Synthetic Data Generation and Evaluation Techniques for Classifiers in Data Starved Medical Applications

With their ability to find solutions among complex relationships of variables, machine learning (ML) techniques are becoming more applicable to various fields, including health risk prediction. However, prediction models are sensitive to the size and distribution of the data they are trained on. ML...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE access Ročník 13; s. 16584 - 16602
Hlavní autoři: Bae, Wan D., Alkobaisi, Shayma, Horak, Matthew, Bankar, Siddheshwari, Bhuvaji, Sartaj, Kim, Sungroul, Park, Choon-Sik
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:2169-3536, 2169-3536
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract With their ability to find solutions among complex relationships of variables, machine learning (ML) techniques are becoming more applicable to various fields, including health risk prediction. However, prediction models are sensitive to the size and distribution of the data they are trained on. ML algorithms rely heavily on vast quantities of training data to make accurate predictions. Ideally, the dataset should have an equal number of samples for each label to encourage the model to make predictions based on the input data rather than the distribution of the training data. In medical applications, class imbalance is a common issue because the occurrence of a disease or risk episode is often rare. This leads to a training dataset where healthy cases outnumber unhealthy ones, resulting in biased prediction models that struggle to detect the minority, unhealthy cases effectively. This paper addresses the problem of class imbalance, given the scarcity of training datasets by improving the quality of generated data. We propose an incremental synthetic data generation system that improves data quality over iterations by gradually adjusting to the data distribution and thus avoids overfitting in classifiers. Through extensive experimental assessments on real asthma patients' datasets, we demonstrate the efficiency and applicability of our proposed system for individual-based health risk prediction models. Incremental SMOTE methods were compared to the original SMOTE variants as well as various architectures of autoencoders. Our incremental data generation system enhances selected state-of-the-art SMOTE methods, resulting in sensitivity improvements for deep transfer learning (TL) classifiers ranging from 4.01% to 7.79%. Compared with the performance of TL without oversampling, the improvement achieved by the incremental SMOTE methods ranged from 27.18% to 40.97%. These results highlight the effectiveness of our technique in predicting asthma risk and their applicability to imbalanced, data-starved medical contexts.
AbstractList With their ability to find solutions among complex relationships of variables, machine learning (ML) techniques are becoming more applicable to various fields, including health risk prediction. However, prediction models are sensitive to the size and distribution of the data they are trained on. ML algorithms rely heavily on vast quantities of training data to make accurate predictions. Ideally, the dataset should have an equal number of samples for each label to encourage the model to make predictions based on the input data rather than the distribution of the training data. In medical applications, class imbalance is a common issue because the occurrence of a disease or risk episode is often rare. This leads to a training dataset where healthy cases outnumber unhealthy ones, resulting in biased prediction models that struggle to detect the minority, unhealthy cases effectively. This paper addresses the problem of class imbalance, given the scarcity of training datasets by improving the quality of generated data. We propose an incremental synthetic data generation system that improves data quality over iterations by gradually adjusting to the data distribution and thus avoids overfitting in classifiers. Through extensive experimental assessments on real asthma patients' datasets, we demonstrate the efficiency and applicability of our proposed system for individual-based health risk prediction models. Incremental SMOTE methods were compared to the original SMOTE variants as well as various architectures of autoencoders. Our incremental data generation system enhances selected state-of-the-art SMOTE methods, resulting in sensitivity improvements for deep transfer learning (TL) classifiers ranging from 4.01% to 7.79%. Compared with the performance of TL without oversampling, the improvement achieved by the incremental SMOTE methods ranged from 27.18% to 40.97%. These results highlight the effectiveness of our technique in predicting asthma risk and their applicability to imbalanced, data-starved medical contexts.
Author Horak, Matthew
Alkobaisi, Shayma
Bae, Wan D.
