The objective of this study was to identify risk factors for enema reduction failure and to establish a combined model that integrates deep learning (DL) features and clinical features for predicting surgical intervention in intussusception in children younger than 8 months of age.

A retrospective study with a prospective validation cohort of intussusception.

The retrospective data were collected from two hospitals in south east China between January 2017 and December 2022. The prospective data were collected between January 2023 and July 2024.

A total of 415 intussusception cases in patients younger than 8 months were included in the study.

280 cases collected from Centre 1 were randomly divided into two groups at a 7:3 ratio: the training cohort (n=196) and the internal validation cohort (n=84). 85 cases collected from Centre 2 were designed as external validation cohort. Pretrained DL networks were used to extract deep transfer learning features, with least absolute shrinkage and selection operator regression selecting the non-zero coefficient features. The clinical features were screened by univariate and multivariate logistic regression analyses. We constructed a combined model that integrated the selected two types of features, along with individual clinical and DL models for comparison. Additionally, the combined model was validated in a prospective cohort (n=50) collected from Centre 1.

In the internal and external validation cohorts, the combined model (area under curve (AUC): 0.911 and 0.871, respectively) demonstrated better performance for predicting surgical intervention in intussusception in children younger than 8 months of age than the clinical model (AUC: 0.776 and 0.740, respectively) and the DL model (AUC: 0.828 and 0.793, respectively). In the prospective validation cohort, the combined model also demonstrated impressive performance with an AUC of 0.890.

The combined model, integrating DL and clinical features, demonstrated stable predictive accuracy, suggesting its potential for improving clinical therapeutic strategies for intussusception.

Proximal gastrectomy (PG) has emerged as the preferred surgical approach for adenocarcinoma of the upper 1/3 stomach and selected cases of oesophagogastric junction adenocarcinoma. We developed a novel oesophagogastric anastomosis technique with an antireflux mechanism (Hao’s Esophagogastrostomy by Fissure Technique). It may have a superior effect on patient weight maintenance compared with the double-tract reconstruction. We intend to conduct a prospective, multicentre, randomised controlled clinical trial to validate this hypothesis.

The primary objective evaluates body weight loss at 12 months postoperatively. Secondary objectives assess surgical safety through comprehensive analysis of complication rates and nutritional parameters, including serial haematological evaluations during follow-up. The study will enrol 52 participants across multiple centres with planned 3-year longitudinal monitoring to evaluate both immediate postoperative outcomes and intermediate-term clinical impacts.

This study was approved by the hospital institutional review board of Huashan Hospital, Fudan University (2024-1173) and is being conducted in accordance with the Declaration of Helsinki and the Good Clinical Practice guidelines. On completion of the study, the results will be published in a peer-reviewed journal.

NCT06679244.

Falls are common causes of disability, reduced disability-adjusted life years and death in older adults. Balance deficits and cognitive impairment are common causes of falls. Dual-task training is a new strategy that can potentially improve balance and cognitive function, leading to decreased falls. The effectiveness and cost-effectiveness of self-administered dual-task (sDT) training to improve balance and prevent falls is not known. We developed sDT training combining physical and cognitive tasks to improve balance and reduce falls. The proposed randomised controlled trial (RCT) with economic evaluation is to test the effectiveness and cost-effectiveness of the sDT compared with self-administered single-task training (sST) in this population.

In this RCT, we will recruit 190 community-dwelling older adults with a history of at least one fall over the last 6 months from 11 elderly centres. The older adults will be randomly assigned to the sDT (n=95) and sST groups (n=95). Each group will be offered in six training workshops to teach the participants either sDT or sST depending on the group allocation. Each workshop will last an hour and will be held once every 2 weeks for 3 months. Besides, the participants will be instructed to repeat the exercises at home two times weekly for 3 months. Following the intervention phase, the participants will continue unsupervised home-based exercises for 6 months. Assessments will be performed before, after and 6 months after completing the intervention. A fall calendar and cost diary will be provided to each older adult to record the number of falls and fall-related costs during and after the intervention to assess fall incidence and cost-effectiveness. Effectiveness will be assessed using a negative binomial regression model following the intention-to-treat principle for falls and a linear mixed model for the additional measure and cost-effectiveness using a Markov model.

This study has ethical approval from the PolyU Institutional Review Board for conducting research on human subjects (Ref: HSEARS20210322005). The results will be disseminated through seminars for individuals and health practitioners, international conferences and published in peer-reviewed journals.

NCT05533333.