Dynamic decision support graph—Visualization of ANN-generated diagnostic indications of pathological conditions developing over time
Summary Objectives A common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic indications cannot be sufficiently well explained. This paper presents a method for visualizing diagnostic indications generated from an artificial n...
Saved in:
Published in | Artificial intelligence in medicine Vol. 42; no. 3; pp. 189 - 198 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Netherlands
Elsevier B.V
01.03.2008
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Summary Objectives A common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic indications cannot be sufficiently well explained. This paper presents a method for visualizing diagnostic indications generated from an artificial neural network-based decision support algorithm (ANN-algorithm) in conditions developing over time. Methods The main idea behind the method is first to calculate and graphically present the decision regions corresponding to the diagnostic indications given as output from the ANN-algorithm, in the space of two selected, clinically established ‘display variables’. Secondly, the trajectory of time series measurement results of these, often biochemical markers, together with the respective 95% confidence intervals are superimposed on the decision regions. This will permit a nurse or clinician to grasp the diagnostic indication graphically at a glance. The indication is further presented in relation to clinical variables that the clinician is already familiar with, thus providing a sort of explanation. The predictive value of the indication is expressed by the proximity of the measurement result to the decision boundary, separating the decision regions, and by a numerically calculated individualized predictive value. Results The method is illustrated as applied to a previously published ANN-algorithm for the early ruling-in and ruling-out of acute myocardial infarction, using monitoring of measurement results of myoglobin and troponin-I in plasma. Conclusion The method is appropriate when there is a limited number of clinically established variables, i.e. variables which the clinician is used to taking into account in clinical reasoning. |
---|---|
AbstractList | Objectives: A common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic indications cannot be sufficiently well explained. This paper presents a method for visualizing diagnostic indications generated from an artificial neural network-based decision support algorithm (ANN-algorithm) in conditions developing over time. Methods: The main idea behind the method is first to calculate and graphically present the decision regions corresponding to the diagnostic indications given as output from the ANN-algorithm, in the space of two selected, clinically established 'display variables'. Secondly, the trajectory of time series measurement results of these, often biochemical markers, together with the respective 95% confidence intervals are superimposed on the decision regions. This wilt permit a nurse or clinician to grasp the diagnostic indication graphically at a glance. The indication is further presented in relation to clinical variables that the clinician is already familiar with, thus providing a sort of explanation. The predictive value of the indication is expressed by the proximity of the measurement result to the decision boundary, separating the decision regions, and by a numerically calculated individualized predictive value. Results: The method is illustrated as applied to a previously published ANN-algorithm for the early ruling-in and ruling-out of acute myocardial infarction, using monitoring of measurement results of myoglobin and troponin-1 in plasma. Conclusion: The method is appropriate when there is a limited number of clinically established variables, i.e. variables which the clinician is used to taking into account in clinical reasoning. Objectives: A common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic indications cannot be sufficiently well explained. This paper presents a method for visualizing diagnostic indications generated from an artificial neural network-based decision support algorithm (ANN-algorithm) in conditions developing over time. Methods: The main idea behind the method is first to calculate and graphically present the decision regions corresponding to the diagnostic indications given as output from the ANN-algorithm, in the space of two selected, clinically established 'display variables'. Secondly, the trajectory