A Novel Approach for Continuous Health Status Monitoring and Automatic Detection of Infection Incidences in People With Type 1 Diabetes Using Machine Learning Algorithms (Part 2): A Personalized Digital Infectious Disease Detection Mechanism

Semisupervised and unsupervised anomaly detection methods have been widely used in various applications to detect anomalous objects from a given data set. Specifically, these methods are popular in the medical domain because of their suitability for applications where there is a lack of a sufficient...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of medical Internet research Jg. 22; H. 8; S. e18912
Hauptverfasser: Woldaregay, Ashenafi Zebene, Launonen, Ilkka Kalervo, Albers, David, Igual, Jorge, Årsand, Eirik, Hartvigsen, Gunnar
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Canada Gunther Eysenbach MD MPH, Associate Professor 12.08.2020
JMIR Publications
Schlagworte:
ISSN:1438-8871, 1439-4456, 1438-8871
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Semisupervised and unsupervised anomaly detection methods have been widely used in various applications to detect anomalous objects from a given data set. Specifically, these methods are popular in the medical domain because of their suitability for applications where there is a lack of a sufficient data set for the other classes. Infection incidence often brings prolonged hyperglycemia and frequent insulin injections in people with type 1 diabetes, which are significant anomalies. Despite these potentials, there have been very few studies that focused on detecting infection incidences in individuals with type 1 diabetes using a dedicated personalized health model. This study aims to develop a personalized health model that can automatically detect the incidence of infection in people with type 1 diabetes using blood glucose levels and insulin-to-carbohydrate ratio as input variables. The model is expected to detect deviations from the norm because of infection incidences considering elevated blood glucose levels coupled with unusual changes in the insulin-to-carbohydrate ratio. Three groups of one-class classifiers were trained on target data sets (regular days) and tested on a data set containing both the target and the nontarget (infection days). For comparison, two unsupervised models were also tested. The data set consists of high-precision self-recorded data collected from three real subjects with type 1 diabetes incorporating blood glucose, insulin, diet, and events of infection. The models were evaluated on two groups of data: raw and filtered data and compared based on their performance, computational time, and number of samples required. The one-class classifiers achieved excellent performance. In comparison, the unsupervised models suffered from performance degradation mainly because of the atypical nature of the data. Among the one-class classifiers, the boundary and domain-based method produced a better description of the data. Regarding the computational time, nearest neighbor, support vector data description, and self-organizing map took considerable training time, which typically increased as the sample size increased, and only local outlier factor and connectivity-based outlier factor took considerable testing time. We demonstrated the applicability of one-class classifiers and unsupervised models for the detection of infection incidence in people with type 1 diabetes. In this patient group, detecting infection can provide an opportunity to devise tailored services and also to detect potential public health threats. The proposed approaches achieved excellent performance; in particular, the boundary and domain-based method performed better. Among the respective groups, particular models such as one-class support vector machine, K-nearest neighbor, and K-means achieved excellent performance in all the sample sizes and infection cases. Overall, we foresee that the results could encourage researchers to examine beyond the presented features into other additional features of the self-recorded data, for example, continuous glucose monitoring features and physical activity data, on a large scale.
AbstractList Background: Semisupervised and unsupervised anomaly detection methods have been widely used in various applications to detect anomalous objects from a given data set. Specifically, these methods are popular in the medical domain because of their suitability for applications where there is a lack of a sufficient data set for the other classes. Infection incidence often brings prolonged hyperglycemia and frequent insulin injections in people with type 1 diabetes, which are significant anomalies. Despite these potentials, there have been very few studies that focused on detecting infection incidences in individuals with type 1 diabetes using a dedicated personalized health model. Objective: This study aims to develop a personalized health model that can automatically detect the incidence of infection in people with type 1 diabetes using blood glucose levels and insulin-to-carbohydrate ratio as input variables. The model is expected to detect deviations from the norm because of infection incidences considering elevated blood glucose levels coupled with unusual changes in the insulin-to-carbohydrate ratio. Methods: Three groups of one-class classifiers were trained on target data sets (regular days) and tested on a data set containing both the target and the nontarget (infection days). For comparison, two unsupervised models were also tested. The data set consists of high-precision self-recorded data collected from three real subjects with type 1 diabetes incorporating blood glucose, insulin, diet, and events of infection. The models were evaluated on two groups of data: raw and filtered data and compared based on their performance, computational time, and number of samples required. Results: The one-class classifiers achieved excellent performance. In comparison, the unsupervised models suffered from performance degradation mainly because of the atypical nature of the data. Among the one-class classifiers, the boundary and domain-based method produced a better description of the data. Regarding the computational time, nearest neighbor, support vector data description, and self-organizing map took considerable training time, which typically increased as the sample size increased, and only local outlier factor and connectivity-based outlier factor took considerable testing time. Conclusions: We demonstrated the applicability of one-class classifiers and unsupervised models for the detection of infection incidence in people with type 1 diabetes. In this patient group, detecting infection can provide an opportunity to devise tailored services and also to detect potential public health threats. The proposed approaches achieved excellent performance; in particular, the boundary and domain-based method performed better. Among the respective groups, particular models such as one-class support vector machine, K-nearest neighbor, and K-means achieved excellent performance in all the sample sizes and infection cases. Overall, we foresee that the results could encourage researchers to examine beyond the presented features into other additional features of the self-recorded data, for example, continuous glucose monitoring features and physical activity data, on a large scale.
