Automatic evidence quality prediction to support evidence-based decision making

Sarker, Abeed; Mollá, Diego; Paris, Cécile

doi:10.1016/j.artmed.2015.04.001

Cited by 21 publications

(20 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our analysis of the tweets during annotation suggested that users often express polarized sentiments when mentioning drug abuse. Therefore, we introduced a feature that has been used in the past for sentiment analysis and polarity classification [ 31 ]. This feature is generated by identifying all synonyms of all nouns, verbs and adjectives using WordNet [ 32 ].…”

Section: Methodsmentioning

confidence: 99%

Social Media Mining for Toxicovigilance: Automatic Monitoring of Prescription Medication Abuse from Twitter

et al. 2016

Self Cite

View full text Add to dashboard Cite

IntroductionPrescription medication overdose is the fastest growing drug-related problem in the USA. The growing nature of this problem necessitates the implementation of improved monitoring strategies for investigating the prevalence and patterns of abuse of specific medications.ObjectivesOur primary aims were to assess the possibility of utilizing social media as a resource for automatic monitoring of prescription medication abuse and to devise an automatic classification technique that can identify potentially abuse-indicating user posts.MethodsWe collected Twitter user posts (tweets) associated with three commonly abused medications (Adderall®, oxycodone, and quetiapine). We manually annotated 6400 tweets mentioning these three medications and a control medication (metformin) that is not the subject of abuse due to its mechanism of action. We performed quantitative and qualitative analyses of the annotated data to determine whether posts on Twitter contain signals of prescription medication abuse. Finally, we designed an automatic supervised classification technique to distinguish posts containing signals of medication abuse from those that do not and assessed the utility of Twitter in investigating patterns of abuse over time.ResultsOur analyses show that clear signals of medication abuse can be drawn from Twitter posts and the percentage of tweets containing abuse signals are significantly higher for the three case medications (Adderall®: 23 %, quetiapine: 5.0 %, oxycodone: 12 %) than the proportion for the control medication (metformin: 0.3 %). Our automatic classification approach achieves 82 % accuracy overall (medication abuse class recall: 0.51, precision: 0.41, F measure: 0.46). To illustrate the utility of automatic classification, we show how the classification data can be used to analyze abuse patterns over time.ConclusionOur study indicates that social media can be a crucial resource for obtaining abuse-related information for medications, and that automatic approaches involving supervised classification and natural language processing hold promises for essential future monitoring and intervention tasks.

show abstract

Section: Methodsmentioning

confidence: 99%

Social Media Mining for Toxicovigilance: Automatic Monitoring of Prescription Medication Abuse from Twitter

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…Elaborating on prostate cancer with data obtained from eight different hospital information systems, complemented with information from a local cancer registry, as the case study, Bettencourt-Silva et al proposed a framework for the construction, quality assessment, and visualization of patient pathways for clinical studies and decision support. As a methodological contribution, Sarker et al [13] presented a fully automatic method for predicting the quality of medical evidence obtained from literature sources. Given the wide variety of medical literature sources currently available through the Internet, the manual appraisal of the quality of evidence is a time-consuming process.…”

Section: Discussion and Outlookmentioning

confidence: 99%

Computerized Clinical Decision Support: Contributions from 2015

Koutkias

Bouaud²

2016

Yearb Med Inform

View full text Add to dashboard Cite

While there are notable examples of routinely used decision support systems, this 2015 review on CDSSs and CPOE systems still shows that, despite methodological contributions, theoretical frameworks, and prototype developments, these technologies are not yet widely spread (at least with their full functionalities) in routine clinical practice. Further research, testing, evaluation, and training are still needed for these tools to be adopted in clinical practice and, ultimately, illustrate the benefits that they promise.

show abstract

“…To prove the hypothesis that deep learning model can perform better than the shallow machine learning algorithms, we choose four well-known algorithms which have been experimented with in multiple studies [7,13,15] that include Naïve Bayes (NB), Decision Tree (DT), Support Vector Machine (SVM), and Gradient Boosted Trees (GBT). A brief description of parameter settings for each algorithm is provided in Table 2.…”

Section: Model Selectionmentioning

confidence: 99%

Deep Learning Based Biomedical Literature Classification Using Criteria of Scientific Rigor

et al. 2020

View full text Add to dashboard Cite

A major blockade to support the evidence-based clinical decision-making is accurately and efficiently recognizing appropriate and scientifically rigorous studies in the biomedical literature. We trained a multi-layer perceptron (MLP) model on a dataset with two textual features, title and abstract. The dataset consisting of 7958 PubMed citations classified in two classes: scientific rigor and non-rigor, is used to train the proposed model. We compare our model with other promising machine learning models such as Support Vector Machine (SVM), Decision Tree, Random Forest, and Gradient Boosted Tree (GBT) approaches. Based on the higher cumulative score, deep learning was chosen and was tested on test datasets obtained by running a set of domain-specific queries. On the training dataset, the proposed deep learning model obtained significantly higher accuracy and AUC of 97.3% and 0.993, respectively, than the competitors, but was slightly lower in the recall of 95.1% as compared to GBT. The trained model sustained the performance of testing datasets. Unlike previous approaches, the proposed model does not require a human expert to create fresh annotated data; instead, we used studies cited in Cochrane reviews as a surrogate for quality studies in a clinical topic. We learn that deep learning methods are beneficial to use for biomedical literature classification. Not only do such methods minimize the workload in feature engineering, but they also show better performance on large and noisy data.

show abstract

Automatic evidence quality prediction to support evidence-based decision making

Cited by 21 publications

References 35 publications

Social Media Mining for Toxicovigilance: Automatic Monitoring of Prescription Medication Abuse from Twitter

Social Media Mining for Toxicovigilance: Automatic Monitoring of Prescription Medication Abuse from Twitter

Computerized Clinical Decision Support: Contributions from 2015

Deep Learning Based Biomedical Literature Classification Using Criteria of Scientific Rigor

Contact Info

Product

Resources

About