BACKGROUND: Over 20 million colonoscopies are performed in China annually. An automatic clinical decision support system (CDSS) with accurate semantic recognition of colonoscopy reports and guideline-based is helpful to relieve the increasing medical burden and standardize the healthcare. In this study, the CDSS was built under a hierarchical-label interpretable classification framework, trained by a state-of-the-art transformer-based model, and validated in a multi-center style. METHODS: We conducted stratified sampling on a previously established dataset containing 302,965 electronic colonoscopy reports with pathology, identified 2041 patients' records representative of overall features, and randomly divided into the training and testing sets (7:3). A total of five main labels and 22 sublabels were applied to annotate each record on a network platform, and the data were trained respectively by three pre-training models on Chinese corpus website, including bidirectional encoder representations from transformers (BERT)-base-Chinese (BC), the BERT-wwm-ext-Chinese (BWEC), and ernie-3.0-base-zh (E3BZ). The performance of trained models was subsequently compared with a randomly initialized model, and the preferred model was selected. Model fine-tuning was applied to further enhance the capacity. The system was validated in five other hospitals with 3177 consecutive colonoscopy cases. RESULTS: The E3BZ pre-trained model exhibited the best performance, with a 90.18% accuracy and a 69.14% Macro-F1 score overall. The model achieved 100% accuracy in identifying cancer cases and 99.16% for normal cases. In external validation, the model exhibited favorable consistency and good performance among five hospitals. CONCLUSIONS The novel CDSS possesses high-level semantic recognition of colonoscopy reports, provides appropriate recommendations, and holds the potential to be a powerful tool for physicians and patients. The hierarchical multi-label strategy and pre-training method should be amendable to manage more medical text in the future.
Humans ; Colonoscopy/methods* ; Deep Learning ; Decision Support Systems, Clinical ; Female ; Male

Objective:To investigate the learning curve for a five-step procedure, namely, a transthoracic single-port assisted laparoscopic transabdominal diaphragmatic approach, for Siewert type II adenocarcinoma of the esophagogastric junction.Methods:In this retrospective cohort study, we analyzed relevant clinical data of 66 patients with Siewert type II adenocarcinoma of the esophagogastric junction who had undergone the five-step procedure performed by the same surgeon in the Gastrointestinal Surgery Department of Guangdong Provincial Hospital of Chinese Medicine from May 2017 to April 2023. The learning curve were plotted using cumulative summation analysis and selected indicators, including intraoperative blood loss, duration of surgery, time to first flatus, time to first tolerance of liquid food, length of hospital stay, and incidence of perioperative complications at different stages were compared. The data were analyzed using SPSS 24.0 statistical software. Numerical data are presented as cases (%) and data were analyzed using the χ 2 test or Fisher's exact test. Normally distributed measurement data are presented as x±s, and independent sample t-testing was performed for inter group comparison. Non-normally distributed measurement data are presented as M( Q1, Q3) and the Mann–Whitney U test was used for inter group comparison. Results:The five-step procedure had been successfully completed without switching to open surgery in all 66 study patients. There were no perioperative deaths, blood loss was 100 (50, 200) mL and duration of surgery 329.4±87.3 minutes. The equation of optimal fit for the duration of surgery was y=0.031x 3-4.4757x 2+164.97x-264.4 ( P<0.001, R2=0.9797). The cumulative summation learning curve reached a vertex when 25 surgical procedures had accumulated. Using 25 cases as the cut-off, we divided the learning curves into learning and proficiency periods and patients into learning (25) and proficiency period groups (41). There were no statistically significant differences between the two groups of patients in sex, age, body mass index, American Society of Anesthesiologists score, history of abdominal surgery, comorbidities, preoperative neoadjuvant therapy, maximum tumor diameter, surgical procedure, or T and N stage of tumor ( P>0.05). The following factors differed significantly (all P<0.05) between the learning and proficiency stages: in the latter there was less intraoperative blood loss (100 [50, 100] ml vs. 200 [100, 200] ml, U=-3.940, P<0.001), shorter duration of surgery ([289.8±50.7] minutes vs. [394.4±96.0] minutes, t=5.034, P<0.001), more mediastinal lymph nodes removed (5 [2, 8] vs. 2 [1, 5], U=-2.518, P=0.012), earlier time to first flatus (2 [2, 3] days vs. 4 [3, 6] days, U=-4.016, P<0.001), earlier time to first tolerance of liquid food (5 [4, 6] days vs. 7 [6, 8] days, U=-2.922, P=0.003), shorter duration of hospital stay (8 [8, 10] vs. 10 [9, 12] days, U=-2.028, P=0.043). The incidence of surgical complications did not differ significantly between the two groups ( P=0.238). Conclusion:Satisfactory results can be achieved with the five-step procedure for patients with Siewert type II adenocarcinoma of the esophagogastric junction once 25 procedures have been performed.

