publication-title: IFAC Proc. Vol. doi: 10.3182/20110828-6-IT-1002.01929 – volume: 62 start-page: 2735 year: 2015 ident: ref_23 article-title: A review of emerging technologies for the management of diabetes mellitus publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2015.2470521 – volume: 7 start-page: 689 year: 2013 ident: ref_54 article-title: An early warning system for hypoglycemic/hyperglycemic events based on fusion of adaptive prediction models publication-title: J. Diabetes Sci. Technol. doi: 10.1177/193229681300700314 – volume: 110 start-page: 175 year: 2018 ident: ref_3 article-title: In-vitro model for assessing glucose diffusion through skin publication-title: Biosens. Bioelectron. doi: 10.1016/j.bios.2018.03.039 – volume: 7 start-page: 789 year: 2013 ident: ref_7 article-title: “Turn it off!”: Diabetes device alarm fatigue considerations for the present and the future publication-title: J. Diabetes Sci. Technol. doi: 10.1177/193229681300700324 – volume: 13 start-page: 111 year: 2011 ident: ref_35 article-title: A new index to optimally design and compare continuous glucose monitoring glucose prediction algorithms publication-title: Diabetes Technol. Ther. doi: 10.1089/dia.2010.0151 – volume: 19 start-page: 800 year: 2019 ident: ref_5 article-title: The progress of glucose monitoring—A review of invasive to minimally and non-invasive techniques, devices and sensors publication-title: Sensors doi: 10.3390/s19040800 – volume: 23 start-page: 1251 year: 2018 ident: ref_14 article-title: An ARIMA model with adaptive orders for predicting blood glucose concentrations and hypoglycemia publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2018.2840690 – volume: 7 start-page: 69311 year: 2019 ident: ref_43 article-title: A multi-patient data-driven approach to blood glucose prediction publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2919184 – volume: 43 start-page: 1947 year: 2003 ident: ref_47 article-title: Random forest: A classification and regression tool for compound classification and QSAR modeling publication-title: J. Chem. Inf. Comput. Sci. doi: 10.1021/ci034160g – ident: ref_30 – volume: 33 start-page: 1249 year: 2010 ident: ref_26 article-title: Real-time hypoglycemia prediction suite using continuous glucose monitoring: A safety net for the artificial pancreas publication-title: Diabetes Care doi: 10.2337/dc09-1487 – volume: 54 start-page: 931 year: 2007 ident: ref_33 article-title: Glucose concentration can be predicted ahead in time from continuous glucose monitoring sensor time-series publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2006.889774 – volume: 7 start-page: 1 year: 2017 ident: ref_28 article-title: Chaotic time series prediction for glucose dynamics in type 1 diabetes mellitus using regime-switching models publication-title: Sci. Rep. doi: 10.1038/s41598-017-06478-4 – volume: 6 start-page: 1142 year: 2012 ident: ref_37 article-title: Inpatient studies of a Kalman-filter-based predictive pump shutoff algorithm publication-title: J. Diabetes Sci. Technol. doi: 10.1177/193229681200600519 – volume: 49 start-page: 37 year: 2020 ident: ref_1 article-title: Diabetes