Background::Acute pulmonary embolism (APE) is a fatal cardiovascular disease, yet missed diagnosis and misdiagnosis often occur due to non-specific symptoms and signs. A simple, objective technique will help clinicians make a quick and precise diagnosis. In population studies, machine learning (ML) plays a critical role in characterizing cardiovascular risks, predicting outcomes, and identifying biomarkers. This work sought to develop an ML model for helping APE diagnosis and compare it against current clinical probability assessment models.Methods::This is a single-center retrospective study. Patients with suspected APE were continuously enrolled and randomly divided into two groups including training and testing sets. A total of 8 ML models, including random forest (RF), Na?ve Bayes, decision tree, K-nearest neighbors, logistic regression, multi-layer perceptron, support vector machine, and gradient boosting decision tree were developed based on the training set to diagnose APE. Thereafter, the model with the best diagnostic performance was selected and evaluated against the current clinical assessment strategies, including the Wells score, revised Geneva score, and Years algorithm. Eventually, the ML model was internally validated to assess the diagnostic performance using receiver operating characteristic (ROC) analysis.Results::The ML models were constructed using eight clinical features, including D-dimer, cardiac troponin T (cTNT), arterial oxygen saturation, heart rate, chest pain, lower limb pain, hemoptysis, and chronic heart failure. Among eight ML models, the RF model achieved the best performance with the highest area under the curve (AUC) (AUC = 0.774). Compared to the current clinical assessment strategies, the RF model outperformed the Wells score ( P = 0.030) and was not inferior to any other clinical probability assessment strategy. The AUC of the RF model for diagnosing APE onset in internal validation set was 0.726. Conclusions::Based on RF algorithm, a novel prediction model was finally constructed for APE diagnosis. When compared to the current clinical assessment strategies, the RF model achieved better diagnostic efficacy and accuracy. Therefore, the ML algorithm can be a useful tool in assisting with the diagnosis of APE.

Purpose: Rheumatoid arthritis (RA) is a chronic systemic autoimmune disease, and Th17 cells are key factors in the pathogenesis of human inflammatory conditions, such as RA. Catalpol (CAT), a component in Rehmanniae Radix (RR), has been found to regulate human immunity. However, the effects of CAT on Th17 cell differentiation and improvement of RA are not clear. Materials and Methods: Collagen-induced arthritis (CIA) mice were constructed to detect the effects of CAT on arthritis and Th17 cells. The effect of CAT on Th17 differentiation was evaluated with let-7g-5p transfection experiments. Flow cytometry was used to detect the proportion of Th17 cells after CAT treatment. Levels of interleukin-17 and RORγt were assessed by qRT-PCR and enzyme-linked immunosorbent assay. The expression of signal transducer and activator of transcription 3 (STAT3) was determined by qRT-PCR and Western blot. Results: We found that the proportion of Th17 cells was negatively associated with let-7g-5p expression in CIA mice. In in vitro experiments, CAT suppressed traditional differentiation of Th17 cells. Simultaneously, CAT significantly decreased Tregs-to-Th17 cells transdifferentiation. Our results demonstrated that CAT inhibited Tregs-to-Th17 cells transdifferentiation by up-regulating let-7g-5p and that the suppressive effect of CAT on traditional differentiation of Th17 cells is not related with let-7-5p. Conclusion Our data indicate that CAT may be a potential modulator of Tregs-to-Th17 cells transdifferentiation by up-regulating let-7g-5p to reduce the expression of STAT3. These results provide new directions for research into RA treatment.

Objective To explore the feasibility and clinical effect of laparoscopic radical cystectomy with intracorporeal Xing's orthotopic neobladder.Methods Forty-one patients who underwent laparoscopic radical cystectomy with intracorporeal Xing's orthotopic neobladder from July 2013 to August 2019.There were 31 cases performed in Beijing Chaoyang hospital and 10 cases in National Cancer Center.Mean age was 59 (range 44-78) years,mean BMI was 25.3 (range 20.1-34.7) kg/m2,and mean CCI was 3 (range 2-6).No urethral stricture or urinary incontinence was found by preoperative examination.No distant metastasis was identified by bone scans,chest X-ray and sonography.Cystoscopy or TURBT was performed on all patients and biopsy was taken to confirm the diagnosis.Preoperative pathology showed 30 cases (73.2％) of MIBC,9 cases of NMIBC (22.0％) and 2 cases (4.9％) of in-situ cancer.Laparoscopic radical cystectomy and lymphadenectomy were performed under general anesthesia.Urinary diversion was completed in the peritoneal cavity,by intercepting the terminal ileum about 60 cm,and taking the proximal ileum 10 cm as input loop on the right side with proximal to distal way,and the middle 40 cm ileum was detubated.After u-shaped suture,the ileum was folded back and stitched into a sphere building a novd orthotopic neobladder with bilateral isoperistaltic afferent limbs.The prognosis of perioperative data and postoperative satisfaction regarding continence were analyzed,continence was defined as 0-1 pad/day.The 41 patients were divided into two groups to compare the difference in term of operation time and blood loss between the first 21 patients and the last 20 patients.Results Mean total operative time was 324.9 mins (range 210-480) mins,and mean estimated blood loss was 177.6(range 50-700) ml.There were significant statistical differences in term of total operation time,construction time and blood loss between the first 21 patients and the next 20 patients (P ＜ 0.05).Postoperative pathological results were urothelial carcinoma in 40 cases (2 in situ carcinoma) and small cell carcinoma in 1 case.Mean number of dissected lymph nodes was 19 (range 11-58),with 7 cases(17.1％)of positive lymph nodes,and 3 cases(7.3％) had positive surgical margin.At a mean follow up of 17.6 (range 2-64) months,36 patients (87.8％) survived,including 2 patients (4.9％) with metastasis and 1 patient (2.4％) with recurrence,and 5 cases (12.2％)died.All patients were able to urinate without catheterization.Thirty-seven patients (90.2％) were satisfied with voiding control during the daytime (0-1 urinal pad),and 29 patients (70.7％) were satisfied with voiding control at nighttime (0-1 urinal pad) by the follow-up 12 months after the operation.Conclusions Total laparoscopic radical cystectomy combined with Xing's orthotopic ileum neobladder is a simple method with fewer postoperative complications and a satisfactory continence rate.