ObjectiveTo explore the efficacy of artificial intelligence (AI) detection on pulmonary nodule compared with multidisciplinary team (MDT) in regional medical center.MethodsWe retrospectively analyzed the clinical data of 102 patients with lung nodules in the Xiamen Fifth Hospital from April to December 2020. There were 57 males and 45 females at age of 36-90 (48.8±11.6) years. The preoperative chest CT was imported into AI system to record the detected lung nodules. The detection rate of pulmonary nodules by AI system was calculated, and the sensitivity, specificity of AI in the different diagnosis of benign and malignant pulmonary was calculated and compared with manual film reading by MDT.ResultsA total of 322 nodules were detected by AI software system, and 305 nodules were manually detected by physicians (P<0.05). Among them, 113 pulmonary nodules were diagnosed by pathologist. Thirty-eight of 40 lung cancer nodules were AI high-risk nodules, the sensitivity was 95.0%, and 25 of 73 benign nodules were AI high-risk nodules, the specificity was 65.8%. Lung cancer nodules were correctly diagnosed by MDT, but benign nodules were still considered as lung cancer at the first diagnosis in 10 patients.ConclusionAI assisted diagnosis system has strong performance in the detection of pulmonary nodules, but it can not content itself with clinical needs in the differentiation of benign and malignant pulmonary nodules. The artificial intelligence system can be used as an auxiliary tool for MDT to detect pulmonary nodules in regional medical center.
ObjevtiveThe morbidity of intensive care unit-acquired swallowing disorder (ICU-ASD) was clarified through meta-analysis by synthesizing previous evidence, in order to provide an evidence-based basis for early identification and intervention of ICU-ASD. Methods A computerized search of PubMed, Embase, Web of Science, The Cochrane Library, CHINAL, China Knowledge Network, Wanfang Data Knowledge Service Platform, and Chinese Science and Technology Journal Database was conducted to retrieve the relevant literature on the morbidity of ICU-ASD published in China and abroad from the database establiment to December 2022. Considering the quality of the included literature, the Chinese database excluded master's theses and non-core journals. Meta-analysis of morbidity was performed using Stata 12.0. Results A total of 19 papers, including 4291 patients, were included. Meta-analysis showed that the overall morbidity of ICU-ASD was 36% [95% confidential interval (CI) 26% - 46%; I2=97.62%, P<0.01]. Subgroup analyses showed that the morbidity of ICU-ASD in Asian, European, South American, and North American was 39% (95%CI 28% - 50%), 23% (95%CI 8% - 44%), 52% (95%CI 46% - 57%), and 39% (95%CI 20% - 61%), respectively; and that the morbidity of male and female ICU-ASD was 36% (95%CI 24% - 48%) and 33% (95%CI 22% - 45%), respectively; the morbidity of ICU-ASD was 41% (95%CI 30% - 52%) and 31% (95%CI 18% - 44%) in the patients with and without hypertension, respectively; the morbidity of ICU-ASD was 58% (95%CI 42% - 73%) and 51% (95%CI 36% - 66%) in the patients with and without respiratory disease respectively; the morbidity of ICU-ASD in the patients with and without diabetes mellitus was 37% (95%CI 24% - 51%) and 39% (95%CI 28% - 51%), respectively; the morbidity of ICU-ASD in the patients with and without renal disease was 40% (95%CI 23% - 59%) and 35% (95%CI 24% - 46%), respectively; the morbidity of ICU-ASD in the patients with intubation caliber ≤7.5 mm and >7.5 mm was 31% (95%CI 19% - 45%) and 37% (95%CI 22% - 54%), respectively; the morbidity of ICU-ASD in the patients with and without heart failure was 58% (95%CI 30% - 84%) and 36% (95%CI 23% - 51%), respectively; and the morbidity of ICU-ASD in patients with and without arrhythmia was 36% (95%CI 11% - 65%) and 31% (95%CI 21% - 42%), respectively; the morbidity of ICU-ASD in the patients with and without neurologic disease was 48% (95%CI 24% - 72%) and 34% (95%CI 15% - 57%), respectively. Begg's test P<0.05, Egger's test P<0.05, suggesting publication bias in the study, and the cut-and-patch method corrected for an overall incidence result of 27% (95%CI 18% - 36%). Conclusions Meta-analysis reveals an overall morbidity of 36% for ICU-ASD and 27% for the cut-and-patch correction. Subgroup analysis reveals that the morbidity of ICU-ASD is significantly higher in patients with hypertension, heart failure, and neurological disorders than in patients without these disorders. Current evidence suggests that the prevalence of ICU-ASD is high and needs to be taken seriously. Timely screening and assessment of swallowing disorders is recommended for intensive care unit patients, especially those with hypertension, heart failure, and neurological disorders.