1.Prediction of Milk Transfer of Drugs Using Machine Learning Methods
Takamasa SAKAI ; Kazuki MATSUI ; Sohma MIURA ; Masaki SASSA ; Hiroshi SAKATA ; Fumiko OHTSU
Japanese Journal of Drug Informatics 2022;24(3):145-153
Objective: Currently, limited information is available on the milk transfer properties of drugs when consumed by lactating women. Therefore, we aim to construct a prediction model of milk transfer of drugs using machine learning methods.Methods: We obtained data from Hale’s Medications & Mothers’ Milk (MMM) and SciFinder®, and then constructed the datasets. The physicochemical and pharmacokinetic data were used as feature variables with M/P ratio ≥ 1 and M/P ratio < 1 as the objective variables, classified into two groups as the classification of milk transferability. In this study, analyses were conducted using machine learning methods: logistic regression, linear support vector machine (linear SVM), kernel method support vector machine (kernel SVM), random forest, and k-nearest neighbor classification. The results were compared to those obtained with the linear regression equation of Yamauchi et al. from a previous study. The analysis was performed using scikit-learn (version 0.24.2) with python (version 3.8.10).Results: Model construction and validation were performed on the training data comprising 159 drugs. The results revealed that the random forest had the highest accuracy, area under the receiver operating characteristic curve (AUC), and F value. Additionally, the results with test data A and B (n = 36, 31), which were not used for training, showed that both F value and accuracy for the random forest and the kernel method SVM exceeded those with the linear regression equation of Yamauchi et al. Conclusion: We were able to construct a predictive model of milk transferability with relatively high performance using a machine learning method capable of nonlinear separation. The predictive model in this study can be applied to drugs with unknown M/P ratios for providing a new source of information on milk transfer.
2.Seven days triple therapy for eradication of Helicobacter pylori does not alter the disease activity of patients with inflammatory bowel disease.
Shinichiro SHINZAKI ; Toshimitsu FUJII ; Shigeki BAMBA ; Maiko OGAWA ; Taku KOBAYASHI ; Masahide OSHITA ; Hiroki TANAKA ; Keiji OZEKI ; Sakuma TAKAHASHI ; Hiroki KITAMOTO ; Kazuhito KANI ; Sohachi NANJO ; Takeshi SUGAYA ; Yuko SAKAKIBARA ; Toshihiro INOKUCHI ; Kazuki KAKIMOTO ; Akihiro YAMADA ; Hisae YASUHARA ; Yoko YOKOYAMA ; Takuya YOSHINO ; Akira MATSUI ; Misaki NAKAMURA ; Taku TOMIZAWA ; Ryosuke SAKEMI ; Noriko KAMATA ; Toshifumi HIBI
Intestinal Research 2018;16(4):609-618
BACKGROUND/AIMS: The influences of Helicobacter pylori eradication therapy on the disease course of inflammatory bowel disease (IBD) are still unclear. We therefore conducted a multicenter, retrospective cohort study to evaluate the safety of H. pylori eradication therapy for IBD patients. METHODS: IBD patients with H. pylori eradication from 2005 to 2015 (eradication group) and control patients (non-eradication group; 2 paired IBD patients without H. pylori eradication matched with each eradicated patient) were included. IBD exacerbation (increased/additional IBD drug or IBD-associated hospitalization/surgery) and disease improvement based on the physicians’ global assessment were investigated at baseline, and at 2 and 6 months after eradication or observation. RESULTS: A total of 429 IBD (378 ulcerative colitis, 51 Crohn’s disease) patients, comprising 144 patients in the eradication group and 285 patients in the non-eradication group, were enrolled at 25 institutions. IBD exacerbation was comparable between groups (eradication group: 8.3% at 2 months [odds ratio, 1.76; 95% confidence interval, 0.78–3.92; P=0.170], 11.8% at 6 months [odds ratio, 1.60; 95% confidence interval, 0.81–3.11; P=0.172]). Based on the physicians’ global assessment at 2 months, none of the patients in the eradication group improved, whereas 3.2% of the patients in the non-eradication group improved (P=0.019). Multivariate analysis revealed that active disease at baseline, but not H. pylori eradication, was an independent factor for IBD exacerbation during 2 months’ observation period. The overall eradication rate was 84.0%–comparable to previous reports in non-IBD patients. CONCLUSIONS: H. pylori eradication therapy does not alter the short-term disease activity of IBD.
Clarithromycin
;
Cohort Studies
;
Colitis, Ulcerative
;
Helicobacter pylori*
;
Helicobacter*
;
Humans
;
Inflammatory Bowel Diseases*
;
Metronidazole
;
Multivariate Analysis
;
Retrospective Studies