Semisupervised and unsupervised anomaly detection methods have been widely used in various applications to detect anomalous objects from a given data set. Specifically, these methods are popular in the medical domain because of their suitability for applications where there is a lack of a sufficient data set for the other classes. Infection incidence often brings prolonged hyperglycemia and frequent insulin injections in people with type 1 diabetes, which are significant anomalies. Despite these potentials, there have been very few studies that focused on detecting infection incidences in individuals with type 1 diabetes using a dedicated personalized health model. This study aims to develop a personalized health model that can automatically detect the incidence of infection in people with type 1 diabetes using blood glucose levels and insulin-to-carbohydrate ratio as input variables. The model is expected to detect deviations from the norm because of infection incidences considering elevated blood glucose levels coupled with unusual changes in the insulin-to-carbohydrate ratio. Three groups of one-class classifiers were trained on target data sets (regular days) and tested on a data set containing both the target and the nontarget (infection days). For comparison, two unsupervised models were also tested. The data set consists of high-precision self-recorded data collected from three real subjects with type 1 diabetes incorporating blood glucose, insulin, diet, and events of infection. The models were evaluated on two groups of data: raw and filtered data and compared based on their performance, computational time, and number of samples required. The one-class classifiers achieved excellent performance. In comparison, the unsupervised models suffered from performance degradation mainly because of the atypical nature of the data. Among the one-class classifiers, the boundary and domain-based method produced a better description of the data. Regarding the computational time, nearest neighbor, support vector data description, and self-organizing map took considerable training time, which typically increased as the sample size increased, and only local outlier factor and connectivity-based outlier factor took considerable testing time. We demonstrated the applicability of one-class classifiers and unsupervised models for the detection of infection incidence in people with type 1 diabetes. In this patient group, detecting infection can provide an opportunity to devise tailored services and also to detect potential public health threats. The proposed approaches achieved excellent performance; in particular, the boundary and domain-based method performed better. Among the respective groups, particular models such as one-class support vector machine, K-nearest neighbor, and K-means achieved excellent performance in all the sample sizes and infection cases. Overall, we foresee that the results could encourage researchers to examine beyond the presented features into other additional features of the self-recorded data, for example, continuous glucose monitoring features and physical activity data, on a large scale.
Semisupervised and unsupervised anomaly detection methods have been widely used in various applications to detect anomalous objects from a given data set. Specifically, these methods are popular in the medical domain because of their suitability for applications where there is a lack of a sufficient data set for the other classes. Infection incidence often brings prolonged hyperglycemia and frequent insulin injections in people with type 1 diabetes, which are significant anomalies. Despite these potentials, there have been very few studies that focused on detecting infection incidences in individuals with type 1 diabetes using a dedicated personalized health model.BACKGROUNDSemisupervised and unsupervised anomaly detection methods have been widely used in various applications to detect anomalous objects from a given data set. Specifically, these methods are popular in the medical domain because of their suitability for applications where there is a lack of a sufficient data set for the other classes. Infection incidence often brings prolonged hyperglycemia and frequent insulin injections in people with type 1 diabetes, which are significant anomalies. Despite these potentials, there have been very few studies that focused on detecting infection incidences in individuals with type 1 diabetes using a dedicated personalized health model.This study aims to develop a personalized health model that can automatically detect the incidence of infection in people with type 1 diabetes using blood glucose levels and insulin-to-carbohydrate ratio as input variables. The model is expected to detect deviations from the norm because of infection incidences considering elevated blood glucose levels coupled with unusual changes in the insulin-to-carbohydrate ratio.OBJECTIVEThis study aims to develop a personalized health model that can automatically detect the incidence of infection in people with type 1 diabetes using blood glucose levels and insulin-to-carbohydrate ratio as input variables. The model is expected to detect deviations from the norm because of infection incidences considering elevated blood glucose levels coupled with unusual changes in the insulin-to-carbohydrate ratio.Three groups of one-class classifiers were trained on target data sets (regular days) and tested on a data set containing both the target and the nontarget (infection days). For comparison, two unsupervised models were also tested. The data set consists of high-precision self-recorded data collected from three real subjects with type 1 diabetes incorporating blood glucose, insulin, diet, and events of infection. The models were evaluated on two groups of data: raw and filtered data and compared based on their performance, computational time, and number of samples required.METHODSThree groups of one-class classifiers were trained on target data sets (regular days) and tested on a data set containing both the target and the nontarget (infection days). For comparison, two unsupervised models were also tested. The data set consists of high-precision self-recorded data collected from three real subjects with type 1 diabetes incorporating blood glucose, insulin, diet, and events of infection. The models were evaluated on two groups of data: raw and filtered data and compared based on their performance, computational time, and number of samples required.The one-class classifiers achieved excellent performance. In comparison, the unsupervised models suffered from performance degradation mainly because of the atypical nature of the data. Among the one-class classifiers, the boundary and domain-based method produced a better description of the data. Regarding the computational time, nearest neighbor, support vector data description, and self-organizing map took considerable training time, which typically increased as the sample size increased, and only local outlier factor and connectivity-based outlier factor took considerable testing time.RESULTSThe one-class classifiers achieved excellent performance. In comparison, the unsupervised models suffered from performance degradation mainly because of the atypical nature of the data. Among the one-class classifiers, the boundary and domain-based method produced a better description of the data. Regarding the computational time, nearest neighbor, support vector data description, and self-organizing map took considerable training time, which typically increased as the sample size increased, and only local outlier factor and connectivity-based outlier factor took considerable testing time.We demonstrated the applicability of one-class classifiers and unsupervised models for the detection of infection incidence in people with type 1 diabetes. In this patient group, detecting infection can provide an opportunity to devise tailored services and also to detect potential public health threats. The proposed approaches achieved excellent performance; in particular, the boundary and domain-based method performed better. Among the respective groups, particular models such as one-class support vector machine, K-nearest neighbor, and K-means achieved excellent performance in all the sample sizes and infection cases. Overall, we foresee that the results could encourage researchers to examine beyond the presented features into other additional features of the self-recorded data, for example, continuous glucose monitoring features and physical activity data, on a large scale.CONCLUSIONSWe demonstrated the applicability of one-class classifiers and unsupervised models for the detection of infection incidence in people with type 1 diabetes. In this patient group, detecting infection can provide an opportunity to devise tailored services and also to detect potential public health threats. The proposed approaches achieved excellent performance; in particular, the boundary and domain-based method performed better. Among the respective groups, particular models such as one-class support vector machine, K-nearest neighbor, and K-means achieved excellent performance in all the sample sizes and infection cases. Overall, we foresee that the results could encourage researchers to examine beyond the presented features into other additional features of the self-recorded data, for example, continuous glucose monitoring features and physical activity data, on a large scale.
