Drug prescription support in dental clinics through drug corpus mining

Wee Pheng GOH, Xiaohui TAO, Ji ZHANG, Jianming YONG, Wenping ZHANG, Haoran XIE

Research output: Journal PublicationsJournal Article (refereed)

Abstract

The rapid increase in the volume and variety of data poses a challenge to safe drug prescription for the dentist. The increasing number of patients that take multiple drugs further exerts pressure on the dentist to make the right decision at point-of-care. Hence, a robust decision support system will enable dentists to make decisions on drug prescription quickly and accurately. Based on the assumption that similar drug pairs have a higher similarity ratio, this paper suggests an innovative approach to obtain the similarity ratio between the drug that the dentist is going to prescribe and the drug that the patient is currently taking. We conducted experiments to obtain the similarity ratios of both positive and negative drug pairs, by using feature vectors generated from term similarities and word embeddings of biomedical text corpus. This model can be easily adapted and implemented for use in a dental clinic to assist the dentist in deciding if a drug is suitable for prescription, taking into consideration the medical profile of the patients. Experimental evaluation of our model’s association of the similarity ratio between two drugs yielded a superior F score of 89%. Hence, such an approach, when integrated within the clinical work flow, will reduce prescription errors and thereby increase the health outcomes of patients.

Original languageEnglish
Pages (from-to)341-349
Number of pages9
JournalInternational Journal of Data Science and Analytics
Volume6
Issue number4
Early online date18 Aug 2018
DOIs
Publication statusPublished - Dec 2018
Externally publishedYes

Fingerprint

Dental Clinics
Drug Prescriptions
Dentists
Pharmaceutical Preparations
Prescriptions
Point-of-Care Systems
Workflow
Pressure
Health

Bibliographical note

This paper is an extension version of the PAKDD 2017 Long Presentation paper “Mining Drug Properties for Decision Support in Dental Clinics”.
This research is partially supported by Glory Dental Surgery (Roxy Square) Pte Ltd, Singapore (http://glory.sg), and undertaken collaboratively with their panel of dentists.

Keywords

  • Adverse relationship
  • Word embeddings
  • Term similarity
  • Personalised prescription
  • Drug properties

Cite this

GOH, Wee Pheng ; TAO, Xiaohui ; ZHANG, Ji ; YONG, Jianming ; ZHANG, Wenping ; XIE, Haoran. / Drug prescription support in dental clinics through drug corpus mining. In: International Journal of Data Science and Analytics. 2018 ; Vol. 6, No. 4. pp. 341-349.
@article{1656975648bf4f2f8bd1472d73399353,
title = "Drug prescription support in dental clinics through drug corpus mining",
abstract = "The rapid increase in the volume and variety of data poses a challenge to safe drug prescription for the dentist. The increasing number of patients that take multiple drugs further exerts pressure on the dentist to make the right decision at point-of-care. Hence, a robust decision support system will enable dentists to make decisions on drug prescription quickly and accurately. Based on the assumption that similar drug pairs have a higher similarity ratio, this paper suggests an innovative approach to obtain the similarity ratio between the drug that the dentist is going to prescribe and the drug that the patient is currently taking. We conducted experiments to obtain the similarity ratios of both positive and negative drug pairs, by using feature vectors generated from term similarities and word embeddings of biomedical text corpus. This model can be easily adapted and implemented for use in a dental clinic to assist the dentist in deciding if a drug is suitable for prescription, taking into consideration the medical profile of the patients. Experimental evaluation of our model’s association of the similarity ratio between two drugs yielded a superior F score of 89{\%}. Hence, such an approach, when integrated within the clinical work flow, will reduce prescription errors and thereby increase the health outcomes of patients.",
keywords = "Adverse relationship, Word embeddings, Term similarity, Personalised prescription, Drug properties",
author = "GOH, {Wee Pheng} and Xiaohui TAO and Ji ZHANG and Jianming YONG and Wenping ZHANG and Haoran XIE",
note = "This paper is an extension version of the PAKDD 2017 Long Presentation paper “Mining Drug Properties for Decision Support in Dental Clinics”. This research is partially supported by Glory Dental Surgery (Roxy Square) Pte Ltd, Singapore (http://glory.sg), and undertaken collaboratively with their panel of dentists.",
year = "2018",
month = "12",
doi = "10.1007/s41060-018-0149-3",
language = "English",
volume = "6",
pages = "341--349",
journal = "International Journal of Data Science and Analytics",
issn = "2364-415X",
number = "4",

