Estimating the Optimal Dexketoprofen Pharmaceutical Formulation with Machine Learning Methods and Statistical Approaches

다국어 초록 (Multilingual Abstract)

Objectives: Orally disintegrating tablets (ODTs) can be utilized without any drinking water; this feature makes ODTs easy touse and suitable for specific groups of patients. Oral administration of drugs is the most commonly used route, and tabletsconstitute the most preferable pharmaceutical dosage form. However, the preparation of ODTs is costly and requires longtrials, which creates obstacles for dosage trials. The aim of this study was to identify the most appropriate formulation usingmachine learning (ML) models of ODT dexketoprofen formulations, with the goal of providing a cost-effective and timereducingsolution. Methods: This research utilized nonlinear regression models, including the k-nearest neighborhood (k-NN), support vector regression (SVR), classification and regression tree (CART), bootstrap aggregating (bagging), randomforest (RF), gradient boosting machine (GBM), and extreme gradient boosting (XGBoost) methods, as well as the t-test, topredict the quantity of various components in the dexketoprofen formulation within fixed criteria. Results: All the modelswere developed with Python libraries. The performance of the ML models was evaluated with R2 values and the root meansquare error. Hardness values of 0.99 and 2.88, friability values of 0.92 and 0.02, and disintegration time values of 0.97 and10.09 using the GBM algorithm gave the best results. Conclusions: In this study, we developed a computational approach toestimate the optimal pharmaceutical formulation of dexketoprofen. The results were evaluated by an expert, and it was foundthat they complied with Food and Drug Administration criteria.

참고문헌 (Reference)

1 Chen T, "XgBoost: a scalable tree boosting system" 785-794, 2016

2 Probst P, "Tunability : importance of hyperparameters of machine learning algorithms" 20 (20): 1934-1965, 2019

3 Wu X, "Top 10 algorithms in data mining" 14 (14): 1-37, 2008

4 Kara I, "The effects of preemptive dexketoprofen use on postoperative pain relief and tramadol consumption" 23 (23): 18-21, 2011

5 McKnight PE, "The Corsini encyclopedia of psychology" John Wiley & Sons 2010

6 김태균, "T test as a parametric statistic" 대한마취통증의학회 68 (68): 540-546, 2015

7 Gunn SR, "Support vector machines for classification and regression" University of Southampton 1998

8 Mesut B, "Statistical investigation of the effect of excipients particle size on orally disintegrating tablets : mannitol grades" 31 (31): 69-91, 2020

9 Center for Drug Evaluation and Research, "Scale-up and postapproval changes: chemistry, manufacturing, and controls: in vitro dissolution testing, and in vivo bioequivalence documentation" Food and Drug Administration

10 Breiman L, "Random forests" 45 (45): 5-32, 2001

11 US Food and Drug Administration, "Q6A specifications:test procedures and acceptance criteria for new drug substances and new drug products: chemical substances" Food and Drug Administration

12 Mohammad Moqaddasi Amiri, "Prediction of Serum Creatinine in Hemodialysis Patients Using a Kernel Approach for Longitudinal Data" 대한의료정보학회 26 (26): 112-118, 2020

13 Selma Dere, "Prediction of Drug–Drug Interactions by Using Profile Fingerprint Vectors and Protein Similarities" 대한의료정보학회 26 (26): 42-49, 2020

14 Ghasemi A, "Normality tests for statistical analysis : a guide for non-statisticians" 10 (10): 486-489, 2012

15 O'Neill ME, "Levene tests of homogeneity of variance for general block and treatment designs" 58 (58): 216-224, 2002

16 European Medicines Agency, "ICH topic Q6a specifications:Test procedures and acceptance criteria for new drug substances and new drug products: Chemical substances" European Medicines Agency

17 Friedman JH, "Greedy function approximation : a gradient boosting machine" 29 (29): 1189-1232, 2001

18 Vetter TR, "Fundamentals of research data and variables : the devil is in the details" 125 (125): 1375-1380, 2017

19 Mesut B, "Design of sustained release tablet formulations of alfuzosin HCl by means of neurofuzzy logic" 32 (32): 1288-1297, 2013

20 Ezcurdia M, "Comparison of the efficacy and tolerability of dexketoprofen and ketoprofen in the treatment of primary dysmenorrhea" (38) : 65S-73S, 1998

21 Adebowale A, "Comparative study of selected data mining algorithms used for intrusion detection" 3 (3): 237-241, 2013

22 Breiman L, "Bagging predictors" 24 (24): 123-140, 1996

23 Ahamad MM, "A machine learning model to identify early stage symptoms of SARS-Cov-2 infected patients" 160 : 113661-, 2020