Search

Data curation has significant research implications irrespective of application areas. As most curated studies rely on databases for data extraction, the availability of data resources is extremely important. Taking a perspective from pharmacology, extracted data contribute to improved drug treatment outcomes and well-being but with some challenges. Considering available pharmacology literature, it is necessary to review articles and other scientific documents carefully. A typical method of accessing articles on journal websites is through long-established searches. In addition to being labor-intensive, this conventional approach often leads to incomplete-content downloads. This paper presents a new methodology with user-friendly models to accept search keywords according to the investigators' research fields for metadata and full-text articles. To accomplish this, scientifically published records on the pharmacokinetics of drugs were extracted from several sources using our navigating tool called the Web Crawler for Pharmacokinetics (WCPK). The results of metadata extraction provided 74,867 publications for four drug classes. Full-text extractions performed with WCPK revealed that the system is highly competent, extracting over 97% of records. This model helps establish keyword-based article repositories, contributing to comprehensive databases for article curation projects. This paper also explains the procedures adopted to build the proposed customizable-live WCPK, from system design and development to deployment phases.

Statement of Problem: Information on predicting the measurements of the nose from selected facial landmarks to assist in maxillofacial prosthodontics is lacking., Purpose: The objective of this study was to identify the efficiency of machine learning models in predicting the length and width of the nose from selected facial landmarks., Material and Methods: Two-dimensional frontal and lateral photographs were made of 100 men and 100 women. Different eye, nose, and ear landmarks were manually measured on the digital images. Various machine learning regression techniques were validated to confirm the accuracy of the length of the nose (LON), nasal bridge length (NBL), lateral alar width (LAW), and nasal tip protrusion (NTP)., Results: The regression models used in this study to predict the width and length of the nose parameters demonstrated a robust predictive capability, as evidenced by the high coefficient of determination score obtained (greater than 0.95). This coefficient of determination suggested the implemented model was able to effectively capture the underlying patterns and relationships within the data, leading to enhanced efficiency in predicting the outcomes. SHapley Additive ExPlanations values demonstrated that for the men-only and women-only datasets, the measurement of the auricular projection was the most important predictor of the LAW, the ear length was the most significant contributor to the LON, and the angle between the nasal bridge length and the ear length was the most significant contributor to the NBL and NTP. For the combined datasets, the distance between the superior edge of the ear to the line measuring the medial canthus width contributed most to the LON and NBL, the ear length was the most significant contributor to LAW, and the angle between the nasal bridge length and the ear length was the most significant predictor of NTP., Conclusions: All selected algorithms provided precise width and length predictions for all data groups and were highly correlated with the actual value. The frontal images can be used to predict the LON and LAW, whereas the lateral images can be used to evaluate the NBL and NTP., (Published by Elsevier Inc.)