No Cover Image

Journal article 462 views 97 downloads

Predicting fracture outcomes from clinical registry data using artificial intelligence supplemented models for evidence-informed treatment (PRAISE) study protocol

Joanna F. Dipnall, Richard Page, Lan Du, Matthew Costa, Ronan Lyons Orcid Logo, Peter Cameron, Richard de Steiger, Raphael Hau, Andrew Bucknill, Andrew Oppy, Elton Edwards, Dinesh Varma, Myong Chol Jung, Belinda Gabbe Orcid Logo

PLOS ONE, Volume: 16, Issue: 9, Start page: e0257361

Swansea University Authors: Ronan Lyons Orcid Logo, Belinda Gabbe Orcid Logo

  • 58743.pdf

    PDF | Version of Record

    © 2021 Dipnall et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

    Download (659.67KB)

Check full text

DOI (Published version): 10.1371/journal.pone.0257361

Abstract

BackgroundDistal radius (wrist) fractures are the second most common fracture admitted to hospital. The anatomical pattern of these types of injuries is diverse, with variation in clinical management, guidelines for management remain inconclusive, and the uptake of findings from clinical trials into...

Full description

Published in: PLOS ONE
ISSN: 1932-6203 1932-6203
Published: Public Library of Science (PLoS) 2021
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa58743
first_indexed 2021-11-22T13:29:12Z
last_indexed 2023-01-11T14:39:33Z
id cronfa58743
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2022-08-15T18:06:59.8175140</datestamp><bib-version>v2</bib-version><id>58743</id><entry>2021-11-22</entry><title>Predicting fracture outcomes from clinical registry data using artificial intelligence supplemented models for evidence-informed treatment (PRAISE) study protocol</title><swanseaauthors><author><sid>83efcf2a9dfcf8b55586999d3d152ac6</sid><ORCID>0000-0001-5225-000X</ORCID><firstname>Ronan</firstname><surname>Lyons</surname><name>Ronan Lyons</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>4bdcc94332b2bd10530c5e71ceb04f14</sid><ORCID>0000-0001-7096-7688</ORCID><firstname>Belinda</firstname><surname>Gabbe</surname><name>Belinda Gabbe</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-11-22</date><deptcode>MEDS</deptcode><abstract>BackgroundDistal radius (wrist) fractures are the second most common fracture admitted to hospital. The anatomical pattern of these types of injuries is diverse, with variation in clinical management, guidelines for management remain inconclusive, and the uptake of findings from clinical trials into routine practice limited. Robust predictive modelling, which considers both the characteristics of the fracture and patient, provides the best opportunity to reduce variation in care and improve patient outcomes. This type of data is housed in unstructured data sources with no particular format or schema. The &#x201C;Predicting fracture outcomes from clinical Registry data using Artificial Intelligence (AI) Supplemented models for Evidence-informed treatment (PRAISE)&#x201D; study aims to use AI methods on unstructured data to describe the fracture characteristics and test if using this information improves identification of key fracture characteristics and prediction of patient-reported outcome measures and clinical outcomes following wrist fractures compared to prediction models based on standard registry data.Methods and designAdult (16+ years) patients presenting to the emergency department, treated in a short stay unit, or admitted to hospital for &gt;24h for management of a wrist fracture in four Victorian hospitals will be included in this study. The study will use routine registry data from the Victorian Orthopaedic Trauma Outcomes Registry (VOTOR), and electronic medical record (EMR) information (e.g. X-rays, surgical reports, radiology reports, images). A multimodal deep learning fracture reasoning system (DLFRS) will be developed that reasons on EMR information. Machine learning prediction models will test the performance with/without output from the DLFRS.DiscussionThe PRAISE study will establish the use of AI techniques to provide enhanced information about fracture characteristics in people with wrist fractures. Prediction models using AI derived characteristics are expected to provide better prediction of clinical and patient-reported outcomes following distal radius fracture.</abstract><type>Journal Article</type><journal>PLOS ONE</journal><volume>16</volume><journalNumber>9</journalNumber><paginationStart>e0257361</paginationStart><paginationEnd/><publisher>Public Library of Science (PLoS)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>1932-6203</issnPrint><issnElectronic>1932-6203</issnElectronic><keywords/><publishedDay>23</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2021</publishedYear><publishedDate>2021-09-23</publishedDate><doi>10.1371/journal.pone.0257361</doi><url/><notes/><college>COLLEGE NANME</college><department>Medical School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MEDS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>VOTOR is funded by the Transport Accident Commission. The PRAISE project is funded by the National Health and Medical Research Council of Australia Ideas Grant (NHMRC- APP2003537). PC is funded by a Medical Research Future Fund Practitioner Fellowship (MRF1139686).