@article{MeinikheimMendelPalmetal., author = {Meinikheim, Michael and Mendel, Robert and Palm, Christoph and Probst, Andreas and Muzalyova, Anna and Scheppach, Markus W. and Nagl, Sandra and Schnoy, Elisabeth and R{\"o}mmele, Christoph and Schulz, Dominik Andreas Helmut Otto and Schlottmann, Jakob and Prinz, Friederike and Rauber, David and R{\"u}ckert, Tobias and Matsumura, Tomoaki and Fern{\´a}ndez-Esparrach, Gl{\`o}ria and Parsa, Nasim and Byrne, Michael F. and Messmann, Helmut and Ebigbo, Alanna}, title = {Influence of artificial intelligence on the diagnostic performance of endoscopists in the assessment of Barrett's esophagus: a tandem randomized and video trial}, series = {Endoscopy}, volume = {56}, journal = {Endoscopy}, publisher = {Georg Thieme Verlag}, address = {Stuttgart}, doi = {10.1055/a-2296-5696}, url = {http://nbn-resolving.de/urn:nbn:de:bvb:898-opus4-72818}, pages = {641 -- 649}, abstract = {Background This study evaluated the effect of an artificial intelligence (AI)-based clinical decision support system on the performance and diagnostic confidence of endoscopists in their assessment of Barrett's esophagus (BE). Methods 96 standardized endoscopy videos were assessed by 22 endoscopists with varying degrees of BE experience from 12 centers. Assessment was randomized into two video sets: group A (review first without AI and second with AI) and group B (review first with AI and second without AI). Endoscopists were required to evaluate each video for the presence of Barrett's esophagus-related neoplasia (BERN) and then decide on a spot for a targeted biopsy. After the second assessment, they were allowed to change their clinical decision and confidence level. Results AI had a stand-alone sensitivity, specificity, and accuracy of 92.2\%, 68.9\%, and 81.3\%, respectively. Without AI, BE experts had an overall sensitivity, specificity, and accuracy of 83.3\%, 58.1\%, and 71.5\%, respectively. With AI, BE nonexperts showed a significant improvement in sensitivity and specificity when videos were assessed a second time with AI (sensitivity 69.8\% [95\%CI 65.2\%-74.2\%] to 78.0\% [95\%CI 74.0\%-82.0\%]; specificity 67.3\% [95\%CI 62.5\%-72.2\%] to 72.7\% [95\%CI 68.2\%-77.3\%]). In addition, the diagnostic confidence of BE nonexperts improved significantly with AI. Conclusion BE nonexperts benefitted significantly from additional AI. BE experts and nonexperts remained significantly below the stand-alone performance of AI, suggesting that there may be other factors influencing endoscopists' decisions to follow or discard AI advice.}, language = {en} } @misc{ScheppachRauberStallhoferetal., author = {Scheppach, Markus W. and Rauber, David and Stallhofer, Johannes and Muzalyova, Anna and Otten, Vera and Manzeneder, Carolin and Schwamberger, Tanja and Wanzl, Julia and Schlottmann, Jakob and Tadic, Vidan and Probst, Andreas and Schnoy, Elisabeth and R{\"o}mmele, Christoph and Fleischmann, Carola and Meinikheim, Michael and Miller, Silvia and M{\"a}rkl, Bruno and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Performance comparison of a deep learning algorithm with endoscopists in the detection of duodenal villous atrophy (VA)}, series = {Endoscopy}, volume = {55}, journal = {Endoscopy}, number = {S02}, publisher = {Thieme}, doi = {10.1055/s-0043-1765421}, pages = {S165}, abstract = {Aims VA is an endoscopic finding of celiac disease (CD), which can easily be missed if pretest probability is low. In this study, we aimed to develop an artificial intelligence (AI) algorithm for the detection of villous atrophy on endoscopic images. Methods 858 images from 182 patients with VA and 846 images from 323 patients with normal duodenal mucosa were used for training and internal validation of an AI algorithm (ResNet18). A separate dataset was used for external validation, as well as determination of detection performance of experts, trainees and trainees with AI support. According to the AI consultation distribution, images were stratified into "easy" and "difficult". Results Internal validation showed 82\%, 85\% and 84\% for sensitivity, specificity and accuracy. External validation showed 90\%, 76\% and 84\%. The