Nithin Kolanu1,2, A Shane Brown3, Amanda Beech4,3,5, Jacqueline R Center6,5,7, Christopher P White6,4,3,5. 1. Clinical Epidemiology/Healthy Ageing Division, Garvan Institute of Medical Research, Sydney, NSW, 2010, Australia. n.kolanu@garvan.org.au. 2. Prince of Wales Hospital, Randwick, Sydney, NSW, Australia. n.kolanu@garvan.org.au. 3. Royal Hospital for Women, Randwick, Sydney, NSW, Australia. 4. Prince of Wales Hospital, Randwick, Sydney, NSW, Australia. 5. University of New South Wales, Sydney, NSW, Australia. 6. Clinical Epidemiology/Healthy Ageing Division, Garvan Institute of Medical Research, Sydney, NSW, 2010, Australia. 7. St Vincent's Hospital Clinical School, Darlinghurst, NSW, Australia.
Abstract
Text-search software can be used to identify people at risk of re-fracture. The software studied identified a threefold higher number of people with fractures compared with conventional case finding. Automated software could assist fracture liaison services to identify more people at risk than traditional case finding. PURPOSE: Fracture liaison services address the post-fracture treatment gap in osteoporosis (OP). Natural language processing (NLP) is able to identify previously unrecognized patients by screening large volumes of radiology reports. The aim of this study was to compare an NLP software tool, XRAIT (X-Ray Artificial Intelligence Tool), with a traditional fracture liaison service at its development site (Prince of Wales Hospital [POWH], Sydney) and externally validate it in an adjudicated cohort from the Dubbo Osteoporosis Epidemiology Study (DOES). METHODS: XRAIT searches radiology reports for fracture-related terms. At the development site (POWH), XRAIT and a blinded fracture liaison clinician (FLC) reviewed 5,089 reports and 224 presentations, respectively, of people 50 years or over during a simultaneous 3-month period. In the external cohort of DOES, XRAIT was used without modification to analyse digitally readable radiology reports (n = 327) to calculate its sensitivity and specificity. RESULTS: XRAIT flagged 433 fractures after searching 5,089 reports (421 true fractures, positive predictive value of 97%). It identified more than a threefold higher number of fractures (421 fractures/339 individuals) compared with manual case finding (98 individuals). Unadjusted for the local reporting style in an external cohort (DOES), XRAIT had a sensitivity of 70% and specificity of 92%. CONCLUSION: XRAIT identifies significantly more clinically significant fractures than manual case finding. High specificity in an untrained cohort suggests that it could be used at other sites. Automated methods of fracture identification may assist fracture liaison services so that limited resources can be spent on treatment rather than case finding.
Text-search software can be used to identify people at risk of re-fracture. The software studied identified a threefold higher number of people with fractures compared with conventional case finding. Automated software could assist fracture liaison services to identify more people at risk than traditional case finding. PURPOSE: Fracture liaison services address the post-fracture treatment gap in osteoporosis (OP). Natural language processing (NLP) is able to identify previously unrecognized patients by screening large volumes of radiology reports. The aim of this study was to compare an NLP software tool, XRAIT (X-Ray Artificial Intelligence Tool), with a traditional fracture liaison service at its development site (Prince of Wales Hospital [POWH], Sydney) and externally validate it in an adjudicated cohort from the Dubbo Osteoporosis Epidemiology Study (DOES). METHODS: XRAIT searches radiology reports for fracture-related terms. At the development site (POWH), XRAIT and a blinded fracture liaison clinician (FLC) reviewed 5,089 reports and 224 presentations, respectively, of people 50 years or over during a simultaneous 3-month period. In the external cohort of DOES, XRAIT was used without modification to analyse digitally readable radiology reports (n = 327) to calculate its sensitivity and specificity. RESULTS: XRAIT flagged 433 fractures after searching 5,089 reports (421 true fractures, positive predictive value of 97%). It identified more than a threefold higher number of fractures (421 fractures/339 individuals) compared with manual case finding (98 individuals). Unadjusted for the local reporting style in an external cohort (DOES), XRAIT had a sensitivity of 70% and specificity of 92%. CONCLUSION: XRAIT identifies significantly more clinically significant fractures than manual case finding. High specificity in an untrained cohort suggests that it could be used at other sites. Automated methods of fracture identification may assist fracture liaison services so that limited resources can be spent on treatment rather than case finding.
Authors: Seoyoung C Kim; Mi-Sook Kim; Gabriel Sanfélix-Gimeno; Hong Ji Song; Jun Liu; Isabel Hurtado; Salvador Peiró; Joongyub Lee; Nam-Kyong Choi; Byung-Joo Park; Jerry Avorn Journal: Am J Med Date: 2015-02-03 Impact factor: 4.965
Authors: Kirsten M B Huntjens; Tineke A C M van Geel; Joop P W van den Bergh; Svenhjalmar van Helden; Paul Willems; Bjorn Winkens; John A Eisman; Piet P Geusens; Peter R G Brink Journal: J Bone Joint Surg Am Date: 2014-02-19 Impact factor: 5.284
Authors: John A Eisman; Earl R Bogoch; Rick Dell; J Timothy Harrington; Ross E McKinney; Alastair McLellan; Paul J Mitchell; Stuart Silverman; Rick Singleton; Ethel Siris Journal: J Bone Miner Res Date: 2012-07-26 Impact factor: 6.741
Authors: O Johnell; J A Kanis; A Odén; I Sernbo; I Redlund-Johnell; C Petterson; C De Laet; B Jönsson Journal: Osteoporos Int Date: 2003-12-23 Impact factor: 4.507
Authors: Axel Wismüller; Adora M DSouza; Anas Z Abidin; M Ali Vosoughi; Christopher Gange; Isabel O Cortopassi; Gracijela Bozovic; Alexander A Bankier; Kiran Batra; Yosef Chodakiewitz; Yin Xi; Christopher T Whitlow; Janardhana Ponnatapura; Gary J Wendt; Eric P Weinberg; Larry Stockmaster; David A Shrier; Min Chul Shin; Roshan Modi; Hao Steven Lo; Seth Kligerman; Aws Hamid; Lewis D Hahn; Glenn M Garcia; Jonathan H Chung; Talissa Altes; Suhny Abbara; Anna S Bader Journal: NPJ Digit Med Date: 2022-08-19