Prediction and factor extraction of drug function by analyzing medical records in developing countries

Min Hu, Yasunobu Nohara, Masafumi Nakamura, Naoki Nakashima

研究成果: 著書/レポートタイプへの貢献会議での発言

抄録

The World Health Organization has declared Bangladesh one of 58 countries facing acute Human Resources for Health (HRH) crisis. Artificial intelligence in healthcare has been shown to be successful for diagnostics. Using machine learning to predict pharmaceutical prescriptions may solve HRH crises. In this study, we investigate a predictive model by analyzing prescription data of 4,543 subjects in Bangladesh. We predict the function of prescribed drugs, comparing three machine-learning approaches. The approaches compare whether a subject shall be prescribed medicine from the 21 most frequently prescribed drug functions. Receiver Operating Characteristics (ROC) were selected as a way to evaluate and assess prediction models. The results show the drug function with the best prediction performance was oral hypoglycemic drugs, which has an average AUC of 0.962. To understand how the variables affect prediction, we conducted factor analysis based on tree-based algorithms and natural language processing techniques.

元の言語英語
ホスト出版物のタイトルMEDINFO 2017
ホスト出版物のサブタイトルPrecision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics
編集者Zhao Dongsheng, Adi V. Gundlapalli, Jaulent Marie-Christine
出版者IOS Press
ページ403-407
ページ数5
ISBN(電子版)9781614998297
DOI
出版物ステータス出版済み - 1 1 2017
イベント16th World Congress of Medical and Health Informatics: Precision Healthcare through Informatics, MedInfo 2017 - Hangzhou, 中国
継続期間: 8 21 20178 25 2017

出版物シリーズ

名前Studies in Health Technology and Informatics
245
ISSN(印刷物)0926-9630
ISSN(電子版)1879-8365

その他

その他16th World Congress of Medical and Health Informatics: Precision Healthcare through Informatics, MedInfo 2017
中国
Hangzhou
期間8/21/178/25/17

Fingerprint

Developing countries
Developing Countries
Medical Records
Health
Bangladesh
Learning systems
Health Resources
Personnel
Pharmaceutical Preparations
Prescriptions
Trees (mathematics)
Natural Language Processing
Factor analysis
Drug products
Artificial intelligence
Artificial Intelligence
Hypoglycemic Agents
ROC Curve
Statistical Factor Analysis
Area Under Curve

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

これを引用

Hu, M., Nohara, Y., Nakamura, M., & Nakashima, N. (2017). Prediction and factor extraction of drug function by analyzing medical records in developing countries. : Z. Dongsheng, A. V. Gundlapalli, & J. Marie-Christine (版), MEDINFO 2017: Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics (pp. 403-407). (Studies in Health Technology and Informatics; 巻数 245). IOS Press. https://doi.org/10.3233/978-1-61499-830-3-403

Prediction and factor extraction of drug function by analyzing medical records in developing countries. / Hu, Min; Nohara, Yasunobu; Nakamura, Masafumi; Nakashima, Naoki.

MEDINFO 2017: Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics. 版 / Zhao Dongsheng; Adi V. Gundlapalli; Jaulent Marie-Christine. IOS Press, 2017. p. 403-407 (Studies in Health Technology and Informatics; 巻 245).

