Deep learning-based endoscopic anatomy classification: an accelerated approach for data preparation and model validation.

BACKGROUND: Photodocumentation during endoscopy procedures is one of the indicators for endoscopy performance quality; however, this indicator is difficult to measure and audit in the endoscopy unit. Emerging artificial intelligence technology may solve this problem, which requires a large amount of material for model development. We developed a deep learning-based endoscopic anatomy classification system through convolutional neural networks with an accelerated data preparation approach. PATIENTS AND METHODS: We retrospectively collected 8,041 images from esophagogastroduodenoscopy (EGD) procedures and labeled them using two experts for nine anatomical locations of the upper gastrointestinal tract. A base model for EGD image multiclass classification was first developed, and an additional 6,091 images were enrolled and classified by the base model. A total of 5,963 images were manually confirmed and added to develop the subsequent enhanced model. Additional internal and external endoscopy image datasets were used to test the model performance. RESULTS: The base model achieved total accuracy of 96.29%. For the enhanced model, the total accuracy was 96.64%. The overall accuracy improved with the enhanced model compared with the base model for the internal test dataset without narrowband images (93.05% vs. 91.25%, p < 0.01) or with narrowband images (92.74% vs. 90.46%, p < 0.01). The total accuracy was 92.56% of the enhanced model on the external test dataset. CONCLUSIONS: We constructed a deep learning-based model with an accelerated approach that can be used for quality control in endoscopy units. The model was also validated with both internal and external datasets with high accuracy.

Elimination of Hepatitis C Virus in a Dialysis Population: A Collaborative Care Model in Taiwan.

RATIONALE & OBJECTIVE: Hemodialysis facilities are high-risk environments for the spread of hepatitis C virus (HCV). Eliminating HCV from all dialysis facilities in a community may be achieved more effectively under a collaborative care model. STUDY DESIGN: Quality improvement study of multidisciplinary collaborative care teams including nephrologists, gastroenterologists, and public health practitioners. SETTING & PARTICIPANTS: All dialysis patients in Changhua County, Taiwan were treated using an interdisciplinary collaborative care model implemented within a broader Changhua-Integrated Program to Stop HCV Infection (CHIPS-C). QUALITY IMPROVEMENT ACTIVITIES: Provision of an HCV care cascade to fill 3 gaps, including screening and testing, diagnosis, and universal direct-acting antiviral (DAA) treatment implemented by collaborating teams of dialysis practitioners and gastroenterologists working under auspices of Changhua Public Health Bureau. OUTCOME: Outcome measures included quality indicators pertaining to 6 steps in HCV care ranging from HCV screening to treatment completion to cure. ANALYTICAL APPROACH: A descriptive analysis. RESULTS: A total of 3,657 patients from 31 dialysis facilities were enrolled. All patients completed HCV screening. The DAA treatment initiation rate and completion rate were 88.9% and 94.0%, respectively. The collaborative care model achieved a cure rate of 166 (96.0%) of 173 patients. No virologic failure occurred. The cumulative treatment ratios for patients with chronic HCV infection increased from 5.3% before interferon-based therapy (2017) to 25.6% after restricted provision of DAA (2017-2018), and then to 89.1% after universal access to DAA (2019). LIMITATIONS: Unclear impact of this collaborative care program on incident dialysis patients entering dialysis facilities each year and on patients with earlier stages of chronic kidney disease. CONCLUSIONS: A collaborative care model in Taiwan increased the rates of diagnosis and treatment for HCV in dialysis facilities to levels near those established by the World Health Organization.