Objective:To investigate the learning curve for a five-step procedure, namely, a transthoracic single-port assisted laparoscopic transabdominal diaphragmatic approach, for Siewert type II adenocarcinoma of the esophagogastric junction.Methods:In this retrospective cohort study, we analyzed relevant clinical data of 66 patients with Siewert type II adenocarcinoma of the esophagogastric junction who had undergone the five-step procedure performed by the same surgeon in the Gastrointestinal Surgery Department of Guangdong Provincial Hospital of Chinese Medicine from May 2017 to April 2023. The learning curve were plotted using cumulative summation analysis and selected indicators, including intraoperative blood loss, duration of surgery, time to first flatus, time to first tolerance of liquid food, length of hospital stay, and incidence of perioperative complications at different stages were compared. The data were analyzed using SPSS 24.0 statistical software. Numerical data are presented as cases (%) and data were analyzed using the χ 2 test or Fisher's exact test. Normally distributed measurement data are presented as x±s, and independent sample t-testing was performed for inter group comparison. Non-normally distributed measurement data are presented as M( Q1, Q3) and the Mann–Whitney U test was used for inter group comparison. Results:The five-step procedure had been successfully completed without switching to open surgery in all 66 study patients. There were no perioperative deaths, blood loss was 100 (50, 200) mL and duration of surgery 329.4±87.3 minutes. The equation of optimal fit for the duration of surgery was y=0.031x 3-4.4757x 2+164.97x-264.4 ( P<0.001, R2=0.9797). The cumulative summation learning curve reached a vertex when 25 surgical procedures had accumulated. Using 25 cases as the cut-off, we divided the learning curves into learning and proficiency periods and patients into learning (25) and proficiency period groups (41). There were no statistically significant differences between the two groups of patients in sex, age, body mass index, American Society of Anesthesiologists score, history of abdominal surgery, comorbidities, preoperative neoadjuvant therapy, maximum tumor diameter, surgical procedure, or T and N stage of tumor ( P>0.05). The following factors differed significantly (all P<0.05) between the learning and proficiency stages: in the latter there was less intraoperative blood loss (100 [50, 100] ml vs. 200 [100, 200] ml, U=-3.940, P<0.001), shorter duration of surgery ([289.8±50.7] minutes vs. [394.4±96.0] minutes, t=5.034, P<0.001), more mediastinal lymph nodes removed (5 [2, 8] vs. 2 [1, 5], U=-2.518, P=0.012), earlier time to first flatus (2 [2, 3] days vs. 4 [3, 6] days, U=-4.016, P<0.001), earlier time to first tolerance of liquid food (5 [4, 6] days vs. 7 [6, 8] days, U=-2.922, P=0.003), shorter duration of hospital stay (8 [8, 10] vs. 10 [9, 12] days, U=-2.028, P=0.043). The incidence of surgical complications did not differ significantly between the two groups ( P=0.238). Conclusion:Satisfactory results can be achieved with the five-step procedure for patients with Siewert type II adenocarcinoma of the esophagogastric junction once 25 procedures have been performed.

