Universal Pre-Ejection Period Estimation Using Seismocardiography: Quantifying the Effects of Sensor Placement and Regression Algorithms

Seismocardiography (SCG), the measurement of local chest vibrations due to the heart and blood movement, is a noninvasive technique to assess cardiac contractility via systolic time intervals such as the pre-ejection period (PEP). Recent studies show that SCG signals measured before and after exerci...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE sensors journal Jg. 18; H. 4; S. 1665 - 1674
Hauptverfasser:	Ashouri, Hazar, Hersek, Sinan, Inan, Omer T.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 15.02.2018
Schlagworte:	accelerometer Accelerometers Electrocardiography ensemble regression Feature extraction heart failure pre-ejection period Seismocardiogram sensor fusion Sensors Sternum Timing unobtrusive cardiovascular monitoring Valves heart failure Seismocardiogram accelerometer ensemble regression sensor fusion unobtrusive cardiovascular monitoring pre-ejection period
ISSN:	1530-437X, 1558-1748
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Seismocardiography (SCG), the measurement of local chest vibrations due to the heart and blood movement, is a noninvasive technique to assess cardiac contractility via systolic time intervals such as the pre-ejection period (PEP). Recent studies show that SCG signals measured before and after exercise can effectively classify compensated and decompensated heart failure patients through PEP estimation. However, the morphology of the SCG signal varies from person to person and sensor placement making it difficult to automatically estimate PEP from SCG and electrocardiogram signals using a global model. In this proof-of-concept study, we address this problem by extracting a set of timing features from SCG signals measured from multiple positions on the upper body. We then test global regression models that combine all the detected features to identify the most accurate model for PEP estimation obtained from the best performing regressor and the best sensor location or combination of locations. Our results show that ensemble regression using extreme gradient boosting with a combination of sensors placed on the sternum and below the left clavicle provide the best RMSE = 11.6 ± 0.4 ms across all subjects. We also show that placing the sensor below the left or right clavicle rather than the conventional placement on the sternum results in more accurate PEP estimates.
AbstractList	Seismocardiography (SCG), the measurement of local chest vibrations due to the heart and blood movement, is a non-invasive technique to assess cardiac contractility via systolic time intervals such as the pre-ejection period (PEP). Recent studies show that SCG signals measured before and after exercise can effectively classify compensated and decompensated heart failure (HF) patients through PEP estimation. However, the morphology of the SCG signal varies from person to person and sensor placement making it difficult to automatically estimate PEP from SCG and electrocardiogram signals using a global model. In this proof-of-concept study, we address this problem by extracting a set of timing features from SCG signals measured from multiple positions on the upper body. We then test global regression models that combine all the detected features to identify the most accurate model for PEP estimation obtained from the best performing regressor and the best sensor location or combination of locations. Our results show that ensemble regression using XGBoost with a combination of sensors placed on the sternum and below the left clavicle provide the best RMSE = 11.6 ± 0.4 ms across all subjects. We also show that placing the sensor below the left or right clavicle rather than the conventional placement on the sternum results in more accurate PEP estimates.Seismocardiography (SCG), the measurement of local chest vibrations due to the heart and blood