of time series measurement results of these, often biochemical markers, together with the respective 95% confidence intervals are superimposed on the decision regions. This will permit a nurse or clinician to grasp the diagnostic indication graphically at a glance. The indication is further presented in relation to clinical variables that the clinician is already familiar with, thus providing a sort of explanation. The predictive value of the indication is expressed by the proximity of the measurement result to the decision boundary, separating the decision regions, and by a numerically calculated individualized predictive value. Results: The method is illustrated as applied to a previously published ANN-algorithm for the early ruling-in and ruling-out of acute myocardial infarction, using monitoring of measurement results of myoglobin and troponin-I in plasma. Conclusion: The method is appropriate when there is a limited number of clinically established variables, i.e. variables which the clinician is used to taking into account in clinical reasoning. A common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic indications cannot be sufficiently well explained. This paper presents a method for visualizing diagnostic indications generated from an artificial neural network-based decision support algorithm (ANN-algorithm) in conditions developing over time. The main idea behind the method is first to calculate and graphically present the decision regions corresponding to the diagnostic indications given as output from the ANN-algorithm, in the space of two selected, clinically established 'display variables'. Secondly, the trajectory of time series measurement results of these, often biochemical markers, together with the respective 95% confidence intervals are superimposed on the decision regions. This will permit a nurse or clinician to grasp the diagnostic indication graphically at a glance. The indication is further presented in relation to clinical variables that the clinician is already familiar with, thus providing a sort of explanation. The predictive value of the indication is expressed by the proximity of the measurement result to the decision boundary, separating the decision regions, and by a numerically calculated individualized predictive value. The method is illustrated as applied to a previously published ANN-algorithm for the early ruling-in and ruling-out of acute myocardial infarction, using monitoring of measurement results of myoglobin and troponin-I in plasma. The method is appropriate when there is a limited number of clinically established variables, i.e. variables which the clinician is used to taking into account in clinical reasoning. OBJECTIVESA common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic indications cannot be sufficiently well explained. This paper presents a method for visualizing diagnostic indications generated from an artificial neural network-based decision support algorithm (ANN-algorithm) in conditions developing over time. METHODSThe main idea behind the method is first to calculate and graphically present the decision regions corresponding to the diagnostic indications given as output from the ANN-algorithm, in the space of two selected, clinically established 'display variables'. Secondly, the trajectory of time series measurement results of these, often biochemical markers, together with the respective 95% confidence intervals are superimposed on the decision regions. This will permit a nurse or clinician to grasp the diagnostic indication graphically at a glance. The indication is further presented in relation to clinical variables that the clinician is already familiar with, thus providing a sort of explanation. The predictive value of the indication is expressed by the proximity of the measurement result to the decision boundary, separating the decision regions, and by a numerically calculated individualized predictive value. RESULTSThe method is illustrated as applied to a previously published ANN-algorithm for the early ruling-in and ruling-out of acute myocardial infarction, using monitoring of measurement results of myoglobin and troponin-I in plasma. CONCLUSIONThe method is appropriate when there is a limited number of clinically established variables, i.e. variables which the clinician is used to taking into account in clinical reasoning. Summary Objectives A common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic indications cannot be sufficiently well explained. This paper presents a method for visualizing diagnostic indications generated from an