000179034 001__ 179034
000179034 005__ 20240917155836.0
000179034 0247_ $$2doi$$a10.1016/j.esmoop.2022.100400
000179034 0247_ $$2pmid$$apmid:35247870
000179034 0247_ $$2altmetric$$aaltmetric:123977990
000179034 037__ $$aDKFZ-2022-00416
000179034 041__ $$aEnglish
000179034 082__ $$a610
000179034 1001_ $$aEchle, A.$$b0
000179034 245__ $$aArtificial intelligence for detection of microsatellite instability in colorectal cancer-a multicentric analysis of a pre-screening tool for clinical application.
000179034 260__ $$aLondon$$bBMJ$$c2022
000179034 3367_ $$2DRIVER$$aarticle
000179034 3367_ $$2DataCite$$aOutput Types/Journal article
000179034 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1726581493_15212
000179034 3367_ $$2BibTeX$$aARTICLE
000179034 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000179034 3367_ $$00$$2EndNote$$aJournal Article
000179034 520__ $$aMicrosatellite instability (MSI)/mismatch repair deficiency (dMMR) is a key genetic feature which should be tested in every patient with colorectal cancer (CRC) according to medical guidelines. Artificial intelligence (AI) methods can detect MSI/dMMR directly in routine pathology slides, but the test performance has not been systematically investigated with predefined test thresholds.We trained and validated AI-based MSI/dMMR detectors and evaluated predefined performance metrics using nine patient cohorts of 8343 patients across different countries and ethnicities.Classifiers achieved clinical-grade performance, yielding an area under the receiver operating curve (AUROC) of up to 0.96 without using any manual annotations. Subsequently, we show that the AI system can be applied as a rule-out test: by using cohort-specific thresholds, on average 52.73% of tumors in each surgical cohort [total number of MSI/dMMR = 1020, microsatellite stable (MSS)/ proficient mismatch repair (pMMR) = 7323 patients] could be identified as MSS/pMMR with a fixed sensitivity at 95%. In an additional cohort of N = 1530 (MSI/dMMR = 211, MSS/pMMR = 1319) endoscopy biopsy samples, the system achieved an AUROC of 0.89, and the cohort-specific threshold ruled out 44.12% of tumors with a fixed sensitivity at 95%. As a more robust alternative to cohort-specific thresholds, we showed that with a fixed threshold of 0.25 for all the cohorts, we can rule-out 25.51% in surgical specimens and 6.10% in biopsies.When applied in a clinical setting, this means that the AI system can rule out MSI/dMMR in a quarter (with global thresholds) or half of all CRC patients (with local fine-tuning), thereby reducing cost and turnaround time for molecular profiling.
000179034 536__ $$0G:(DE-HGF)POF4-313$$a313 - Krebsrisikofaktoren und Prävention (POF4-313)$$cPOF4-313$$fPOF IV$$x0
000179034 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
000179034 650_7 $$2Other$$aLynch syndrome
000179034 650_7 $$2Other$$aartificial intelligence
000179034 650_7 $$2Other$$abiomarker
000179034 650_7 $$2Other$$acolorectal cancer
000179034 650_7 $$2Other$$adeep learning
000179034 650_7 $$2Other$$amicrosatellite instability
000179034 7001_ $$aGhaffari Laleh, N.$$b1
000179034 7001_ $$aQuirke, P.$$b2
000179034 7001_ $$aGrabsch, H. I.$$b3
000179034 7001_ $$aMuti, H. S.$$b4
000179034 7001_ $$aSaldanha, O. L.$$b5
000179034 7001_ $$aBrockmoeller, S. F.$$b6
000179034 7001_ $$avan den Brandt, P. A.$$b7
000179034 7001_ $$aHutchins, G. G. A.$$b8
000179034 7001_ $$aRichman, S. D.$$b9
000179034 7001_ $$aHorisberger, K.$$b10
000179034 7001_ $$aGalata, C.$$b11
000179034 7001_ $$aEbert, M. P.$$b12
000179034 7001_ $$aEckardt, M.$$b13
000179034 7001_ $$0P:(DE-He78)3c0da8e3caa2aa50cad85152aa0465ad$$aBoutros, M.$$b14$$udkfz
000179034 7001_ $$aHorst, D.$$b15
000179034 7001_ $$aReissfelder, C.$$b16
000179034 7001_ $$0P:(DE-He78)9b2a61b2abe4a64ca23b6783b7c4fe63$$aAlwers, E.$$b17$$udkfz
000179034 7001_ $$0P:(DE-He78)1e33961c8780aca9b76d776d1fdc1ebb$$aBrinker, T. J.$$b18$$udkfz
000179034 7001_ $$aLanger, R.$$b19
000179034 7001_ $$aJenniskens, J. C. A.$$b20