BackgroundSemisupervised and unsupervised anomaly detection methods have been widely used in various applications to detect anomalous objects from a given data set. Specifically, these methods are popular in the medical domain because of their suitability for applications where there is a lack of a sufficient data set for the other classes. Infection incidence often brings prolonged hyperglycemia and frequent insulin injections in people with type 1 diabetes, which are significant anomalies. Despite these potentials, there have been very few studies that focused on detecting infection incidences in individuals with type 1 diabetes using a dedicated personalized health model. ObjectiveThis study aims to develop a personalized health model that can automatically detect the incidence of infection in people with type 1 diabetes using blood glucose levels and insulin-to-carbohydrate ratio as input variables. The model is expected to detect deviations from the norm because of infection incidences considering elevated blood glucose levels coupled with unusual changes in the insulin-to-carbohydrate ratio. MethodsThree groups of one-class classifiers were trained on target data sets (regular days) and tested on a data set containing both the target and the nontarget (infection days). For comparison, two unsupervised models were also tested. The data set consists of high-precision self-recorded data collected from three real subjects with type 1 diabetes incorporating blood glucose, insulin, diet, and events of infection. The models were evaluated on two groups of data: raw and filtered data and compared based on their performance, computational time, and number of samples required. ResultsThe one-class classifiers achieved excellent performance. In comparison, the unsupervised models suffered from performance degradation mainly because of the atypical nature of the data. Among the one-class classifiers, the boundary and domain-based method produced a better description of the data. Regarding the computational time, nearest neighbor, support vector data description, and self-organizing map took considerable training time, which typically increased as the sample size increased, and only local outlier factor and connectivity-based outlier factor took considerable testing time. ConclusionsWe demonstrated the applicability of one-class classifiers and unsupervised models for the detection of infection incidence in people with type 1 diabetes. In this patient group, detecting infection can provide an opportunity to devise tailored services and also to detect potential public health threats. The proposed approaches achieved excellent performance; in particular, the boundary and domain-based method performed better. Among the respective groups, particular models such as one-class support vector machine, K-nearest neighbor, and K-means achieved excellent performance in all the sample sizes and infection cases. Overall, we foresee that the results could encourage researchers to examine beyond the presented features into other additional features of the self-recorded data, for example, continuous glucose monitoring features and physical activity data, on a large scale.
Author Årsand, Eirik
Igual, Jorge
Hartvigsen, Gunnar
Woldaregay, Ashenafi Zebene
Launonen, Ilkka Kalervo
Albers, David
AuthorAffiliation 4 Department of Biomedical Informatics Columbia University New York, NY United States
5 Universidad Politecnica Valencia Valencia Spain
3 Department of Pediatrics, Informatics and Data Science University of Colorado Aurora, CO United States
2 Department of Clinical Research University Hospital of North Norway Tromsø Norway
1 Department of Computer Science University of Tromsø – The Arctic University of Norway Tromsø Norway
AuthorAffiliation_xml – name: 4 Department of Biomedical Informatics Columbia University New York, NY United States
– name: 1 Department of Computer Science University of Tromsø – The Arctic University of Norway Tromsø Norway
– name: 2 Department of Clinical Research University Hospital of North Norway Tromsø Norway