algorithm was significantly more sensitive and accurate than trainees, trainees with AI support and experts in endoscopy. AI support in trainees was associated with significantly improved performance. While all endoscopists showed significantly lower detection for "difficult" images, AI performance remained stable. Conclusions The algorithm outperformed trainees and experts in sensitivity and accuracy for VA detection. The significant improvement with AI support suggests a potential clinical benefit. Stable performance of the algorithm in "easy" and "difficult" test images may indicate an advantage in macroscopically challenging cases.}, language = {en} } @misc{RoserMeinikheimMendeletal., author = {Roser, David and Meinikheim, Michael and Mendel, Robert and Palm, Christoph and Probst, Andreas and Muzalyova, Anna and Scheppach, Markus W. and Nagl, Sandra and Schnoy, Elisabeth and R{\"o}mmele, Christoph and Schulz, Dominik Andreas Helmut Otto and Schlottmann, Jakob and Prinz, Friederike and Rauber, David and R{\"u}ckert, Tobias and Matsumura, Tomoaki and Fernandez-Esparrach, G. and Parsa, Nasim and Byrne, Michael F. and Messmann, Helmut and Ebigbo, Alanna}, title = {Human-Computer Interaction: Impact of Artificial Intelligence on the diagnostic confidence of endoscopists assessing videos of Barrett's esophagus}, series = {Endoscopy}, volume = {56}, journal = {Endoscopy}, number = {S 02}, publisher = {Georg Thieme Verlag}, issn = {1438-8812}, doi = {10.1055/s-0044-1782859}, pages = {79}, abstract = {Aims Human-computer interactions (HCI) may have a relevant impact on the performance of Artificial Intelligence (AI). Studies show that although endoscopists assessing Barrett's esophagus (BE) with AI improve their performance significantly, they do not achieve the level of the stand-alone performance of AI. One aspect of HCI is the impact of AI on the degree of certainty and confidence displayed by the endoscopist. Indirectly, diagnostic confidence when using AI may be linked to trust and acceptance of AI. In a BE video study, we aimed to understand the impact of AI on the diagnostic confidence of endoscopists and the possible correlation with diagnostic performance. Methods 22 endoscopists from 12 centers with varying levels of BE experience reviewed ninety-six standardized endoscopy videos. Endoscopists were categorized into experts and non-experts and randomly assigned to assess the videos with and without AI. Participants were randomized in two arms: Arm A assessed videos first without AI and then with AI, while Arm B assessed videos in the opposite order. Evaluators were tasked with identifying BE-related neoplasia and rating their confidence with and without AI on a scale from 0 to 9. Results The utilization of AI in Arm A (without AI first, with AI second) significantly elevated confidence levels for experts and non-experts (7.1 to 8.0 and 6.1 to 6.6, respectively). Only non-experts benefitted from AI with a significant increase in accuracy (68.6\% to 75.5\%). Interestingly, while the confidence levels of experts without AI were higher than those of non-experts with AI, there was no significant difference in accuracy between these two groups (71.3\% vs. 75.5\%). In Arm B (with AI first, without AI second), experts and non-experts experienced a significant reduction in confidence (7.6 to 7.1 and 6.4 to 6.2, respectively), while maintaining consistent accuracy levels (71.8\% to 71.8\% and 67.5\% to 67.1\%, respectively). Conclusions AI significantly enhanced confidence levels for both expert and non-expert endoscopists. Endoscopists felt significantly more uncertain in their assessments without AI. Furthermore, experts with or without AI consistently displayed higher confidence levels than non-experts with AI, irrespective of comparable outcomes. These findings underscore the possible role of AI in improving diagnostic confidence during endoscopic assessment.