RÉSUMÉ
Background/Aims: An increase in postprandial intestinal gas plays a role in bloating symptoms. We aim to study the utility of spot breath hydrogen (H2) level in predicting the response to a low fermentable oligo-, di-, mono-saccharides, and polyols (FODMAPs) diet. Methods: Patients with functional gastrointestinal disorders diagnosed by Rome IV criteria with bothersome bloating for > 6 months were prospectively enrolled. Patients completed 7-day food diaries and collected a breath sample 2 hours after their usual lunch at baseline and 4 weeks after low FODMAPs dietary advice by a dietitian. The responder was defined as an improvement of ≥ 30% bloating scores in the fourth week. Results: Thirty-eight patients (32 female, 52.6 ± 13.8 years; 22 irritable bowel syndrome) completed the study. Twenty-one patients (55%) were classified as responders. Baseline global gastrointestinal symptoms, bloating, abdominal pain scores, and numbers of high FODMAPs items were similar between responders and non-responders. Both groups significantly decreased high FODMAPs items intake with similar numbers at the follow-up. The area under the curve for predicting low FODMAPs responsiveness using baseline H2 levels was 0.692 (95%CI, 0.51-0.86; P < 0.05), with the best cutoff at 8 parts per million (sensitivity 66.7%, specificity 82.4%). 66% of responders had baseline H2 level > 8 parts per million vs 17% of non-responders (P < 0.05). The baseline spot hydrogen level in responders was 9.5 (3.3-17.3) vs 4.5 (3.3-6.3) in non-responders (P < 0.05). Conclusions: A higher baseline breath hydrogen level was associated with bloating improvement after low FODMAPs dietary advice. A spot breath test after lunch, a simple point-of-care test, is possibly helpful in managing patients with bloating.
RÉSUMÉ
PURPOSE: Detection of hepatocellular carcinoma (HCC) is crucial during surveillance by ultrasound. We previously developed an artificial intelligence (AI) system based on convolutional neural network for detection of focal liver lesions (FLLs) in ultrasound. The primary aim of this study was to evaluate whether the AI system can assist non-expert operators to detect FLLs in real-time, during ultrasound examinations. METHOD: This single-center prospective randomized controlled study evaluated the AI system in assisting non-expert and expert operators. Patients with and without FLLs were enrolled and had ultrasound performed twice, with and without AI assistance. McNemar's test was used to compare paired FLL detection rates and false positives between groups with and without AI assistance. RESULTS: 260 patients with 271 FLLs and 244 patients with 240 FLLs were enrolled into the groups of non-expert and expert operators, respectively. In non-experts, FLL detection rate in the AI assistance group was significantly higher than the no AI assistance group (36.9 % vs 21.4 %, p < 0.001). In experts, FLL detection rates were not significantly different between the groups with and without AI assistance (66.7 % vs 63.3 %, p = 0.32). False positive detection rates in the groups with and without AI assistance were not significantly different in both non-experts (14.2 % vs 9.2 %, p = 0.08) and experts (8.6 % vs 9.0 %, p = 0.85). CONCLUSIONS: The AI system resulted in significant increase in detection of FLLs during ultrasound examinations by non-experts. Our findings may support future use of the AI system in resource-limited settings where ultrasound examinations are performed by non-experts. The study protocol was registered under the Thai Clinical Trial Registry (TCTR20201230003), which is part of the WHO ICTRP Registry Network. The registry can be accessed via the following URL: https://trialsearch.who.int/Trial2.aspx?TrialID=TCTR20201230003.