Andreas Edenberg*

Neo Clinic, Oslo, Norway

*Corresponding Author: Andreas Edenberg, Neo Clinic, Oslo, Norway.

Received: November 14, 2024; Published: December 03, 2024

Abstract

Artificial intelligence has made many headlines in the past 12 months, spearheaded by the capabilities demonstrated with genera tive AI by ChatGPT. Within almost every industry and every branch, there is an ever-rising optimism that AI can solve everything ranging from climate problems to food shortages. Namely in medicine, the most promising uses of AI so far lie within diagnostics uti lizing image analysis. To utilize the machine learning abilities and capabilities of AWS’ Sage Maker algorithm to improve classification and diagnosis of hiatal hernia. Machine learning prediction models from AWS were used to classify and diagnose hiatal hernia using the Hill classification. The dataset model was previously trained with Sage Maker to achieve high accuracy and sensitivity for ana lyzing the researched dataset. It was acquired by performing gastroscopic examinations in the Neo Clinic Oslo in 2022. All patients received primary gastroesophageal reflux disease (GERD) evaluation. During the study period, 982 patients underwent gastroscopic examinations. In total, 112 Hill I, 70 Hill II, 35 Hill III and 12 Hill IV hernias were identified and classified. The Hill I hernia was the most commonly found type of hill hernia. The present small, single-center proof-of-concept study shows once more that AI has great potential in aiding modern medicine. Machine learning derived analytic models were able to accurately detect and classify present hill hernias out of many endoscopic findings. Harnessing this ability and expanding it to most other diagnostics using image analysis can further improve adequate diagnosis and classification of certain conditions.

Keywords: Hiatal Hernia; Hill Hernia; Gastroscopy; Ai Machine Learning

References

1. Hill LD and RA Kozarek. “The gastroesophageal flap valve”. Journal of Clinical Gastroenterology 3 (2019): 194-197.
2. Goodwin M., et al. “Atypical and typical manifestations of the hiatal hernia”. Annals of Laparoscopic and Endoscopic Surgery (2020):
3. Chiesa-Estomba CM., et al. “Exploring the potential of Chat-GPT as a supportive tool for sialendoscopy clinical decision making and patient information support”. European Archives of oto-Rhino-Laryngology: Official Journal of the European Federation of Oto-Rhino-Laryngological Societies (EUFOS): Affiliated with the German Society for Oto-Rhino-Laryngology - Head and Neck Surgery (2023).
4. ChatGPT: Optimizing Language Models for Dialogue. OpenAI (2023).
5. Parviainen J and Rantala J. “Chatbot breakthrough in the 2020s? An ethical reflection on the trend of automated consultations in health care”. Medicine, Health Care and Philosophy 25 (2022): 61-71.
6. Rahwan Iyad., et al. “Machine behaviour”. Nature 568 (2019): 477-568.
7. Vial A., et al. “The role of deep learning and radiomic feature extraction in cancer-specific predictive modelling: a review”. Translational Cancer Research3 (2018): 803-816.
8. Yiming Ding., et al. “A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the Brain”. Radiology 2 (2019): 456-464.
9. Visaggi P., et al. “Artificial Intelligence in the Diagnosis of Upper Gastrointestinal Diseases”. Journal of Clinical Gastroenterology1 (2022): 23-35.
10. Kononenko I. “Machine learning for medical diagnosis: history, state of the art and perspective”. Artificial Intelligence in Medicine 1 (2001): 89-109.
11. Magoulas GD and Prentza A. “Machine learning in medical applications”. Lecture Notes in Computer Science (2001): 300-307.
12. Kahrilas PJ., et al. “Approaches to the diagnosis and grading of hiatal hernia”. Best Practice and Research. Clinical Gastroenterology4 (2008): 601-616.
13. Hansdotter I., et al. “Hill classification is superior to the axial length of a hiatal hernia for assessment of the mechanical anti-reflux barrier at the gastroesophageal junction”. Endoscopy International Open 3 (2016): E311-317.

Citation

Citation: Andreas Edenberg. “Artificial Intelligence in Hill Classification of Hiatal Hernia". Acta Scientific Gastrointestinal Disorders 8.1 (2025): 03-07.

Copyright

Copyright: © 2025 Andreas Edenberg. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.