artificial neural network-based decision support algorithm (ANN-algorithm) in conditions developing over time. Methods The main idea behind the method is first to calculate and graphically present the decision regions corresponding to the diagnostic indications given as output from the ANN-algorithm, in the space of two selected, clinically established ‘display variables’. Secondly, the trajectory of time series measurement results of these, often biochemical markers, together with the respective 95% confidence intervals are superimposed on the decision regions. This will permit a nurse or clinician to grasp the diagnostic indication graphically at a glance. The indication is further presented in relation to clinical variables that the clinician is already familiar with, thus providing a sort of explanation. The predictive value of the indication is expressed by the proximity of the measurement result to the decision boundary, separating the decision regions, and by a numerically calculated individualized predictive value. Results The method is illustrated as applied to a previously published ANN-algorithm for the early ruling-in and ruling-out of acute myocardial infarction, using monitoring of measurement results of myoglobin and troponin-I in plasma. Conclusion The method is appropriate when there is a limited number of clinically established variables, i.e. variables which the clinician is used to taking into account in clinical reasoning. |
Author | Ellenius, Johan Groth, Torgny |
Author_xml | – sequence: 1 fullname: Ellenius, Johan – sequence: 2 fullname: Groth, Torgny |
BackLink | https://www.ncbi.nlm.nih.gov/pubmed/18459185$$D View this record in MEDLINE/PubMed https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-110466$$DView record from Swedish Publication Index http://kipublications.ki.se/Default.aspx?queryparsed=id:116783239$$DView record from Swedish Publication Index |
BookMark | eNqFkstu1DAUhi1URC_wBghlxaoZfImdZIM0arlJVVkA3VqOfZJ6mrGDnQwaVqx4Ap6QJ8Ehoy6QUBeWrXO-_7fl85-iI-cdIPSc4BXBRLzarFQYt2BWFOMylVYY00fohFQly2kl8BE6wTVjORO8PEanMW5wAgsinqBjUhW8JhU_QT8v905trc4MaButd1mchsGHMeuCGm5___h1Y-OkevtdjXPXt9n6-jrvwEFQI5jMWNU5H8dkYZ2x-i8WZ25Q463vfZdqfaZ9ai4tAzvo_WBdl_kdhGy0W3iKHreqj_DssJ-hL2_ffL54n199fPfhYn2Va87YmDNO29aIkoFpSAGlqRknlKpWNE0tNKVa4BYLTErOaKVBN7gkrKAta4qGE87OUL34xm8wTI0cgt2qsJde2XT2Rh7qd3ZeMoIkRJQVo6xO2vP_ai_tzVr60MlpSgpcCJHwlwuefL9OEEe5tVFD3ysHfopS1KSsBa8fBCnmBSeMJLBYQB18jAHa-ycQLOdMyI1cMiHnTMzVlIkke3Hwn5q5dy86hCABrxcA0s_vLAQZtQWnwdgAepTG24du-NdA99bNc7-DPcSNn4JLU5VERiqx_DTnco4lLjEmDDP2B3mm5QY |
CitedBy_id | crossref_primary_10_1016_j_eswa_2010_10_072 crossref_primary_10_1016_j_archger_2011_09_006 crossref_primary_10_1063_5_0172609 crossref_primary_10_1007_s10462_017_9552_8 |
Cites_doi | 10.3109/00365519509088453 10.1016/S0140-6736(96)91555-X 10.1016/S0003-4975(97)00225-7 10.1097/00019501-199504000-00009 10.1142/S0129065797000380 10.1016/0303-8467(94)00067-G 10.1200/JCO.2005.12.156 10.1016/S0169-2607(96)01782-8 10.1016/S0933-3657(00)00064-6 10.1136/heart.90.1.99 10.1016/S0009-9120(00)00169-7 10.1093/clinchem/43.10.1919 10.3109/00365519509088447 10.1136/jamia.1996.97084516 10.1016/S0196-0644(94)70045-1 10.1016/j.ijcard.2005.12.019 10.1016/S0933-3657(96)00359-4 10.1016/0933-3657(95)00044-5 10.1016/S1386-5056(00)00064-2 10.1093/clinchem/47.4.624 10.1016/0020-7101(95)01138-5 10.1016/j.ejheart.2003.12.011 10.1016/S1386-5056(00)00065-4 |
ContentType | Journal Article |
Copyright | Elsevier B.V. 2007 Elsevier B.V. |
Copyright_xml | – notice: Elsevier B.V. – notice: 2007 Elsevier B.V. |
DBID | CGR CUY CVF ECM EIF NPM AAYXX CITATION 7QO 8FD FR3 P64 7X8 ADTPV AOWAS DF2 |
DOI | 10.1016/j.artmed.2007.10.002 |
DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed CrossRef Biotechnology Research Abstracts Technology Research Database Engineering Research Database Biotechnology and BioEngineering Abstracts MEDLINE - Academic SwePub SwePub Articles SWEPUB Uppsala universitet |
DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) CrossRef Engineering Research Database Biotechnology Research Abstracts Technology Research Database Biotechnology and BioEngineering Abstracts MEDLINE - Academic |
DatabaseTitleList | Engineering Research Database MEDLINE MEDLINE - Academic |
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 – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine Computer Science |
EISSN | 1873-2860 |
EndPage | 198 |
ExternalDocumentID | oai_prod_swepub_kib_ki_se_116783239 oai_DiVA_org_uu_110466 10_1016_j_artmed_2007_10_002 18459185 S0933365707001303 1_s2_0_S0933365707001303 |
