<b>Signal Detection of Adverse Drug Reactions through LASSO Logistic Regression </b><b>Using an Electronic Health Records Database</b>：<b>A Case-Control Study </b>

DOI Web Site Web Site 13 References Open Access
  • HAYASHI Hiroshi
    Department of Healthcare Information Systems, School of Public Health, The University of Tokyo
  • HIRAMATSU Tatsuo
    Department of Healthcare Information Management, The University of Tokyo Hospital
  • KOIDE Daisuke
    Department of Clinical Epidemiology and Systems, Graduate School of Medicine, The University of Tokyo
  • TANAKA Katsuya
    Department of Healthcare Information Management, The University of Tokyo Hospital
  • OHE Kazuhiko
    Department of Healthcare Information Systems, School of Public Health, The University of Tokyo Department of Healthcare Information Management, The University of Tokyo Hospital

Bibliographic Information

Other Title
  • <b>電子カルテデータベースからの LASSO ロジスティック回帰による医薬品副作用シグナルの検出： ケース・コントロール研</b><b>究 </b>
  • 電子カルテデータベースからのLASSOロジスティック回帰による医薬品副作用シグナルの検出 : ケース・コントロール研究
  • デンシ カルテデータベース カラ ノ LASSO ロジスティック カイキ ニ ヨル イヤクヒン フクサヨウ シグナル ノ ケンシュツ : ケース ・ コントロール ケンキュウ

Search this article

Description

<p>Objective：The objective of this study was to apply Least Absolute Shrinkage and Selection Operator （LASSO）logistic regression to detection of adverse drug reaction （ADR） signals using an electronic health records database as a comprehensive and quantitative method to supplement the current pharmacovigilance activities in Japan.</p><p>Design：case-control study</p><p>Methods：We analyzed data from 40767 inpatients using a single-institution hospital database and identified two ADRs, suspected pancreatitis and thrombocytopenia, using abnormal laboratory test results. LASSO logistic regression analysis was applied to detect ADR signals with adjustment for age, sex, comorbidities and medical procedures. The positive predictive value （PPV） was calculated using reference standard of known drug-ADR associations based on drug product labels.</p><p>Results：The number of case group was 6735 for suspected pancreatitis and 11561 for thrombocytopenia. The number of ADR signals detected using LASSO logistic regression was 27 for suspected pancreatitis and 40 for thrombocytopenia. The calculated PPV was 3.7% for suspected pancreatitis and 55.0% for thrombocytopenia.</p><p>Conclusion：LASSO logistic regression analysis efficiently detects ADR signals by adjusting for confounding factors such as comorbidities and medical procedures. The false positive signals may contain unknown signals and further signal assessment will be needed.</p><p></p>

Journal

References(13)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top