1
|
Meinikheim M, Mendel R, Palm C, Probst A, Muzalyova A, Scheppach MW, Nagl S, Schnoy E, Römmele C, Schulz DAH, Schlottmann J, Prinz F, Rauber D, Rückert T, Matsumura T, Fernández-Esparrach G, Parsa N, Byrne MF, Messmann H, Ebigbo A. Influence of artificial intelligence on the diagnostic performance of endoscopists in the assessment of Barrett's esophagus: a tandem randomized and video trial. Endoscopy 2024. [PMID: 38547927 DOI: 10.1055/a-2296-5696] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 05/04/2024]
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.
Collapse
Affiliation(s)
- Michael Meinikheim
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| | - Robert Mendel
- Regensburg Medical Image Computing, Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany
| | - Christoph Palm
- Regensburg Medical Image Computing, Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany
| | - Andreas Probst
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| | - Anna Muzalyova
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| | - Markus W Scheppach
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| | - Sandra Nagl
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| | - Elisabeth Schnoy
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| | - Christoph Römmele
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| | - Dominik A H Schulz
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| | - Jakob Schlottmann
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| | - Friederike Prinz
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| | - David Rauber
- Regensburg Medical Image Computing, Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany
| | - Tobias Rückert
- Regensburg Medical Image Computing, Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany
| | - Tomoaki Matsumura
- Department of Gastroenterology, Chiba University Graduate School of Medicine, Chiba, Japan
| | - Glòria Fernández-Esparrach
- Endoscopy Unit, Gastroenterology Department, ICMDM, Hospital Clínic de Barcelona, Barcelona, Spain
- Faculty of Medicine, University of Barcelona, Barcelona, Spain
- Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain
- Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), Barcelona, Spain
| | - Nasim Parsa
- Division of Gastroenterology and Hepatology, Mayo Clinic, Scottsdale, United States
- Satisfai Health, Vancouver, Canada
| | - Michael F Byrne
- Satisfai Health, Vancouver, Canada
- Gastroenterology, Vancouver General Hospital, The University of British Columbia, Vancouver, Canada
| | - Helmut Messmann
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| | - Alanna Ebigbo
- Department of Gastroenterology, University Hospital Augsburg, Augsburg, Germany
| |
Collapse
|
2
|
Schlottmann J, Miller S, Scheurig-Münkler C, Merkl C, Weber T, Eser S, Fuchs A, Messmann H, Probst A. [Acute abdomen-Rare cause in an 80-year-old female patient under immunosuppressive treatment]. Inn Med (Heidelb) 2024; 65:503-507. [PMID: 37831085 PMCID: PMC11058932 DOI: 10.1007/s00108-023-01593-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Accepted: 09/04/2023] [Indexed: 10/14/2023]
Abstract
An 80-year-old woman presented to the emergency department due to abdominal pain. She had a history of opportunistic pneumonia under the effects of immunosuppression after the diagnosis of autoimmune hepatitis. The imaging showed an omental cake formation and the suspicion of peritoneal carcinomatosis. The patient developed an acute abdomen during the hospital stay, followed by exploratory laparotomy. In the presence of extensive intra-abdominal abscess formation both surgically acquired material and blood culture revealed disseminated nocardiosis. The course was fatal due to fulminant septic shock.
Collapse
Affiliation(s)
- J Schlottmann
- 3. Medizinische Klinik, Universitätsklinikum Augsburg, Stenglinstraße 2, 86156, Augsburg, Deutschland.
| | - S Miller
- Institut für Pathologie und molekulare Diagnostik, Universitätsklinikum Augsburg, Augsburg, Deutschland
| | - C Scheurig-Münkler
- Klinik für Diagnostische und Interventionelle Radiologie und Neuroradiologie, Universitätsklinikum Augsburg, Augsburg, Deutschland
| | - C Merkl
- Klinik für Allgemein‑, Viszeral- und Transplantationschirurgie, Universitätsklinikum Augsburg, Augsburg, Deutschland
| | - T Weber
- 3. Medizinische Klinik, Universitätsklinikum Augsburg, Stenglinstraße 2, 86156, Augsburg, Deutschland
| | - S Eser
- 3. Medizinische Klinik, Universitätsklinikum Augsburg, Stenglinstraße 2, 86156, Augsburg, Deutschland
| | - A Fuchs
- 3. Medizinische Klinik, Universitätsklinikum Augsburg, Stenglinstraße 2, 86156, Augsburg, Deutschland
| | - H Messmann
- 3. Medizinische Klinik, Universitätsklinikum Augsburg, Stenglinstraße 2, 86156, Augsburg, Deutschland
| | - A Probst
- 3. Medizinische Klinik, Universitätsklinikum Augsburg, Stenglinstraße 2, 86156, Augsburg, Deutschland
| |
Collapse
|
3
|
Ebigbo A, Tadic V, Schlottmann J, Braun G, Prinz F, Wanzl J, Ayoub M, Kraus L, Scheppach M, Nagl S, Schnoy E, Weber T, Probst A, Messmann H, Römmele C. Evaluation of a single-use gastroscope in patients presenting with suspected upper gastrointestinal hemorrhage: a pilot feasibility study (One-Scope I). Endoscopy 2023; 55:940-944. [PMID: 37160261 DOI: 10.1055/a-2089-5969] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 05/11/2023]
Abstract
BACKGROUND : Outbreaks of multidrug-resistant bacteria due to contaminated duodenoscopes and infection risks during the COVID-19 pandemic have driven the development of single-use endoscopes. The first single-use gastroscope is now available in Europe. Besides waste disposal and cost issues, the infection risk and performance remain unclear. We aimed to evaluate a single-use gastroscope in patients with signs of upper gastrointestinal bleeding. METHODS : 20 consecutive patients presenting with clinical signs of upper gastrointestinal bleeding between October and November 2022 were included in this case series. The primary aim was technical success, defined as access to the descending duodenum and adequate assessment of the upper gastrointestinal tract for the presence of a bleeding site. RESULTS : The primary aim was achieved in 19/20 patients (95 %). The bleeding site was identified in 18 patients. A therapeutic intervention was performed in six patients (two cap-mounted clips, one standard hemostatic clip, two variceal band ligations, one hemostatic powder, two adrenaline injections); technical and clinical success were achieved in all six patients. Two crossovers to a standard gastroscope occurred. CONCLUSIONS : Use of single-use gastroscopes may be feasible for patients presenting for urgent endoscopic evaluation and treatment of upper gastrointestinal bleeding.
