RESUMEN
OBJECTIVES: Stool characteristics may change depending on the endoscopic activity of ulcerative colitis (UC). We developed a deep learning model using stool photos of patients with UC (DLSUC) to predict endoscopic mucosal inflammation. METHODS: This was a prospective multicenter study conducted in six tertiary referral hospitals. Patients scheduled to undergo endoscopy for mucosal inflammation monitoring were asked to take photos of their stool using smartphones within 1 week before the day of endoscopy. DLSUC was developed using 2161 stool pictures from 306 patients and tested on 1047 stool images from 126 patients. The ulcerative colitis endoscopic index of severity (UCEIS) was used to define endoscopic activity. The performance of DLSUC in endoscopic activity prediction was compared with that of fecal calprotectin (Fcal). RESULTS: The area under the receiver operating characteristic curve (AUC) of DLSUC for predicting endoscopic activity was 0.801 (95% confidence interval [CI] 0.717-0.873), which was not statistically different from the AUC of Fcal (0.837 [95% CI, 0.767-0.899, DeLong's P=0.458]). When rectal sparing cases (23/126, 18.2%) were excluded, the AUC of DLSUC increased to 0.849 (95% CI, 0.760-0.919). The accuracy, sensitivity, and specificity of DLSUC in predicting endoscopic activity were 0.746, 0.662, and 0.877 in all patients and 0.845, 0.745, and 0.958 in patients without rectal sparing, respectively. Active patients classified by DLSUC were more likely to experience disease relapse during a median 8-month follow-up (log-rank test, P=0.002). CONCLUSIONS: DLSUC demonstrated a good discriminating power similar to that of Fcal in predicting endoscopic activity with improved accuracy in patients without rectal sparing. This study implies that stool photos are a useful monitoring tool for typical UC.
RESUMEN
Wheels have been commonly used for locomotion in mobile robots and transportation systems because of their simple structure and energy efficiency. However, the performance of wheels in overcoming obstacles is limited compared with their advantages in driving on normal flat ground. Here, we present a variable-stiffness wheel inspired by the surface tension of a liquid droplet. In a liquid droplet, as the cohesive force of the outermost liquid molecules increases, the net force pulling the liquid molecules inward also increases. This leads to high surface tension, resulting in the liquid droplet reverting to a circular shape from its distorted shape induced by gravitational forces. Similarly, the shape and stiffness of a wheel were controlled by changing the traction force at the outermost smart chain block. As the tension of the wire spokes connected to each chain block increased, the wheel characteristics reflected those of a general circular-rigid wheel, which has an advantage in high-speed locomotion on normal flat ground. Conversely, the modulus of the wheel decreased as the tension of the wire spoke decreased, and the wheel was easily deformed according to the shape of obstacles. This makes the wheel suitable for overcoming obstacles without requiring complex control or sensing systems. On the basis of this mechanism, a wheel was applied to a two-wheeled wheelchair system weighing 120 kilograms, and the state transition between a circular high-modulus state and a deformable low-modulus state was realized in real time when the wheelchair was driven in an outdoor environment.
RESUMEN
Recent research has demonstrated the potential of fecal microbiome analysis using machine learning (ML) in the diagnosis of inflammatory bowel disease (IBD), mainly Crohn's disease (CD) and ulcerative colitis (UC). This study employed the sparse partial least squares discriminant analysis (sPLS-DA) ML technique to develop a robust prediction model for distinguishing among CD, UC, and healthy controls (HCs) based on fecal microbiome data. Using data from multicenter cohorts, we conducted 16S rRNA gene sequencing of fecal samples from patients with CD (n = 671) and UC (n = 114) while forming an HC cohort of 1462 individuals from the Kangbuk Samsung Hospital Healthcare Screening Center. A streamlined pipeline based on HmmUFOTU was used. After a series of filtering steps, 1517 phylotypes and 1846 samples were retained for subsequent analysis. After 100 rounds of downsampling with age, sex, and sample size matching, and division into training and test sets, we constructed two binary prediction models to distinguish between IBD and HC and CD and UC using the training set. The binary prediction models exhibited high accuracy and area under the curve (for differentiating IBD from HC (mean accuracy, 0.950; AUC, 0.992) and CD from UC (mean accuracy, 0.945; AUC, 0.988)), respectively, in the test set. This study underscores the diagnostic potential of an ML model based on sPLS-DA, utilizing fecal microbiome analysis, highlighting its ability to differentiate between IBD and HC and distinguish CD from UC.