The study data was collected from 47 Chinese healthy subjects in 2017 at the Second Affiliated Hospital of Zhejiang University, School of Medicine (Hangzhou, Zhejiang, China). Male and female volunteers who aged from 18 to 45 years with a body mass index between 19 and 26 kg∙m− 2 were enrolled. The inclusion criteria were as follows: (1) there were no clinically relevant abnormalities identified by subjects’ medical history, physical examination, clinical laboratory tests, vital signs, chest x-ray, and 12-lead ECG. (2) There were no smoke, drug or alcohol abuse allowed by subjects. (3) There were no breastfeeding, pregnant or childbearing potential of female subjects during the study. Subjects were excluded as follows: (1) there was any positive blood screen for HIV or hepatitis or any positive urine drug screen. (2) There was any hospital admission or major surgery, any donation of blood or acute loss of blood or any participation in other clinical trials within 3 months preceding the studies. (3) There was any heavy tea or coffee drinkers of more than 1 L/day. (4) There was any history of allergies to the study medicines or related substances.
2.2 Study Design and Safety Assessment
The study in was registered in ChicTR, the registration numbers were CTR20170876 and the full date of registration was 04/AUG/2017.A single dose of 20mg omeprazole tablet (AstraZeneca Pharmaceutical Co Ltd. Britain) was administered with 240 mL of water after an overnight fast. A high calorie meal was given within 30 minutes before drug administration and water was forbidden 1 hour before and after drug administration. Blood samples (2 mL each) were collected in K2EDTA anticoagulant tubes at predose and 0.5, 1, 1.5, 2, 2.5, 3, 3.5, 4, 4.5, 5, 6, 7, 8, 10, 12 hours postdose. The blood samples were centrifuged at 3000 g and stored at -80℃ until analysis. A validated liquid chromatography tandem mass spectrometry (LC-MS/MS) method was used to determine the plasma concentrations of Omeprazole by SHANGHAI XIHUA SCIENTIFIC CO., Ltd
For all studies, safety assessments included vital sign, 12-lead ECG, physical examinations, and clinical tests. Adverse events were evaluated with regard to their seriousness, intensity, time course, outcome, and relationship to the study drug.
2.3 Pharmacokinetic Statistical Analysis
Pharmacokinetic analysis was performed by WinNonlin software (Version 6.4, Pharsight Corporation, Mountain View, California), and a noncompartmental method was used to calculate pharmacokinetic parameters. 47 subjects were divided into low-age group ( < = 26years old, 24 subjects) and high-age group (> 26years old, 23 subjects) based on the calculation of the median age. Pharmacokinetic data from the low-age and high-age groups or male and female groups were compared by Student t-test.
2.4 PCA and PSO-BPANN modeling
All the data of 47 Chinese subjects of demographic characteristics as well as routine biochemical and hematological investigations were collected. A total of 12 variables were reconstruct and convert into independent or irrelative variables by Principal component analysis (PCA), which can lower the data dimension and maintain the most original variable information. Main calculation procedures of PCA are as follows: (1) the data of Chinese subjects collected was carried out on standardized processing. (2) The characteristic value and feature vector of the correlation coefficient matrix R were calculated to make up new indicator variables. (3) The mprincipal components were chosen and the information contribution rate and accumulated contribution rate were calculated.
Particle Swarm Optimization (PSO), presented by Eberhart and Kennedy in 1995, was a heuristic and evolutionary algorithm which inspired by the behavior of birds to locate desirable positions in a given area through cooperation and competition . Some entities, called particles, were scattered in the search space in the PSO. The position of each particle represents a possible solution and each solution is the way that in the search of a position in a space, particles change the flying distance and directions via changing the speed. Each particle remembers its optimal position piD in the searching history in the iteration process. All the optimal positions of all particles is the global optimal position pgD. The equation and parameter of particle movement are as follows:
Where i, j, D stand for the particle, the current iteration amount and the particle dimension, respectively. and are the velocity and position in the j iteration. Non-negative constant c1 and c2 are the learning factor, which determines the effects of and on the new velocity. r1 and r2 are the pseudo random amount evenly distributed in the interval [0, 1]. ω is the inertia weight, adjusting the searching ability in the solution domain [12, 13].
BPANN is a kind of machine learning technology which minimized the error between the network outputs and the desired outputs, adjusted the weights and biases by a small amount at a time through a gradient-based procedure[14, 15].The BPANN comprises two procedures: a forward stage where the input signals moved forward through the network and a backward stage where the error is propagated backward from the output layer to the input layer. The error is calculated in the output layer and the parameters is updated for the direction in which the performance function most rapidly decreases.
Although the BPANN algorithm is widely used, it might become stuck at the local minimum if the initial weights and biases are far from the optimal values that can give the global optimal solutions. Several metaheuristic optimization algorithms, such as PSO, genetic algorithm, and harmony search algorithm were combined with BPANN to overcome this shortcoming [17–19]. In this study, PSO had been chosen to improve the performance of BPANN due to its simplicity and wide applicability. Through the global search ability of the PSO algorithm, the initial weights and biases of the BPANN were obtained and the true global optimization and performance improvement were found. The overall calculation process was shown in Fig. 1.