– name: 3 Department of Pediatrics, Informatics and Data Science University of Colorado Aurora, CO United States
– name: 5 Universidad Politecnica Valencia Valencia Spain
Author_xml – sequence: 1
  givenname: Ashenafi Zebene
  orcidid: 0000-0002-9464-3407
  surname: Woldaregay
  fullname: Woldaregay, Ashenafi Zebene
– sequence: 2
  givenname: Ilkka Kalervo
  orcidid: 0000-0002-0565-800X
  surname: Launonen
  fullname: Launonen, Ilkka Kalervo
– sequence: 3
  givenname: David
  orcidid: 0000-0002-5369-526X
  surname: Albers
  fullname: Albers, David
– sequence: 4
  givenname: Jorge
  orcidid: 0000-0003-3408-4014
  surname: Igual
  fullname: Igual, Jorge
– sequence: 5
  givenname: Eirik
  orcidid: 0000-0002-9520-1408
  surname: Årsand
  fullname: Årsand, Eirik
– sequence: 6
  givenname: Gunnar
  orcidid: 0000-0001-8771-9867
  surname: Hartvigsen
  fullname: Hartvigsen, Gunnar
BackLink https://www.ncbi.nlm.nih.gov/pubmed/32784179$$D View this record in MEDLINE/PubMed
BookMark eNpdkt9u0zAUhyM0xP6wV0CWENIQKsSJUydcIEUtsEotTGITl9aJc9J6Su1iu5PGW_MGnK7d1O7KsfP5Oz_b5zQ5ss5ikpzz9GPGq-EnXlY8e5GccJGXg7KU_Gjv-zg5DeE2TbNUVPxVcpxnshRcVifJv5r9cHfYs3q18g70gnXOs5Gz0di1Wwd2idDHBfsVIdJs5qyJzhs7Z2BbVq-jW0I0mo0xoo7GWeY6NrHdbjKx2rRoNQZmLLtCt-qR_TYkvL5fIeNsbKChrYHdhI10RgmMRTZF8HazUPdzKhcXy8AursBHlr3_zGoy-eAs9OYvtuSYmwj9U1nKOTYBIeBerBnqBVgTlq-Tlx30Ac9341ly8-3r9ehyMP35fTKqpwMtChkHskCo9JA3uRQdcCF0k1eihabDTOuuLLNhhrrtoMuKdiiGRcdFw5GQNm1bwPwsmWy9rYNbtfJmCf5eOTDqYcH5uaLzGN2jkq1AKdIOC62pRN5UyLkGqiWGElJJri9b12rdLLHVaKOH_kB6-MeahZq7OyVFkeYyI8HFTuDdnzWGqJYmaOx7sEj3pTKRi7SQ1EiEvn2G3rq1p7smSlacjpqnKVFv9hM9RXnsLAI-bAHtXQgeO6XpkTZPQQFNr3iqNn2rHvqW6HfP6EfhIfcfSijwbA
CitedBy_id crossref_primary_10_1186_s13098_022_00969_9
crossref_primary_10_1007_s11042_020_10242_8
Cites_doi 10.1053/beem.2001.0168
10.1016/j.diabres.2017.03.024
10.1002/0470030240
10.1023/b:mach.0000008084.60811.49
10.1177/193229680900300604
10.1109/icpr.2004.1334542
10.1056/NEJM197309202891207
10.1016/s0167-8655(99)00087-2
10.1016/j.ifacol.2016.07.014
10.1016/j.sigpro.2013.12.026
10.1155/2014/730712
10.5772/7544
10.1016/j.artmed.2005.03.002
10.1002/cnm.2833
10.1007/s10479-016-2187-3
10.1177/1460458211428427
10.1146/annurev.nutr.24.012003.132159
10.1145/1541880.1541882
10.1016/0002-9343(82)90511-3
10.1109/dsaa.2016.8
10.1371/journal.pone.0152173
10.2196/11512
10.1007/s10618-019-00661-z
10.3233/ida-130630
10.1109/jcn.2011.6157411
10.1197/jamia.M1345
10.1177/0142331217724508
10.1016/s2589-7500(19)30222-5
10.1214/aoms/1177704472
10.1007/978-3-319-67526-8
10.1210/jcem-69-2-317
10.1016/j.procs.2015.08.220
10.1007/978-94-015-3994-4
10.1080/00401706.1999.10485670
10.1109/tsmcb.2006.876189
10.2196/preprints.18911
10.1016/s0031-3203(96)00142-2
10.1016/j.yasu.2013.03.002
10.1186/s40504-018-0076-z
10.1016/j.aci.2018.08.003
10.2217/14750708.4.1.97
10.1016/j.neucom.2008.05.003
10.4236/jsip.2012.31006
10.1016/j.neucom.2013.12.002
10.1016/S0002-9343(99)80083-7
10.1145/335191.335388
10.1126/scisignal.2003508
10.1017/s026988891300043x
10.2196/11030
ContentType Journal Article
Copyright Ashenafi Zebene Woldaregay, Ilkka Kalervo Launonen, David Albers, Jorge Igual, Eirik Årsand, Gunnar Hartvigsen. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 12.08.2020.
2020. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Ashenafi Zebene Woldaregay, Ilkka Kalervo Launonen, David Albers, Jorge Igual, Eirik Årsand, Gunnar Hartvigsen. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 12.08.2020. 2020
Copyright_xml – notice: Ashenafi Zebene Woldaregay, Ilkka Kalervo Launonen, David Albers, Jorge Igual, Eirik Årsand, Gunnar Hartvigsen. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 12.08.2020.
– notice: 2020. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: Ashenafi Zebene Woldaregay, Ilkka Kalervo Launonen, David Albers, Jorge Igual, Eirik Årsand, Gunnar Hartvigsen. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 12.08.2020. 2020
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
3V.
7QJ
7RV
7X7
7XB
8FI
8FJ
8FK
ABUWG
AFKRA
ALSLI
AZQEC
BENPR
CCPQU
CNYFK
DWQXO
E3H
F2A
FYUFA
GHDGH
K9.