}, language = {en} } @article{RoserMeinikheimMuzalyovaetal., author = {Roser, David and Meinikheim, Michael and Muzalyova, Anna and Mendel, Robert and Palm, Christoph and Probst, Andreas and Nagl, Sandra and Scheppach, Markus W. and R{\"o}mmele, Christoph and Schnoy, Elisabeth and Parsa, Nasim and Byrne, Michael F. and Messmann, Helmut and Ebigbo, Alanna}, title = {Artificial intelligence-assisted endoscopy and examiner confidence : a study on human-artificial intelligence interaction in Barrett's Esophagus (With Video)}, series = {DEN Open}, volume = {6}, journal = {DEN Open}, number = {1}, publisher = {Wiley}, doi = {10.1002/deo2.70150}, pages = {8}, abstract = {Objective Despite high stand-alone performance, studies demonstrate that artificial intelligence (AI)-supported endoscopic diagnostics often fall short in clinical applications due to human-AI interaction factors. This video-based trial on Barrett's esophagus aimed to investigate how examiner behavior, their levels of confidence, and system usability influence the diagnostic outcomes of AI-assisted endoscopy. Methods The present analysis employed data from a multicenter randomized controlled tandem video trial involving 22 endoscopists with varying degrees of expertise. Participants were tasked with evaluating a set of 96 endoscopic videos of Barrett's esophagus in two distinct rounds, with and without AI assistance. Diagnostic confidence levels were recorded, and decision changes were categorized according to the AI prediction. Additional surveys assessed user experience and system usability ratings. Results AI assistance significantly increased examiner confidence levels (p < 0.001) and accuracy. Withdrawing AI assistance decreased confidence (p < 0.001), but not accuracy. Experts consistently reported higher confidence than non-experts (p < 0.001), regardless of performance. Despite improved confidence, correct AI guidance was disregarded in 16\% of all cases, and 9\% of initially correct diagnoses were changed to incorrect ones. Overreliance on AI, algorithm aversion, and uncertainty in AI predictions were identified as key factors influencing outcomes. The System Usability Scale questionnaire scores indicated good to excellent usability, with non-experts scoring 73.5 and experts 85.6. Conclusions Our findings highlight the pivotal function of examiner behavior in AI-assisted endoscopy. To fully realize the benefits of AI, implementing explainable AI, improving user interfaces, and providing targeted training are essential. Addressing these factors could enhance diagnostic accuracy and confidence in clinical practice.}, language = {en} } @article{ScheppachRauberStallhoferetal., author = {Scheppach, Markus W. and Rauber, David and Stallhofer, Johannes and Muzalyova, Anna and Otten, Vera and Manzeneder, Carolin and Schwamberger, Tanja and Wanzl, Julia and Schlottmann, Jakob and Tadic, Vidan and Probst, Andreas and Schnoy, Elisabeth and R{\"o}mmele, Christoph and Fleischmann, Carola and Meinikheim, Michael and Miller, Silvia and M{\"a}rkl, Bruno and Stallmach, Andreas and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Detection of duodenal villous atrophy on endoscopic images using a deep learning algorithm}, series = {Gastrointestinal Endoscopy}, journal = {Gastrointestinal Endoscopy}, publisher = {Elsevier}, doi = {10.1016/j.gie.2023.01.006}, abstract = {Background and aims Celiac disease with its endoscopic manifestation of villous atrophy is underdiagnosed worldwide. The application of artificial intelligence (AI) for the macroscopic detection of villous atrophy at routine esophagogastroduodenoscopy may improve diagnostic performance. Methods A dataset of 858 endoscopic images of 182 patients with villous atrophy and 846 images from 323 patients with normal duodenal mucosa was collected and used to train a ResNet 18 deep learning model to detect villous atrophy. An external data set was used to test the algorithm, in addition to six fellows and four board certified gastroenterologists. Fellows could consult the AI algorithm's result during the test. From their consultation distribution, a stratification of test images into "easy" and "difficult" was performed and used for classified performance measurement. Results External validation of the AI algorithm yielded values of 90 \%, 76 \%, and 84 \% for sensitivity, specificity, and accuracy, respectively. Fellows scored values of 63 \%, 72 \% and 67 \%, while the corresponding values in experts were 72 \%, 69 \% and 71 \%, respectively. AI consultation significantly improved all trainee performance statistics. While fellows and experts showed significantly lower performance for "difficult" images, the performance of the AI algorithm was stable. Conclusion In this study, an AI algorithm outperformed endoscopy fellows and experts in the detection of villous atrophy on endoscopic still images. AI decision support significantly improved the performance of non-expert endoscopists. The stable performance on "difficult" images suggests a further positive add-on effect in challenging cases.}, language = {en} } @article{ScheppachMendelMuzalyovaetal., author = {Scheppach, Markus W. and Mendel, Robert and Muzalyova, Anna and Rauber, David and Probst, Andreas and Nagl, Sandra and R{\"o}mmele, Christoph and Yip, Hon Chi and Lau, Louis Ho Shing and G{\"o}lder, Stefan Karl and Schmidt, Arthur and Kouladouros, Konstantinos and Abdelhafez, Mohamed and Walter, Benjamin M. and Meinikheim, Michael and Chiu, Philip Wai Yan and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {Artificial intelligence improves submucosal vessel detection during third space endoscopy}, series = {Endoscopy}, journal = {Endoscopy}, publisher = {Thieme}, address = {Stuttgart}, doi = {10.1055/a-2534-1164}, abstract = {Background and study aims: While artificial intelligence (AI) shows high potential in decision support for diagnostic gastrointestinal endoscopy, its role in therapeutic endoscopy remains unclear. Third space endoscopic procedures pose the risk of intraprocedural bleeding. Therefore, we aimed to develop an AI algorithm for intraprocedural blood vessel detection. Patients and Methods: Using a test dataset with 101 standardized video clips containing 200 predefined submucosal blood vessels, 19 endoscopists were evaluated for the vessel detection rate (VDR) and time (VDT) with and without support of an AI algorithm. Test subjects were grouped according to experience in ESD. Results: With AI support, endoscopists VDR increased from 56.4\% [CI 54.1-58.6] to 72.4\% [CI 70.3-74.4]. Endoscopists' VDT dropped from 6.7sec [CI 6.2-7.1] to 5.2sec [CI 4.8-5.7]. False positive (FP) readings appeared in 4.5\% of frames and were marked significantly shorter than true positives (6.0sec [CI 5.28-6.70] vs. 0.7sec [CI 0.55-0.87]). Conclusions: AI improved the vessel detection rate and time of endoscopists during third space endoscopy. While these data need to be corroborated by clinical trials, AI may prove to be an invaluable tool for the improvement of endoscopic interventions.}, language = {en} } @misc{ScheppachMendelMuzalyovaetal., author = {Scheppach, Markus W. and Mendel, Robert and Muzalyova, Anna and Rauber, David and Probst, Andreas and Nagl, Sandra and R{\"o}mmele, Christoph and Yip, Hon Chi and Lau, Louis Ho Shing and G{\"o}lder, Stefan Karl and Schmidt, Arthur and Kouladouros, Konstantinos and Abdelhafez, Mohamed and Walter, B. and Meinikheim, Michael and Chiu, Philip Wai Yan and Palm, Christoph and Messmann, Helmut and Ebigbo, Alanna}, title = {K{\"u}nstliche Intelligenz erh{\"o}ht die Gef{\"a}ßerkennung von Endoskopikern bei third space Endoskopie}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {62}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {09}, publisher = {Georg Thieme Verlag KG}, doi = {10.1055/s-0044-1790087}, pages = {e830}, abstract = {Einleitung: K{\"u}nstliche Intelligenz (KI)-Algorithmen unterst{\"u}tzen Endoskopiker bei der Erkennung und Charakterisierung von Kolonpolypen in der klinischen Praxis und f{\"u}hren zu einer Erh{\"o}hung der Adenomdetektionsrate. Auch bei therapeutischen Maßnahmen wie der endoskopischen Submukosadissektion (ESD) k{\"o}nne relevante anatomische Strukturen durch KI mit hoher Genauigkeit erkannt und im endoskopischen Bild in Echtzeit markiert werden. Der Effekt einer solchen Applikation auf die Gef{\"a}ßdetektion von Endoskopikern ist bislang nicht erforscht. Ziele: In dieser Studie wurde der Effekt eines KI-Algorithmus zur Echtzeit-Gef{\"a}ßmarkierung bei ESD auf die Gef{\"a}ßdetektionsrate von Endoskopikern untersucht. Methodik: 