movement, is a non-invasive technique to assess cardiac contractility via systolic time intervals such as the pre-ejection period (PEP). Recent studies show that SCG signals measured before and after exercise can effectively classify compensated and decompensated heart failure (HF) patients through PEP estimation. However, the morphology of the SCG signal varies from person to person and sensor placement making it difficult to automatically estimate PEP from SCG and electrocardiogram signals using a global model. In this proof-of-concept study, we address this problem by extracting a set of timing features from SCG signals measured from multiple positions on the upper body. We then test global regression models that combine all the detected features to identify the most accurate model for PEP estimation obtained from the best performing regressor and the best sensor location or combination of locations. Our results show that ensemble regression using XGBoost with a combination of sensors placed on the sternum and below the left clavicle provide the best RMSE = 11.6 ± 0.4 ms across all subjects. We also show that placing the sensor below the left or right clavicle rather than the conventional placement on the sternum results in more accurate PEP estimates. Seismocardiography (SCG), the measurement of local chest vibrations due to the heart and blood movement, is a noninvasive technique to assess cardiac contractility via systolic time intervals such as the pre-ejection period (PEP). Recent studies show that SCG signals measured before and after exercise can effectively classify compensated and decompensated heart failure patients through PEP estimation. However, the morphology of the SCG signal varies from person to person and sensor placement making it difficult to automatically estimate PEP from SCG and electrocardiogram signals using a global model. In this proof-of-concept study, we address this problem by extracting a set of timing features from SCG signals measured from multiple positions on the upper body. We then test global regression models that combine all the detected features to identify the most accurate model for PEP estimation obtained from the best performing regressor and the best sensor location or combination of locations. Our results show that ensemble regression using extreme gradient boosting with a combination of sensors placed on the sternum and below the left clavicle provide the best RMSE = 11.6 ± 0.4 ms across all subjects. We also show that placing the sensor below the left or right clavicle rather than the conventional placement on the sternum results in more accurate PEP estimates. Seismocardiography (SCG), the measurement of local chest vibrations due to the heart and blood movement, is a non-invasive technique to assess cardiac contractility via systolic time intervals such as the pre-ejection period (PEP). Recent studies show that SCG signals measured before and after exercise can effectively classify compensated and decompensated heart failure (HF) patients through PEP estimation. However, the morphology of the SCG signal varies from person to person and sensor placement making it difficult to automatically estimate PEP from SCG and electrocardiogram signals using a global model. In this proof-of-concept study, we address this problem by extracting a set of timing features from SCG signals measured from multiple positions on the upper body. We then test global regression models that combine all the detected features to identify the most accurate model for PEP estimation obtained from the best performing regressor and the best sensor location or combination of locations. Our results show that ensemble regression using XGBoost with a combination of sensors placed on the sternum and below the left clavicle provide the best RMSE = 11.6 ± 0.4 ms across all subjects. We also show that placing the sensor below the left or right clavicle rather than the conventional placement on the sternum results in more accurate PEP estimates.