KB0
M0S
M1O
NAPCQ
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQQKQ
PQUKI
PRINS
PRQQA
7X8
5PM
DOA
DOI 10.2196/18912
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
ProQuest Central (Corporate)
Applied Social Sciences Index & Abstracts (ASSIA)
Nursing & Allied Health Database
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Social Science Premium Collection
ProQuest Central Essentials
ProQuest Central
ProQuest One
Library & Information Science Collection
ProQuest Central Korea
Library & Information Sciences Abstracts (LISA)
Library & Information Science Abstracts (LISA)
ProQuest Health & Medical Collection
Health Research Premium Collection (Alumni)
ProQuest Health & Medical Complete (Alumni)
Nursing & Allied Health Database (Alumni Edition)
ProQuest Health & Medical Collection
Library Science Database
Nursing & Allied Health Premium
Proquest Central Premium
ProQuest One Academic (New)
ProQuest Publicly Available Content Database
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
ProQuest One Social Sciences
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)
Library and Information Science Abstracts (LISA)
ProQuest Central Essentials
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest One Health & Nursing
Applied Social Sciences Index and Abstracts (ASSIA)
ProQuest Central China
ProQuest Central
ProQuest Library Science
ProQuest Health & Medical Research Collection
Health Research Premium Collection
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
Library & Information Science Collection
ProQuest Central (New)
Social Science Premium Collection
ProQuest One Social Sciences
ProQuest One Academic Eastern Edition
ProQuest Nursing & Allied Health Source
ProQuest Hospital Collection
Health Research Premium Collection (Alumni)
ProQuest Hospital Collection (Alumni)
Nursing & Allied Health Premium
ProQuest Health & Medical Complete
ProQuest One Academic UKI Edition
ProQuest Nursing & Allied Health Source (Alumni)
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList Publicly Available Content Database
MEDLINE
MEDLINE - Academic

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: 7RV
  name: Nursing & Allied Health Database
  url: https://search.proquest.com/nahs
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Library & Information Science
Public Health
EISSN 1438-8871
ExternalDocumentID oai_doaj_org_article_7d4e740fe5cc4da3b9e11caabf467a07
PMC7450372
32784179
10_2196_18912
Genre Research Support, Non-U.S. Gov't
Journal Article
GrantInformation_xml – fundername: NLM NIH HHS
  grantid: R01 LM012734
GroupedDBID ---
.4I
.DC
29L
2WC
36B
53G
5GY
5VS
77I
77K
7RV
7X7
8FI
8FJ
AAFWJ
AAKPC
AAWTL
AAYXX
ABDBF
ABIVO
ABUWG
ACGFO
ADBBV
AEGXH
AENEX
AFFHD
AFKRA
AFPKN
AIAGR
ALMA_UNASSIGNED_HOLDINGS
ALSLI
AOIJS
BAWUL
BCNDV
BENPR
CCPQU
CITATION
CNYFK
CS3
DIK
DU5
DWQXO
E3Z
EAP
EBD
EBS
EJD
ELW
EMB
EMOBN
ESX
F5P
FRP
FYUFA
GROUPED_DOAJ
GX1
HMCUK
HYE
IAO
KQ8
M1O
M48
NAPCQ
OK1
OVT
P2P
PGMZT
PHGZM
PHGZT
PIMPY
PPXIY
PQQKQ
PRQQA
RNS
RPM
SJN
SV3
TR2
UKHRP
XSB
ACUHS
ALIPV
CGR
CUY
CVF
ECM
EIF
NPM
3V.
7QJ
7XB
8FK
AZQEC
E3H
F2A
K9.
PJZUB
PKEHL
PQEST
PQUKI
PRINS
7X8
5PM
ID FETCH-LOGICAL-c457t-75ea9c61b374fa144cb394dabfe2ccf88262ecdfaf25d6465f14b1e94dd0ddae3
IEDL.DBID DOA
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000575055000016&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1438-8871
1439-4456
IngestDate Fri Oct 03 12:51:53 EDT 2025
Tue Nov 04 01:50:25 EST 2025
Sun Nov 09 12:19:14 EST 2025
Sat Nov 08 22:23:51 EST 2025
Mon Jul 21 05:51:29 EDT 2025
Sat Nov 29 03:22:28 EST 2025
Tue Nov 18 21:30:52 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 8
Keywords self-recorded health data
type 1 diabetes
decision support techniques
infection detection
syndromic surveillance
outbreak detection system
Language English
License Ashenafi Zebene Woldaregay, Ilkka Kalervo Launonen, David Albers, Jorge Igual, Eirik Årsand, Gunnar Hartvigsen. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 12.08.2020.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The complete bibliographic information, a link to the original publication on http://www.jmir.org/, as well as this copyright and license information must be included.
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c457t-75ea9c61b374fa144cb394dabfe2ccf88262ecdfaf25d6465f14b1e94dd0ddae3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0001-8771-9867
0000-0002-9464-3407
0000-0002-5369-526X
0000-0002-9520-1408
0000-0002-0565-800X
0000-0003-3408-4014
OpenAccessLink https://doaj.org/article/7d4e740fe5cc4da3b9e11caabf467a07
PMID 32784179
PQID 2791646300
PQPubID 2033121
ParticipantIDs doaj_primary_oai_doaj_org_article_7d4e740fe5cc4da3b9e11caabf467a07
pubmedcentral_primary_oai_pubmedcentral_nih_gov_7450372
proquest_miscellaneous_2434057196
proquest_journals_2791646300
pubmed_primary_32784179
crossref_citationtrail_10_2196_18912
crossref_primary_10_2196_18912
PublicationCentury 2000
PublicationDate 2020-08-12
PublicationDateYYYYMMDD 2020-08-12
PublicationDate_xml – month: 08
  year: 2020
  text: 2020-08-12
  day: 12
PublicationDecade 2020