Technology Use in Adults with Type 1 and Type 2 Diabetes publication-title: Endocrinol. Metab. Clin. doi: 10.1016/j.ecl.2019.10.006 – volume: 19 start-page: 4482 year: 2019 ident: ref_41 article-title: Utility of Big Data in Predicting Short-Term Blood Glucose Levels in Type 1 Diabetes Mellitus Through Machine Learning Techniques publication-title: Sensors doi: 10.3390/s19204482 – volume: 29 start-page: 349 year: 2003 ident: ref_48 article-title: Comparison of neural network and multiple linear regression as dissolution predictors publication-title: Drug Dev. Ind. Pharm. doi: 10.1081/DDC-120018209 – ident: ref_16 doi: 10.1109/NEUREL.2018.8586990 – volume: 9 start-page: 31 year: 2019 ident: ref_22 article-title: Current diabetes technology: Striving for the artificial pancreas publication-title: Diagnostics doi: 10.3390/diagnostics9010031 – volume: 1 start-page: 624 year: 2007 ident: ref_13 article-title: Hypoglycemia detection and prediction using continuous glucose monitoring-a study on hypoglycemic clamp data publication-title: J. Diabetes Sci. Technol. doi: 10.1177/193229680700100505 – volume: 53 start-page: 1333 year: 2015 ident: ref_27 article-title: Comparative assessment of glucose prediction models for patients with type 1 diabetes mellitus applying sensors for glucose and physical activity monitoring publication-title: Med. Biol. Eng. Comput. doi: 10.1007/s11517-015-1320-9 – ident: ref_50 – ident: ref_29 – volume: 33 start-page: 1013 year: 2010 ident: ref_25 article-title: Prevention of nocturnal hypoglycemia using predictive alarm algorithms and insulin pump suspension publication-title: Diabetes Care doi: 10.2337/dc09-2303 – volume: 36 start-page: 793 year: 2013 ident: ref_34 article-title: Real-time improvement of continuous glucose monitoring accuracy: The smart sensor concept publication-title: Diabetes Care doi: 10.2337/dc12-0736 – ident: ref_15 – volume: 12 start-page: 81 year: 2010 ident: ref_42 article-title: Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring publication-title: Diabetes Technol. Ther. doi: 10.1089/dia.2009.0076 – volume: 14 start-page: 157 year: 2009 ident: ref_24 article-title: Universal glucose models for predicting subcutaneous glucose concentration in humans publication-title: IEEE Trans. Inf. Technol. Biomed. doi: 10.1109/TITB.2009.2034141 – volume: 10 start-page: 1149 year: 2016 ident: ref_20 article-title: How much is short-term glucose prediction in type 1 diabetes improved by adding insulin delivery and meal content information to CGM data? A proof-of-concept study publication-title: J. Diabetes Sci. Technol. doi: 10.1177/1932296816654161 – ident: ref_40 doi: 10.1109/ICMLA.2013.30 – ident: ref_8 doi: 10.1177/193229681000400106 – volume: 49 start-page: 1 year: 2020 ident: ref_2 article-title: Evolution of Diabetes Technology publication-title: Endocrinol. Metab. Clin. doi: 10.1016/j.ecl.2019.10.009 – volume: 43 start-page: 383 year: 2019 ident: ref_9 article-title: Continuous glucose monitoring sensors for diabetes management: A review of technologies and applications publication-title: Diabetes Metab. J. doi: 10.4093/dmj.2019.0121 – volume: 33 start-page: e2833 year: 2017 ident: ref_19 article-title: A review of personalized blood glucose prediction strategies for T1DM patients publication-title: Int. J. Numer. Methods Biomed. Eng. doi: 10.1002/cnm.2833 – volume: 55 start-page: 643 year: 2003 ident: ref_46 article-title: Determination of the spread parameter in the Gaussian kernel for classification and regression publication-title: Neurocomputing doi: 10.1016/S0925-2312(02)00632-X |