Genre | Research Support, Non-U.S. Gov't Journal Article |
GroupedDBID | --- --K --M .1- .DC .FO .~1 0R~ 1B1 1P~ 1RT 1~. 1~5 23N 4.4 457 4G. 53G 5GY 5VS 7-5 71M 77K 8P~ 9JM 9JN AACTN AAEDT AAIAV AAIKJ AAKOC AALMO AALRI AAOAW AAPBV AAQFI AAQXK AAWTL AAXUO ABBOA ABBQC ABFNM ABIVO ABLVK ABMAC ABMZM ABPIF ABPTK ABXDB ABYKQ ACDAQ ACGFS ACIUM ACNNM ACRLP ACZNC ADALY ADBBV ADEZE ADJOM AEBSH AEKER AENEX AEVXI AFCTW AFKWA AFRHN AFTJW AFXIZ AGHFR AGUBO AGYEJ AHHHB AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV AJRQY AJUYK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ ANZVX AOUOD ASPBG AVWKF AZFZN BKOJK BLXMC BNPGV CS3 EBS EFJIC EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GBOLZ HEA HMK HMO HVGLF HZ~ IHE IPNFZ J1W KOM LCYCR LZ2 M29 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SAE SDF SDG SDP SEL SES SEW SPC SPCBC SSH SSV SSZ T5K UHS WH7 WUQ Z5R ~G- AAEDW AAYFN ABJNI ADMUD AXJTR EFLBG AAXKI AFJKZ AKRWK CGR CUY CVF ECM EIF NPM AAYXX CITATION 7QO 8FD FR3 P64 7X8 ADTPV AOWAS DF2 |
ID | FETCH-LOGICAL-c533t-352ffd673edb14e7d935122af6bb96c22c60f060175328cecb071342f3b4b5153 |
IEDL.DBID | AIKHN |
ISSN | 0933-3657 1873-2860 |
IngestDate | Sun Oct 13 03:42:50 EDT 2024 Tue Oct 01 22:29:02 EDT 2024 Sat Aug 17 01:56:48 EDT 2024 Sun Sep 29 07:17:02 EDT 2024 Thu Sep 26 19:27:23 EDT 2024 Sat Sep 28 08:46:28 EDT 2024 Fri Feb 23 02:25:16 EST 2024 Thu Oct 27 06:35:46 EDT 2022 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 3 |
Keywords | Myoglobin Visualization Artificial neural network Acute myocardial infarction Troponin-I |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c533t-352ffd673edb14e7d935122af6bb96c22c60f060175328cecb071342f3b4b5153 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
PMID | 18459185 |
PQID | 20545131 |
PQPubID | 23462 |
PageCount | 10 |
ParticipantIDs | swepub_primary_oai_prod_swepub_kib_ki_se_116783239 swepub_primary_oai_DiVA_org_uu_110466 proquest_miscellaneous_69179659 proquest_miscellaneous_20545131 crossref_primary_10_1016_j_artmed_2007_10_002 pubmed_primary_18459185 elsevier_sciencedirect_doi_10_1016_j_artmed_2007_10_002 elsevier_clinicalkeyesjournals_1_s2_0_S0933365707001303 |
PublicationCentury | 2000 |
PublicationDate | 2008-03-01 |
PublicationDateYYYYMMDD | 2008-03-01 |
PublicationDate_xml | – month: 03 year: 2008 text: 2008-03-01 day: 01 |
PublicationDecade | 2000 |
PublicationPlace | Netherlands |
PublicationPlace_xml | – name: Netherlands |
PublicationTitle | Artificial intelligence in medicine |
PublicationTitleAlternate | Artif Intell Med |
PublicationYear | 2008 |
Publisher | Elsevier B.V |
Publisher_xml | – name: Elsevier B.V |
References | Aase (bib27) 1999; 12 Forsstrom, Irjala, Selen, Nystrom, Eklund (bib9) 1995; 222 Ellenius, Groth (bib20) 2000; 60 Eklund, Forsstrom (bib8) 1995; 222 Kamm, Hall (bib23) 1999 Taylor, Yu, Sandler (bib11) 2005; 23 (bib1) 2001 Ellenius, Groth (bib16) 2000; 57 Reategui, Campbell, Leao (bib5) 1997; 9 Lindahl, Venge, Wallentin (bib18) 1995; 6 French, White (bib28) 2004; 90 Miller (bib2) 1996; 3 Baxt, Skora (bib25) 1996; 347 Kennedy, Harrison, Burton, Fraser, Hamer, MacArthur (bib26) 1997; 52 Downs, Harrison, Kennedy, Cross (bib7) 1996; 8 Berg (bib24) 1997 Ichimura, Tazaki, Yoshida (bib3) 1995; 40 Trull (bib14) 2001; 34 Ellenius, Groth, Lindahl, Wallentin (bib17) 1997; 43 Wu, Smith (bib13) 2004; 6 National Heart Attack Alert Program Coordinating Committee, 60 minutes to Treatment Working Group. Emergency department: rapid identification and treatment of patients with acute myocardial infarction. Ann Emerg Med 1994; 23(2):311–29. Duffy (bib12) 2001; 47 Hayashi, Setiono, Yoshida (bib4) 2000; 20 Craven, Shavlik (bib6) 1997; 8 Lippmann, Shahian (bib10) 1997; 63 Eggers, Ellenius, Dellborg, Groth, Oldgren, Swahn (bib19) 2007; 114 Kamm, Hall (bib22) 1999 Langemann, Mendelowitsch, Landolt, Alessandri, Gratzl (bib15) 1995; 97 Ellenius (10.1016/j.artmed.2007.10.002_bib16) 2000; 57 Langemann (10.1016/j.artmed.2007.10.002_bib15) 1995; 97 Lindahl (10.1016/j.artmed.2007.10.002_bib18) 1995; 6 Hayashi (10.1016/j.artmed.2007.10.002_bib4) 2000; 20 Ichimura (10.1016/j.artmed.2007.10.002_bib3) 1995; 40 Kamm (10.1016/j.artmed.2007.10.002_bib23) 1999 Miller (10.1016/j.artmed.2007.10.002_bib2) 1996; 3 Baxt (10.1016/j.artmed.2007.10.002_bib25) 1996; 347 Lippmann (10.1016/j.artmed.2007.10.002_bib10) 1997; 63 Taylor (10.1016/j.artmed.2007.10.002_bib11) 2005; 23 Berg (10.1016/j.artmed.2007.10.002_bib24) 1997 (10.1016/j.artmed.2007.10.002_bib1) 2001 Wu (10.1016/j.artmed.2007.10.002_bib13) 2004; 6 Forsstrom (10.1016/j.artmed.2007.10.002_bib9) 1995; 222 10.1016/j.artmed.2007.10.002_bib21 Reategui (10.1016/j.artmed.2007.10.002_bib5) 1997; 9 Trull (10.1016/j.artmed.2007.10.002_bib14) 2001; 34 Kennedy (10.1016/j.artmed.2007.10.002_bib26) 1997; 52 Kamm (10.1016/j.artmed.2007.10.002_bib22) 1999 Downs (10.1016/j.artmed.2007.10.002_bib7) 1996; 8 Eggers (10.1016/j.artmed.2007.10.002_bib19) 2007; 114 Ellenius (10.1016/j.artmed.2007.10.002_bib20) 2000; 60 French (10.1016/j.artmed.2007.10.002_bib28) 2004; 90 Ellenius (10.1016/j.artmed.2007.10.002_bib17) 1997; 43 Duffy (10.1016/j.artmed.2007.10.002_bib12) 2001; 47 Craven (10.1016/j.artmed.2007.10.002_bib6) 1997; 8 Eklund (10.1016/j.artmed.2007.10.002_bib8) 1995; 222 Aase (10.1016/j.artmed.2007.10.002_bib27) 1999; 12 |