}

Drug prescription support in dental clinics through drug corpus mining. / GOH, Wee Pheng; TAO, Xiaohui; ZHANG, Ji; YONG, Jianming; ZHANG, Wenping; XIE, Haoran.

In: International Journal of Data Science and Analytics, Vol. 6, No. 4, 12.2018, p. 341-349.

Research output: Journal PublicationsJournal Article (refereed)

TY - JOUR

T1 - Drug prescription support in dental clinics through drug corpus mining

AU - GOH, Wee Pheng

AU - TAO, Xiaohui

AU - ZHANG, Ji

AU - YONG, Jianming

AU - ZHANG, Wenping

AU - XIE, Haoran

N1 - This paper is an extension version of the PAKDD 2017 Long Presentation paper “Mining Drug Properties for Decision Support in Dental Clinics”. This research is partially supported by Glory Dental Surgery (Roxy Square) Pte Ltd, Singapore (http://glory.sg), and undertaken collaboratively with their panel of dentists.

PY - 2018/12

Y1 - 2018/12

N2 - The rapid increase in the volume and variety of data poses a challenge to safe drug prescription for the dentist. The increasing number of patients that take multiple drugs further exerts pressure on the dentist to make the right decision at point-of-care. Hence, a robust decision support system will enable dentists to make decisions on drug prescription quickly and accurately. Based on the assumption that similar drug pairs have a higher similarity ratio, this paper suggests an innovative approach to obtain the similarity ratio between the drug that the dentist is going to prescribe and the drug that the patient is currently taking. We conducted experiments to obtain the similarity ratios of both positive and negative drug pairs, by using feature vectors generated from term similarities and word embeddings of biomedical text corpus. This model can be easily adapted and implemented for use in a dental clinic to assist the dentist in deciding if a drug is suitable for prescription, taking into consideration the medical profile of the patients. Experimental evaluation of our model’s association of the similarity ratio between two drugs yielded a superior F score of 89%. Hence, such an approach, when integrated within the clinical work flow, will reduce prescription errors and thereby increase the health outcomes of patients.

AB - The rapid increase in the volume and variety of data poses a challenge to safe drug prescription for the dentist. The increasing number of patients that take multiple drugs further exerts pressure on the dentist to make the right decision at point-of-care. Hence, a robust decision support system will enable dentists to make decisions on drug prescription quickly and accurately. Based on the assumption that similar drug pairs have a higher similarity ratio, this paper suggests an innovative approach to obtain the similarity ratio between the drug that the dentist is going to prescribe and the drug that the patient is currently taking. We conducted experiments to obtain the similarity ratios of both positive and negative drug pairs, by using feature vectors generated from term similarities and word embeddings of biomedical text corpus. This model can be easily adapted and implemented for use in a dental clinic to assist the dentist in deciding if a drug is suitable for prescription, taking into consideration the medical profile of the patients. Experimental evaluation of our model’s association of the similarity ratio between two drugs yielded a superior F score of 89%. Hence, such an approach, when integrated within the clinical work flow, will reduce prescription errors and thereby increase the health outcomes of patients.

KW - Adverse relationship

KW - Word embeddings

KW - Term similarity

KW - Personalised prescription

KW - Drug properties

U2 - 10.1007/s41060-018-0149-3

DO - 10.1007/s41060-018-0149-3

M3 - Journal Article (refereed)

VL - 6

SP - 341

EP - 349

JO - International Journal of Data Science and Analytics

JF - International Journal of Data Science and Analytics

SN - 2364-415X

IS - 4

ER -