Park, Choon-Sik
Bankar, Siddheshwari
Bhuvaji, Sartaj
Kim, Sungroul
Author_xml – sequence: 1
  givenname: Wan D.
  orcidid: 0000-0002-4611-5546
  surname: Bae
  fullname: Bae, Wan D.
  organization: Department of Computer Science, Seattle University, Seattle, WA, USA
– sequence: 2
  givenname: Shayma
  orcidid: 0000-0003-4237-7976
  surname: Alkobaisi
  fullname: Alkobaisi, Shayma
  email: shayma.alkobaisi@uaeu.ac.ae
  organization: College of Information Technology, United Arab Emirates University, Al Ain, United Arab Emirates
– sequence: 3
  givenname: Matthew
  orcidid: 0009-0008-3968-3626
  surname: Horak
  fullname: Horak, Matthew
  organization: Amazon AWS Lambda, Seattle, WA, USA
– sequence: 4
  givenname: Siddheshwari
  orcidid: 0009-0004-1613-3569
  surname: Bankar
  fullname: Bankar, Siddheshwari
  organization: Department of Computer Science, Seattle University, Seattle, WA, USA
– sequence: 5
  givenname: Sartaj
  orcidid: 0009-0006-4594-7857
  surname: Bhuvaji
  fullname: Bhuvaji, Sartaj
  organization: Department of Computer Science, Seattle University, Seattle, WA, USA
– sequence: 6
  givenname: Sungroul
  orcidid: 0000-0001-8726-9288
  surname: Kim
  fullname: Kim, Sungroul
  organization: Department of ICT Environmental Health System, Graduate School, Soonchunhyang University, Asan, South Korea
– sequence: 7
  givenname: Choon-Sik
  orcidid: 0000-0001-7955-2526
  surname: Park
  fullname: Park, Choon-Sik
  organization: Department of Internal Medicine, Soonchunhyang University Bucheon Hospital, Bucheon, South Korea
BookMark eNqFkU1v2zAMho2hA9p1_QXdwcDOyfRlWzoGXtYW6LBDurNAS9SiwLMySSnQfz-5Lopil_EikuBDinw_VGdTmLCqrilZU0rUl03fb3e7NSOsWfOGs2LvqgtGW7UqYXv2xj-vrlI6kGKypJruotrvnqa8x-xN_RUy1Dc4YYTsw1TDZOvtI4ynJXxAs5_8nxOm2oVY9yOk5J3HmGo_LfAuQ3xEW39H6w2M9eZ4HIsz4-lj9d7BmPDq5b2sfn7bPvS3q_sfN3f95n5lBFF5BYaKxkqnumFAaoWVTcsc7xzpuGIEOgRw0JpWNnLgUjArOLHSurYDJqThl9Xd0tcGOOhj9L8hPukAXj8nQvylIZZ1R9RqaIWThrRKcjFIpjqkyLhhRAqKZu71eel1jGFePOtDOMWpfF9z2lLeUclpqeJLlYkhpYjudSolelZILwrpWSH9olCh1D-U8fn5VDmCH__DflpYj4hvpknRlbPwv_YzoLA
CODEN IAECCG
CitedBy_id crossref_primary_10_1109_ACCESS_2025_3578826
Cites_doi 10.1097/MCP.0b013e32834db288
10.5391/ijfis.2017.17.4.229
10.1542/peds.105.5.1029
10.1613/jair.953
10.1016/j.knosys.2020.106368
10.1016/j.ins.2019.11.004
10.1145/3523089.3523096
10.3390/en13174291
10.1093/bib/bbab277
10.1186/2047-2501-2-3
10.1109/BigData55660.2022.10020487
10.1145/3511808.3557699
10.1371/journal.pone.0244233
10.1109/INDIN51400.2023.10218063
10.3390/app10010159
10.1016/j.eswa.2022.117023
10.1155/2018/6275435
10.1109/ISBI.2017.7950523
10.1002/9781118646106.ch3
10.1016/j.procs.2018.10.517
10.1145/3422622
10.1038/s41598-021-93543-8
10.1016/j.ins.2013.07.007
10.1109/DSAA.2018.00025
10.1007/978-3-540-39804-2_12
10.1613/jair.1.11192
10.1016/j.aap.2020.105950
10.1186/s13638-020-01689-2
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID 97E
ESBDL
RIA
RIE
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
DOA
