200 (stratified) randomly-selected patient charts to confirm SjS. The charts were used to train the RF model, subsequently applied on the 1,447 patients to select additional 200 patient charts for the ML-guided chart review. ML-guided-chart-review results were used to refine model prediction and identify and confirm the use of SNOMED codes as an SjS-diagnosis proxy (AUC=85%, sensitivity=75%, speci-ficity=70%). Phase 2: RF and OCT models were estimated on all 1,647 patients to identify early indicators of SjS. Notable early predictors from the RF model (AUC=86%, sensitivity=90%, specificity=65%) included: patient's age and sex, specialist visits (e.g., rheumatology, ophthalmology), tests (e.g., anti-SSA/SSB, RNP antibody/SCL-70, ANA and RF titer, complement, immunoglobulin blood), and vaccinations (e.g., DPT). OCT results were consistent with RF results though model performance was slightly worse (e.g., AUC=64%). Conclusions: Advanced ML methods can be used to inform clinicians about early indicators to facilitate timely diagnosis of SjS.
Previous studies on the adverse events of acute pulmonary embolism (APE) were mostly limited to single marker, and short follow-up duration, from hospitalization to up to 30 days. We aimed to predict the long-term prognosis of patients with APE by joint assessment of D-dimer, N-Terminal Pro-Brain Natriuretic Peptide (NT-ProBNP), and troponin I (cTnI). Newly diagnosed patients of APE from January 2011 to December 2015 were recruited from three hospitals. Medical information of the patients was collected retrospectively by reviewing medical records. Adverse events (APE recurrence and all-cause mortality) of all enrolled patients were followed up via telephone. D-dimer > 0.50 mg/L, NT-ProBNP > 500 pg/mL, and cTnI > 0.40 ng/mL were defined as the abnormal. Kaplan–Meier curve was used to compare the cumulative survival rate between patients with different numbers of abnormal markers. Cox proportional hazard regression model was used to further test the association between numbers of abnormal markers and long-term prognosis of patients with APE after adjusting for potential confounding. During follow-up, APE recurrence and all-cause mortality happened in 78 (30.1%) patients. The proportion of APE recurrence and death in one abnormal marker, two abnormal markers, and three abnormal markers groups were 7.69%, 28.21%, and 64.10% respectively. Patients with three abnormal markers had the lowest survival rate than those with one or two abnormal markers (Log-rank test, P < 0.001). After adjustment, patients with two or three abnormal markers had a significantly higher risk of the total adverse event compared to those with one abnormal marker. The hazard ratios (95% confidence interval) were 6.27 (3.24, 12.12) and 10.7 (4.1, 28.0), respectively. Separate analyses for APE recurrence and all-cause death found similar results. A joint test of abnormal D-dimer, NT-ProBNP, and cTnI in APE patients could better predict the long-term risk of APE recurrence and all-cause mortality.
The aim of the present study was to investigate the correlation between apolipoprotein E (ApoE) gene polymorphisms and the occurrence of urolithiasis and dyslipidemia. A total of 180 Uyghur individuals, including 90 urolithiasis patients and 90 healthy controls, were enrolled in this study. The blood lipid profiles of the patients and controls were investigated and compared, and the composition of the urinary calculi was determined. The polymorphisms of the ApoE alleles were analyzed using polymerase chain reaction-restriction fragment length polymorphism analysis. Three common genotypes of the ApoE gene, E3/3, E3/4 and E4/4, were detected in the urolithiasis patients and control group. In the patient group, 28 patients with the E3/3 genotype (30.1%), 58 patients with the E3/4 genotype (64.4%) and four patients with the E4/4 genotype (4.5%) were identified. By contrast, in the control group, 52 patients with the E3/3 genotype (57.8%), 35 patients with the E3/4 genotype (38.9%) and three patients with the E4/4 genotype (3.3%) were identified. The frequency of the E3/4 genotype was found to be significantly higher in the patient group when compared with the control group (χ2=12.96; P<0.001). In addition, the frequency of the E4 allele was significantly higher in the patient group when compared with the control group (χ2= 6.61; P=0.025). In conclusion, the occurrence of urolithiasis was found to be associated with ApoE gene polymorphisms, and the E4 allele may be a potential susceptibility factor for urolithiasis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.