References_xml | – volume: 47 start-page: 624 year: 2001 end-page: 630 ident: bib12 article-title: Carcinoembryonic antigen as a marker for colorectal cancer: is it clinically useful? publication-title: Clin Chem contributor: fullname: Duffy – volume: 90 start-page: 99 year: 2004 end-page: 106 ident: bib28 article-title: Clinical implications of the new definition of myocardial infarction publication-title: Heart contributor: fullname: White – volume: 222 start-page: 75 year: 1995 end-page: 81 ident: bib9 article-title: Using data preprocessing and single layer perceptron to analyze laboratory data publication-title: Scand J Clin Lab Invest Suppl contributor: fullname: Eklund – volume: 34 start-page: 3 year: 2001 end-page: 7 ident: bib14 article-title: The clinical validation of novel strategies for monitoring transplant recipients publication-title: Clin Biochem contributor: fullname: Trull – volume: 43 start-page: 1919 year: 1997 end-page: 1925 ident: bib17 article-title: Early assessment of patients with suspected acute myocardial infarction by biochemical monitoring and neural network analysis publication-title: Clin Chem contributor: fullname: Wallentin – volume: 63 start-page: 1635 year: 1997 end-page: 1643 ident: bib10 article-title: Coronary artery bypass risk prediction using neural networks publication-title: Ann Thorac Surg contributor: fullname: Shahian – year: 1997 ident: bib24 article-title: Rationalizing medical work: decision-support techniques and medical practises contributor: fullname: Berg – volume: 114 start-page: 366 year: 2007 end-page: 374 ident: bib19 article-title: Validation of neural networks for early diagnosis of acute myocardial infarction and prediction of infarct size publication-title: Int J Cardiol contributor: fullname: Swahn – volume: 52 start-page: 93 year: 1997 end-page: 103 ident: bib26 article-title: An artificial neural network system for diagnosis of acute myocardial infarction (AMI) in the accident and emergency department: evaluation and comparison with serum myoglobin measurements publication-title: Comput Methods Programs Biomed contributor: fullname: MacArthur – volume: 8 start-page: 373 year: 1997 end-page: 384 ident: bib6 article-title: Understanding time series networks: a case study in rule extraction publication-title: Int J Neural Syst contributor: fullname: Shavlik – volume: 57 start-page: 181 year: 2000 end-page: 202 ident: bib16 article-title: Methods for selection of adequate neural network structures with application to early assessment of chest pain patients by biochemical monitoring publication-title: Int J Med Inform contributor: fullname: Groth – volume: 6 start-page: 355 year: 2004 end-page: 358 ident: bib13 article-title: Biological variation of the natriuretic peptides and their role in monitoring patients with heart failure publication-title: Eur J Heart Fail contributor: fullname: Smith – volume: 23 start-page: 816 year: 2005 end-page: 825 ident: bib11 article-title: Individualized predictions of disease progression following radiation therapy for prostate cancer publication-title: J Clin Oncol contributor: fullname: Sandler – year: 1999 ident: bib23 article-title: Performance characteristics of the cardiac troponin-I (cTnI) method on the stratus CS STAT fluorometric analyzer. Technical bulletin contributor: fullname: Hall – year: 1999 ident: bib22 article-title: Performance characteristics of the myoglobin (Myo) method on the stratus CS STAT fluorometric analyzer. Technical bulletin contributor: fullname: Hall – volume: 9 start-page: 5 year: 1997 end-page: 27 ident: bib5 article-title: Combining a neural network with case-based reasoning in a diagnostic system publication-title: Artif Intell Med contributor: fullname: Leao – volume: 6 start-page: 321 year: 1995 end-page: 328 ident: bib18 article-title: Early diagnosis and exclusion of acute myocardial infarction using biochemical monitoring. The