Le Zhang, Tyra Lagerberg, Qi Chen, Laura Ghirardi, Brian M D'Onofrio, Henrik Larsson, Alexander Viktorin, Zheng Chang
{"title":"Prediction of treatment dosage and duration from free-text prescriptions: an application to ADHD medications in the Swedish prescribed drug register.","authors":"Le Zhang, Tyra Lagerberg, Qi Chen, Laura Ghirardi, Brian M D'Onofrio, Henrik Larsson, Alexander Viktorin, Zheng Chang","doi":"10.1136/ebmental-2020-300231","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Accurate estimation of daily dosage and duration of medication use is essential to pharmacoepidemiological studies using electronic healthcare databases. However, such information is not directly available in many prescription databases, including the Swedish Prescribed Drug Register.</p><p><strong>Objective: </strong>To develop and validate an algorithm for predicting prescribed daily dosage and treatment duration from free-text prescriptions, and apply the algorithm to ADHD medication prescriptions.</p><p><strong>Methods: </strong>We developed an algorithm to predict daily dosage from free-text prescriptions using 8000 ADHD medication prescriptions as the training sample, and estimated treatment periods while taking into account several features including titration, stockpiling and non-perfect adherence. The algorithm was implemented to all ADHD medication prescriptions from the Swedish Prescribed Drug Register in 2013. A validation sample of 1000 ADHD medication prescriptions, independent of the training sample, was used to assess the accuracy for predicted daily dosage.</p><p><strong>Findings: </strong>In the validation sample, the overall accuracy for predicting daily dosage was 96.8%. Specifically, the natural language processing model (NLP1 and NLP2) have an accuracy of 99.2% and 96.3%, respectively. In an application to ADHD medication prescriptions in 2013, young adult ADHD medication users had the highest probability of discontinuing treatments as compared with other age groups. The daily dose of methylphenidate use increased with age substantially.</p><p><strong>Conclusions: </strong>The algorithm provides a flexible approach to estimate prescribed daily dosage and treatment duration from free-text prescriptions using register data. The algorithm showed a good performance for predicting daily dosage in external validation.</p><p><strong>Clinical implications: </strong>The structured output of the algorithm could serve as basis for future pharmacoepidemiological studies evaluating utilization, effectiveness, and safety of medication use, which would facilitate evidence-based treatment decision-making.</p>","PeriodicalId":12233,"journal":{"name":"Evidence Based Mental Health","volume":" ","pages":"146-152"},"PeriodicalIF":11.4000,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1136/ebmental-2020-300231","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Evidence Based Mental Health","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1136/ebmental-2020-300231","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2021/4/1 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"PSYCHIATRY","Score":null,"Total":0}
引用次数: 11
Abstract
Background: Accurate estimation of daily dosage and duration of medication use is essential to pharmacoepidemiological studies using electronic healthcare databases. However, such information is not directly available in many prescription databases, including the Swedish Prescribed Drug Register.
Objective: To develop and validate an algorithm for predicting prescribed daily dosage and treatment duration from free-text prescriptions, and apply the algorithm to ADHD medication prescriptions.
Methods: We developed an algorithm to predict daily dosage from free-text prescriptions using 8000 ADHD medication prescriptions as the training sample, and estimated treatment periods while taking into account several features including titration, stockpiling and non-perfect adherence. The algorithm was implemented to all ADHD medication prescriptions from the Swedish Prescribed Drug Register in 2013. A validation sample of 1000 ADHD medication prescriptions, independent of the training sample, was used to assess the accuracy for predicted daily dosage.
Findings: In the validation sample, the overall accuracy for predicting daily dosage was 96.8%. Specifically, the natural language processing model (NLP1 and NLP2) have an accuracy of 99.2% and 96.3%, respectively. In an application to ADHD medication prescriptions in 2013, young adult ADHD medication users had the highest probability of discontinuing treatments as compared with other age groups. The daily dose of methylphenidate use increased with age substantially.
Conclusions: The algorithm provides a flexible approach to estimate prescribed daily dosage and treatment duration from free-text prescriptions using register data. The algorithm showed a good performance for predicting daily dosage in external validation.
Clinical implications: The structured output of the algorithm could serve as basis for future pharmacoepidemiological studies evaluating utilization, effectiveness, and safety of medication use, which would facilitate evidence-based treatment decision-making.
期刊介绍：
Evidence-Based Mental Health alerts clinicians to important advances in treatment, diagnosis, aetiology, prognosis, continuing education, economic evaluation and qualitative research in mental health. Published by the British Psychological Society, the Royal College of Psychiatrists and the BMJ Publishing Group the journal surveys a wide range of international medical journals applying strict criteria for the quality and validity of research. Clinicians assess the relevance of the best studies and the key details of these essential studies are presented in a succinct, informative abstract with an expert commentary on its clinical application.Evidence-Based Mental Health is a multidisciplinary, quarterly publication.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
