Improving reference prioritisation with PICO recognitionCitation formats

Standard

Improving reference prioritisation with PICO recognition. / Brockmeier, Austin ; Ju, Meizhi; Przybyla, Piotr; Ananiadou, Sophia.

In: BMC Medical Informatics and Decision Making, Vol. 19, 06.12.2019.

Research output: Contribution to journalArticlepeer-review

Harvard

Brockmeier, A, Ju, M, Przybyla, P & Ananiadou, S 2019, 'Improving reference prioritisation with PICO recognition', BMC Medical Informatics and Decision Making, vol. 19. https://doi.org/10.1186/s12911-019-0992-8

APA

Brockmeier, A., Ju, M., Przybyla, P., & Ananiadou, S. (2019). Improving reference prioritisation with PICO recognition. BMC Medical Informatics and Decision Making, 19. https://doi.org/10.1186/s12911-019-0992-8

Vancouver

Brockmeier A, Ju M, Przybyla P, Ananiadou S. Improving reference prioritisation with PICO recognition. BMC Medical Informatics and Decision Making. 2019 Dec 6;19. https://doi.org/10.1186/s12911-019-0992-8

Author

Brockmeier, Austin ; Ju, Meizhi ; Przybyla, Piotr ; Ananiadou, Sophia. / Improving reference prioritisation with PICO recognition. In: BMC Medical Informatics and Decision Making. 2019 ; Vol. 19.

Bibtex

@article{a178a963c69f4de6863eef653909d615,
title = "Improving reference prioritisation with PICO recognition",
abstract = "Machine learning can assist with multiple tasks during systematic reviews to facilitate the rapid retrieval of relevant references during screening and to identify and extract information relevant to the study characteristics, which include the PICO elements of patient/population, intervention, comparator, and outcomes. The latter requires techniques for identifying and categorising fragments of text, known as named entity recognition.MethodsA publicly available corpus of PICO annotations on biomedical abstracts is used to train a named entity recognition model, which is implemented as a recurrent neural network. This model is then applied to a separate collection of abstracts for references from systematic reviews within biomedical and health domains. The occurrences of words tagged in the context of specific PICO contexts are used as additional features for a relevancy classification model. Simulations of the machine learning-assisted screening are used to evaluate the work saved by the relevancy model with and without the PICO features. Chi-squared and statistical significance of positive predicted values are used to identify words that are more indicative of relevancy within PICO contexts.Inclusion of PICO features improves the performance metric on 15 of the 20 collections, with substantial gains on certain systematic reviews. Examples of words whose PICO context are more precise can explain this increase.Words within PICO tagged segments in abstracts are predictive features for determining inclusion. Combining PICO annotation model into the relevancy classification pipeline is a promising approach. The annotations may be useful on their own to aid users in pinpointing necessary information for data extraction, or to facilitate semantic search.",
keywords = "Text Mining, Machine Learning, PICO, active learning, Evidence-Based Medicine",
author = "Austin Brockmeier and Meizhi Ju and Piotr Przybyla and Sophia Ananiadou",
year = "2019",
month = dec,
day = "6",
doi = "10.1186/s12911-019-0992-8",
language = "English",
volume = "19",
journal = "BMC Medical Informatics and Decision Making",
issn = "1472-6947",
publisher = "Springer Nature",

}

RIS

TY - JOUR

T1 - Improving reference prioritisation with PICO recognition

AU - Brockmeier, Austin

AU - Ju, Meizhi

AU - Przybyla, Piotr

AU - Ananiadou, Sophia

PY - 2019/12/6

Y1 - 2019/12/6

N2 - Machine learning can assist with multiple tasks during systematic reviews to facilitate the rapid retrieval of relevant references during screening and to identify and extract information relevant to the study characteristics, which include the PICO elements of patient/population, intervention, comparator, and outcomes. The latter requires techniques for identifying and categorising fragments of text, known as named entity recognition.MethodsA publicly available corpus of PICO annotations on biomedical abstracts is used to train a named entity recognition model, which is implemented as a recurrent neural network. This model is then applied to a separate collection of abstracts for references from systematic reviews within biomedical and health domains. The occurrences of words tagged in the context of specific PICO contexts are used as additional features for a relevancy classification model. Simulations of the machine learning-assisted screening are used to evaluate the work saved by the relevancy model with and without the PICO features. Chi-squared and statistical significance of positive predicted values are used to identify words that are more indicative of relevancy within PICO contexts.Inclusion of PICO features improves the performance metric on 15 of the 20 collections, with substantial gains on certain systematic reviews. Examples of words whose PICO context are more precise can explain this increase.Words within PICO tagged segments in abstracts are predictive features for determining inclusion. Combining PICO annotation model into the relevancy classification pipeline is a promising approach. The annotations may be useful on their own to aid users in pinpointing necessary information for data extraction, or to facilitate semantic search.

AB - Machine learning can assist with multiple tasks during systematic reviews to facilitate the rapid retrieval of relevant references during screening and to identify and extract information relevant to the study characteristics, which include the PICO elements of patient/population, intervention, comparator, and outcomes. The latter requires techniques for identifying and categorising fragments of text, known as named entity recognition.MethodsA publicly available corpus of PICO annotations on biomedical abstracts is used to train a named entity recognition model, which is implemented as a recurrent neural network. This model is then applied to a separate collection of abstracts for references from systematic reviews within biomedical and health domains. The occurrences of words tagged in the context of specific PICO contexts are used as additional features for a relevancy classification model. Simulations of the machine learning-assisted screening are used to evaluate the work saved by the relevancy model with and without the PICO features. Chi-squared and statistical significance of positive predicted values are used to identify words that are more indicative of relevancy within PICO contexts.Inclusion of PICO features improves the performance metric on 15 of the 20 collections, with substantial gains on certain systematic reviews. Examples of words whose PICO context are more precise can explain this increase.Words within PICO tagged segments in abstracts are predictive features for determining inclusion. Combining PICO annotation model into the relevancy classification pipeline is a promising approach. The annotations may be useful on their own to aid users in pinpointing necessary information for data extraction, or to facilitate semantic search.

KW - Text Mining

KW - Machine Learning

KW - PICO

KW - active learning

KW - Evidence-Based Medicine

U2 - 10.1186/s12911-019-0992-8

DO - 10.1186/s12911-019-0992-8

M3 - Article

VL - 19

JO - BMC Medical Informatics and Decision Making

JF - BMC Medical Informatics and Decision Making

SN - 1472-6947

ER -