Home > Publications database > Artificial intelligence for detection of microsatellite instability in colorectal cancer-a multicentric analysis of a pre-screening tool for clinical application. > print

001     179034
005     20240917155836.0
024 7 _ |a 10.1016/j.esmoop.2022.100400
|2 doi
024 7 _ |a pmid:35247870
|2 pmid
024 7 _ |a altmetric:123977990
|2 altmetric
037 _ _ |a DKFZ-2022-00416
041 _ _ |a English
082 _ _ |a 610
100 1 _ |a Echle, A.
|b 0
245 _ _ |a Artificial intelligence for detection of microsatellite instability in colorectal cancer-a multicentric analysis of a pre-screening tool for clinical application.
260 _ _ |a London
|c 2022
|b BMJ
336 7 _ |a article
|2 DRIVER
336 7 _ |a Output Types/Journal article
|2 DataCite
336 7 _ |a Journal Article
|b journal
|m journal
|0 PUB:(DE-HGF)16
|s 1726581493_15212
|2 PUB:(DE-HGF)
336 7 _ |a ARTICLE
|2 BibTeX
336 7 _ |a JOURNAL_ARTICLE
|2 ORCID
336 7 _ |a Journal Article
|0 0
|2 EndNote
520 _ _ |a Microsatellite 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.
536 _ _ |a 313 - Krebsrisikofaktoren und Prävention (POF4-313)
|0 G:(DE-HGF)POF4-313
|c POF4-313
|f POF IV
|x 0
588 _ _ |a Dataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de
650 _ 7 |a Lynch syndrome
|2 Other
650 _ 7 |a artificial intelligence
|2 Other
650 _ 7 |a biomarker
|2 Other
650 _ 7 |a colorectal cancer
|2 Other
650 _ 7 |a deep learning
|2 Other
650 _ 7 |a microsatellite instability
|2 Other
700 1 _ |a Ghaffari Laleh, N.
|b 1
700 1 _ |a Quirke, P.
|b 2
700 1 _ |a Grabsch, H. I.
|b 3
700 1 _ |a Muti, H. S.
|b 4
700 1 _ |a Saldanha, O. L.
|b 5
700 1 _ |a Brockmoeller, S. F.
|b 6
700 1 _ |a van den Brandt, P. A.
|b 7
700 1 _ |a Hutchins, G. G. A.
|b 8
700 1 _ |a Richman, S. D.
|b 9
700 1 _ |a Horisberger, K.
|b 10
700 1 _ |a Galata, C.
|b 11
700 1 _ |a Ebert, M. P.
|b 12
700 1 _ |a Eckardt, M.
|b 13
700 1 _ |a Boutros, M.
|0 P:(DE-He78)3c0da8e3caa2aa50cad85152aa0465ad
|b 14
|u dkfz
700 1 _ |a Horst, D.
|b 15
700 1 _ |a Reissfelder, C.
|b 16
700 1 _ |a Alwers, E.
|0 P:(DE-He78)9b2a61b2abe4a64ca23b6783b7c4fe63
|b 17
|u dkfz
700 1 _ |a Brinker, T. J.
|0 P:(DE-He78)1e33961c8780aca9b76d776d1fdc1ebb
|b 18
|u dkfz
700 1 _ |a Langer, R.
|b 19
700 1 _ |a Jenniskens, J. C. A.
|b 20
700 1 _ |a Offermans, K.
|b 21
700 1 _ |a Mueller, W.
|b 22
700 1 _ |a Gray, R.
|b 23
700 1 _ |a Gruber, S. B.
|b 24
700 1 _ |a Greenson, J. K.
|b 25
700 1 _ |a Rennert, G.
|b 26
700 1 _ |a Bonner, J. D.
|b 27
700 1 _ |a Schmolze, D.
|b 28
700 1 _ |a Chang-Claude, J.
|0 P:(DE-He78)c259d6cc99edf5c7bc7ce22c7f87c253
|b 29
|u dkfz
700 1 _ |a Brenner, H.
|0 P:(DE-He78)90d5535ff896e70eed81f4a4f6f22ae2
|b 30
|u dkfz
700 1 _ |a Trautwein, C.
|b 31
700 1 _ |a Boor, P.
|b 32
700 1 _ |a Jaeger, D.
|b 33
700 1 _ |a Gaisa, N. T.
|b 34
700 1 _ |a Hoffmeister, M.
