The development and validation of a prediction model of lithium carbonate blood concentration by artificial neural network: a retrospective study.

BACKGROUND: Bipolar disorder (BD) is common in clinical practice. Lithium (Li) carbonate is often used in the treatment of BD. However, the therapeutic dose of Li carbonate is close to the toxic dose, and Li poisoning is prone to occur. Precise prediction of Li concentration will help clinician to identify patients at high risk of toxic dose of Li carbonate. The purpose of this study was to establish a model for predicting the blood concentration of Li carbonate through an artificial neural network (ANN), and to provide a basis for the clinical rapid and effective formulation of individualized dosing regimens. METHODS: Patients with BD who were diagnosed and treated in our hospital from October 2016 to April 2021 were enrolled as the research participants. We collected patient demographic data, including age and gender; physical examination information, including height and weight; laboratory test results, including liver and renal function, and Li concentrations; medication information, including Li carbonate usage, concomitant medications, and dose; and information on comorbidities and adverse reactions. The Li concentration data of 236 patients were randomly divided into 2 groups: 195 cases in the training group and 41 cases in the test group. The ANN fitting module of SPSS 26.0 was used for modeling and prediction. RESULTS: A total of 236 patients with BD were included in this study. Daily dose (before testing Li concentration), age, alanine aminotransferase (ALT), aspartate aminotransferase (AST), albumin (ALB), total bilirubin (TBIL), and creatinine (Cr), and co-administered zopiclone, quinine, tipine, lorazepam, olanzapine, valproate, metoprolol, and statins were used as model input variables for training. The test results of the model in the testing group showed that the correlation coefficient between the predicted value of Li concentration and the actual value was r=0.9883, r2=0.9767, P<0.001, the prediction error range was -0.05 to 0.07 mmol/L, and the deviation range was -18.52 to 13.04%; the mean absolute error was 0.03, and the mean prediction error deviation was between -10% and 10% in 33 cases (80.5%). CONCLUSIONS: The correlation, accuracy, and precision of ANN prediction are worthy to be further investigated to predict the blood concentration of Li carbonate.

Psychological Status and Job Burnout of Nurses Working in the Frontline of the Novel Coronavirus in China During the Delta Variant Outbreak: A Cross-Sectional Survey.

Purpose: Investigating psychological status and job burnout of nurses working in the frontline of the novel coronavirus in Zhangjiajie city in China during the Delta variant outbreak, comparing differences and analyzing factors of these two variables between the nurses from different nucleic acid testing (NAT) sites. Patients and methods: This survey was conducted from August 1 to 31, 2021. The participants were 512 nurses, 198 nurses of whom were from temporary NAT sites in communities/towns in Zhangjiajie city, and the rest were from NAT sites inside hospitals. The psychological status and the job burnout were measured by the Symptom Checklist-90 (SCL-90) and the Maslach Burnout Inventory-General Scale (MBI-GS). Results: The prevalence of the SCL-90 positive result and job burnout were 49.4% and 61.1%, respectively. The factors influencing the psychological status of nurses included the contact with COVID-19 patients or their body fluids and specimens, working seniority and the duration of working in the frontline of the novel coronavirus. The independent risk factors of nurses' job burnout included the following four factors. Firstly, the contact with COVID-19 patients or their body fluids and specimens (OR=150.95, 95% CI=(44.87,507.77), P<0.001). Secondly, five to nine years of working seniority (OR=8.91, 95% CI=(3.59,22.14), P<0.001). Thirdly, 10 to 19 days (OR=2.63, 95% CI=(1.19,5.82), P=0.017), 20 to 29 days (OR=161.31, 95% CI=(49.48,525.9), P<0.001). Lastly, more than 30 days (OR=92.05, 95% CI=(33.88,250.14), P<0.001) of working in the frontline of the novel coronavirus. Conclusion: The prevalence of psychological problems and job burnout were at a high level among nurses working in the frontline of the novel coronavirus in different NAT sites. The nurses from NAT sites inside hospitals and temporary NAT sites in communities/towns in Zhangjiajie city had an equal risk of developing psychological problems and job burnout. Interventions need to be immediately implemented to promote psychological well-being and decrease job burnout of nurses.

Prognostic value of enhancement rate by enhanced ultrasound in hepatitis B virus-positive hepatocellular carcinoma undergoing radiofrequency ablation.

AIM: To assess the prognostic significance of enhancement rate (ER) measured by contrast-enhanced ultrasonography (CEUS) in patients with hepatocellular carcinoma (HCC) undergoing radiofrequency ablation (RFA). MATERIALS AND METHODS: A total of 253 patients with single primary HCC undergoing preoperative CEUS and RFA were enrolled in this study. The ER were evaluated though pretreatment CEUS. After a mean follow-up of 36.8 ± 10.2 months, the correlation of ER measured by CEUS and survival after RFA was analyzed by univariate and multivariate analysis. The optimal cutoff ER value to predict survival was determined using receiver-operating characteristic analysis. RESULTS: Mean follow-up period for all 253 patients was 36.8 ± 10.2 months, 31.2% of patients had died at endpoint. The optimal cutoff ER value predicting survival was 2.2 dB/s. Univariate analysis demonstrated that patients with a high ER level had poorer OS (62.8 months vs 48.8 months, P = 0.02) and recurrence-free survival (RFS = 60.2 months vs 47.4 months, P = 0.03) than patients with a low ER level. ER measured by CEUS also been confirmed as independent risk factor for overall survival (hazard ratio [HR], 1.87; 95% confidence interval [95% CI], 1.21-7.25; P < 0.01) and RFS (HR, 1.67; 95% CI, 1.08-6.21; P < 0.01) in multivariate analysis enrolling gender, BMI, tumor size, antiviral therapy, HBV DNA, histological differentiation, Child-Pugh score and tumor node metastasis (TNM) stage. CONCLUSIONS: ER measured by CEUS was a significant predictive factor for survival after RFA for HCC.