DOI 10.1109/ACCESS.2025.3532222
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005-present
IEEE Open Access Journals
IEEE All-Society Periodicals Package (ASPP) 1998-Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Engineered Materials Abstracts
METADEX
Technology Research Database
Materials Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
Materials Research Database
Engineered Materials Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
METADEX
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Materials Research 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: RIE
  name: IEEE Xplore Digital Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 2169-3536
EndPage 16602
ExternalDocumentID oai_doaj_org_article_9b64f8c069834b8297e1e23c20841ecc
10_1109_ACCESS_2025_3532222
10847858
Genre orig-research
GrantInformation_xml – fundername: United Arab Emirates University, United Arab Emirates, under UAEU-NFRP
  grantid: G00004281
  funderid: 10.13039/501100006013
– fundername: Ministry of Science and ICT, South Korea, under the National Research Foundation of Korea
  grantid: NRF-2022R1A2C1010172
– fundername: Seattle University, USA, under the Thomas Bannan Chair Engineering Award
  grantid: 11-0-1-480530
– fundername: Soonchunhyang University, South Korea
  funderid: 10.13039/501100002560
GroupedDBID 0R~
4.4
5VS
6IK
97E
AAJGR
ABAZT
ABVLG
ACGFS
ADBBV
AGSQL
ALMA_UNASSIGNED_HOLDINGS
BCNDV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
ESBDL
GROUPED_DOAJ
IPLJI
JAVBF
KQ8
M43
M~E
O9-
OCL
OK1
RIA
RIE
RNS
AAYXX
CITATION
7SC
7SP
7SR
8BQ
8FD
JG9
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c409t-ac145d8f97bbe1d4d8562f37f073920a7eaafa6c6858b3842d430d8df67a248c3
IEDL.DBID DOA
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001410337900032&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2169-3536
IngestDate Fri Oct 03 12:53:08 EDT 2025
Mon Jun 30 13:02:29 EDT 2025
Tue Nov 18 22:32:16 EST 2025
Sat Nov 29 04:27:20 EST 2025
Wed Aug 27 01:53:11 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License https://creativecommons.org/licenses/by/4.0/legalcode
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c409t-ac145d8f97bbe1d4d8562f37f073920a7eaafa6c6858b3842d430d8df67a248c3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0009-0008-3968-3626
0000-0002-4611-5546
0009-0004-1613-3569
0000-0001-8726-9288
0000-0001-7955-2526
0009-0006-4594-7857
0000-0003-4237-7976
OpenAccessLink https://doaj.org/article/9b64f8c069834b8297e1e23c20841ecc
PQID 3161371831
PQPubID 4845423
PageCount 19
ParticipantIDs proquest_journals_3161371831
ieee_primary_10847858
crossref_primary_10_1109_ACCESS_2025_3532222
doaj_primary_oai_doaj_org_article_9b64f8c069834b8297e1e23c20841ecc
crossref_citationtrail_10_1109_ACCESS_2025_3532222
PublicationCentury 2000
PublicationDate 20250000
2025-00-00
20250101
2025-01-01
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 20250000
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE access