BIOMACS Study Group. Biochemicals markers of acute coronary syndromes publication-title: Coron Artery Dis contributor: fullname: Wallentin – volume: 222 start-page: 21 year: 1995 end-page: 30 ident: bib8 article-title: Computational intelligence for laboratory information systems publication-title: Scand J Clin Lab Invest Suppl contributor: fullname: Forsstrom – volume: 347 start-page: 12 year: 1996 end-page: 15 ident: bib25 article-title: Prospective validation of artificial neural network trained to identify acute myocardial infarction publication-title: Lancet contributor: fullname: Skora – volume: 8 start-page: 403 year: 1996 end-page: 428 ident: bib7 article-title: Application of the fuzzy ARTMAP neural network model to medical pattern classification tasks publication-title: Artif Intell Med contributor: fullname: Cross – volume: 12 start-page: 55 year: 1999 end-page: 74 ident: bib27 article-title: Computer aided diagnostics of acute chest pain publication-title: Hjerteforum contributor: fullname: Aase – volume: 20 start-page: 205 year: 2000 end-page: 216 ident: bib4 article-title: A comparison between two neural network rule extraction techniques for the diagnosis of hepatobiliary disorders publication-title: Artif Intell Med contributor: fullname: Yoshida – volume: 97 start-page: 149 year: 1995 end-page: 155 ident: bib15 article-title: Experimental and clinical monitoring of glucose by microdialysis publication-title: Clin Neurol Neurosurg contributor: fullname: Gratzl – year: 2001 ident: bib1 publication-title: Clinical applications of artificial neural networks – volume: 60 start-page: 1 year: 2000 end-page: 20 ident: bib20 article-title: Transferability of neural network-based decision support algorithms for early assessment of chest-pain patients publication-title: Int J Med Inform contributor: fullname: Groth – volume: 3 start-page: 429 year: 1996 end-page: 431 ident: bib2 article-title: Evaluating evaluations of medical diagnostic systems publication-title: J Am Med Inform Assoc contributor: fullname: Miller – volume: 40 start-page: 139 year: 1995 end-page: 146 ident: bib3 article-title: Extraction of fuzzy rules using neural networks with structure level adaptation—verification to the diagnosis of hepatobiliary disorders publication-title: Int J Biomed Comput contributor: fullname: Yoshida – year: 1997 ident: 10.1016/j.artmed.2007.10.002_bib24 contributor: fullname: Berg – year: 1999 ident: 10.1016/j.artmed.2007.10.002_bib22 contributor: fullname: Kamm – volume: 222 start-page: 75 year: 1995 ident: 10.1016/j.artmed.2007.10.002_bib9 article-title: Using data preprocessing and single layer perceptron to analyze laboratory data publication-title: Scand J Clin Lab Invest Suppl doi: 10.3109/00365519509088453 contributor: fullname: Forsstrom – volume: 347 start-page: 12 issue: 8993 year: 1996 ident: 10.1016/j.artmed.2007.10.002_bib25 article-title: Prospective validation of artificial neural network trained to identify acute myocardial infarction publication-title: Lancet doi: 10.1016/S0140-6736(96)91555-X contributor: fullname: Baxt – volume: 63 start-page: 1635 issue: 6 year: 1997 ident: 10.1016/j.artmed.2007.10.002_bib10 article-title: Coronary artery bypass risk prediction using neural networks publication-title: Ann Thorac Surg doi: 10.1016/S0003-4975(97)00225-7 contributor: fullname: Lippmann – volume: 6 start-page: 321 issue: 4 year: 1995 ident: 10.1016/j.artmed.2007.10.002_bib18 article-title: Early diagnosis and exclusion of acute myocardial infarction using biochemical monitoring. The BIOMACS Study Group. Biochemicals markers of acute coronary syndromes publication-title: Coron Artery Dis doi: 10.1097/00019501-199504000-00009 contributor: fullname: Lindahl – volume: 8 start-page: 373 issue: 4 year: 1997 ident: 10.1016/j.artmed.2007.10.002_bib6 article-title: Understanding time series networks: a case study in rule extraction publication-title: Int J Neural Syst doi: 10.1142/S0129065797000380 contributor: fullname: Craven – volume: 97 start-page: 149 issue: 2 year: 1995 ident: 10.1016/j.artmed.2007.10.002_bib15 article-title: Experimental and clinical monitoring of glucose by microdialysis publication-title: Clin Neurol Neurosurg doi: 10.1016/0303-8467(94)00067-G contributor: fullname: Langemann – volume: 23 start-page: 816 issue: 4 year: 2005 ident: 10.1016/j.artmed.2007.10.002_bib11 article-title: Individualized predictions of disease progression following radiation therapy for prostate cancer publication-title: J Clin Oncol doi: 10.1200/JCO.2005.12.156 contributor: fullname: Taylor – year: 1999 ident: 10.1016/j.artmed.2007.10.002_bib23 contributor: fullname: Kamm – volume: 52 start-page: 93 issue: 2 year: 1997 ident: 10.1016/j.artmed.2007.10.002_bib26 article-title: An artificial neural network system for diagnosis of acute myocardial infarction (AMI) in the accident and emergency department: evaluation and comparison with serum myoglobin measurements publication-title: Comput Methods Programs Biomed doi: 10.1016/S0169-2607(96)01782-8 contributor: fullname: Kennedy – volume: 12 start-page: 55 issue: Suppl. 