Browsing by Subject "Pathologists"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Artificial intelligence assistance significantly improves Gleason grading of prostate biopsies by pathologists
    (Springer Nature, 2021) Bulten, Wouter; Balkenhol, Maschenka; Belinga, Jean-Joël Awoumou; Brilhante, Américo; Çakır, Aslı; Egevad, Lars; Eklund, Martin; Farré, Xavier; Geronatsiou, Katerina; Molinié, Vincent; Pereira, Guilherme; Roy, Paromita; Saile, Günter; Salles, Paulo; Schaafsma, Ewout; Tschui, Joëlle; Vos, Anne-Marie; ISUP Pathology Imagebase Expert Panel; van Boven, Hester; Vink, Robert; van der Laak, Jeroen; Hulsbergen-van der Kaa, Christina; Litjens, Geert; Pathology and Laboratory Medicine, School of Medicine
    The Gleason score is the most important prognostic marker for prostate cancer patients, but it suffers from significant observer variability. Artificial intelligence (AI) systems based on deep learning can achieve pathologist-level performance at Gleason grading. However, the performance of such systems can degrade in the presence of artifacts, foreign tissue, or other anomalies. Pathologists integrating their expertise with feedback from an AI system could result in a synergy that outperforms both the individual pathologist and the system. Despite the hype around AI assistance, existing literature on this topic within the pathology domain is limited. We investigated the value of AI assistance for grading prostate biopsies. A panel of 14 observers graded 160 biopsies with and without AI assistance. Using AI, the agreement of the panel with an expert reference standard increased significantly (quadratically weighted Cohen's kappa, 0.799 vs. 0.872; p = 0.019). On an external validation set of 87 cases, the panel showed a significant increase in agreement with a panel of international experts in prostate pathology (quadratically weighted Cohen's kappa, 0.733 vs. 0.786; p = 0.003). In both experiments, on a group-level, AI-assisted pathologists outperformed the unassisted pathologists and the standalone AI system. Our results show the potential of AI systems for Gleason grading, but more importantly, show the benefits of pathologist-AI synergy.
  • Thumbnail Image
    Item
    Changes in USMLE Step 1 Result Reporting: A Pass or Fail for Pathology Programs?
    (Elsevier, 2021-03-18) Whaley, Rumeal D.; Booth, Adam L.; Mirza, Kamran M.; Pathology and Laboratory Medicine, School of Medicine
  • Thumbnail Image
    Item
    Recommendations for Clinical CYP2D6 Genotyping Allele Selection: A Joint Consensus Recommendation of the Association for Molecular Pathology, College of American Pathologists, Dutch Pharmacogenetics Working Group of the Royal Dutch Pharmacists Association, and the European Society for Pharmacogenomics and Personalized Therapy
    (Elsevier, 2021) Pratt, Victoria M.; Cavallari, Larisa H.; Del Tredici, Andria L.; Gaedigk, Andrea; Hachad, Houda; Ji, Yuan; Kalman, Lisa V.; Ly, Reynold C.; Moyer, Ann M.; Scott, Stuart A.; van Schaik, R.H.N.; Whirl-Carrillo, Michelle; Weck, Karen E.; Medical and Molecular Genetics, School of Medicine
    The goals of the Association for Molecular Pathology Clinical Practice Committee's Pharmacogenomics (PGx) Working Group are to define the key attributes of pharmacogenetic alleles recommended for clinical testing, and to determine a minimal set of variants that should be included in clinical PGx genotyping assays. This document series provides recommendations on a minimal panel of variant alleles (Tier 1) and an extended panel of variant alleles (Tier 2) that will aid clinical laboratories in designing assays for PGx testing. When developing these recommendations, the Association for Molecular Pathology PGx Working Group considered the functional impact of the variant alleles, allele frequencies in multiethnic populations, the availability of reference materials, as well as other technical considerations with regard to PGx testing. The ultimate goal of this Working Group is to promote standardization of PGx gene/allele testing across clinical laboratories. This document is focused on clinical CYP2D6 PGx testing that may be applied to all cytochrome P450 2D6-metabolized medications. These recommendations are not meant to be interpreted as prescriptive but to provide a reference guide for clinical laboratories that may be either implementing PGx testing or reviewing and updating their existing platform.