Objective: To investigate the neuroprotective effect of mesenchymal stem cells (MSC) combined with low⁃intensity transcranial ultrasound (LITUS) treatment on traumatic brain injury (TBI) . Methods: Seventy⁃two SD rats were randomly divided into four groups , namely , control group , TBI group , MSC injection group , and combined treatment group , with 18 rats in each group. TBI model was established by applying a pneumatic controlled cortical impingement instrument. Within 24 h after surgery , MSC was injected into the injury site by microinjector and microinjector pump using in situ injection. After injection , the injury site was treated with LITUS for 28 consecutive days using an ultrasound stimulator. The modified neurological functioning score ( mNSS) was performed on rats in each group at 1 , 3 , 7 , 14 , 21 and 28 days postoperatively , and then the brains were extracted to detect pathological changes at the injury site and the mRNA and protein expression of brain⁃derived neurotrophic factor (BDNF) , growth associated protein⁃43 ( GAP⁃43) , postsynaptic density protein⁃95 ( PSD⁃95 ) and glial fibrillary acidic protein(GFAP) by HE staining , immunohistochemistry , Western blot and RT⁃PCR. Results: Compared with the control group , the mNSS score increased in the TBI group (P < 0. 05) , the expression of GAP⁃43 and PSD⁃95 decreased , and the expression of GFAP increased ( P < 0. 05 ) ; Compared with the TBI group , the mNSS score of MSC group was lower (P < 0. 05) , the expression of BDNF , GAP⁃43 , PSD⁃95 increased , and the expression of GFAP decreased (P < 0. 05) ; mNSS scores were lower in the combined treatment group than those in the MSC group (P < 0. 05) , the expression of BDNF , GAP⁃43 , PSD⁃95 increased , and the expression of GFAP decreased (P < 0. 05) . Conclusion The mechanism by which MSC combined with LITUS exerts neuroprotective effects in TBI may be related to the promotion of BDNF , GAP⁃43 , and PSD⁃95 expression and reduction of GFAP expression.

Background: and Purpose The rate of donepezil discontinuation and the underlying reasons for discontinuation in Asian patients with Alzheimer’s disease (AD) are currently unknown. We aimed to determine the treatment discontinuation rates in AD patients who had newly been prescribed donepezil in routine clinical practice in Asia. Methods: This 1-year observational study involved 38 institutions in seven Asian countries, and it evaluated 398 participants aged 50–90 years with a diagnosis of probable AD and on newly prescribed donepezil monotherapy. The primary endpoint was the rate of donepezil discontinuation over 1 year. Secondary endpoints included the reason for discontinuation,treatment duration, changes in cognitive function over the 1-year study period, and compliance as assessed using a clinician rating scale (CRS) and visual analog scale (VAS). Results: Donepezil was discontinued in 83 (20.9%) patients, most commonly due to an adverse event (43.4%). The mean treatment duration was 103.67 days in patients who discontinued. Among patients whose cognitive function was assessed at baseline and 1 year, there were no significant changes in scores on the Mini-Mental State Examination, Montreal Cognitive Assessment, and Trail-Making Test–Black and White scores, whereas the Clinical Dementia Rating score increased significantly (p<0.001). Treatment compliance at 1 year was 96.8% (306/316) on the CRS and 92.6±14.1% (mean±standard deviation) on the VAS. Conclusions In patients on newly prescribed donepezil, the primary reason for discontinuation was an adverse event. Cognitive assessments revealed no significant worsening at 1 year, indicating that continuous donepezil treatment contributes to the maintenance of cognitive function.

Background: and Purpose The rate of donepezil discontinuation and the underlying reasons for discontinuation in Asian patients with Alzheimer’s disease (AD) are currently unknown. We aimed to determine the treatment discontinuation rates in AD patients who had newly been prescribed donepezil in routine clinical practice in Asia. Methods: This 1-year observational study involved 38 institutions in seven Asian countries, and it evaluated 398 participants aged 50–90 years with a diagnosis of probable AD and on newly prescribed donepezil monotherapy. The primary endpoint was the rate of donepezil discontinuation over 1 year. Secondary endpoints included the reason for discontinuation,treatment duration, changes in cognitive function over the 1-year study period, and compliance as assessed using a clinician rating scale (CRS) and visual analog scale (VAS). Results: Donepezil was discontinued in 83 (20.9%) patients, most commonly due to an adverse event (43.4%). The mean treatment duration was 103.67 days in patients who discontinued. Among patients whose cognitive function was assessed at baseline and 1 year, there were no significant changes in scores on the Mini-Mental State Examination, Montreal Cognitive Assessment, and Trail-Making Test–Black and White scores, whereas the Clinical Dementia Rating score increased significantly (p<0.001). Treatment compliance at 1 year was 96.8% (306/316) on the CRS and 92.6±14.1% (mean±standard deviation) on the VAS. Conclusions In patients on newly prescribed donepezil, the primary reason for discontinuation was an adverse event. Cognitive assessments revealed no significant worsening at 1 year, indicating that continuous donepezil treatment contributes to the maintenance of cognitive function.