</funders><projectreference/><lastEdited>2022-08-15T18:06:59.8175140</lastEdited><Created>2021-11-22T13:26:44.4934438</Created><path><level id="1">Faculty of Medicine, Health and Life Sciences</level><level id="2">Swansea University Medical School - Medicine</level></path><authors><author><firstname>Joanna F.</firstname><surname>Dipnall</surname><order>1</order></author><author><firstname>Richard</firstname><surname>Page</surname><order>2</order></author><author><firstname>Lan</firstname><surname>Du</surname><order>3</order></author><author><firstname>Matthew</firstname><surname>Costa</surname><order>4</order></author><author><firstname>Ronan</firstname><surname>Lyons</surname><orcid>0000-0001-5225-000X</orcid><order>5</order></author><author><firstname>Peter</firstname><surname>Cameron</surname><order>6</order></author><author><firstname>Richard de</firstname><surname>Steiger</surname><order>7</order></author><author><firstname>Raphael</firstname><surname>Hau</surname><order>8</order></author><author><firstname>Andrew</firstname><surname>Bucknill</surname><order>9</order></author><author><firstname>Andrew</firstname><surname>Oppy</surname><order>10</order></author><author><firstname>Elton</firstname><surname>Edwards</surname><order>11</order></author><author><firstname>Dinesh</firstname><surname>Varma</surname><order>12</order></author><author><firstname>Myong Chol</firstname><surname>Jung</surname><order>13</order></author><author><firstname>Belinda</firstname><surname>Gabbe</surname><orcid>0000-0001-7096-7688</orcid><order>14</order></author></authors><documents><document><filename>58743__21626__5e48176d067d471f837c94120b84a814.pdf</filename><originalFilename>58743.pdf</originalFilename><uploaded>2021-11-22T13:28:30.2993555</uploaded><type>Output</type><contentLength>675505</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2021 Dipnall et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2022-08-15T18:06:59.8175140 v2 58743 2021-11-22 Predicting fracture outcomes from clinical registry data using artificial intelligence supplemented models for evidence-informed treatment (PRAISE) study protocol 83efcf2a9dfcf8b55586999d3d152ac6 0000-0001-5225-000X Ronan Lyons Ronan Lyons true false 4bdcc94332b2bd10530c5e71ceb04f14 0000-0001-7096-7688 Belinda Gabbe Belinda Gabbe true false 2021-11-22 MEDS BackgroundDistal radius (wrist) fractures are the second most common fracture admitted to hospital. The anatomical pattern of these types of injuries is diverse, with variation in clinical management, guidelines for management remain inconclusive, and the uptake of findings from clinical trials into routine practice limited. Robust predictive modelling, which considers both the characteristics of the fracture and patient, provides the best opportunity to reduce variation in care and improve patient outcomes. This type of data is housed in unstructured data sources with no particular format or schema. The “Predicting fracture outcomes from clinical Registry data using Artificial Intelligence (AI) Supplemented models for Evidence-informed treatment (PRAISE)” study aims to use AI methods on unstructured data to describe the fracture characteristics and test if using this information improves identification of key fracture characteristics and prediction of patient-reported outcome measures and clinical outcomes following wrist fractures compared to prediction models based on standard registry data.Methods and designAdult (16+ years) patients presenting to the emergency department, treated in a short stay unit, or admitted to hospital for >24h for management of a wrist fracture in four Victorian hospitals will be included in this study. The study will use routine registry data from the Victorian Orthopaedic Trauma Outcomes Registry (VOTOR), and electronic medical record (EMR) information (e.g. X-rays, surgical reports, radiology reports, images). A multimodal deep learning fracture reasoning system (DLFRS) will be developed that reasons on EMR information. Machine learning prediction models will test the performance with/without output from the DLFRS.DiscussionThe PRAISE study will establish the use of AI techniques to provide enhanced information about fracture characteristics in people with wrist fractures. Prediction models using AI derived characteristics are expected to provide better prediction of clinical and patient-reported outcomes following distal radius fracture. Journal Article PLOS ONE 16 9 e0257361 Public Library of Science (PLoS) 1932-6203 1932-6203 23 9 2021 2021-09-23 10.1371/journal.pone.0257361 COLLEGE NANME Medical School COLLEGE CODE MEDS Swansea University VOTOR is funded by the Transport Accident Commission. The PRAISE project is funded by the National Health and Medical Research Council of Australia Ideas Grant (NHMRC- APP2003537). PC is funded by a Medical Research Future Fund Practitioner Fellowship (MRF1139686). 2022-08-15T18:06:59.8175140 2021-11-22T13:26:44.4934438 Faculty of Medicine, Health and Life Sciences Swansea University Medical School - Medicine Joanna F. Dipnall 1 Richard Page 2 Lan Du 3 Matthew Costa 4 Ronan Lyons 0000-0001-5225-000X 5 Peter Cameron 6 Richard de Steiger 7 Raphael Hau 8 Andrew Bucknill 9 Andrew Oppy 10 Elton Edwards 11 Dinesh Varma 12 Myong Chol Jung 13 Belinda Gabbe 0000-0001-7096-7688 14 58743__21626__5e48176d067d471f837c94120b84a814.pdf 58743.pdf 2021-11-22T13:28:30.2993555 Output 675505 application/pdf Version of Record true © 2021 Dipnall et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. true eng http://creativecommons.org/licenses/by/4.0/