|0 P:(DE-He78)6c5d058b7552d071a7fa4c5e943fff0f
|b 35
|u dkfz
700 1 _ |a West, N. P.
|b 36
700 1 _ |a Kather, J. N.
|b 37
773 _ _ |a 10.1016/j.esmoop.2022.100400
|g Vol. 7, no. 2, p. 100400 -
|0 PERI:(DE-600)2844985-X
|n 2
|p 100400
|t ESMO open
|v 7
|y 2022
|x 2059-7029
909 C O |p VDB
|o oai:inrepo02.dkfz.de:179034
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 14
|6 P:(DE-He78)3c0da8e3caa2aa50cad85152aa0465ad
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 17
|6 P:(DE-He78)9b2a61b2abe4a64ca23b6783b7c4fe63
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 18
|6 P:(DE-He78)1e33961c8780aca9b76d776d1fdc1ebb
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 29
|6 P:(DE-He78)c259d6cc99edf5c7bc7ce22c7f87c253
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 30
|6 P:(DE-He78)90d5535ff896e70eed81f4a4f6f22ae2
910 1 _ |a Deutsches Krebsforschungszentrum
|0 I:(DE-588b)2036810-0
|k DKFZ
|b 35
|6 P:(DE-He78)6c5d058b7552d071a7fa4c5e943fff0f
913 1 _ |a DE-HGF
|b Gesundheit
|l Krebsforschung
|1 G:(DE-HGF)POF4-310
|0 G:(DE-HGF)POF4-313
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-300
|4 G:(DE-HGF)POF
|v Krebsrisikofaktoren und Prävention
|x 0
914 1 _ |y 2022
915 _ _ |a Creative Commons Attribution-NonCommercial CC BY-NC (No Version)
|0 LIC:(DE-HGF)CCBYNCNV
|2 V:(DE-HGF)
|b DOAJ
|d 2020-09-06
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0160
|2 StatID
|b Essential Science Indicators
|d 2020-09-06
915 _ _ |a WoS
|0 StatID:(DE-HGF)0113
|2 StatID
|b Science Citation Index Expanded
|d 2020-09-06
915 _ _ |a Article Processing Charges
|0 StatID:(DE-HGF)0561
|2 StatID
|d 2020-09-06
915 _ _ |a Fees
|0 StatID:(DE-HGF)0700
|2 StatID
|d 2020-09-06
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0200
|2 StatID
|b SCOPUS
|d 2022-11-17
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0300
|2 StatID
|b Medline
|d 2022-11-17
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0501
|2 StatID
|b DOAJ Seal
|d 2021-01-19T12:30:42Z
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0500
|2 StatID
|b DOAJ
|d 2021-01-19T12:30:42Z
915 _ _ |a Peer Review
|0 StatID:(DE-HGF)0030
|2 StatID
|b DOAJ : Blind peer review
|d 2021-01-19T12:30:42Z
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0199
|2 StatID
|b Clarivate Analytics Master Journal List
|d 2022-11-17
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)0150
|2 StatID
|b Web of Science Core Collection
|d 2022-11-17
915 _ _ |a DBCoverage
|0 StatID:(DE-HGF)1030
|2 StatID
|b Current Contents - Life Sciences
|d 2022-11-17
920 1 _ |0 I:(DE-He78)B110-20160331
|k B110
|l B110 Signalwege funktionelle Genomik
|x 0
920 1 _ |0 I:(DE-He78)C070-20160331
|k C070
|l C070 Klinische Epidemiologie und Alternf.
|x 1
920 1 _ |0 I:(DE-He78)C140-20160331
|k C140
|l NWG Digitale Biomarker in der Onkologie
|x 2
920 1 _ |0 I:(DE-He78)C020-20160331
|k C020
|l C020 Epidemiologie von Krebs
|x 3
920 1 _ |0 I:(DE-He78)C120-20160331
|k C120
|l Präventive Onkologie
|x 4
920 1 _ |0 I:(DE-He78)HD01-20160331
|k HD01
|l DKTK HD zentral
|x 5
980 _ _ |a journal
980 _ _ |a VDB
980 _ _ |a I:(DE-He78)B110-20160331
980 _ _ |a I:(DE-He78)C070-20160331
980 _ _ |a I:(DE-He78)C140-20160331
980 _ _ |a I:(DE-He78)C020-20160331
980 _ _ |a I:(DE-He78)C120-20160331
980 _ _ |a I:(DE-He78)HD01-20160331
980 _ _ |a UNRESTRICTED

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21