PublicationPlace Canada
PublicationPlace_xml – name: Canada
– name: Toronto
– name: Toronto, Canada
PublicationTitle Journal of medical Internet research
PublicationTitleAlternate J Med Internet Res
PublicationYear 2020
Publisher Gunther Eysenbach MD MPH, Associate Professor
JMIR Publications
Publisher_xml – name: Gunther Eysenbach MD MPH, Associate Professor
– name: JMIR Publications
References Mehrotra, KG (ref9) 2017
ref13
ref57
ref56
ref15
ref59
ref14
ref58
ref52
ref11
Tang, J (ref34) 2002
ref55
ref10
ref54
ref19
ref18
ref51
Clark, M (ref17) 2004
ref46
ref45
ref48
ref42
ref41
Hajizadeh, S (ref47) 2014
ref44
Mazhelis, O (ref16) 2006; 2006
ref43
Tax, DM (ref12) 2002
ref49
ref7
ref3
ref6
ref40
Hawkins, DM (ref8) 1980
ref35
ref37
ref36
ref31
ref30
ref33
ref32
ref2
ref39
ref38
Janssens, JH (ref65) 2013
Cohen, G (ref5) 2008; 136
ref71
ref70
ref24
ref68
ref23
ref67
ref26
ref25
ref69
Cohen, G (ref4) 2004; 107
ref20
ref64
ref63
ref22
ref66
ref21
ref28
ref27
ref29
Dunning, T (ref1) 2014
ref60
McNamara, LA (ref50) 2018
ref62
ref61
Spinosa, EJ (ref53) 2005; 4
References_xml – ident: ref62
  doi: 10.1053/beem.2001.0168
– year: 2013
  ident: ref65
  publication-title: Outlier Selection and One-Class Classification
– ident: ref18
  doi: 10.1016/j.diabres.2017.03.024
– year: 2004
  ident: ref17
  publication-title: Understanding Diabetes
  doi: 10.1002/0470030240
– ident: ref27
  doi: 10.1023/b:mach.0000008084.60811.49
– volume: 2006
  start-page: 29
  issue: 36
  year: 2006
  ident: ref16
  publication-title: S Afr Comput J
– ident: ref61
  doi: 10.1177/193229680900300604
– ident: ref43
  doi: 10.1109/icpr.2004.1334542
– ident: ref59
  doi: 10.1056/NEJM197309202891207
– ident: ref29
  doi: 10.1016/s0167-8655(99)00087-2
– ident: ref69
– ident: ref48
  doi: 10.1016/j.ifacol.2016.07.014
– ident: ref30
– ident: ref3
  doi: 10.1016/j.sigpro.2013.12.026
– ident: ref13
  doi: 10.1155/2014/730712
– ident: ref46
  doi: 10.5772/7544
– ident: ref6
  doi: 10.1016/j.artmed.2005.03.002
– ident: ref57
  doi: 10.1002/cnm.2833
– ident: ref40
  doi: 10.1007/s10479-016-2187-3
– ident: ref22
  doi: 10.1177/1460458211428427
– year: 2002
  ident: ref12
  publication-title: One-Class Classification: Concept Learning in the Absence of Counter-Examples
– ident: ref23
– ident: ref60
  doi: 10.1146/annurev.nutr.24.012003.132159
– ident: ref7
  doi: 10.1145/1541880.1541882
– ident: ref21
  doi: 10.1016/0002-9343(82)90511-3
– ident: ref54
– ident: ref37
  doi: 10.1109/dsaa.2016.8
– ident: ref36
  doi: 10.1371/journal.pone.0152173
– ident: ref71
  doi: 10.2196/11512
– ident: ref33
– ident: ref42
  doi: 10.1007/s10618-019-00661-z
– ident: ref44
  doi: 10.3233/ida-130630
– ident: ref51
  doi: 10.1109/jcn.2011.6157411
– ident: ref55
  doi: 10.1197/jamia.M1345
– ident: ref66
  doi: 10.1177/0142331217724508
– volume: 107
  start-page: 716
  issue: Pt 1
  year: 2004
  ident: ref4
  publication-title: Stud Health Technol Inform
– ident: ref68
  doi: 10.1016/s2589-7500(19)30222-5
– ident: ref39
  doi: 10.1214/aoms/1177704472
– volume: 4
  start-page: 608
  issue: 3
  year: 2005
  ident: ref53
  publication-title: Genet Mol Res
– year: 2017
  ident: ref9
  publication-title: Anomaly Detection Principles and Algorithms
  doi: 10.1007/978-3-319-67526-8
– ident: ref58
  doi: 10.1210/jcem-69-2-317
– ident: ref2
  doi: 10.1016/j.procs.2015.08.220
– year: 2002
  ident: ref34
  publication-title: Advances in Knowledge Discovery and Data Mining
– year: 1980
  ident: ref8
  publication-title: Identification of Outliers
  doi: 10.1007/978-94-015-3994-4
– ident: ref32
– ident: ref38
  doi: 10.1080/00401706.1999.10485670
– ident: ref52
  doi: 10.1109/jcn.2011.6157411
– ident: ref70
– year: 2018
  ident: ref50
  publication-title: Principles and Practice of Pediatric Infectious Diseases. Fifth Edition
– year: 2014
  ident: ref1
  publication-title: Practical Machine Learning: A New Look at Anomaly Detection
– ident: ref64
  doi: 10.1109/tsmcb.2006.876189
– ident: ref19
  doi: 10.2196/preprints.18911
– ident: ref63
– ident: ref49
  doi: 10.1016/s0031-3203(96)00142-2
– ident: ref25
  doi: 10.1016/j.yasu.2013.03.002
– ident: ref67
  doi: 10.1186/s40504-018-0076-z
– ident: ref45
  doi: 10.1016/j.aci.2018.08.003
– year: 2014
  ident: ref47
  publication-title: Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshop
– ident: ref28
– ident: ref26
  doi: 10.2217/14750708.4.1.97
– ident: ref15
  doi: 10.1016/j.neucom.2008.05.003
– ident: ref41
  doi: 10.4236/jsip.2012.31006
– ident: ref11
  doi: 10.1016/j.neucom.2013.12.002
– volume: 136
  start-page: 21
  year: 2008
  ident: ref5
  publication-title: Stud Health Technol Inform
– ident: ref24
  doi: 10.1016/S0002-9343(99)80083-7
– ident: ref31
  doi: 10.1145/335191.335388
– ident: ref20
  doi: 10.1126/scisignal.2003508
– ident: ref10
  doi: 10.1017/s026988891300043x
– ident: ref56
  doi: 10.2196/11030
– ident: ref35
– ident: ref14
SSID ssj0020491
Score 2.3313441
Snippet Semisupervised and unsupervised anomaly detection methods have been widely used in various applications to detect anomalous objects from a given data set....
