Objective
To develop an evaluation tool for the screening of high risk population for oral complications in critically ill patients, which can be performed accurately and scientifically.
Methods
Basing on the related foreign oral assessment scale, combined with the method of brainstorming, expert consultation, method of clinical status and so on, the item pool of the assessment scale was determined. Five nursing experts and two oral experts assessed the content validity and 50 ICU nurses were tested. Then, the screening accuracy of the assessment scale was proved by application in 100 critically ill patients selected randomly.
Results
The Cronbach’s a coefficient of final version of the High Risk Assessment Scale for Oral Complications in Critically Ill Patients (including seven parts contents of oral health assessment and oral pH value test) was 0.815, the content validity index (Sr-CVI/Ave) was 0.932. The results of 50 nurses to the 91.2% assessment items of the assessment scale were very important and important. For screening related indicators of oral complications in high-risk patients, the sensitivity of the assessment scale was 97.53%, the specificity was 94.11%, the positive predictive value was 98.75%, the negative predictive value was 88.89%, and the crude agreement was 95%.
Conclusion
There are good reliability, validity and a high accuracy of screening test in the High Risk Assessment Scale for Oral Complications in Critically Ill Patients. It can be used for screening patients at high risk for oral complications in critically ill patients, and help clinical nurses to complete the oral health status of the critically ill patients quickly.
ObjectiveTo investigate the effect of an artificial intelligence (AI)-powered voice cloning education system based on the self-reference effect on patient outcomes, and to compare the educational effects of a physician's voice versus the patient's own voice. MethodsA prospective, three-arm, parallel-group randomized controlled trial was conducted. A total of 150 thoracic surgery inpatients at the First Hospital of Lanzhou University from May to September 2025 were included and randomly assigned in a 1 : 1 : 1 ratio to a traditional education group (control group, n=50), a physician’s voice-cloned AI education group (intervention group 1, n=50), and a patient's own voice-cloned AI education group (intervention group 2, n=50). The primary outcome was the education content compliance rate, which was automatically assessed using the DeepSeek-R1 model. Secondary outcomes included knowledge mastery, educational satisfaction, treatment adherence, quality of life (SF-36), and psychological status (HADS). ResultsA total of 145 (96.7%) patients completed the trial. There were no significant differences in age [(54.2±10.1) years, (55.8±9.7) years, and (53.9±10.5) years, respectively] or sex distribution (male/female: 28/20, 26/22, and 27/22, respectively) among the three groups (all P>0.05). The immediate post-education content compliance rates of both AI intervention groups were significantly higher than that of the control group (P<0.001). The patient’s own voice-cloned AI education group was significantly superior to the physician's voice-cloned AI education group and the control group in terms of knowledge mastery at discharge, treatment adherence at the 1-month follow-up, and anxiety and depression scores at the 1-month follow-up (all P<0.05). ConclusionAn AI-powered education model leveraging the self-reference effect throughpatient’s own voice cloning significantly improves patient outcomes. This approach demonstrates superior results in knowledge retention, treatment adherence, and psychological well-being compared to traditional methods and physician’s voice cloning, offering a new paradigm for personalized and scalable intelligent health education.