Author	Inan, Omer T. Hersek, Sinan Ashouri, Hazar
Author_xml	– sequence: 1 givenname: Hazar orcidid: 0000-0003-4134-0880 surname: Ashouri fullname: Ashouri, Hazar email: hazarashouri@gatech.edu organization: School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA – sequence: 2 givenname: Sinan orcidid: 0000-0001-7333-005X surname: Hersek fullname: Hersek, Sinan email: shersek3@gatech.edu organization: School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA – sequence: 3 givenname: Omer T. surname: Inan fullname: Inan, Omer T. email: inan@gatech.edu organization: School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/29867294$$D View this record in MEDLINE/PubMed
BookMark	eNp9UUuP0zAQjtAi9gE_ACEhH7mkTB6ubQ5Iq1V4aQWFpRI3y7HHrVeJ3bXTlfoP-Nkk21IBB04eeb7HzHzn2YkPHrPseQGzogDx-tNN83lWQsFmJeNsXvJH2VlBKc8LVvOTqa4gryv24zQ7T-kWoBCMsifZaSn4nJWiPst-Lr27x5hURxYR8-YW9eCCJwuMLhjSpMH16uFnmZxfkRt0qQ9aRePCKqrNeveGfN0qPzi7m_rDGklj7aiSSLAj3KcQyaJTGnv0A1HekG-4ipjSJHrZrUJ0w7pPT7PHVnUJnx3ei2z5rvl-9SG__vL-49Xlda7rQgy51W2lFUWrakBqW0orRitbzectKGNag4ZVtKSWCqNAC8oNAOUAjAtoRVldZG_3uptt26PR41BRdXITxz3jTgbl5N8d79ZyFe4lFbyCUowCrw4CMdxtMQ2yd0lj1ymPYZtkCRRqTgXACH35p9fR5Pf5R0CxB-gYUopoj5AC5BSxnCKWU8TyEPHIYf9wtBseIhrHdd1_mS_2TIeIRyde1jDt9gt-97f3
CODEN	ISJEAZ
CitedBy_id	crossref_primary_10_1109_JSEN_2019_2951068 crossref_primary_10_1109_JSEN_2024_3382347 crossref_primary_10_1109_JBHI_2020_3009903 crossref_primary_10_1088_2057_1976_ad6a67 crossref_primary_10_1109_JBHI_2020_3032938 crossref_primary_10_1007_s42835_025_02339_7 crossref_primary_10_1093_jamia_ocad067 crossref_primary_10_1109_JBHI_2020_3021532 crossref_primary_10_1109_JBHI_2019_2931872 crossref_primary_10_3390_s23115351 crossref_primary_10_1109_TBME_2023_3264940 crossref_primary_10_3390_s24072139 crossref_primary_10_1038_s41598_020_74150_5 crossref_primary_10_1109_JTEHM_2024_3368291 crossref_primary_10_1007_s13755_019_0071_7 crossref_primary_10_3390_math9182243 crossref_primary_10_1038_s44325_024_00034_6 crossref_primary_10_1109_JSEN_2019_2944235 crossref_primary_10_1002_smm2_1311 crossref_primary_10_1109_JBHI_2020_2980979 crossref_primary_10_3389_fphys_2021_748367 crossref_primary_10_1109_TBME_2020_3014040
Cites_doi	10.1093/jnci/djk018 10.1109/TBME.2016.2600945 10.1016/j.cardfail.2016.06.135 10.1016/j.jacc.2013.01.022 10.1016/0002-9149(71)90435-8 10.1111/j.2517-6161.1996.tb02080.x 10.1007/s10994-006-6226-1 10.1109/IEMBS.2007.4353199 10.1109/EMBC.2012.6346795 10.1111/j.1469-8986.1979.tb01519.x 10.2307/1267351 10.1161/01.cir.0000441139.02102.80 10.3390/s16060787 10.1145/2939672.2939785 10.1214/aos/1013203451 10.1161/CIR.0b013e31820a55f5 10.1109/JSEN.2017.2701349 10.1109/TBME.2016.2641958 10.1109/TITB.2011.2161998
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION NPM 7X8 5PM
DOI	10.1109/JSEN.2017.2787628
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed MEDLINE - Academic PubMed Central (Full Participant titles)
DatabaseTitle	CrossRef PubMed MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic PubMed
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Geography Engineering
EISSN	1558-1748
EndPage	1674
ExternalDocumentID	PMC5983029 29867294 10_1109_JSEN_2017_2787628 8240598
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: National Heart, Lung and Blood Institute grantid: R01HL130619 funderid: 10.13039/100000050 – fundername: NHLBI NIH HHS grantid: R01 HL130619
GroupedDBID	-~X 0R~ 29I 4.4 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AGQYO AHBIQ AJQPL AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 EBS EJD F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TWZ AAYXX CITATION NPM RIG 7X8 5PM
ID	FETCH-LOGICAL-c419t-fcb3ca5efa40e5fb553753f366b0addbded73525f59da0c958d0058007890b923
IEDL.DBID	RIE
ISICitedReferencesCount	26
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000423207200039&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1530-437X
