Assessment of Helicobacter pylori infection by deep learning based on endoscopic videos in real time.

BACKGROUND AND AIMS: Endoscopic assessment of Helicobacter pylori infection is a simple and effective method. Here, we aimed to develop a deep learning-based system named Intelligent Detection Endoscopic Assistant-Helicobacter pylori (IDEA-HP) to assess H. pylori infection by using endoscopic videos in real time. METHODS: Endoscopic data were retrospectively obtained from Zhejiang Cancer Hospital (ZJCH) for the development, validation, and testing of the system. Stored videos from ZJCH were used for assessing and comparing the performance of IDEA-HP with that of endoscopists. Prospective consecutive patients undergoing esophagogastroduodenoscopy were enrolled to assess the applicability of clinical practice. The urea breath test was used as the gold standard for diagnosing H. pylori infection. RESULTS: In 100 videos, IDEA-HP achieved a similar overall accuracy of assessing H. pylori infection to that of experts (84.0% vs. 83.6% [P = 0.729]). Nevertheless, the diagnostic accuracy (84.0% vs. 74.0% [P<0.001]) and sensitivity (82.0% vs. 67.2% [P<0.001]) of IDEA-HP were significantly higher than those of the beginners. In 191 prospective consecutive patients, IDEA-HP achieved accuracy, sensitivity, and specificity of 85.3% (95% CI: 79.0%-89.3%), 83.3% (95% CI: 72.8%-90.5%), and 85.8% (95% CI: 77.7%-91.4%), respectively. CONCLUSIONS: Our results show that IDEA-HP has great potential for assisting endoscopists in assessing H. pylori infection status during actual clinical work.

Correlation of the detection rate of upper GI cancer with artificial intelligence score: results from a multicenter trial (with video).

BACKGROUND AND AIMS: The quality of EGD is a prerequisite for a high detection rate of upper GI lesions, especially early gastric cancer. Our previous study showed that an artificial intelligence system, named intelligent detection endoscopic assistant (IDEA), could help to monitor blind spots and provide an operation score during EGD. Here, we verified the effectiveness of IDEA to help evaluate the quality of EGD in a large-scale multicenter trial. METHODS: Patients undergoing EGD in 12 hospitals were consecutively enrolled. All hospitals were equipped with IDEA developed using deep convolutional neural networks and long short-term memory. Patients were examined by EGD, and the results were recorded by IDEA. The primary outcome was the detection rate of upper GI cancer. Secondary outcomes were part scores, total scores, and endoscopic procedure time, which were analyzed by IDEA. RESULTS: A total of 17,787 patients were recruited. The total detection rate of cancer-positive cases was 1.50%, ranging from .60% to 3.94% in each hospital. The total detection rate of early cancer-positive cases was .36%, ranging from .00% to 1.58% in each hospital. The average total score analyzed by IDEA ranged from 64.87 ± 16.87 to 83.50 ± 9.57 in each hospital. The cancer detection rate in each hospital was positively correlated with total score (r = .775, P = .003). Similarly, the early cancer detection rate was positively correlated with total score (r = .756, P = .004). CONCLUSIONS: This multicenter trial confirmed that the quality of the EGD result is positively correlated with the detection rate of cancer, which can be monitored by IDEA. (Clinical trial registration number: ChiCTR2000029001.).

A novel model for predicting fatty liver disease by means of an artificial neural network.

BACKGROUND: The artificial neural network (ANN) emerged recently as a potent diagnostic tool, especially for complicated systemic diseases. This study aimed to establish a diagnostic model for the recognition of fatty liver disease (FLD) by virtue of the ANN. METHODS: A total of 7,396 pairs of gender- and age-matched subjects who underwent health check-ups at the First Affiliated Hospital, College of Medicine, Zhejiang University (Hangzhou, China) were enrolled to establish the ANN model. Indices available in health check-up reports were utilized as potential input variables. The performance of our model was evaluated through a receiver-operating characteristic (ROC) curve analysis. Other outcome measures included diagnostic accuracy, sensitivity, specificity, Cohen's k coefficient, Brier score, and Hosmer-Lemeshow test. The Fatty Liver Index (FLI) and the Hepatic Steatosis Index (HSI), retrained using our training-group data with its original designated input variables, were used as comparisons in the capability of FLD diagnosis. RESULTS: Eight variables (age, gender, body mass index, alanine aminotransferase, aspartate aminotransferase, uric acid, total triglyceride, and fasting plasma glucose) were eventually adopted as input nodes of the ANN model. By applying a cut-off point of 0.51, the area under ROC curves of our ANN model in predicting FLD in the testing group was 0.908 [95% confidence interval (CI), 0.901-0.915]-significantly higher (P < 0.05) than that of the FLI model (0.881, 95% CI, 0.872-0.891) and that of the HSI model (0.885; 95% CI, 0.877-0.893). Our ANN model exhibited higher diagnostic accuracy, better concordance with ultrasonography results, and superior capability of calibration than the FLI model and the HSI model. CONCLUSIONS: Our ANN system showed good capability in the diagnosis of FLD. It is anticipated that our ANN model will be of both clinical and epidemiological use in the future.

Intelligent detection endoscopic assistant: An artificial intelligence-based system for monitoring blind spots during esophagogastroduodenoscopy in real-time.

BACKGROUND: Observation of the entire stomach during esophagogastroduodenoscopy (EGD) is important; however, there is a lack of effective evaluation tools. AIMS: To develop an artificial intelligence (AI)-assisted EGD system able to automatically monitor blind spots in real-time. METHODS: An AI-based system, called the Intelligent Detection Endoscopic Assistant (IDEA), was developed using a deep convolutional neural network (DCNN) and long short-term memory (LSTM). The performance of IDEA for recognition of gastric sites in images and videos was evaluated. Primary outcomes included diagnostic accuracy, sensitivity, and specificity. RESULTS: A total of 170,297 images and 5779 endoscopic videos were collected to develop the system. As the test group, 3100 EGD images were acquired to evaluate the performance of DCNN in recognition of gastric sites in images. The sensitivity, specificity, and accuracy of DCNN were determined as 97.18%,99.91%, and 99.83%, respectively. To assess the performance of IDEA in recognition of gastric sites in EGD videos, 129 videos were used as the test group. The sensitivity, specificity, and accuracy of IDEA were 96.29%,93.32%, and 95.30%, respectively. CONCLUSIONS: IDEA achieved high accuracy for recognition of gastric sites in real-time. The system can be applied as a powerful assistant tool for monitoring blind spots during EGD.

Successful treatment of multi-drug resistant tuberculosis by double lung transplantation.

A 24-year-old man suffering from end-stage, multi-drug, resistant tuberculosis and right heart failure underwent bilateral, single-lung transplantation with extracorporeal membrane oxygenator support. He was successfully weaned and discharged from the hospital 30 days later. Sputum cultures have been negative for tuberculosis since discharge, and for almost 2 years thereafter. Anti-tuberculosis medication was discontinued 4 months postoperatively.