title Predicting fracture outcomes from clinical registry data using artificial intelligence supplemented models for evidence-informed treatment (PRAISE) study protocol
spellingShingle Predicting fracture outcomes from clinical registry data using artificial intelligence supplemented models for evidence-informed treatment (PRAISE) study protocol
Ronan Lyons
Belinda Gabbe
title_short Predicting fracture outcomes from clinical registry data using artificial intelligence supplemented models for evidence-informed treatment (PRAISE) study protocol
title_full Predicting fracture outcomes from clinical registry data using artificial intelligence supplemented models for evidence-informed treatment (PRAISE) study protocol
title_fullStr Predicting fracture outcomes from clinical registry data using artificial intelligence supplemented models for evidence-informed treatment (PRAISE) study protocol
title_full_unstemmed Predicting fracture outcomes from clinical registry data using artificial intelligence supplemented models for evidence-informed treatment (PRAISE) study protocol
title_sort Predicting fracture outcomes from clinical registry data using artificial intelligence supplemented models for evidence-informed treatment (PRAISE) study protocol
author_id_str_mv 83efcf2a9dfcf8b55586999d3d152ac6
4bdcc94332b2bd10530c5e71ceb04f14
author_id_fullname_str_mv 83efcf2a9dfcf8b55586999d3d152ac6_***_Ronan Lyons
4bdcc94332b2bd10530c5e71ceb04f14_***_Belinda Gabbe
author Ronan Lyons
Belinda Gabbe
author2 Joanna F. Dipnall
Richard Page
Lan Du
Matthew Costa
Ronan Lyons
Peter Cameron
Richard de Steiger
Raphael Hau
Andrew Bucknill
Andrew Oppy
Elton Edwards
Dinesh Varma
Myong Chol Jung
Belinda Gabbe
format Journal article
container_title PLOS ONE
container_volume 16
container_issue 9
container_start_page e0257361
publishDate 2021
institution Swansea University
issn 1932-6203
1932-6203
doi_str_mv 10.1371/journal.pone.0257361
publisher Public Library of Science (PLoS)
college_str Faculty of Medicine, Health and Life Sciences
hierarchytype
hierarchy_top_id facultyofmedicinehealthandlifesciences
hierarchy_top_title Faculty of Medicine, Health and Life Sciences
hierarchy_parent_id facultyofmedicinehealthandlifesciences
hierarchy_parent_title Faculty of Medicine, Health and Life Sciences
department_str Swansea University Medical School - Medicine{{{_:::_}}}Faculty of Medicine, Health and Life Sciences{{{_:::_}}}Swansea University Medical School - Medicine
document_store_str 1
active_str 0
description BackgroundDistal radius (wrist) fractures are the second most common fracture admitted to hospital. The anatomical pattern of these types of injuries is diverse, with variation in clinical management, guidelines for management remain inconclusive, and the uptake of findings from clinical trials into routine practice limited. Robust predictive modelling, which considers both the characteristics of the fracture and patient, provides the best opportunity to reduce variation in care and improve patient outcomes. This type of data is housed in unstructured data sources with no particular format or schema. The “Predicting fracture outcomes from clinical Registry data using Artificial Intelligence (AI) Supplemented models for Evidence-informed treatment (PRAISE)” study aims to use AI methods on unstructured data to describe the fracture characteristics and test if using this information improves identification of key fracture characteristics and prediction of patient-reported outcome measures and clinical outcomes following wrist fractures compared to prediction models based on standard registry data.Methods and designAdult (16+ years) patients presenting to the emergency department, treated in a short stay unit, or admitted to hospital for >24h for management of a wrist fracture in four Victorian hospitals will be included in this study. The study will use routine registry data from the Victorian Orthopaedic Trauma Outcomes Registry (VOTOR), and electronic medical record (EMR) information (e.g. X-rays, surgical reports, radiology reports, images). A multimodal deep learning fracture reasoning system (DLFRS) will be developed that reasons on EMR information. Machine learning prediction models will test the performance with/without output from the DLFRS.DiscussionThe PRAISE study will establish the use of AI techniques to provide enhanced information about fracture characteristics in people with wrist fractures. Prediction models using AI derived characteristics are expected to provide better prediction of clinical and patient-reported outcomes following distal radius fracture.
published_date 2021-09-23T14:11:01Z
_version_ 1821324357679448064
score 11.564073

Similar Items