IngestDate	Tue Sep 30 16:44:05 EDT 2025 Wed Oct 01 13:00:58 EDT 2025 Thu Jan 02 23:03:32 EST 2025 Sat Nov 29 05:42:44 EST 2025 Tue Nov 18 20:44:37 EST 2025 Wed Aug 27 02:30:44 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	4
Keywords	heart failure Seismocardiogram accelerometer ensemble regression sensor fusion unobtrusive cardiovascular monitoring pre-ejection period
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c419t-fcb3ca5efa40e5fb553753f366b0addbded73525f59da0c958d0058007890b923
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0001-7333-005X 0000-0003-4134-0880
OpenAccessLink	https://www.ncbi.nlm.nih.gov/pmc/articles/5983029
PMID	29867294
PQID	2050485900
PQPubID	23479
PageCount	10
ParticipantIDs	pubmedcentral_primary_oai_pubmedcentral_nih_gov_5983029 crossref_primary_10_1109_JSEN_2017_2787628 pubmed_primary_29867294 crossref_citationtrail_10_1109_JSEN_2017_2787628 ieee_primary_8240598 proquest_miscellaneous_2050485900
PublicationCentury	2000
PublicationDate	2018-02-15
PublicationDateYYYYMMDD	2018-02-15
PublicationDate_xml	– month: 02 year: 2018 text: 2018-02-15 day: 15
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	IEEE sensors journal
PublicationTitleAbbrev	JSEN
PublicationTitleAlternate	IEEE Sens J
PublicationYear	2018
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 ref12 ref14 ref10 dietterich (ref18) 2002; 2 demšar (ref27) 2006; 7 ref2 katz (ref1) 1977 ref17 ref16 pedregosa (ref26) 2011; 12 friedman (ref19) 2001 ref25 ref20 ref22 ref21 liaw (ref24) 2002; 2 tavakolian (ref11) 2010 ref8 ref7 ref9 ref4 bishop (ref15) 2006 ref3 ref6 ref5 tibshirani (ref23) 1996; 58
References_xml	– ident: ref20 doi: 10.1093/jnci/djk018 – ident: ref14 doi: 10.1109/TBME.2016.2600945 – volume: 12 start-page: 2825 year: 2011 ident: ref26 article-title: Scikit-learn: Machine learning in Python publication-title: J Mach Learn Res – ident: ref5 doi: 10.1016/j.cardfail.2016.06.135 – ident: ref3 doi: 10.1016/j.jacc.2013.01.022 – ident: ref7 doi: 10.1016/0002-9149(71)90435-8 – volume: 58 start-page: 267 year: 1996 ident: ref23 article-title: Regression shrinkage and selection via the lasso publication-title: J Roy Statist Soc Series B (Methodol ) doi: 10.1111/j.2517-6161.1996.tb02080.x – ident: ref25 doi: 10.1007/s10994-006-6226-1 – ident: ref13 doi: 10.1109/IEMBS.2007.4353199 – ident: ref12 doi: 10.1109/EMBC.2012.6346795 – start-page: 450 year: 1977 ident: ref1 publication-title: Physiology of the Heart – ident: ref6 doi: 10.1111/j.1469-8986.1979.tb01519.x – year: 2006 ident: ref15 publication-title: Pattern Recognition and Machine Learning – volume: 2 start-page: 18 year: 2002 ident: ref24 article-title: Classification and regression by randomforest publication-title: R News – ident: ref22 doi: 10.2307/1267351 – ident: ref2 doi: 10.1161/01.cir.0000441139.02102.80 – ident: ref9 doi: 10.3390/s16060787 – year: 2001 ident: ref19 publication-title: The Elements of Statistical Learning – ident: ref16 doi: 10.1145/2939672.2939785 – volume: 2 start-page: 110 year: 2002 ident: ref18 article-title: Ensemble learning publication-title: The Handbook of Brain Theory and Neural Networks – ident: ref17 doi: 10.1214/aos/1013203451 – ident: ref4 doi: 10.1161/CIR.0b013e31820a55f5 – ident: ref8 doi: 10.1109/JSEN.2017.2701349 – ident: ref21 doi: 10.1109/TBME.2016.2641958 – ident: ref10 doi: 10.1109/TITB.2011.2161998 – start-page: 1055 year: 2010 ident: ref11 article-title: Estimation of hemodynamic parameters from seismocardiogram publication-title: Proc Comput Cardiol – volume: 7 start-page: 1 year: 2006 ident: ref27 article-title: Statistical comparisons of classifiers over multiple data sets publication-title: J Mach Learn Res
SSID	ssj0019757
Score	2.3295376
Snippet	Seismocardiography (SCG), the measurement of local chest vibrations due to the heart and blood movement, is a noninvasive technique to assess cardiac... Seismocardiography (SCG), the measurement of local chest vibrations due to the heart and blood movement, is a non-invasive technique to assess cardiac...
