Literature mining on pharmacokinetics numerical data: a feasibility study

Abstract

A feasibility study of literature mining is conducted on drug PK parameter numerical data with a sequential mining strategy. Firstly, an entity template library is built to retrieve pharmacokinetics relevant articles. Then a set of tagging and extraction rules are applied to retrieve PK data from the article abstracts. To estimate the PK parameter population-average mean and between-study variance, a linear mixed meta-analysis model and an E-M algorithm are developed to describe the probability distributions of PK parameters. Finally, a cross-validation procedure is developed to ascertain false-positive mining results. Using this approach to mine midazolam (MDZ) PK data, an 88% precision rate and 92% recall rate are achieved, with an F-score=90%. It greatly out-performs a conventional data mining approach (support vector machine), which has an F-score of 68.1%. Further investigate on 7 more drugs reveals comparable performances of our sequential mining approach.

Figure 1

The Architecture of Literature Mining tool

Figure 2

Precision Performance Analysis of the Machine Learning Algorithm in all MDZ Related Abstracts

Figure 3

The Estimated Clearance Distribution Note: The BLUE curve shows systemic clearance; the GREEN curve shows oral clearance. The 95% confidence interval is marked on each curve using vertical lines.

Figure 4

MDZ Clearance Data Note: (a) contains all mined MDZ clearance data before evaluation and outlier removal, and (b) contains the MDZ clearance data after evaluation outlier removal. The BLUE dots are true clearance data from MDZ PK relevant abstracts; the RED and GREEN dots are false MDZ clearance data, in which the red ones were removed by EM validation as outliers and green ones were not.

Figure 5

Recall and Precision Performance Analysis of the Machine Learning Algorithm in a MDZ Abstracts Subset