Artificial intelligence supports literature screening in medical guideline development: towards up-to-date medical guidelines

Wouter Harmsen; Janke de Groot; Albert Harkema; Ingeborg van Dusseldorp; Jonathan De Bruin; Sofie Van den Brand; Rens Van de Schoot

doi:10.5281/ZENODO.5031907

Artificial intelligence supports literature screening in medical guideline development: towards up-to-date medical guidelines

Wouter Harmsen, Janke de Groot, Albert Harkema, Ingeborg van Dusseldorp, Jonathan De Bruin, Sofie Van den Brand, Rens Van de Schoot

Research output: Working paper › Preprint › Academic

Abstract

In a time of exponential growth of new evidence supporting clinical decision making, combined with a labor-intensive process of selecting this evidence, there is a need for methods to speed up current processes in order to keep medical guidelines up-to-date. The purpose of this study was to evaluate the performance and feasibility of active learning to support the selection of relevant publications within the context of medical guideline development.

Original language	English
Publisher	Zenodo
Pages	1-18
DOIs	https://doi.org/10.5281/ZENODO.5031907
Publication status	Published - 25 Jun 2021

Keywords

guideline development
medical guidelines
text data
natural language processing
active learning
machine learning
systematic reviewing

Access to Document

10.5281/ZENODO.5031907Licence: CC BY

Artificial intelligence supports literature screening in medical guideline developmentSubmitted manuscript, 364 KBLicence: CC BY

1 Article
1 Software

An open source machine learning framework for efficient and transparent systematic reviews
Schoot, R. V. D., Bruin, J. D., Schram, R., Zahedi, P., Boer, J. D., Weijdema, F., Kramer, B., Huijts, M., Hoogerwerf, M., Ferdinands, G., Harkema, A., Willemsen, J., Ma, Y., Fang, Q., Hindriks, S., Tummers, L. & Oberski, D., Feb 2021, In: Nature Machine Intelligence. 3, 2, p. 125-133 9 p.
Research output: Contribution to journal › Article › Academic › peer-review

Open Access
File
Scripts for paper on Towards up-to-date medical guidelines
Harmsen, W., de Groot, J., Harkema, A., van Dusseldorp, I., De Bruin, J., Van den Brand, S. & Van de Schoot, R., 2021
Research output: Non-textual form › Software › Academic

Open Access

Cite this

@techreport{6a8c018477fc4f6280ed613a8a0689f6,

title = "Artificial intelligence supports literature screening in medical guideline development: towards up-to-date medical guidelines",

abstract = "In a time of exponential growth of new evidence supporting clinical decision making, combined with a labor-intensive process of selecting this evidence, there is a need for methods to speed up current processes in order to keep medical guidelines up-to-date. The purpose of this study was to evaluate the performance and feasibility of active learning to support the selection of relevant publications within the context of medical guideline development.",

keywords = "guideline development, medical guidelines, text data, natural language processing, active learning, machine learning, systematic reviewing",

author = "Wouter Harmsen and {de Groot}, Janke and Albert Harkema and {van Dusseldorp}, Ingeborg and {De Bruin}, Jonathan and {Van den Brand}, Sofie and {Van de Schoot}, Rens",

year = "2021",

month = jun,

day = "25",

doi = "10.5281/ZENODO.5031907",

language = "English",

pages = "1--18",

publisher = "Zenodo",

type = "WorkingPaper",

institution = "Zenodo",

}

TY - UNPB

T1 - Artificial intelligence supports literature screening in medical guideline development: towards up-to-date medical guidelines

AU - Harmsen, Wouter

AU - de Groot, Janke

AU - Harkema, Albert

AU - van Dusseldorp, Ingeborg

AU - De Bruin, Jonathan

AU - Van den Brand, Sofie

AU - Van de Schoot, Rens

PY - 2021/6/25

Y1 - 2021/6/25

N2 - In a time of exponential growth of new evidence supporting clinical decision making, combined with a labor-intensive process of selecting this evidence, there is a need for methods to speed up current processes in order to keep medical guidelines up-to-date. The purpose of this study was to evaluate the performance and feasibility of active learning to support the selection of relevant publications within the context of medical guideline development.

AB - In a time of exponential growth of new evidence supporting clinical decision making, combined with a labor-intensive process of selecting this evidence, there is a need for methods to speed up current processes in order to keep medical guidelines up-to-date. The purpose of this study was to evaluate the performance and feasibility of active learning to support the selection of relevant publications within the context of medical guideline development.

KW - guideline development

KW - medical guidelines

KW - text data

KW - natural language processing

KW - active learning

KW - machine learning

KW - systematic reviewing

U2 - 10.5281/ZENODO.5031907

DO - 10.5281/ZENODO.5031907

M3 - Preprint

SP - 1

EP - 18

BT - Artificial intelligence supports literature screening in medical guideline development: towards up-to-date medical guidelines

PB - Zenodo

ER -

Artificial intelligence supports literature screening in medical guideline development: towards up-to-date medical guidelines

Abstract

Keywords

Access to Document

Fingerprint

Research output

An open source machine learning framework for efficient and transparent systematic reviews

Scripts for paper on Towards up-to-date medical guidelines

Cite this