SourceID	pubmedcentral proquest pubmed crossref ieee
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	1665
SubjectTerms	accelerometer Accelerometers Electrocardiography ensemble regression Feature extraction heart failure pre-ejection period Seismocardiogram sensor fusion Sensors Sternum Timing unobtrusive cardiovascular monitoring Valves
Title	Universal Pre-Ejection Period Estimation Using Seismocardiography: Quantifying the Effects of Sensor Placement and Regression Algorithms
URI	https://ieeexplore.ieee.org/document/8240598 https://www.ncbi.nlm.nih.gov/pubmed/29867294 https://www.proquest.com/docview/2050485900 https://pubmed.ncbi.nlm.nih.gov/PMC5983029
Volume	18
WOSCitedRecordID	wos000423207200039&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-1748 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0019757 issn: 1530-437X databaseCode: RIE dateStart: 20010101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3da9RAEB_aIqgPfrRW40dZwScx7eaSze76VuSK-HCcVuHeQvYjvZM2keRO8D_wz3Zmk4aeFMG3wM4kG2ZmZ3b3NzMAb3hS5iZxNkZf72JUCkfJypO4tNwIm2eVy11oNiFnM7VY6PkOvBtzYbz3AXzmj-kx3OW7xm7oqOxEofsRWu3CrpSyz9Uabwy0DFU90YB5nKVyMdxgJlyffDqfzgjEJY8nkoxfbfmg0FTltvjyb5jkDb9z9vD_ZvwIHgzxJTvtFeIx7Ph6H-7fqDq4D3eHxufLXwfwewBmIMu89fH0e0Bm1WyOtI1jU1wA-txGFrAF7Nyvuit0fwRi7d_xnn3elIQ4onwphuEk6wsid6ypkLzumpbN6ayeZsrK2rEv_qIH39bs9PKiaVfr5VX3BL6dTb9--BgPzRlimyV6HVfWpLYUvioz7kVlhEhx51OleW44rpnGeSep1GoltCu51UI5amFIIYnmBsPKQ9irm9o_A5ZUJe4aLY5irKFVrrVLcy-NMjmXVa4i4NfiKuxQuZwaaFwWYQfDdUESLkjCxSDhCN6OLD_6sh3_Ij4gyY2Eg9AieH2tEwXaHF2klLVvNh0yC1z4qN9qBE97HRmZJ_gDuGHJIpBb2jMSUD3v7ZF6tQx1vfGbKZ_o57dP5wXcw0krQown4iXsrduNfwV37M_1qmuP0CQW6iiYxB8__gvO
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9QwDLfGQBo8DNgGlPERJJ4Q3dKPtMnepummAeN0sCHdW9Um6e7Q1qL2Don_gD8bO-2qHZqQeKtUp01kO7aTn22AtzzIkyIw2kdbb3wUCkPJyqGfa14IncSlSYxrNpGOx3I6VZM1eD_kwlhrHfjM7tGju8s3tV7SUdm-RPMjlLwDd0Uch0GXrTXcGajU1fVEFeZ-HKXT_g4z4Gr_49loTDCudC9MSf3lihVybVVu8zD_BkresDzHD_9vzo9gs_cw2WEnEo9hzVZb8OBG3cEt2Ohbn89-bcPvHpqBQyaN9UffHTarYhOkrQ0b4RbQZTcyhy5gZ3beXqEBJBhr940D9mWZE-aIMqYYOpSsK4ncsrpE8qqtGzah03qaKcsrw77aiw5-W7HDy4u6mS9mV-0OfDsenR-d-H17Bl_HgVr4pS4inQtb5jG3oiyEiDD2KaMkKTjumoWxJqViq6VQJudaCWmoiSE5JYoX6Fg-gfWqruwzYEGZY9yo8S16G0omSpkosWkhi4SnZSI94NfsynRfu5xaaFxmLobhKiMOZ8ThrOewB--GIT-6wh3_It4mzg2EPdM8eHMtExlqHV2l5JWtly0OFrj1UcdVD552MjIMDnEBGLLEHqQr0jMQUEXv1TfVfOYqe-M_Ix6q57dP5zVsnJx_Ps1OP4w_7cJ9XIAk_HggXsD6olnal3BP_1zM2-aVU4w_9a8OLQ
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=Universal+Pre-Ejection+Period+Estimation+Using+Seismocardiography%3A+Quantifying+the+Effects+of+Sensor+Placement+and+Regression+Algorithms&rft.jtitle=IEEE+sensors+journal&rft.au=Ashouri%2C+Hazar&rft.au=Hersek%2C+Sinan&rft.au=Inan%2C+Omer+T.&rft.date=2018-02-15&rft.issn=1530-437X&rft.volume=18&rft.issue=4&rft.spage=1665&rft.epage=1674&rft_id=info:doi/10.1109%2Fjsen.2017.2787628&rft_id=info%3Apmid%2F29867294&rft.externalDocID=PMC5983029
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-437X&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-437X&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-437X&client=summon