Patients advise their peers on how to cope with their illness in daily life on online support groups. To date, no efforts have been made to automatically extract recommended coping strategies from... Show morePatients advise their peers on how to cope with their illness in daily life on online support groups. To date, no efforts have been made to automatically extract recommended coping strategies from online patient discussion groups. We introduce this new task, which poses a number of challenges including complex, long entities, a large long-tailed label space, and cross-document relations. We present an initial ontology for coping strategies as a starting point for future research on coping strategies, and the first end-to-end pipeline for extracting coping strategies for side effects. We also compared two possible computational solutions for this novel and highly challenging task; multi-label classification and named entity recognition (NER) with entity linking (EL). We evaluated our methods on the discussion forum from the Facebook group of the worldwide patient support organization ‘GIST support international’ (GSI); GIST support international donated the data to us. We found that coping strategy extraction is difficult and both methods attain limited performance (measured with score) on held out test sets; multi-label classification outperforms NER+EL ( vs ). An inspection of the multi-label classification output revealed that for some of the incorrect predictions, the reference label is close to the predicted label in the ontology (e.g. the predicted label ‘juice’ instead of the more specific reference label ‘grapefruit juice’). Performance increased to when we evaluated at a coarser level of the ontology. We conclude that our pipeline can be used in a semi-automatic setting, in interaction with domain experts to discover coping strategies for side effects from a patient forum. For example, we found that patients recommend ginger tea for nausea and magnesium and potassium supplements for cramps. This information can be used as input for patient surveys or clinical studies. Show less
Background and Objectives: Adverse drug reactions on sexual functioning (sADRs) may seriously decrease a person's quality of life. A multitude of diseases and drugs are known risk factors for... Show moreBackground and Objectives: Adverse drug reactions on sexual functioning (sADRs) may seriously decrease a person's quality of life. A multitude of diseases and drugs are known risk factors for sexual dysfunction.To inform patients better about these potential effects, more insight is needed on the estimated number of patients at high risk for sADRs and their characteristics.Methods: This cross-sectional study estimated the number of patients in the Netherlands who were dispensed drugs with a potential very high risk (>10%) or high risk (1-10%) for sADRs as registered in the Summary of Product Characteristics, the official drug information text in Europe.Results: In April 2019, 2.06% of the inhabitants of the Netherlands received drugs with >10% risk for sADRs and 7.76% with 1-10% risk.The majority of these patients had at least one additional risk factor for decreased sexual function such as high age or depression. Almost half of the patients were identified with two or more morbidities influencing sexual functioning. Paroxetine, sertraline and spironolactone were the most dispensed drugs with a potential >10% risk for sADRs. One-third of their first dispenses were not followed by a second dispense, with a higher risk of discontinuation for a decreasing number of morbidities.Conclusion: About 1 in 11 inhabitants of the Netherlands was dispensed a drug with a potential high risk for sADRs, often with other risk factors for sexual complaints. Further research is needed whether these users actually experience sADRs, to understand its impact on multimorbid patients and to provide alternatives if needed. Show less