PublicationTitleAbbrev Access
PublicationYear 2025
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref15
ref14
ref30
ref11
ref10
(ref6) 2023
ref2
(ref31) 2023
ref1
ref17
ref19
ref18
ref24
ref23
ref26
ref25
ref20
ref22
ref21
Xu (ref16); 32
ref28
ref27
ref29
ref8
ref7
ref9
ref4
ref3
ref5
References_xml – volume: 32
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref16
  article-title: Modeling tabular data using conditional GAN
– ident: ref3
  doi: 10.1097/MCP.0b013e32834db288
– ident: ref12
  doi: 10.5391/ijfis.2017.17.4.229
– ident: ref1
  doi: 10.1542/peds.105.5.1029
– volume-title: Gretel
  year: 2023
  ident: ref31
– ident: ref5
  doi: 10.1613/jair.953
– ident: ref11
  doi: 10.1016/j.knosys.2020.106368
– ident: ref4
  doi: 10.1016/j.ins.2019.11.004
– ident: ref13
  doi: 10.1145/3523089.3523096
– ident: ref17
  doi: 10.3390/en13174291
– ident: ref21
  doi: 10.1093/bib/bbab277
– ident: ref2
  doi: 10.1186/2047-2501-2-3
– ident: ref19
  doi: 10.1109/BigData55660.2022.10020487
– ident: ref22
  doi: 10.1145/3511808.3557699
– ident: ref7
  doi: 10.1371/journal.pone.0244233
– ident: ref23
  doi: 10.1109/INDIN51400.2023.10218063
– ident: ref29
  doi: 10.3390/app10010159
– ident: ref28
  doi: 10.1016/j.eswa.2022.117023
– ident: ref9
  doi: 10.1155/2018/6275435
– ident: ref30
  doi: 10.1109/ISBI.2017.7950523
– ident: ref10
  doi: 10.1002/9781118646106.ch3
– ident: ref26
  doi: 10.1016/j.procs.2018.10.517
– volume-title: The Synthetic Data Vault
  year: 2023
  ident: ref6
– ident: ref15
  doi: 10.1145/3422622
– ident: ref18
  doi: 10.1038/s41598-021-93543-8
– ident: ref8
  doi: 10.1016/j.ins.2013.07.007
– ident: ref25
  doi: 10.1109/DSAA.2018.00025
– ident: ref24
  doi: 10.1007/978-3-540-39804-2_12
– ident: ref14
  doi: 10.1613/jair.1.11192
– ident: ref20
  doi: 10.1016/j.aap.2020.105950
– ident: ref27
  doi: 10.1186/s13638-020-01689-2
SSID ssj0000816957
Score 2.340757
Snippet With their ability to find solutions among complex relationships of variables, machine learning (ML) techniques are becoming more applicable to various fields,...
SourceID doaj
proquest
crossref
ieee
SourceType Open Website
Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 16584
SubjectTerms Algorithms
Asthma
Autoencoders
Boosting
class imbalance problem
Classification algorithms
Complex variables
control coefficient
Data models
data starved contexts
Datasets
Generative adversarial networks
Health risk assessment
Machine learning
Medical services
Prediction models
Predictive models
rare event prediction
Synthetic data
synthetic minority oversampling technique
Training data
transfer learning
SummonAdditionalLinks – databaseName: IEEE Electronic Library (IEL)
  dbid: RIE