8 year: 1999 ident: 10.1016/j.artmed.2007.10.002_bib27 article-title: Computer aided diagnostics of acute chest pain publication-title: Hjerteforum contributor: fullname: Aase – volume: 20 start-page: 205 issue: 3 year: 2000 ident: 10.1016/j.artmed.2007.10.002_bib4 article-title: A comparison between two neural network rule extraction techniques for the diagnosis of hepatobiliary disorders publication-title: Artif Intell Med doi: 10.1016/S0933-3657(00)00064-6 contributor: fullname: Hayashi – volume: 90 start-page: 99 issue: 1 year: 2004 ident: 10.1016/j.artmed.2007.10.002_bib28 article-title: Clinical implications of the new definition of myocardial infarction publication-title: Heart doi: 10.1136/heart.90.1.99 contributor: fullname: French – volume: 34 start-page: 3 issue: 1 year: 2001 ident: 10.1016/j.artmed.2007.10.002_bib14 article-title: The clinical validation of novel strategies for monitoring transplant recipients publication-title: Clin Biochem doi: 10.1016/S0009-9120(00)00169-7 contributor: fullname: Trull – volume: 43 start-page: 1919 issue: 10 year: 1997 ident: 10.1016/j.artmed.2007.10.002_bib17 article-title: Early assessment of patients with suspected acute myocardial infarction by biochemical monitoring and neural network analysis publication-title: Clin Chem doi: 10.1093/clinchem/43.10.1919 contributor: fullname: Ellenius – volume: 222 start-page: 21 year: 1995 ident: 10.1016/j.artmed.2007.10.002_bib8 article-title: Computational intelligence for laboratory information systems publication-title: Scand J Clin Lab Invest Suppl doi: 10.3109/00365519509088447 contributor: fullname: Eklund – volume: 3 start-page: 429 issue: 6 year: 1996 ident: 10.1016/j.artmed.2007.10.002_bib2 article-title: Evaluating evaluations of medical diagnostic systems publication-title: J Am Med Inform Assoc doi: 10.1136/jamia.1996.97084516 contributor: fullname: Miller – ident: 10.1016/j.artmed.2007.10.002_bib21 doi: 10.1016/S0196-0644(94)70045-1 – volume: 114 start-page: 366 issue: 3 year: 2007 ident: 10.1016/j.artmed.2007.10.002_bib19 article-title: Validation of neural networks for early diagnosis of acute myocardial infarction and prediction of infarct size publication-title: Int J Cardiol doi: 10.1016/j.ijcard.2005.12.019 contributor: fullname: Eggers – volume: 9 start-page: 5 issue: 1 year: 1997 ident: 10.1016/j.artmed.2007.10.002_bib5 article-title: Combining a neural network with case-based reasoning in a diagnostic system publication-title: Artif Intell Med doi: 10.1016/S0933-3657(96)00359-4 contributor: fullname: Reategui – volume: 8 start-page: 403 issue: 4 year: 1996 ident: 10.1016/j.artmed.2007.10.002_bib7 article-title: Application of the fuzzy ARTMAP neural network model to medical pattern classification tasks publication-title: Artif Intell Med doi: 10.1016/0933-3657(95)00044-5 contributor: fullname: Downs – volume: 60 start-page: 1 issue: 1 year: 2000 ident: 10.1016/j.artmed.2007.10.002_bib20 article-title: Transferability of neural network-based decision support algorithms for early assessment of chest-pain patients publication-title: Int J Med Inform doi: 10.1016/S1386-5056(00)00064-2 contributor: fullname: Ellenius – volume: 47 start-page: 624 issue: 4 year: 2001 ident: 10.1016/j.artmed.2007.10.002_bib12 article-title: Carcinoembryonic antigen as a marker for colorectal cancer: is it clinically useful? publication-title: Clin Chem doi: 10.1093/clinchem/47.4.624 contributor: fullname: Duffy – volume: 40 start-page: 139 issue: 2 year: 1995 ident: 10.1016/j.artmed.2007.10.002_bib3 article-title: Extraction of fuzzy rules using neural networks with structure level adaptation—verification to the diagnosis of hepatobiliary disorders publication-title: Int J Biomed Comput doi: 10.1016/0020-7101(95)01138-5 contributor: fullname: Ichimura – volume: 6 start-page: 355 issue: 3 year: 2004 ident: 10.1016/j.artmed.2007.10.002_bib13 article-title: Biological variation of the natriuretic peptides and their role in monitoring patients with heart failure publication-title: Eur J Heart Fail doi: 10.1016/j.ejheart.2003.12.011 contributor: fullname: Wu – year: 2001 ident: 10.1016/j.artmed.2007.10.002_bib1 – volume: 57 start-page: 181 issue: 2/3 year: 2000 ident: 10.1016/j.artmed.2007.10.002_bib16 article-title: Methods for selection of adequate neural network structures with application to early assessment of chest pain patients by biochemical monitoring publication-title: Int J Med Inform doi: 10.1016/S1386-5056(00)00065-4 contributor: fullname: Ellenius |