| SSID | ssj0023338 |
| Score | 2.4861574 |
| Snippet | In type 1 diabetes management, the availability of algorithms capable of accurately forecasting future blood glucose (BG) concentrations and hypoglycemic... |
| SourceID | doaj pubmedcentral proquest pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 1647 |
| SubjectTerms | Algorithms Blood Glucose - analysis Blood Glucose Self-Monitoring data-driven modeling Datasets Diabetes Employment Glucose monitoring glucose sensor Humans Hypoglycemia - diagnosis Insulin Monte Carlo simulation Neural networks Parameter estimation Population Sensors signal processing time series |
| SummonAdditionalLinks | – databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3Pb9MwFLZg4wAHfsMCAxnEgYu1OnZthwtat44eUJkQSLtFjuN0lUrS1SlS_yn-Rt5L0rCiiQunKo0dvabfe35f_PI9Qt5JlxUD8BtmkqJg0nHFMl4MmAWvtMoZ8HXTNJvQ06m5uEjOuwduoSur3MbEJlDnlcNn5EdAE3QsYT0VH5dXDLtG4e5q10LjNtlHpTLA-f5oPD3_2lMuAQys1RMSQO6PAhCcISpo7axCjVj_TRnm34WS11aeswf_a_NDcr_LOelxC5JH5JYvH5N715QIn5Bf2KLT2YBF0LQq6Ke2kp1-xpqiQG2Z08lmWc0WG4fV9HSMZZLhA50ARFhdMfykJ31PQ7wEsFzwombqtNXjgKNTW1t2usIQS48XMzC2vvwR6AjW0pzCPBTLmpfrah16E9qog2Y2s-mXcrF5Sr6fjb-dTFjXyoE54N81g7BhC1QpN3lhVZ4MPc9clok4yQyAyMNNEk5zl0O2ygvLhYE0z8XSuqGyRjnxjOyVVekPCAWOY632mJsKmakEN3KBlWVSSx9zMYzI--1fm7pO5xzbbSxS4DuIgrRHQUTe9kOXrbjHTYNGiI9-AOpxN19Uq1nauXeKCQBESu6Vs5JbnXCvk9hYJQuFb9NH5HCLkLQLEiH9A4-IvOlPg3vjno0tPdxrHIM5cTJQEXnegrG3RAilIQmBX6x3YLpj6u6Zcn7ZSIhroMWQyr34t1kvyd0YS3jwDX59SPbq1dq_Infcz3oeVq87X_sNRtw3Ig priority: 102 providerName: ProQuest |
| Title | Forecasting of Glucose Levels and Hypoglycemic Events: Head-to-Head Comparison of Linear and Nonlinear Data-Driven Algorithms Based on Continuous Glucose Monitoring Data Only |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/33673415 https://www.proquest.com/docview/2497246393 https://www.proquest.com/docview/2498511906 https://pubmed.ncbi.nlm.nih.gov/PMC7956406 https://doaj.org/article/21230111e6ca41a791e7928a64f68180 |
| Volume | 21 |
| WOSCitedRecordID | wos000628579100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: DOA dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: M~E dateStart: 20010101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: BENPR dateStart: 20010101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Health & Medical Collection customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: 7X7 dateStart: 20010101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 1424-8220 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0023338 issn: 1424-8220 databaseCode: PIMPY dateStart: 20010101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lj9MwEB7BwgEOiOdSWCqDOHCxtolTP7htd7sUiS0VAqmcIsdxdiuVZNWkSL3wk_iNzCRp1KKVuHBJFMeOxpkZez5l8g3A28gl2QD9hmuTZTxygeRJkA24Ra-00mn0dV0Xm1DTqZ7PzWyn1BflhDX0wM2LO6alleqhe-lsFFhlAq9MqK2MMkn_KdPqO1BmC6ZaqCUQeTU8QgJB_XGJwGZIzFl7u09N0n9TZPl3guTOjnP-EB60oSI7aUR8BLd8_hju7xAIPoHfVFnT2ZJyl1mRsQ9NAjr7RKlAJbN5yiab6-JyuXGUBM_GlN1YvmcT1CyvCk5ndtqVIqRHIDhF46-HThsaDbw6s5XlZytaGdnJ8rJYLaqrHyUb4RaYMhxHHFeLfF2sy06EZrEgMevR7HO-3DyFb-fjr6cT3lZg4A5hc8XR221G5OI6zaxMzdAHiUsSEZpEo-59JIVwKnApBplBZgOhMTpzYWTdUFotnXgGB3mR--fAEJpYqzyFlCJKpKHvrwimkkhFPgzEsAfvtpqJXUtPTlUyljHCFFJi3CmxB2-6rtcNJ8dNnUak3q4D0WjXDWhccWtc8b-MqwdHW-OIW98uYwSsKsSZG9GD191t9Er61GJzj--a-lAoawayB4eNLXWSCCEVxg44Y7VnZXui7t_JF1c187dCNIsR2Iv_MbeXcC-k_Bz6PV8dwUG1WvtXcNf9rBblqg-31VzVR92HO6PxdPalX7sYHi9-jbFt9vFi9v0PUbwsHg |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB6VFAk48H4ECiwIJC6rxl5n10ZCqG1aEjUNPRSpnMx6vU4jBTvEDih_qr-RGdsxDaq49cApSrzrzG7m9WXH3wC88UyUdNBuuB8kCfeMI3nkJB2u0Sq1ND7aul82m1CjkX96GhxvwPnqWRgqq1z5xNJRx5mh_8i3ESYo18N4Kj7OfnDqGkWnq6sWGpVaHNrlL4Rs-YdBD3_ft657sH-y1-d1VwFuEAoWHDVYJ0SY7ceJlnHQtU5koki4QeTjeix-hzDKMTEmTk6iHeFjxmFcT5uu1L40Au97DTY9VPZOCzaPB0fHXxuIJxDxVfxFQgSd7RwBVZcYu9aiXtkc4LKM9u_CzAuR7uDO_7ZHd-F2nVOzncoI7sGGTe_DrQtMiw_gnFqQGp1TkTfLEvapqtRnQ6qZyplOY9ZfzrLxdGnoaQG2T2Wg-XvWRxPgRcbple01PRvpFojicanl1FHFN4LverrQvDenEMJ2pmPcnOLse852MVeIGc4jMrBJusgWeSNC5VVJzHI2-5xOlw_hy5Vs2CNopVlqnwBDDKe1spR7Cy-SAR1UI-qMPOVZ1xHdNrxbqVJoah53aicyDRHPkdaFjda14XUzdFaRl1w2aJf0sRlAfOPlB9l8HNbuK6QEByOBY6XRnqNV4FgVuL6WXiKJLaANWyuNDGsnmId_1LENr5rL6L7oTEqnFveaxlDOH3RkGx5Xyt9IIoRUmGThitWaWayJun4lnZyVFOkKYT-mqk__LdZLuNE_ORqGw8Ho8BncdKlcidgK1Ba0ivnCPofr5mcxyecvajtn8O2qzeY3c26U5g |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB6VghAceD8MBRYEEpdV4teujYRQ2zSkahV6ACk3s16v00jBDrEDyp_iB_DrmPGrDaq49cApSrzr7G7mm50vO_4G4LWn47SPuOFBmKbc07bgsZ32uUJUKqEDxHpQFZuQ43EwmYQnW_C7fRaG0ipbn1g56iTX9B95D2mCdDzcT91e2qRFnAyGHxbfOVWQopPWtpxGbSJHZv0T6Vvx_nCAv_UbxxkefN4f8abCANdIC0uO1qxSEs8OklSJJPSNHes4dp0wDnBuBr_P1dLWCQZRdqpsN8DoQzue0r5QgdAu3vcKXCVJQXIKcnJG9lzkfrWSkeuG_V6B1Mon7a6N_a8qE3BRbPt3iua5PW94-39erTtwq4m02W4NjbuwZbJ7cPOc_uJ9-EWFSbUqKPWb5Sn7WOfvs2PKpCqYyhI2Wi_y6Xyt6RkCdkDJocU7NkJg8DLn9Mr2u0qOdAvk9jjVquu4ViHBdwNVKj5Y0sbCdudTXJzy9FvB9jCCSBj2I4mwWbbKV0U3hNrX0jCr3uxTNl8_gC-XsmAPYTvLM_MYGDI7paShiNz1YhHS8TVy0diTnnFs17fgbWtWkW7U3anIyDxClkcWGHUWaMGrrumiljS5qNEe2WbXgFTIqw_y5TRqnFpEYQ_uD7YRWnm2kqFtZOgESnipIA0BC3Za64wa11hEZ6ZpwcvuMjo1OqlSmcG1pjbEBMK-sOBRDYRuJIg1iaEXzlhuQGRjqJtXstlpJZwuQ19gAPvk38N6AdcRK9Hx4fjoKdxwKIeJJAzkDmyXy5V5Btf0j3JWLJ9XgGfw9bIx8wec-pwT |
| 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=Forecasting+of+Glucose+Levels+and+Hypoglycemic+Events%3A+Head-to-Head+Comparison+of+Linear+and+Nonlinear+Data-Driven+Algorithms+Based+on+Continuous+Glucose+Monitoring+Data+Only&rft.jtitle=Sensors+%28Basel%2C+Switzerland%29&rft.au=Prendin%2C+Francesco&rft.au=Del+Favero%2C+Simone&rft.au=Vettoretti%2C+Martina&rft.au=Sparacino%2C+Giovanni&rft.date=2021-02-27&rft.pub=MDPI&rft.eissn=1424-8220&rft.volume=21&rft.issue=5&rft_id=info:doi/10.3390%2Fs21051647&rft_id=info%3Apmid%2F33673415&rft.externalDocID=PMC7956406 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1424-8220&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1424-8220&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1424-8220&client=summon |