000179034 7001_ $$aOffermans, K.$$b21
000179034 7001_ $$aMueller, W.$$b22
000179034 7001_ $$aGray, R.$$b23
000179034 7001_ $$aGruber, S. B.$$b24
000179034 7001_ $$aGreenson, J. K.$$b25
000179034 7001_ $$aRennert, G.$$b26
000179034 7001_ $$aBonner, J. D.$$b27
000179034 7001_ $$aSchmolze, D.$$b28
000179034 7001_ $$0P:(DE-He78)c259d6cc99edf5c7bc7ce22c7f87c253$$aChang-Claude, J.$$b29$$udkfz
000179034 7001_ $$0P:(DE-He78)90d5535ff896e70eed81f4a4f6f22ae2$$aBrenner, H.$$b30$$udkfz
000179034 7001_ $$aTrautwein, C.$$b31
000179034 7001_ $$aBoor, P.$$b32
000179034 7001_ $$aJaeger, D.$$b33
000179034 7001_ $$aGaisa, N. T.$$b34
000179034 7001_ $$0P:(DE-He78)6c5d058b7552d071a7fa4c5e943fff0f$$aHoffmeister, M.$$b35$$udkfz
000179034 7001_ $$aWest, N. P.$$b36
000179034 7001_ $$aKather, J. N.$$b37
000179034 773__ $$0PERI:(DE-600)2844985-X$$a10.1016/j.esmoop.2022.100400$$gVol. 7, no. 2, p. 100400 -$$n2$$p100400$$tESMO open$$v7$$x2059-7029$$y2022
000179034 909CO $$ooai:inrepo02.dkfz.de:179034$$pVDB
000179034 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)3c0da8e3caa2aa50cad85152aa0465ad$$aDeutsches Krebsforschungszentrum$$b14$$kDKFZ
000179034 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)9b2a61b2abe4a64ca23b6783b7c4fe63$$aDeutsches Krebsforschungszentrum$$b17$$kDKFZ
000179034 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)1e33961c8780aca9b76d776d1fdc1ebb$$aDeutsches Krebsforschungszentrum$$b18$$kDKFZ
000179034 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)c259d6cc99edf5c7bc7ce22c7f87c253$$aDeutsches Krebsforschungszentrum$$b29$$kDKFZ
000179034 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)90d5535ff896e70eed81f4a4f6f22ae2$$aDeutsches Krebsforschungszentrum$$b30$$kDKFZ
000179034 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)6c5d058b7552d071a7fa4c5e943fff0f$$aDeutsches Krebsforschungszentrum$$b35$$kDKFZ
000179034 9131_ $$0G:(DE-HGF)POF4-313$$1G:(DE-HGF)POF4-310$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lKrebsforschung$$vKrebsrisikofaktoren und Prävention$$x0
000179034 9141_ $$y2022
000179034 915__ $$0LIC:(DE-HGF)CCBYNCNV$$2V:(DE-HGF)$$aCreative Commons Attribution-NonCommercial CC BY-NC (No Version)$$bDOAJ$$d2020-09-06
000179034 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2020-09-06
000179034 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2020-09-06
000179034 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2020-09-06
000179034 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2020-09-06
000179034 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2022-11-17
000179034 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2022-11-17
000179034 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-01-19T12:30:42Z
000179034 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-01-19T12:30:42Z
000179034 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Blind peer review$$d2021-01-19T12:30:42Z
000179034 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2022-11-17
000179034 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2022-11-17
000179034 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2022-11-17
000179034 9201_ $$0I:(DE-He78)B110-20160331$$kB110$$lB110 Signalwege funktionelle Genomik$$x0
000179034 9201_ $$0I:(DE-He78)C070-20160331$$kC070$$lC070 Klinische Epidemiologie und Alternf.$$x1
000179034 9201_ $$0I:(DE-He78)C140-20160331$$kC140$$lNWG Digitale Biomarker in der Onkologie$$x2
000179034 9201_ $$0I:(DE-He78)C020-20160331$$kC020$$lC020 Epidemiologie von Krebs$$x3
000179034 9201_ $$0I:(DE-He78)C120-20160331$$kC120$$lPräventive Onkologie$$x4
000179034 9201_ $$0I:(DE-He78)HD01-20160331$$kHD01$$lDKTK HD zentral$$x5
000179034 980__ $$ajournal
000179034 980__ $$aVDB
000179034 980__ $$aI:(DE-He78)B110-20160331
000179034 980__ $$aI:(DE-He78)C070-20160331
000179034 980__ $$aI:(DE-He78)C140-20160331
000179034 980__ $$aI:(DE-He78)C020-20160331
000179034 980__ $$aI:(DE-He78)C120-20160331
000179034 980__ $$aI:(DE-He78)HD01-20160331
000179034 980__ $$aUNRESTRICTED