SSID | ssj0007416 |
Score | 1.867814 |
Snippet | Summary Objectives A common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic... A common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic indications cannot be... Objectives: A common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic indications... OBJECTIVESA common objection to using artificial neural networks in clinical decision support systems is that the reasoning behind diagnostic indications... |
SourceID | swepub proquest crossref pubmed elsevier |
SourceType | Open Access Repository Aggregation Database Index Database Publisher |
StartPage | 189 |
SubjectTerms | Acute myocardial infarction Algorithms Angina Pectoris - blood Angina Pectoris - etiology Artificial Intelligence Artificial neural network Biomarkers - blood Computer Graphics Confidence Intervals Decision Support Systems, Clinical Decision Support Techniques Diagnosis, Computer-Assisted Disease Progression Electrocardiography Female Humans Internal Medicine Male MEDICIN Medicin och hälsovetenskap MEDICINE Models, Biological Myocardial Infarction - blood Myocardial Infarction - complications Myocardial Infarction - diagnosis Myoglobin Myoglobin - blood Neural Networks (Computer) Other Predictive Value of Tests Sensitivity and Specificity Time Factors Troponin I - blood troponin-1 Troponin-I Visualization |
Title | Dynamic decision support graph—Visualization of ANN-generated diagnostic indications of pathological conditions developing over time |
URI | https://www.clinicalkey.es/playcontent/1-s2.0-S0933365707001303 https://dx.doi.org/10.1016/j.artmed.2007.10.002 https://www.ncbi.nlm.nih.gov/pubmed/18459185 https://search.proquest.com/docview/20545131 https://search.proquest.com/docview/69179659 https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-110466 http://kipublications.ki.se/Default.aspx?queryparsed=id:116783239 |
Volume | 42 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwEB61Wwlx4VFe4VF8gGPYxHac5rhqqRYQe4FWvVmJY1cBaXfVbK6IE7-AX8gvYcZ2WqBUSBz24nWeHs98k_lmBuAFWhlbW-VSw22GDkpZpBW3bWpVnUvuEFI0nuW7UPNj-fa0ON2CgzEXhmiVUfcHne61dRyZxrc5XXfd9AP54oKYG6UPv4lt2EFzJOUEdmZv3s0XFwqZQIcvuSdESgeMGXSe5oWnRLMTahl6mhe_zkJdRaB_lBf1JunoDtyKWJLNwu3ehS273IXbY58GFrftLtx4HwPo9-DbYehAz9rYW4f1w5ogOPOVq398_X7S9ZRnGbIz2cqx2WKRnvni1AhOWRuoeXhFRtHu-MGP5lFv41GTMvSy20AGY5dpWYzoooy62d-H46PXHw_maWzFkBrEg5sUYZpzrSqFbZtc2rKtBCIFXjvVNJUynBuVOSrtgt4P3zfWND5JlTvRyAYhk3gAk-VqaR8Bs1mrZJ61RuZOcoPOvMsdN9zURVWUpUggHV-_XoeKG3qkon3SYbmoeWZJo7hcCZTjGukxmxT1n-3jZux1rnuuM31FYH498jeZ02hO_nHN56MwaNyOFGOpl3Y19DgJIWku8utnKHSQqYpjAg-DFF0-5b4sKsRPCbwMYnXxD9UAP-xOZnp1fqaHAd22TCqVAP_LPDK8Oo5_7uine6sp3IbKW1SP__uhn8DNQJYhAt5TmGzOB_sMEdmm2YPtV1_yvbjvfgInSTok |
link.rule.ids | 230,315,786,790,891,4521,24144,27955,27956,45618,45712 |
linkProvider | Elsevier |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NbtNAEB6VIkEv_BRozV_3AEcTe9de18eopQrQ5kJb9bay17uVqZREdXxFnHiCPmGfhJndNQFKhcQhl80kjr2zM99kvpkBeINexlRG2lhzk2CAUuRxyU0TG1mlGbcIKWrH8p3KyUn28Sw_W4O9oRaGaJXB9nub7qx1WBmFpzlatO3oM8XigpgbhUu_iTtwl9AA8brefV3xPAhyuIZ7QsQkPtTPOZIXfiE6Hd_J0JG8-G3-6Sb-_KO5qHNIB4_gQUCSbOx_7GNYM7NNeDhMaWDh0G7CvaOQPn8C3_f9_HnWhMk6rOsXBMCZ61t9_e3qtO2oytLXZrK5ZePpND53rakRmrLGE_Pwioxy3eHvPpKjycaDHWUYYzeeCsZWRVmMyKKMZtk_hZOD98d7kzgMYog1osFljCDN2kYWwjR1mpmiKQXiBF5ZWdel1JxrmVhq7IKxD9_VRteuRJVbUWc1AibxDNZn85nZBmaSRmZp0ugstRnXGMrb1HLNdZWXeVGICOLh8auF77ehBiLaF-W3i0ZnFrSK2xVBMeyRGmpJ0fqZLhzFTqWq4ypRN9Tl10_-pnEKnck_rrkzKIPCw0gZlmpm5n2HQghIU5HeLiExPKYejhFseS1a3eVulpeIniJ469Xq5zvUAXy_PR2r-eW56nsM2pJMygj4X-TI7aqwftHSS3VGUbINTbcon__3Te_A_cnx0aE6_DD99AI2PG2GqHgvYX152ZtXiM2W9Wt39n4ABGA6-Q |
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=Dynamic+decision+support+graph--visualization+of+ANN-generated+diagnostic+indications+of+pathological+conditions+developing+over+time&rft.jtitle=Artificial+intelligence+in+medicine&rft.au=Ellenius%2C+Johan&rft.au=Groth%2C+Torgny&rft.date=2008-03-01&rft.issn=0933-3657&rft.volume=42&rft.issue=3&rft.spage=189&rft_id=info:doi/10.1016%2Fj.artmed.2007.10.002&rft_id=info%3Apmid%2F18459185&rft.externalDocID=18459185 |
thumbnail_m | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F09333657%2FS0933365708X0003X%2Fcov150h.gif |