Background: Semisupervised and unsupervised anomaly detection methods have been widely used in various applications to detect anomalous objects from a given...
BackgroundSemisupervised and unsupervised anomaly detection methods have been widely used in various applications to detect anomalous objects from a given data...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage e18912
SubjectTerms Algorithms
Blood
Carbohydrates
Data
Datasets
Degradation
Description
Diabetes
Diabetes Complications - complications
Diabetes Mellitus, Type 1 - complications
Diabetics
Diet
Glucose
Groups
Health problems
Health services
Health status
Humans
Hyperglycemia
Incidence
Infections
Infectious diseases
Influenza
Insulin
Machine learning
Machine Learning - standards
Methods
Multimedia
Original Paper
Physical activity
Physical fitness
Precision Medicine - methods
Public health
Suitability
Support vector machines
Tests
Time
Type 1 diabetes mellitus
SummonAdditionalLinks – databaseName: Nursing & Allied Health Database
  dbid: 7RV
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELagoAqp4rEUCLTVIFUIDlETx1knXNBCqbjsaoV49Bb5lW2kNimbbA_8a_4BY8cbuhXiwjFrrzNJxuN5fkPIYWJLu5iWoZZChExESSg1HYcSB7TD_6bSNZvgs1l2eprPvcOt9WmVa5noBLVulPWRH1GeWyisJIreXf4IbdcoG131LTRukzuxPbuRn_nnb4PBhdpvvE12bLozMtpRnOUx3Th_HEz_33TLmymS186ckwf_S-1Dct9rmzDp2eMRuWXqEdn3tQrwCnwxkv044Hf5iGxPfbx9RHZ6rx70xUqPya8JzJorgyt6KHLA_4NFuKrqVbNq_USwKixe9QLDeg5B1Bomq65xCLFwbDqXAlZDU1oi_AUKq77HaQtVDXOX3A7fK1zQmssQg8_facFlOsDUZYIa8CCxC5icL_B23dlFC6_nuCmAvnkLE5ivLY6fRuMaC9soZbgt0nncR6mukTU1tiK6ai92ydeTj18-fAp904hQsZR3IU-NyNU4lglnpUBzUckkZ1rI0lClSjQoxtQoXYqSpho_UVrGTMYGp-hIa2GSJ2SrbmrzjEBm62e0KSUbG8YMF6XUWZ5lLNUq0lQH5HDNSoXyiOq2scd5gZaV5bjCcVxADoZplz2EyM0J7y0fDoMW8dv90CwXhRcgBddIAYtKkyqFj5PI3MSxEvhceNSJiAdkb82JhRdDbfGHDQPychhGAWKjQqI2-IoLyhKrtCM1AXnaM_1ASeLC0jwPCN_YDhukbo7U1ZkDKecsjRJOn_-brBfkHrUODIsxTPfIVrdcmX1yV111Vbs8cLv5N5s0XS4
  priority: 102
  providerName: ProQuest
Title A Novel Approach for Continuous Health Status Monitoring and Automatic Detection of Infection Incidences in People With Type 1 Diabetes Using Machine Learning Algorithms (Part 2): A Personalized Digital Infectious Disease Detection Mechanism
URI https://www.ncbi.nlm.nih.gov/pubmed/32784179
https://www.proquest.com/docview/2791646300
https://www.proquest.com/docview/2434057196
https://pubmed.ncbi.nlm.nih.gov/PMC7450372
https://doaj.org/article/7d4e740fe5cc4da3b9e11caabf467a07
Volume 22
WOSCitedRecordID wos000575055000016&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: 1438-8871
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0020491
  issn: 1438-8871
  databaseCode: DOA
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVPQU
  databaseName: Health & Medical Collection
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0020491
  issn: 1438-8871
  databaseCode: 7X7
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Library Science Database
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0020491
  issn: 1438-8871
  databaseCode: M1O
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/libraryscience
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Nursing & Allied Health Database
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0020491
  issn: 1438-8871
  databaseCode: 7RV
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/nahs
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0020491
  issn: 1438-8871
  databaseCode: BENPR
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Publicly Available Content Database
  customDbUrl:
  eissn: 1438-8871
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0020491
  issn: 1438-8871
