Identifying Medications that Patients Stopped Taking in Online Health Forums

Patients may stop taking medications after a certain point for various reasons, such as severe side effects, prohibitive costs, or ineffective treatments. Being able to analyze the reason patients stop taking medications is very important to medical practitioners, for example, who can come up with new treatment plans, prescribe different medication if there are side effects. In this paper, we focus on online health forums and define the problem as a binary classification task (i.e., if a patient has stopped taking a medication or not). We chose to focus on health forums here since these are the platforms usually patients go to ask for support online. We propose linguistics features of various complexity and present an in-depth analysis of the results which give us new insights into the task at hand.

[1]  Umeshwar Dayal,et al.  PrefixSpan: Mining Sequential Patterns by Prefix-Projected Growth , 2001, ICDE 2001.

[2]  Martin Keller,et al.  The epidemiology of major depressive episodes: results from the International Consortium of Psychiatric Epidemiology (ICPE) surveys , 2003, International journal of methods in psychiatric research.

[3]  W. Fleischhacker,et al.  Factors influencing compliance in schizophrenia patients. , 2003, The Journal of clinical psychiatry.

[4]  T. Pachinger,et al.  Medication adherence among psychotic patients before admission to inpatient treatment. , 2004, Psychiatric services.

[5]  M. Dimatteo.  Variations in Patients’ Adherence to Medical Recommendations: A Quantitative Review of 50 Years of Research , 2004, Medical care.

[6]  K. Ohe,et al.  Patient Status Classification by using Rule based Sentence Extraction and BM 25-kNN based Classifier , 2006 .

[7]  Aaron M. Cohen,et al.  Case Report: Five-way Smoking Status Classification Using Text Hot-Spot Identification and Error-correcting Output Codes , 2008, J. Am. Medical Informatics Assoc..

[8]  Peter D. Stetson,et al.  Use of Semantic Features to Classify Patient Smoking Status , 2008, AMIA.

[9]  Dan Roth,et al.  Understanding the Value of Features for Coreference Resolution , 2008, EMNLP.

[10]  Matthew R. Sydes,et al.  Technical Brief: Using Implicit Information to Identify Smoking Status in Smoke-blind Medical Discharge Summaries , 2008, J. Am. Medical Informatics Assoc..

[11]  Yuan Luo,et al.  Identifying patient smoking status from medical discharge records. , 2008, Journal of the American Medical Informatics Association : JAMIA.

[12]  Brian Wilson,et al.  Case Report: Identifying Smokers with a Medical Extraction System , 2008, J. Am. Medical Informatics Assoc..

[13]  Heng Ji,et al.  Language Specific Issue and Feature Exploration in Chinese Event Extraction , 2009, NAACL.

[14]  Larry Davidson,et al.  Why and how people decide to stop taking prescribed psychiatric medication: exploring the subjective process of choice. , 2009, Psychiatric rehabilitation journal.

[15]  Alberto Maria Segre,et al.  The Use of Twitter to Track Levels of Disease Activity and Public Concern in the U.S. during the Influenza A H1N1 Pandemic , 2011, PloS one.

[16]  Richard B. Berlin,et al.  Predicting adverse drug events from personal health messages. , 2011, AMIA ... Annual Symposium proceedings. AMIA Symposium.

[17]  Bruce R. Schatz,et al.  Aggregating Personal Health Messages for Scalable Comparative Effectiveness Research , 2013, BCB.

[18]  G Niklas Norén,et al.  Pharmacovigilance for a Revolving World: Prospects of Patient-Generated Data on the Internet , 2014, Drug Safety.

[19]  Yen S. Low,et al.  Text Mining for Adverse Drug Events: the Promise, Challenges, and State of the Art , 2014, Drug Safety.

[20]  Erik Cambria,et al.  SenticNet 3: A Common and Common-Sense Knowledge Base for Cognition-Driven Sentiment Analysis , 2014, AAAI.

[21]  Ryen W. White,et al.  Toward Enhanced Pharmacovigilance Using Patient-Generated Data on the Internet , 2014, Clinical pharmacology and therapeutics.

[22]  Danqi Chen,et al.  A Fast and Accurate Dependency Parser using Neural Networks , 2014, EMNLP.

[23]  ChengXiang Zhai,et al.  SideEffectPTM: an unsupervised topic model to mine adverse drug reactions from health forums , 2014, BCB.

[24]  Claire Cardie,et al.  Timeline generation: tracking individuals on twitter , 2013, WWW.

[25]  Jeffrey Heer,et al.  Forum77: An Analysis of an Online Health Forum Dedicated to Addiction Recovery , 2015, CSCW.

[26]  Mark Dredze,et al.  Combining Search, Social Media, and Traditional Data Sources to Improve Influenza Surveillance , 2015, PLoS Comput. Biol..

[27]  Mark Dredze,et al.  Assessing the Validity of Online Drug Forums as a Source for Estimating Demographic and Temporal Trends in Drug Use , 2016, Journal of addiction medicine.