Tao Hoang1, Jixue Liu2, Nicole Pratt3, Vincent W Zheng4, Kevin C Chang5, Elizabeth Roughead3, Jiuyong Li2. 1. School of Information Technology and Mathematical Sciences, University of South Australia, Mawson Lakes, Adelaide, South Australia 5095, Australia. Electronic address: hoatn002@mymail.unisa.edu.au. 2. School of Information Technology and Mathematical Sciences, University of South Australia, Mawson Lakes, Adelaide, South Australia 5095, Australia. 3. School of Pharmacy and Medical Sciences, University of South Australia, City East Campus, North Terrace, Adelaide, South Australia 5000, Australia. 4. Advanced Digital Sciences Center, 1 Fusionopolis Way, #08-10 Connexis North Tower, Singapore 138632, Singapore. 5. Department of Computer Science, University of Illinois at Urbana-Champaign, 201 N Goodwin Ave, Urbana, IL 61801, United States.
Abstract
MOTIVATION: Prescribing cascade (PC) occurs when an adverse drug reaction (ADR) is misinterpreted as a new medical condition, leading to further prescriptions for treatment. Additional prescriptions, however, may worsen the existing condition or introduce additional adverse effects (AEs). Timely detection and prevention of detrimental PCs is essential as drug AEs are among the leading causes of hospitalization and deaths. Identifying detrimental PCs would enable warnings and contraindications to be disseminated and assist the detection of unknown drug AEs. Nonetheless, the detection is difficult and has been limited to case reports or case assessment using administrative health claims data. Social media is a promising source for detecting signals of detrimental PCs due to the public availability of many discussions regarding treatments and drug AEs. OBJECTIVE: In this paper, we investigate the feasibility of detecting detrimental PCs from social media. METHODS: The detection, however, is challenging due to the data uncertainty and data rarity in social media. We propose a framework to mine sequences of drugs and AEs that signal detrimental PCs, taking into account the data uncertainty and data rarity. RESULTS: We conduct experiments on two real-world datasets collected from Twitter and Patient health forum. Our framework achieves encouraging results in the validation against known detrimental PCs (F1=78% for Twitter and 68% for Patient) and the detection of unknown potential detrimental PCs (Precision@50=72% and NDCG@50=95% for Twitter, Precision@50=86% and NDCG@50=98% for Patient). In addition, the framework is efficient and scalable to large datasets. CONCLUSION: Our study demonstrates the feasibility of generating hypotheses of detrimental PCs from social media to reduce pharmacists' guesswork.
MOTIVATION: Prescribing cascade (PC) occurs when an adverse drug reaction (ADR) is misinterpreted as a new medical condition, leading to further prescriptions for treatment. Additional prescriptions, however, may worsen the existing condition or introduce additional adverse effects (AEs). Timely detection and prevention of detrimental PCs is essential as drug AEs are among the leading causes of hospitalization and deaths. Identifying detrimental PCs would enable warnings and contraindications to be disseminated and assist the detection of unknown drug AEs. Nonetheless, the detection is difficult and has been limited to case reports or case assessment using administrative health claims data. Social media is a promising source for detecting signals of detrimental PCs due to the public availability of many discussions regarding treatments and drug AEs. OBJECTIVE: In this paper, we investigate the feasibility of detecting detrimental PCs from social media. METHODS: The detection, however, is challenging due to the data uncertainty and data rarity in social media. We propose a framework to mine sequences of drugs and AEs that signal detrimental PCs, taking into account the data uncertainty and data rarity. RESULTS: We conduct experiments on two real-world datasets collected from Twitter and Patient health forum. Our framework achieves encouraging results in the validation against known detrimental PCs (F1=78% for Twitter and 68% for Patient) and the detection of unknown potential detrimental PCs (Precision@50=72% and NDCG@50=95% for Twitter, Precision@50=86% and NDCG@50=98% for Patient). In addition, the framework is efficient and scalable to large datasets. CONCLUSION: Our study demonstrates the feasibility of generating hypotheses of detrimental PCs from social media to reduce pharmacists' guesswork.