% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@ARTICLE{Echle:179034,
      author       = {A. Echle and N. Ghaffari Laleh and P. Quirke and H. I.
                      Grabsch and H. S. Muti and O. L. Saldanha and S. F.
                      Brockmoeller and P. A. van den Brandt and G. G. A. Hutchins
                      and S. D. Richman and K. Horisberger and C. Galata and M. P.
                      Ebert and M. Eckardt and M. Boutros$^*$ and D. Horst and C.
                      Reissfelder and E. Alwers$^*$ and T. J. Brinker$^*$ and R.
                      Langer and J. C. A. Jenniskens and K. Offermans and W.
                      Mueller and R. Gray and S. B. Gruber and J. K. Greenson and
                      G. Rennert and J. D. Bonner and D. Schmolze and J.
                      Chang-Claude$^*$ and H. Brenner$^*$ and C. Trautwein and P.
                      Boor and D. Jaeger and N. T. Gaisa and M. Hoffmeister$^*$
                      and N. P. West and J. N. Kather},
      title        = {{A}rtificial intelligence for detection of microsatellite
                      instability in colorectal cancer-a multicentric analysis of
                      a pre-screening tool for clinical application.},
      journal      = {ESMO open},
      volume       = {7},
      number       = {2},
      issn         = {2059-7029},
      address      = {London},
      publisher    = {BMJ},
      reportid     = {DKFZ-2022-00416},
      pages        = {100400},
      year         = {2022},
      abstract     = {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.},
      keywords     = {Lynch syndrome (Other) / artificial intelligence (Other) /
                      biomarker (Other) / colorectal cancer (Other) / deep
                      learning (Other) / microsatellite instability (Other)},
      cin          = {B110 / C070 / C140 / C020 / C120 / HD01},
      ddc          = {610},
      cid          = {I:(DE-He78)B110-20160331 / I:(DE-He78)C070-20160331 /
                      I:(DE-He78)C140-20160331 / I:(DE-He78)C020-20160331 /
                      I:(DE-He78)C120-20160331 / I:(DE-He78)HD01-20160331},
      pnm          = {313 - Krebsrisikofaktoren und Prävention (POF4-313)},
      pid          = {G:(DE-HGF)POF4-313},
      typ          = {PUB:(DE-HGF)16},
      pubmed       = {pmid:35247870},
      doi          = {10.1016/j.esmoop.2022.100400},
      url          = {https://inrepo02.dkfz.de/record/179034},
}