59 third space Endoskopievideos wurde aus der Datenbank des Universit{\"a}tsklinikums Augsburg extrahiert. Auf 5470 Einzelbildern dieser Untersuchungen wurde submukosale Blutgef{\"a}ße annotiert. Zusammen mit weiteren 179681 unmarkierten Bildern wurde ein DeepLabV3+ neuronales Netzwerk mit einer semi-supervised learning Methode darin trainiert, submukosale Blutgef{\"a}ße auf dem endoskopischen Bild zu erkennen und in Echtzeit einzuzeichnen. Anhand eines Videotests mit 101 Videoclips und 200 vordefinierten Blutgef{\"a}ßen wurden 19 Endoskopiker mit und ohne KI Unterst{\"u}tzung getestet. Ergebnis: Der Algorithmus erkannte in dem Videotest 93.5\% der Gef{\"a}ße in einer Detektionszeit von im Median 0,3 Sekunden. Die Gef{\"a}ßdetektionsrate von Endoskopikern erh{\"o}hte sich durch KI Unterst{\"u}tzung von 56,4\% auf 72,4\% (p<0.001). Die Gef{\"a}ßdetektionszeit reduzierte sich durch KI-Unterst{\"u}tzung von 6,7 auf 5.2 Sekunden (p<0.001). Der Algorithmus zeigte eine Rate an falsch positiven Detektionen in 4.5\% der Einzelbilder. Falsch positiv erkannte Strukturen wurde k{\"u}rzer detektiert, als richtig positive (0.7 und 6.0 Sekunden, p<0.001). Schlussfolgerung: KI Unterst{\"u}tzung f{\"u}hrte zu einer erh{\"o}hten Gef{\"a}ßdetektionsrate und schnelleren Gef{\"a}ßdetektionszeit von Endoskopikern. Ein m{\"o}glicher klinischer Effekt auf die intraprozedurale Komplikationsrate oder Operationszeit k{\"o}nnte in prospektiven Studien ermittelt werden.}, language = {de} } @misc{RoserMeinikheimMendeletal., author = {Roser, David and Meinikheim, Michael and Mendel, Robert and Palm, Christoph and Muzalyova, Anna and Rauber, David and R{\"u}ckert, Tobias and Parsa, Nasim and Byrne, Michael F. and Messmann, Helmut and Ebigbo, Alanna}, title = {Mensch-Maschine-Interaktion: Einfluss k{\"u}nstlicher Intelligenz auf das diagnostische Vertrauen von Endoskopikern bei der Beurteilung des Barrett-{\"O}sophagus}, series = {Zeitschrift f{\"u}r Gastroenterologie}, volume = {62}, journal = {Zeitschrift f{\"u}r Gastroenterologie}, number = {09}, publisher = {Georg Thieme Verlag KG}, doi = {10.1055/s-0044-1789656}, pages = {e575 -- e576}, abstract = {Ziele: Das Ziel der Studie war es, den Einfluss von KI auf die diagnostische Sicherheit (Konfidenzniveau) von Endoskopikern anhand von B{\"O}-Videos zu untersuchen und m{\"o}gliche Korrelationen mit der Untersuchungsqualit{\"a}t zu erforschen. Methodik: 22 Endoskopiker aus zw{\"o}lf Zentren mit unterschiedlicher Barrett-Erfahrung untersuchten 96 standardisierte Endoskopievideos. Die Untersucher wurden in Experten und Nicht-Experten eingeteilt und nach dem Zufallsprinzip f{\"u}r die Bewertung der Videos mit oder ohne KI eingeteilt. Die Teilnehmer wurden in zwei Gruppen aufgeteilt: Arm A bewertete zun{\"a}chst Videos ohne KI und dann mit KI, w{\"a}hrend Arm B die umgekehrte Reihenfolge einhielt. Die Untersucher hatten die Aufgabe, B{\"O}-assoziierte Neoplasien zu erkennen und ihr Konfidenzniveau sowohl mit als auch ohne KI auf einer Skala von 0 bis 9 anzugeben. Ergebnis: In Arm A erh{\"o}hte der Einsatz von KI das Konfidenzniveau bei beiden signifikant (p<0.001). Bemerkenswert ist, dass jedoch nur Nicht-Experten durch die KI eine signifikante Verbesserung der Sensitivit{\"a}t und Spezifit{\"a}t (p<0.001 bzw. p<0.05) erfuhren. W{\"a}hrend Experten ohne KI im Vergleich zu Nicht-Experten mit KI ein h{\"o}heres Konfidenzniveau aufwiesen, gab es keinen signifikanten Unterschied in der Genauigkeit. In Arm B zeigten beide Gruppen eine signifikante Abnahme des Konfidenzniveaus (p<0.001) bei gleichbleibender Genauigkeit. Dar{\"u}ber hinaus wurden in 9\% der Entscheidungen trotz korrekter KI eine falsche Wahl getroffen. Schlussfolgerung: Der Einsatz k{\"u}nstlicher Intelligenz steigerte das Konfidenzniveau sowohl bei Experten als auch bei Nicht-Experten signifikant - ein Effekt, der im Studienmodell reversibel war. Dar{\"u}ber hinaus wiesen Experten mit oder ohne KI durchweg h{\"o}here Konfidenzniveaus auf als Nicht-Experten mit KI, trotz vergleichbarer Ergebnisse. Zudem konnte beobachtet werden, dass die Untersucher in 9\% der F{\"a}lle die KI zuungunsten des Patienten ignorierten.}, language = {de} }