Combining classifiers for robust PICO element detection

Abstract

BackgroundFormulating a clinical information need in terms of the four atomic parts which are Population/Problem, Intervention, Comparison and Outcome (known as PICO elements) facilitates searching for a precise answer within a large medical citation database. However, using PICO defined items in the information retrieval process requires a search engine to be able to detect and index PICO elements in the collection in order for the system to retrieve relevant documents.MethodsIn this study, we tested multiple supervised classification algorithms and their combinations for detecting PICO elements within medical abstracts. Using the structural descriptors that are embedded in some medical abstracts, we have automatically gathered large training/testing data sets for each PICO element.ResultsCombining multiple classifiers using a weighted linear combination of their prediction scores achieves promising results with an f-measure score of 86.3% for P, 67% for I and 56.6% for O.ConclusionsOur experiments on the identification of PICO elements showed that the task is very challenging. Nevertheless, the performance achieved by our identification method is competitive with previously published results and shows that this task can be achieved with a high accuracy for the P element but lower ones for I and O elements.

Efficacy of Vitamin D3 Supplementation on Osseointegration of Implants

“…1). 26 The addressed focused question was "does VD3 supplementation influence osseointegration around implants?" (P) Participants: it was essential for subjects to have undergone implant treatment.…”

Role of Diode Lasers (800–980 Nm) as Adjuncts to Scaling and Root Planing in the Treatment of Chronic Periodontitis: A Systematic Review

“…25 The addressed focused question was ''Is SRP with adjunct diode laser (810-980 nm) therapy more effective in the treatment of CP than when CP is treated by SRP alone?'' (P) Participants: population of the study who underwent SRP with or without diode laser therapy (I) Types of interventions: SRP with and without adjunct laser therapy C) Control Intervention: SRP alone (O) Outcome measures: reduction in the severity of periodontal inflammatory parameters (such as plaque index, bleeding on probing, probing depth, and CAL).…”

Machine learning techniques for the automation of literature reviews and systematic reviews in EFSA

“…For example, PICO detection in abstracts by means of SVM-based machine learning is discussed in Boudin et al (2010aBoudin et al ( , 2010b. Likewise, Robinson (2012) applies naïve Bayes, multinomial naïve Bayes, SVM, logistic regression and random forests to the task of identifying abstracts with patient oriented outcomes based on reliable evidence.…”