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La9wwEB6SkENz6DOhm6ZFhx7rVLJkSzpuNwk9lFBoCrkJPelCccruJtB_n5GsXbaUBHIzRsKyP43m5fkG4KMIwqdepQa1G22EFrJxFuVRhhQjY55RV3hmv8nLS3V9rb_XYvVSCxNjLD-fxdN8WXL54cbf5lAZSjiepapTu7ArZT8Wa20CKrmDhO5kZRZiVH-ezmb4EugDtt0p73JKof1H-xSS_tpV5b-juOiXixdPXNlLeF4NSTIdkX8FO3F4DQdb9IJv4NePvwPadziAnNmVJSPFdEaC2CGQ8w3RN7laM7kuCRqxpHTKnKfcJZvMh3EyWqWLuxhIzeyQ6Vbm-xB-Xpxfzb42tbNC49GfWzXWM9EFlbR0LrIggkIzKHGZct6upVZGa5PtfSand1yJNghOgwqpl7YVyvMj2BtuhvgWiA1WUd_H3mbPhDInvOtosiEFp520E2jXX9z4Sjueu1_8NsX9oNqMMJkMk6kwTeDTZtKfkXXj8eFfMpSboZkyu9xAjEyVQKNdL5LytNeKC5criiOLLfctQsdwI0_gMOO69bwR0gmcrHeGqfK9NBwNZY5qnbPjB6a9g2d5iWO05gT2Vovb-B72_d1qvlx8KFv3HtAj7So
  priority: 102
  providerName: IEEE
Title Synthetic Data Generation and Evaluation Techniques for Classifiers in Data Starved Medical Applications
URI https://ieeexplore.ieee.org/document/10847858
https://www.proquest.com/docview/3161371831
https://doaj.org/article/9b64f8c069834b8297e1e23c20841ecc
Volume 13
WOSCitedRecordID wos001410337900032&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: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: DOA
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center)
  customDbUrl:
  eissn: 2169-3536
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816957
  issn: 2169-3536
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3NSxwxFA9FPNRDUau49YMcPHZqMslMkuO6rnhQEWrBW8gnLpRp2V0FL_7tvmSyyxShvfQyh-GFzPtI3nt5k99D6JR77mIrYwXejVRccVFZA-tR-BgCpY4Sm3Fmr8XtrXx4UHeDVl_pn7AeHrgX3JmyLY_SkVZJxm26CBpoqJmrieQU5k-7LxFqkEzlPVjSVjWiwAxRos7GkwlwBAlh3XxjTaov1H-4oozYX1qsvNuXs7O53EafSpSIx_3X7aAPodtFWwPswM_o8ftLB8EbEOALszS4x49OYsam83i6RvHG9yuY1gWGCBXnNpizmFpg41nXD4aQc_4cPC5lGzwelLX30I_L6f3kqiptEyoHydqyMo7yxsuohLWBeu4lxDiRiZiKcjUxIhgTTesS8rxlkteeM-Klj60wNZeO7aON7lcXDhA23kji2tCalHYQarmzDYnGR2-VFWaE6pUEtSuY4qm1xU-dcwuidC92ncSui9hH6Ot60O8eUuPv5OdJNWvShIedX4CV6GIl-l9WMkJ7SbGD-cArA_8jdLTStC6Ld6EZRMEMfDajX_7H3IfoY-KnP7c5QhvL-VM4RpvueTlbzE-y3cLz5nV6km8fvgEffvEI
linkProvider Directory of Open Access Journals
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1baxQxFD7UKqgPXiuutpoHH52a20ySx3Xb0uK6CK7Qt5ArXZCp7G4L_nuTTHZZEQXfhiFhMvPl5NzmfAfgHffcxU7GJmk33HDFRWNNkkfhYwiEOIJt4ZmditlMXl6qL7VYvdTChBDKz2fhOF-WXL6_djc5VJYkPJ2lspV34G7LOcVDudY2pJJ7SKhWVG4hgtWH8WSSXiN5gbQ9Zm1OKtDf9E-h6a99Vf44jIuGOXv8n2t7Ao-qKYnGA_ZPYS_0z-DhDsHgc7j6-rNPFl4agE7M2qCBZDpjgUzv0emW6hvNN1yuK5TMWFR6ZS5i7pONFv0wOdmly9vgUc3toPFO7vsAvp2dzifnTe2t0Ljk0a0b4whvvYxKWBuI514mQygyEXPmjmIjgjHRdC7T01smOfWcYS997IShXDr2Avb76z68BGS8kdh1oTPZN8HEcmdbHI2P3iorzAjo5otrV4nHc_-L77o4IFjpASadYdIVphG83076MfBu_Hv4xwzldmgmzS43Eka6yqBWtuNROtwpybjNNcWBBMocTdCRtJVHcJBx3XneAOkIDjc7Q1cJX2mWTGWWFDsjr_4y7S3cP59_nurpxezTa3iQlzvEbg5hf728CUdwz92uF6vlm7KNfwFHs_Bx
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=Synthetic+Data+Generation+and+Evaluation+Techniques+for+Classifiers+in+Data+Starved+Medical+Applications&rft.jtitle=IEEE+access&rft.au=Bae%2C+Wan+D.&rft.au=Alkobaisi%2C+Shayma&rft.au=Horak%2C+Matthew&rft.au=Bankar%2C+Siddheshwari&rft.date=2025&rft.issn=2169-3536&rft.eissn=2169-3536&rft.volume=13&rft.spage=16584&rft.epage=16602&rft_id=info:doi/10.1109%2FACCESS.2025.3532222&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_ACCESS_2025_3532222
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon