Development of a Real-time Force-based Algorithm for Infusion Failure Detection
Continuous subcutaneous insulin infusion (CSII) is a common treatment option for people with diabetes (PWD), but insulin infusion failures pose a significant challenge, leading to hyperglycemia, diabetes burnout, and increased hospitalizations. Current CSII pumps' occlusion alarm systems are li...
Saved in:
Published in | Journal of diabetes science and technology p. 19322968241247530 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
United States
23.04.2024
|
Subjects | |
Online Access | Get more information |
Cover
Loading…
Abstract | Continuous subcutaneous insulin infusion (CSII) is a common treatment option for people with diabetes (PWD), but insulin infusion failures pose a significant challenge, leading to hyperglycemia, diabetes burnout, and increased hospitalizations. Current CSII pumps' occlusion alarm systems are limited in detecting infusion failures; therefore, a more effective detection method is needed.
We conducted five preclinical animal studies to collect data on infusion failures, utilizing both insulin and non-insulin boluses. Data were captured using in-line pressure and flow rate sensors, with additional force data from CSII pumps' onboard sensors in one study. A novel classifier model was developed using this dataset, aimed at detecting different types of infusion failures through direct utilization of force sensor data. Performance was compared against various occlusion alarm thresholds from commercially available CSII pumps.
The testing dataset included 251 boluses. The Bagging classifier model showed the highest performance metrics among the models tested, exhibiting high accuracy (96%), sensitivity (94%), and specificity (98%), with lower false-positive and false-negative rate compared with traditional occlusion alarm pressure thresholds.
Our study developed a novel non-threshold classifier that outperforms current occlusion alarm systems in CSII pumps in detecting infusion failures. This advancement has the potential to reduce the risk of hyperglycemia and hospitalizations due to undetected infusion failures, offering a more reliable and effective CSII therapy for PWD. Further studies involving human participants are recommended to validate these findings and assess the classifier's performance in a real-world setting. |
---|---|
AbstractList | Continuous subcutaneous insulin infusion (CSII) is a common treatment option for people with diabetes (PWD), but insulin infusion failures pose a significant challenge, leading to hyperglycemia, diabetes burnout, and increased hospitalizations. Current CSII pumps' occlusion alarm systems are limited in detecting infusion failures; therefore, a more effective detection method is needed.
We conducted five preclinical animal studies to collect data on infusion failures, utilizing both insulin and non-insulin boluses. Data were captured using in-line pressure and flow rate sensors, with additional force data from CSII pumps' onboard sensors in one study. A novel classifier model was developed using this dataset, aimed at detecting different types of infusion failures through direct utilization of force sensor data. Performance was compared against various occlusion alarm thresholds from commercially available CSII pumps.
The testing dataset included 251 boluses. The Bagging classifier model showed the highest performance metrics among the models tested, exhibiting high accuracy (96%), sensitivity (94%), and specificity (98%), with lower false-positive and false-negative rate compared with traditional occlusion alarm pressure thresholds.
Our study developed a novel non-threshold classifier that outperforms current occlusion alarm systems in CSII pumps in detecting infusion failures. This advancement has the potential to reduce the risk of hyperglycemia and hospitalizations due to undetected infusion failures, offering a more reliable and effective CSII therapy for PWD. Further studies involving human participants are recommended to validate these findings and assess the classifier's performance in a real-world setting. |
Author | Wilcox, John H Lal, Rayhan A Hughes, Michael S Blanco, Luis E |
Author_xml | – sequence: 1 givenname: Luis E orcidid: 0009-0004-6677-3695 surname: Blanco fullname: Blanco, Luis E organization: Diatech Diabetes, Inc., Memphis, TN, USA – sequence: 2 givenname: John H orcidid: 0009-0003-0525-0383 surname: Wilcox fullname: Wilcox, John H organization: Diatech Diabetes, Inc., Memphis, TN, USA – sequence: 3 givenname: Michael S orcidid: 0000-0002-3729-0350 surname: Hughes fullname: Hughes, Michael S organization: Stanford University, Stanford, CA, USA – sequence: 4 givenname: Rayhan A orcidid: 0000-0002-8055-944X surname: Lal fullname: Lal, Rayhan A organization: Stanford University, Stanford, CA, USA |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38654491$$D View this record in MEDLINE/PubMed |
BookMark | eNo1j8tKxDAYRoMozkUfwI3kBaLJn6RJlsOM1YGBAdH1kKZ_tNI2pRfBt7eirr6PszhwVuS8TS0SciP4nRDG3AsnAVxmQQlQRkt-RpY_jEnBzYKshuGDc62sMZdkIW2mlXJiSY47_MQ6dQ22I02RevqMvmZj1SDNUx-QFX7Akm7qt9RX43tDY-rpvo3TUKWW5r6qpx7pDkcM40yuyEX09YDXf7smr_nDy_aJHY6P--3mwAJoOTKwADJaLZU0mQcPNmih5RwCGoJzGcr5cG4Utw5FUKow0ZRCRpNpMAHW5PbX201Fg-Wp66vG91-n_zL4BqCGTf4 |
ContentType | Journal Article |
DBID | NPM |
DOI | 10.1177/19322968241247530 |
DatabaseName | PubMed |
DatabaseTitle | PubMed |
DatabaseTitleList | PubMed |
Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
DeliveryMethod | no_fulltext_linktorsrc |
Discipline | Medicine |
EISSN | 1932-3107 |
ExternalDocumentID | 38654491 |
Genre | Journal Article |
GrantInformation_xml | – fundername: NIDDK NIH HHS grantid: P30 DK116074 – fundername: NIDDK NIH HHS grantid: K23 DK138267 |
GroupedDBID | --- 0R~ 54M AACMV AACTG AAEWN AAGMC AAJPV AAKGS AANEX AARDL AATAA AATBZ AAUAS ABAWP ABCCA ABJIS ABJNI ABLUO ABPNF ABQXT ABVFX ACARO ACDXX ACFEJ ACGFO ACGFS ACGZU ACJER ACJTF ACLFY ACLZU ACOXC ACROE ACSIQ ACTQU ACUAV ACUIR ACXKE ACXMB ADBBV ADDVE ADRRZ ADVBO AECGH AEDTQ AEKYL AEPTA AERKM AESZF AEUHG AEUIJ AEWDL AEWHI AFKRG AFMOU AFQAA AGKLV AGWFA AIOMO AJUZI AJXAJ ALKWR ALMA_UNASSIGNED_HOLDINGS ALTZF AMCVQ ANDLU AOIJS ARTOV AUTPY AYAKG BAWUL BBRGL BDDNI BKIIM BPACV BSEHC BWJAD C45 DC. DV7 E3Z EBS EJD F5P FHBDP GROUPED_SAGE_PREMIER_JOURNAL_COLLECTION H13 J8X JCYGO K.F M4V NPM O9- OK1 OVD P2P P6G ROL RPM SCNPE SFC SFH SHG SJN SPQ SPV TEORI TR2 |
ID | FETCH-LOGICAL-c253t-28223f8534376a2a28c5153177252c996e32520074089e1c44b7f7d13f76527c2 |
IngestDate | Fri Oct 18 09:00:38 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Keywords | infusion site insulin delivery failure insulin pump algorithm occlusion detection |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c253t-28223f8534376a2a28c5153177252c996e32520074089e1c44b7f7d13f76527c2 |
ORCID | 0009-0003-0525-0383 0009-0004-6677-3695 0000-0002-3729-0350 0000-0002-8055-944X |
PMID | 38654491 |
ParticipantIDs | pubmed_primary_38654491 |
PublicationCentury | 2000 |
PublicationDate | 2024-04-23 |
PublicationDateYYYYMMDD | 2024-04-23 |
PublicationDate_xml | – month: 04 year: 2024 text: 2024-04-23 day: 23 |
PublicationDecade | 2020 |
PublicationPlace | United States |
PublicationPlace_xml | – name: United States |
PublicationTitle | Journal of diabetes science and technology |
PublicationTitleAlternate | J Diabetes Sci Technol |
PublicationYear | 2024 |
SSID | ssj0054877 |
Score | 2.4083683 |
Snippet | Continuous subcutaneous insulin infusion (CSII) is a common treatment option for people with diabetes (PWD), but insulin infusion failures pose a significant... |
SourceID | pubmed |
SourceType | Index Database |
StartPage | 19322968241247530 |
Title | Development of a Real-time Force-based Algorithm for Infusion Failure Detection |
URI | https://www.ncbi.nlm.nih.gov/pubmed/38654491 |
hasFullText | |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1ba8IwFA5ug7GXsft95GFvUjFpauqjGxM31IEo-CZtTKawVXH1Yfv1O0naWryMbS-lJLZIv68nJ6ffOQehO6WqUlf1hlc8kHqDQpyQValDCPjOZa6kNIW0W-1Ko8ee-16_UMirluZxWBJfa_NK_oMqjAGuOkv2D8hmN4UBOAd84QgIw_FXGOcUPzbPsQNun6PbxRfrk5mQjl6jhsXa2-tkNo5H70ZT-BSpuQ6RFevBWGvSweTERo8VbXBUs_BsmgJkRJcrIfn7NyCQCbw25-OPRYYD2B1hlzij0lkkQ8xfR9ZGJdL9RRS2aboQFDvB5wjMTy0fmaBG0GKTh0vSWlNwDsHI27a2iYXUY7Ra8aluew17pfJ6O26-JP_4W4Bi-m6A1W1LGbNNv36eXSqtnU5toS3ua_PY1qEeu4zrnRxPPoPrCl0r_2UP7abXL21JjGvSPUD7CVS4ZglyiAoyOkK7rUQ1cYxecjzBE4UDnPEE53iCM55g4AlOeYITnuCMJyeoV3_sPjScpJGGI6jnxo6WCrsKHDMGy0lAA-oLcGPBc-TUowJ2vNKluvwWZ2W_KolgLOSKD4mreMWjXNBTtB1NInmOcEBURVJBSFhWjCs_hDtSTw4lcYecSnWBzuyjGExttZRB-pAuN85cob0Ffa7RjoLXU96ArxeHtwaTb3g-TUc |
link.rule.ids | 786 |
linkProvider | National Library of Medicine |
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=Development+of+a+Real-time+Force-based+Algorithm+for+Infusion+Failure+Detection&rft.jtitle=Journal+of+diabetes+science+and+technology&rft.au=Blanco%2C+Luis+E&rft.au=Wilcox%2C+John+H&rft.au=Hughes%2C+Michael+S&rft.au=Lal%2C+Rayhan+A&rft.date=2024-04-23&rft.eissn=1932-3107&rft.spage=19322968241247530&rft_id=info:doi/10.1177%2F19322968241247530&rft_id=info%3Apmid%2F38654491&rft_id=info%3Apmid%2F38654491&rft.externalDocID=38654491 |