Video-Based Deep Learning to Detect Dyssynergic Defecation with 3D High-Definition Anorectal Manometry
Digestive Diseases and Sciences · 2023-05 · 68 (5) · 2015-2022
DOI: 10.1007/s10620-022-07759-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Digestive Diseases and Sciences, online erschienen am 19.11.2022. Verfasst von Joshua J Levy und 8 weiteren Autor:innen. Beteiligte Einrichtung: Section of Gastroenterology and Hepatology, Dartmouth-Hitchcock Health, One Medical Center Drive, Lebanon, NH, 03756, USA. Hauptthemen laut MEDLINE: Defecation, Deep Learning. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 16 Literaturangaben. Gefördert von: NIGMS NIH HHS.
Abstract (Originalsprache)
BACKGROUND: We developed a deep learning algorithm to evaluate defecatory patterns to identify dyssynergic defecation using 3-dimensional high definition anal manometry (3D-HDAM). AIMS: We developed a 3D-HDAM deep learning algorithm to evaluate for dyssynergia. METHODS: Spatial-temporal data were extracted from consecutive 3D-HDAM studies performed between 2018 and 2020 at Dartmouth-Hitchcock Health. The technical procedure and gold standard definition of dyssynergia were based on the London consensus, adapted to the needs of 3D-HDAM technology. Three machine learning models were generated: (1) traditional machine learning informed by conventional anorectal function metrics, (2) deep learning, and (3) a hybrid approach. Diagnostic accuracy was evaluated using bootstrap sampling to calculate area-under-the-curve (AUC). To evaluate overfitting, models were validated by adding 502 simulated defecation maneuvers with diagnostic ambiguity. RESULTS: 302 3D-HDAM studies representing 1208 simulated defecation maneuvers were included (average age 55.2 years; 80.5% women). The deep learning model had comparable diagnostic accuracy [AUC 0.91 (95% confidence interval 0.89-0.93)] to traditional [AUC 0.93(0.92-0.95)] and hybrid [AUC 0.96(0.94-0.97)] predictive models in training cohorts. However, the deep learning model handled ambiguous tests more cautiously than other models; the deep learning model was more likely to designate an ambiguous test as inconclusive [odds ratio 4.21(2.78-6.38)] versus traditional/hybrid approaches. CONCLUSIONS: Deep learning is capable of considering complex spatial-temporal information on 3D-HDAM technology. Future studies are needed to evaluate the clinical context of these preliminary findings.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Section of Gastroenterology and Hepatology, Dartmouth-Hitchcock Health, One Medical Center Drive, Lebanon, NH, 03756, USA.
- Quantitative Biomedical Sciences, Geisel School of Medicine at Dartmouth, Lebanon, NH, USA.
- Department of Epidemiology, Geisel School of Medicine at Dartmouth, Lebanon, NH, USA.
- Emerging Diagnostic and Investigative Technologies, Department of Pathology and Laboratory Medicine, Dartmouth-Hitchcock Health, Lebanon, NH, USA.
- Departments of Pharmacology and Toxicology, and Community and Family Medicine, Geisel School of Medicine at Dartmouth, Lebanon, NH, USA.
- Division of Gastroenterology and Hepatology, Michigan Medicine, Ann Arbor, MI, USA.
Förderung
- NIGMS NIH HHS
Zitieren
APA
Levy, J. J., Navas, C. M., Chandra, J. A., Christensen, B. C., Vaickus, L. J., Curley, M., Chey, W. D., Baker, J. R., & Shah, E. D. (2023). Video-Based Deep Learning to Detect Dyssynergic Defecation with 3D High-Definition Anorectal Manometry. Digestive Diseases and Sciences, 68(5), 2015-2022. https://doi.org/10.1007/s10620-022-07759-3
Vancouver
Levy JJ, Navas CM, Chandra JA, Christensen BC, Vaickus LJ, Curley M, et al. Video-Based Deep Learning to Detect Dyssynergic Defecation with 3D High-Definition Anorectal Manometry. Digestive Diseases and Sciences. 2023;68(5):2015-2022. doi:10.1007/s10620-022-07759-3
BibTeX
@article{Levy2023,
author = {Levy, Joshua J and Navas, Christopher M and Chandra, Joan A and Christensen, Brock C and Vaickus, Louis J and Curley, Michael and Chey, William D and Baker, Jason R and Shah, Eric D},
title = {Video-Based Deep Learning to Detect Dyssynergic Defecation with 3D High-Definition Anorectal Manometry},
journal = {Digestive Diseases and Sciences},
year = {2023},
volume = {68},
number = {5},
pages = {2015--2022},
doi = {10.1007/s10620-022-07759-3}
}
EUVIMED