Clozapine is the most effective drug for treatment-resistant schizophrenia, and the dosage and concentration of clozapine in the treatment of mental illness vary greatly in different populations and are affected by many factors.
The serum clozapine concentration of 3734 psychiatric patients was detected, and data on daily dose, sex, age and other medical records were collected for statistical analysis.
The mean daily dose, mean serum concentration and mean C/D (concentration/dose) ratio of clozapine were 191.02 ± 113.47 mg/day, 326.15 ± 235.66 ng/mL and 1.94 ± 1.25 ng/mL per mg/day, respectively. There was difference in daily dose between sexes, and females had higher daily dose (p <0.01), higher serum clozapine concentrations (p < 0.01) and higher C/D ratios (p < 0.01). There were significant differences in daily dose (p < 0.001), serum drug concentration (p < 0.001) and C/D ratio (p < 0.001) among different age groups. The daily dose decreased with age (p for trend < 0.001), and the C/D ratio increased with age (p for trend < 0.001). Inpatients and outpatients had no difference in daily dose, but inpatients had higher serum concentration (p < 0.001) and C/D ratio (p < 0.001). There was no difference in daily dose among different occupations, but there were significant differences in serum concentration (p < 0.001) and C/D ratio (p < 0.001), and unemployed patients may have higher serum concentration and C/D ratio. Duration of disease, comorbidity, marital status, and psychotic type may influence the daily dose and serum concentration.
The effective daily dose and serum concentration of clozapine in the study area may be lower than recommended levels, and women have higher serum concentrations and slower metabolic rates. With increasing age, the daily dose decreases, and the metabolic rate slows. Inpatient status and occupation of patients may influence the serum concentration and metabolic rate of clozapine.

Tacrolimus is a major immunosuppressor against post-transplant rejection in kidney transplant recipients. However, the narrow therapeutic index of tacrolimus and considerable variability among individuals are challenges for therapeutic outcomes. The aim of this study was to compare different machine learning and deep learning algorithms and establish individualized dose prediction models by using the best performing algorithm. Therefore, among the 10 commonly used algorithms we compared, the TabNet algorithm outperformed other algorithms with the highest R2 (0.824), the lowest prediction error [mean absolute error (MAE) 0.468, mean square error (MSE) 0.558, and root mean square error (RMSE) 0.745], and good performance of overestimated (5.29%) or underestimated dose percentage (8.52%). In the final prediction model, the last tacrolimus daily dose, the last tacrolimus therapeutic drug monitoring value, time after transplantation, hematocrit, serum creatinine, aspartate aminotransferase, weight, CYP3A5, body mass index, and uric acid were the most influential variables on tacrolimus daily dose. Our study provides a reference for the application of deep learning technique in tacrolimus dose estimation, and the TabNet model with desirable predictive performance is expected to be expanded and applied in future clinical practice.

The personal exposure of 51 graduate students to PM2.5 and BC in Shanghai was evaluated using portable PM2.5 and BC samplers. Global positioning systems and activity diaries were used to evaluate the microenvironments/activities that contributed to the total daily exposure of the participants, as well as to accurately estimate the PM2.5 and BC doses received by each participant. The mean PM2.5 and BC exposure concentrations were 110.0 and 5.3 μg m(-3), respectively. These exposure levels were considered extremely high and comparable to those measured in a busy urban street canyon for 24 h. High daily inhaled doses in terms of both PM2.5 and BC concentrations were measured, obtaining 1062.2 and 45.9 μg day(-1), respectively. Indoor activities significantly contributed to the students\' daily dose. Eating contributed the least to PM2.5 and BC exposure, whereas outdoor activities contributed the most. PM2.5 dose intensity from indoor eating slightly exceeded BC dose intensity; conversely, transportation showed higher exposure for BC than PM2.5.