  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/eLvHCXMwrV1Lb9QwELagoAoJISgUAu1qkCoEh6iJ48QJty1tBYddoopHOUV-ZRupzaIm2wP_mn_A2PGudiskLlwsJbbsif05mYlnviHkILGhXUzLUEshQiaiJJSaZqHECu34v6l0ySb4dJqfnxflWqov6xM20AMPE3fINTOcRbVJlWJaJLIwcayEkDVucTHEkaPWszSmvKmFem-8TR5aR2eE2GGcFzHd-PI4gv6_aZW3nSPXvjanj8kjrybCeBDvCblj2h2y74MM4A34KCI7q-C35w7ZnviD8qfk9xim8xuDPXjOcMD2YKmomnaBxj4M4UdgdU28Gna2_cUHotUwXvRzR-UKx6Z3vlotzGs7qL_At8qQjLSDpoXSeaHD9wY7tHYtxOAdbTpwLgkwcS6bBjyb6wzGlzMcrr-46uBtiYsA9N17GEO5NA1-GY19zGxGk9WwKOfxcJy0JtbE2NDlprt6Rr6ennz58DH02R1CxVLehzw1olBZLBPOaoF2nZJJgSssa0OVqlHzz6hRuhY1TXXGsrSOmYwNNtGR1sIku2SrnbfmBYHcBrpoU0uWGYZwEbXUeZHnLNUq0lQH5GC58pXy1Oc2A8dlhSaQBUjlABKQ0arZz4Hr43aDIwubVaWl5nY3ELCVB2z1L8AGZG8Jusq_L7qK8sISvSVRFJDXq2rc6fb4RrQGp7iiLLHaNUoTkOcDRleSJO78mBcB4Rvo3RB1s6ZtLhybOGdplHD68n882yvygNr_EZYymO6Rrf56YfbJfXXTN931iNzlZ99sec5dmY_IvaOTaXk2cpsXy0n8Ge-Vnybljz9Lz1Kj
linkProvider Directory of Open Access Journals
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1fb9MwELfGQANp4s_4V9jGIQ0ED9ESx6kbJIQKY9q0terDEHsLju10lbZkLO0QfCi-G9-AO8ft1gnxxgOPiR37kpzPd-e73zG2EVNqlzB5YHKlAqHCOMgNbwc5NhiH_81zV2xC9vudw8N0sMB-TnNhKKxyKhOdoDaVJh_5JpcpQWHFYfju9GtAVaPodHVaQqNhiz37_RuabPXb3S38vy843_548GEn8FUFAi0SOQ5kYlWq21EeS1EotCd0HqfCqLywXOsCNc42t9oUquCJwRmTIhJ5ZLGLCY1RNsZxr7HrKMclhZDJwwsDD7XtaIktU3g1MvZm1EkjPrffubIAf9Jlr4ZkXtrjtu_8b1_nLrvttWnoNux_jy3YcoWt-VwMeAk-2YqYD7wUW2FLPR9PsMKWG68lNMlY99mvLvSrc4sjeqh1wOeBELxG5aSa1L4jkIqOV41AJM8oqNJAdzKuHAIubNmxC3EroSqICH-Bwrip4VrDqISBC96HzyMckNwBEIGPT6rBRXJAz0W6WvAguEPoHg9xuvHRSQ2vBrjogb9-A10YTC2qH9bgGEMqBDObFuncak7hLpHVs5TxPapPHrBP_-QHPWSLZVXaxww6lB9kbJGLthXCSlXkppN2OiIxOjTctNjGlHUz7RHjqXDJcYaWI3F45ji8xdZn3U4biJSrHd4T388aCdHc3ajOhpkXkJk0SIEIC5toja8T56mNIq3wvXArV6FssdUp52dezNbZBdu32PNZMwpIOvVSpcVPnHERk1GC1LTYo2aRzSiJ3bG7TFtMzi2_OVLnW8rRkQNhlyIJY8mf_J2sZ-zmzkFvP9vf7e89Zbc4OWsIT5mvssXx2cSusRv6fDyqz9adJAH25V8vzt_nkb4r
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1fb9MwED-NDU1IE3_Gv8I2DmkgeIiWOE7dICHU0U1MY1WFQOwtOLbTVdqSsbRD8NH4VnwDzo5b1gnxtgceEzv2Jbk739l3vwPYjG1qF9d5oHMpAy7DOMg1awc5NWiH_81yV2xC9Pudw8N0sAA_p7kwNqxyqhOdotaVsnvkW0ykFgorDsOtwodFDHq7b06_BraClD1pnZbTaFhk33z_Ru5b_XqvR__6GWO7Ox_fvgt8hYFA8USMA5EYmap2lMeCF5J8C5XHKdcyLwxTqiDrs82M0oUsWKJp9qSIeB4Z6qJDraWJadxrsCTIyCDpWtre6Q8-zNw9sr2jZVixwdbE5ltRJ43Y3OrnigT8zbK9HKB5YcXbvfU_f6vbcNPb2dhtBOMOLJhyFdZ9lgY-R5-GZdkSvX5bheUDH2mwCivNfiY2aVp34VcX-9W5oRE9CDvS82ixvUblpJrUviNa452uGlVp90xRlhq7k3HlsHGxZ8Yu-K3EqrBE-AtS00111xpHJQ5cWD9-HtGAdqMAI_SRSzW6GA88cDGwBj087hC7x0Oabnx0UuOLAakDZC9fYRcHU1_rh9E0xtCWiJlNS3T2mvO5C2QdGJsLPqpP7sGnK_lB92GxrErzELBjM4e0KXLeNpwbIYtcd9JOhydahZrpFmxO2ThTHkveljQ5zsintNyeOW5vwcas22kDnnK5w7aVgVmjxTp3N6qzYeZVZyY0UcDDwiRK0evEeWqiSEl6L1rkZShasDaVgswr4Dr7IwIteDprJtVpz8NkaegTZ4zH1l0halrwoBG4GSWxO5AXaQvEnCjOkTrfUo6OHDy74EkYC_bo32Q9gWWSyez9Xn__MdxgdhfHAi2zNVgcn03MOlxX5-NRfbbh1QrCl6uWzt8erchM
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=A+Novel+Approach+for+Continuous+Health+Status+Monitoring+and+Automatic+Detection+of+Infection+Incidences+in+People+With+Type+1+Diabetes+Using+Machine+Learning+Algorithms+%28Part+2%29%3A+A+Personalized+Digital+Infectious+Disease+Detection+Mechanism&rft.jtitle=Journal+of+medical+Internet+research&rft.au=Woldaregay%2C+Ashenafi+Zebene&rft.au=Launonen%2C+Ilkka+Kalervo&rft.au=Albers%2C+David&rft.au=Igual%2C+Jorge&rft.date=2020-08-12&rft.pub=JMIR+Publications&rft.eissn=1438-8871&rft.volume=22&rft.issue=8&rft.spage=e18912&rft_id=info:doi/10.2196%2F18912&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_7d4e740fe5cc4da3b9e11caabf467a07
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1438-8871&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1438-8871&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1438-8871&client=summon