Objective To explore the clinical value of 18F-fluorodeoxyglucose (FDG) PET/CT in assessing antineutrophil cytoplasmic antibody-associated vasculitis (AAV).Methods Fifteen patients (7 males,8 females,age (66±11) years) with AAV between January 2015 and June 2017 were retrospectively analyzed.There were 6 patients diagnosed as granulomatosis with polyangiitis (GPA),7 diagnosed as microscopic polyangiitis (MPA) and 2 diagnosed as eosinophilic granulomatosis with polyangiitis (EGPA).All patients underwent 18 F-FDG PET/CT and the image features were observed and analyzed.The maximum standardized uptake value (SUVmax) of the positive lesion was measured.The relationship between the SUVmax and C reactive protein (CRP) was analyzed with Pearson correlation.The SUVmax and the number of lesion sites were compared by two-sample t test between the CRP-elevated and CRP-normal patients.Results A total of 56 lesions in the 14 of 15 AAV patients were detected by PET/CT.The positive findings distributed in 15 tissues and organs,including the nasopharynxes (n =9),lungs (n =9),kidneys (n =8),spleen (n =6),lymph nodes (n =6),bone marrow (n =4),skin (n =3),prostate (n =2),aortas (n =2),vertebral soft tissues (n =2),orbita (n =1),parotid gland (n =1),thyroid gland (n =1),liver (n =1) and pancreas (n=1).The 60.7％ (34/56) of lesions were clinically unsuspected occult lesions.GPA lesions mainly invaded the nasopharynxes,lungs and kidneys;MPA lesions mainly invaded the kidneys and spleen;EGPA lesions mainly invaded the nasopharynxes,lymph nodes and bone marrow.There was no significant correlation between the level of CRP and the SUVmax of AAV lesions (r=0.462,P＞0.05).No differences in the SUVmax were observed between patients with elevated CRP levels and those with normal CRP levels (t=1.451,P＞0.05).But more lesion sites were observed in patients with elevated CRP (t=3.456,P＜0.05).Conclusions 18F-FDG PET/CT shows positive findings in multiple sites in AAV patients,including clinically unsuspected sites.This imaging technique may be a useful tool for diagnosis and evaluation of AAV.

AIDS antiviral therapy (ART) has achieved great success.Originaly,AIDS had been regarded as a fatal disease,but it has become a kind of infectious disease that could be cured and administrated.Global HIV / AIDS cases were still up to about 38 million,but more than half have been effectively treated.In addition to drug treatment,at present,some new technologies and new methods,such as genome editing,have also been involved in the treatment of AIDS,and in the humanized animal experiment has shown very good results.There is no doubt that AIDS will eventually be stopped its epidemic.However,with the continuous development of AIDS antiviral treatment,the most fundamental problem is that HIV latent library has become increasingly prominent one,whether molecular therapy and hybrid cure have being developed for AIDS treatment,there are still such problem existence.Great efforts shoud be made to continuously search for new markers of latent viral cells and to reduce the latent pool.In addition,despite the prevention and treatment of AIDS has made great achievements,but the world still produces nearly 6000 cases of HIV/AIDS every day.Therefore,the development of safe and effective vaccine,whether in the field of prevention,or in clinical treatment,has its positive significance.

Objective To investigate the anesthetic management of perventricular closure of ventricular septal defects (VSD) under transesophageal echocardiography. Methods A retrospective review of the clinical data of 52 children who underwent perventricular closure of VSD under transesophageal echocardiography were analyzed. All the children were performed tracheal intubation under general anesthesia, and the electrocardiogram, pulse blood oxygen saturation, invasive arterial pressure, central venous pressure, end tidal carbon dioxide partial pressure, temperature and urine output were continuously monitored throughout the procedure. The transesophageal echocardiography was necessary for guiding transcatheter or per-ventricular device placement. Results Perventricular closure of VSD was successfully completed in 51 children under transesophageal echocardiography, the operation time was (76.7 ± 36.4) min, the anesthesia time was (89.5 ± 27.1) min; 1 child was converted to open surgical repair. Conclusions The intraoperative transesophageal echocardiography technology is the key to the success of the surgery. At the same time of analgesia and sedation, the anesthesia doctor needs to pay attention to the changes of hemodynamics in children.