研究成果: 著書/レポートタイプへの貢献会議での発言

Hu, M, Nohara, Y, Nakamura, M & Nakashima, N 2017, Prediction and factor extraction of drug function by analyzing medical records in developing countries. : Z Dongsheng, AV Gundlapalli & J Marie-Christine (版), MEDINFO 2017: Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics. Studies in Health Technology and Informatics, 巻. 245, IOS Press, pp. 403-407, 16th World Congress of Medical and Health Informatics: Precision Healthcare through Informatics, MedInfo 2017, Hangzhou, 中国, 8/21/17. https://doi.org/10.3233/978-1-61499-830-3-403
Hu M, Nohara Y, Nakamura M, Nakashima N. Prediction and factor extraction of drug function by analyzing medical records in developing countries. : Dongsheng Z, Gundlapalli AV, Marie-Christine J, 編集者, MEDINFO 2017: Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics. IOS Press. 2017. p. 403-407. (Studies in Health Technology and Informatics). https://doi.org/10.3233/978-1-61499-830-3-403
Hu, Min ; Nohara, Yasunobu ; Nakamura, Masafumi ; Nakashima, Naoki. / Prediction and factor extraction of drug function by analyzing medical records in developing countries. MEDINFO 2017: Precision Healthcare through Informatics - Proceedings of the 16th World Congress on Medical and Health Informatics. 編集者 / Zhao Dongsheng ; Adi V. Gundlapalli ; Jaulent Marie-Christine. IOS Press, 2017. pp. 403-407 (Studies in Health Technology and Informatics).
@inproceedings{5aff5f688ddf4bc4ba0969b8f0028e3c,
title = "Prediction and factor extraction of drug function by analyzing medical records in developing countries",
abstract = "The World Health Organization has declared Bangladesh one of 58 countries facing acute Human Resources for Health (HRH) crisis. Artificial intelligence in healthcare has been shown to be successful for diagnostics. Using machine learning to predict pharmaceutical prescriptions may solve HRH crises. In this study, we investigate a predictive model by analyzing prescription data of 4,543 subjects in Bangladesh. We predict the function of prescribed drugs, comparing three machine-learning approaches. The approaches compare whether a subject shall be prescribed medicine from the 21 most frequently prescribed drug functions. Receiver Operating Characteristics (ROC) were selected as a way to evaluate and assess prediction models. The results show the drug function with the best prediction performance was oral hypoglycemic drugs, which has an average AUC of 0.962. To understand how the variables affect prediction, we conducted factor analysis based on tree-based algorithms and natural language processing techniques.",
author = "Min Hu and Yasunobu Nohara and Masafumi Nakamura and Naoki Nakashima",
year = "2017",
month = "1",
day = "1",
doi = "10.3233/978-1-61499-830-3-403",
language = "English",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press",
pages = "403--407",
editor = "Zhao Dongsheng and Gundlapalli, {Adi V.} and Jaulent Marie-Christine",
booktitle = "MEDINFO 2017",
address = "Netherlands",

}

TY - GEN

T1 - Prediction and factor extraction of drug function by analyzing medical records in developing countries

AU - Hu, Min

AU - Nohara, Yasunobu

AU - Nakamura, Masafumi

AU - Nakashima, Naoki

PY - 2017/1/1

Y1 - 2017/1/1

N2 - The World Health Organization has declared Bangladesh one of 58 countries facing acute Human Resources for Health (HRH) crisis. Artificial intelligence in healthcare has been shown to be successful for diagnostics. Using machine learning to predict pharmaceutical prescriptions may solve HRH crises. In this study, we investigate a predictive model by analyzing prescription data of 4,543 subjects in Bangladesh. We predict the function of prescribed drugs, comparing three machine-learning approaches. The approaches compare whether a subject shall be prescribed medicine from the 21 most frequently prescribed drug functions. Receiver Operating Characteristics (ROC) were selected as a way to evaluate and assess prediction models. The results show the drug function with the best prediction performance was oral hypoglycemic drugs, which has an average AUC of 0.962. To understand how the variables affect prediction, we conducted factor analysis based on tree-based algorithms and natural language processing techniques.

AB - The World Health Organization has declared Bangladesh one of 58 countries facing acute Human Resources for Health (HRH) crisis. Artificial intelligence in healthcare has been shown to be successful for diagnostics. Using machine learning to predict pharmaceutical prescriptions may solve HRH crises. In this study, we investigate a predictive model by analyzing prescription data of 4,543 subjects in Bangladesh. We predict the function of prescribed drugs, comparing three machine-learning approaches. The approaches compare whether a subject shall be prescribed medicine from the 21 most frequently prescribed drug functions. Receiver Operating Characteristics (ROC) were selected as a way to evaluate and assess prediction models. The results show the drug function with the best prediction performance was oral hypoglycemic drugs, which has an average AUC of 0.962. To understand how the variables affect prediction, we conducted factor analysis based on tree-based algorithms and natural language processing techniques.

UR - http://www.scopus.com/inward/record.url?scp=85040517273&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040517273&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-830-3-403

DO - 10.3233/978-1-61499-830-3-403

M3 - Conference contribution

C2 - 29295125

AN - SCOPUS:85040517273

T3 - Studies in Health Technology and Informatics

SP - 403

EP - 407

BT - MEDINFO 2017

A2 - Dongsheng, Zhao

A2 - Gundlapalli, Adi V.

A2 - Marie-Christine, Jaulent

PB - IOS Press

ER -