Collapse
Affiliation(s)
- Alanna Ebigbo
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Vidan Tadic
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Jakob Schlottmann
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Georg Braun
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Friederike Prinz
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Julia Wanzl
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Mousa Ayoub
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Lisa Kraus
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Markus Scheppach
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Sandra Nagl
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Elisabeth Schnoy
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Tobias Weber
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Andreas Probst
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Helmut Messmann
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| | - Christoph Römmele
- Gastroenterology, Faculty of Medicine, University Hospital of Augsburg, Augsburg, Germany
| |
Collapse
|
4
|
Scheppach MW, Rauber D, Stallhofer J, Muzalyova A, Otten V, Manzeneder C, Schwamberger T, Wanzl J, Schlottmann J, Tadic V, Probst A, Schnoy E, Römmele C, Fleischmann C, Meinikheim M, Miller S, Märkl B, Stallmach A, Palm C, Messmann H, Ebigbo A. Detection of duodenal villous atrophy on endoscopic images using a deep learning algorithm. Gastrointest Endosc 2023; 97:911-916. [PMID: 36646146 DOI: 10.1016/j.gie.2023.01.006] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/28/2022] [Revised: 12/16/2022] [Accepted: 01/01/2023] [Indexed: 01/18/2023]
Abstract
BACKGROUND AND AIMS Celiac disease with its endoscopic manifestation of villous atrophy (VA) is underdiagnosed worldwide. The application of artificial intelligence (AI) for the macroscopic detection of VA at routine EGD may improve diagnostic performance. METHODS A dataset of 858 endoscopic images of 182 patients with VA and 846 images from 323 patients with normal duodenal mucosa was collected and used to train a ResNet18 deep learning model to detect VA. An external dataset was used to test the algorithm, in addition to 6 fellows and 4 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 corresponding values of 63%, 72%, and 67% and experts scored 72%, 69%, and 71%, respectively. AI consultation significantly improved all trainee performance statistics. Although fellows and experts showed significantly lower performance for difficult images, the performance of the AI algorithm was stable. CONCLUSIONS In this study, an AI algorithm outperformed endoscopy fellows and experts in the detection of VA on endoscopic still images. AI decision support significantly improved the performance of nonexpert endoscopists. The stable performance on difficult images suggests a further positive add-on effect in challenging cases.
Collapse
Affiliation(s)
- Markus W Scheppach
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - David Rauber
- Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany; Regensburg Center of Biomedical Engineering, Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany
| | - Johannes Stallhofer
- Department of Internal Medicine IV (Gastroenterology, Hepatology, and Infectious Diseases), Jena University Hospital, Jena, Germany
| | - Anna Muzalyova
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Vera Otten
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Carolin Manzeneder
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Tanja Schwamberger
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Julia Wanzl
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Jakob Schlottmann
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Vidan Tadic
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Andreas Probst
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Elisabeth Schnoy
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Christoph Römmele
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Carola Fleischmann
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Michael Meinikheim
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Silvia Miller
- Department of Pathology, University Hospital of Augsburg, Augsburg, Germany
| | - Bruno Märkl
- Department of Pathology, University Hospital of Augsburg, Augsburg, Germany
| | - Andreas Stallmach
- Department of Internal Medicine IV (Gastroenterology, Hepatology, and Infectious Diseases), Jena University Hospital, Jena, Germany
| | - Christoph Palm
- Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany; Regensburg Center of Biomedical Engineering, Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany
| | - Helmut Messmann
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| | - Alanna Ebigbo
- Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany
| |
Collapse
|
5
|
Schloon H, Schlottmann J, Lenard HG, Goebel HH. The development of skeletal muscles in premature infants. I. Fibre size and histochemical differentiation. Eur J Pediatr 1979; 131:49-60. [PMID: 436856 DOI: 10.1007/bf00442785] [Citation(s) in RCA: 19] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Biopsies from various skeletal muscles were taken post mortem from infants with conceptional ages between 25 and 40 weeks. Cryostat sections were analysed quantitatively. The growth of the mean fibre diameter follows an exponential curve, which is mainly due to an initial predominance of type II-fibres. Before the 34th week of gestation only isolated large "Wohlfart"-fibres show type I staining characteristics. A great number of smaller type I-fibres appear suddenly around the 34th week. Their percentage of the total fibre population increases linearly to 40% at term. The development of the "tonic" type I-fibres correlates with certain aspects of gross motor development. The importance of normal data in the diagnosis of certain congenital myopathies is emphasized.
Collapse
|