Automatic assessment of bowel preparation by an artificial intelligence model and its clinical applicability.

BACKGROUND AND AIM: Reliable bowel preparation assessment is important in colonoscopy. However, current scoring systems are limited by laborious and time-consuming tasks and interobserver variability. We aimed to develop an artificial intelligence (AI) model to assess bowel cleanliness and evaluate its clinical applicability. METHODS: A still image-driven AI model to assess the Boston Bowel Preparation Scale (BBPS) was developed and validated using 2361 colonoscopy images. For evaluating real-world applicability, the model was validated using 113 10-s colonoscopy video clips and 30 full colonoscopy videos to identify "adequate (BBPS 2-3)" or "inadequate (BBPS 0-1)" preparation. The model was tested with an external dataset of 29 colonoscopy videos. The clinical applicability of the model was evaluated using 225 consecutive colonoscopies. Inter-rater variability was analyzed between the AI model and endoscopists. RESULTS: The AI model achieved an accuracy of 94.0% and an area under the receiver operating characteristic curve of 0.939 with the still images. Model testing with an external dataset showed an accuracy of 95.3%, an area under the receiver operating characteristic curve of 0.976, and a sensitivity of 100% for the detection of inadequate preparations. The clinical applicability study showed an overall agreement rate of 85.3% between endoscopists and the AI model, with Fleiss' kappa of 0.686. The agreement rate was lower for the right colon compared with the transverse and left colon, with Fleiss' kappa of 0.563, 0.575, and 0.789, respectively. CONCLUSIONS: The AI model demonstrated accurate bowel preparation assessment and substantial agreement with endoscopists. Further refinement of the AI model is warranted for effective monitoring of qualified colonoscopy in large-scale screening programs.

Effects of dual-task resistance exercise on cognition, mood, depression, functional fitness, and activities of daily living in older adults with cognitive impairment: a single-blinded, randomized controlled trial.

BACKGROUND: Regular exercise is emphasized for the improvement of functional capacity and independence of older adults. This study aimed to compare the effects of a dual-task resistance exercise program and resistance exercise on cognition, mood, depression, physical function, and activities of daily living (ADL) in older adults with cognitive impairment. METHODS: A total of 44 older adults participated in the study. Participants were randomly allocated to an experimental group (n = 22) performing a dual-task resistance exercise program for cognitive function improvement and a control group (n = 22) performing a resistance exercise program. Both groups performed the exercise for 40 min per session, three times a week, for 6 weeks (18 sessions). Cognition, mood, depression, functional fitness, and ADL were quantified before and after the intervention using the Mini-Mental State Examination (MMSE), profile of mood states (POMS), geriatric depression scale (GDS), senior fitness test (SFT), and Korean version of ADL, respectively. RESULTS: There was a significant time and group interaction on the MMSE (p = 0.044). There were no significant time and group interactions in the POMS, GDS, SFT, or ADL. Cognitive function (p < 0.001), mood (p < 0.001), depression (p < 0.001), functional fitness (p < 0.001), and ADL (p < 0.001) significantly improved after dual-task resistance exercise, and cognitive function (p < 0.001), mood (p < 0.001), depression (p < 0.001), functional fitness (p < 0.001), and ADL (p < 0.001) significantly improved after resistance exercise. CONCLUSIONS: Dual-task resistance exercise is more effective than resistance exercise in improving cognitive function in older adults with cognitive impairment. Both dual-task resistance exercise and resistance exercise improves mood, depression, functional fitness, and ADL after the intervention. We propose using dual-task resistance exercises for cognitive and physical health management in the older adults with cognitive impairment. TRIAL REGISTRATION: This study was registered with the Clinical Research Information Service (WHO International Clinical Trials Registry Platform) (Registration ID, KCT0005389; Registration date, 09/09/2020).

Effectiveness of Switching to Subcutaneous Infliximab in Ulcerative Colitis Patients Experiencing Intravenous Infliximab Failure.

Background/Aims: Studies on elective switching to the subcutaneous (SC) formulation of infliximab revealed comparable efficacy and safety and higher infliximab level than those exhibited by intravenous (IV) infliximab. However, no studies have reported on the effectiveness of SC switching in ulcerative colitis (UC) patients who experienced IV infliximab failure during maintenance treatment. Methods: This retrospective study included UC patients who had been switched to SC infliximab because of IV infliximab failure, between January 2021 and January 2023. Group A was defined as having clinically and biochemically active UC (secondary loss of response), and group B consisted of patients with stable symptoms but biochemically active UC. Results: Twenty-three patients met the inclusion criteria: 15 in group A and eight in group B. The serum infliximab levels significantly increased after SC switching in both groups. The electively switched group also exhibited increased infliximab levels after SC switching. Patients in group A showed improved partial Mayo score with a significant decrease in fecal calprotectin and C-reactive protein after switching. In group B, the fecal calprotectin level significantly decreased without clinical relapse after switching. A high proportion of patients (≥80%) in both groups achieved clinical and/or biochemical responses at the last follow-up. During the follow-up period, only two patients in group A discontinued SC infliximab, and only one complained of severe injection site reaction. Conclusions: In UC patients who experience IV infliximab failure during maintenance treatment, switching to SC infliximab may be a promising option because of better efficacy and safety.

Safety of Biologics and Small Molecules for Inflammatory Bowel Diseases in Organ Transplant Recipients.

PURPOSE: This study aimed to evaluate the safety of biologics and small molecules for the treatment of inflammatory bowel diseases (IBD) in patients receiving antirejection therapies after organ transplants. MATERIALS AND METHODS: We reviewed the medical records of patients with IBD who received organ transplants at the Asan Medical Center between January 1989 and December 2021. We compared the parameters of patients receiving biologics or small molecules to those of patients without those therapies. RESULTS: This study included a total of 53 patients (ulcerative colitis, 41; Crohn's disease, 6; and gastrointestinal Behçet's disease, 6). Among them, 15 patients were receiving biologics or small molecules and 38 were not. During a mean follow-up of 119 months, the proportion of patients experiencing severe infections was significantly higher in those treated with biologics or small molecules than in those not treated. However, other safety outcomes (e.g., malignancies, adverse events, including organizing pneumonia or hepatic failure, and death) were not different between the two groups. Kaplan-Meier curve analysis revealed no significant difference in the safety outcome rate related to the use of biologics or small molecules. During follow-up, eight patients underwent bowel resections for IBD. The rate of bowel resection was not different between the two groups. CONCLUSION: The use of biologics or small molecules for patients with IBD who received organ transplants did not show a significant difference in safety outcomes. However, the possibility of severe infections must be considered.