دورية أكاديمية
Accuracy of an artificial intelligence algorithm for detecting moderate-to-severe vertebral compression fractures on abdominal and thoracic computed tomography scans.
| العنوان: | Accuracy of an artificial intelligence algorithm for detecting moderate-to-severe vertebral compression fractures on abdominal and thoracic computed tomography scans. |
|---|---|
| المؤلفون: | Pereira RFB; Hospital Sírio-Libanês, São Paulo, SP, Brazil., Helito PVP; Hospital Sírio-Libanês, São Paulo, SP, Brazil.; Instituto de Radiologia do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (InRad/HC-FMUSP), São Paulo, SP, Brazil.; Department of Radiology, Aspetar Qatar Orthopaedic and Sports Medicine Hospital. Doha, Qatar., Leão RV; Hospital Sírio-Libanês, São Paulo, SP, Brazil.; Instituto de Radiologia do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (InRad/HC-FMUSP), São Paulo, SP, Brazil., Rodrigues MB; Department of Radiology, Aspetar Qatar Orthopaedic and Sports Medicine Hospital. Doha, Qatar., Correa MFP; Hospital Sírio-Libanês, São Paulo, SP, Brazil.; Instituto de Radiologia do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (InRad/HC-FMUSP), São Paulo, SP, Brazil., Rodrigues FV; Hospital Sírio-Libanês, São Paulo, SP, Brazil.; Instituto de Radiologia do Hospital das Clínicas da Faculdade de Medicina da Universidade de São Paulo (InRad/HC-FMUSP), São Paulo, SP, Brazil. |
| المصدر: | Radiologia brasileira [Radiol Bras] 2024 May 03; Vol. 57, pp. e20230102. Date of Electronic Publication: 2024 May 03 (Print Publication: 2024). |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: Colegio Brasileiro De Radiologia Country of Publication: Brazil NLM ID: 1305000 Publication Model: eCollection Cited Medium: Print ISSN: 0100-3984 (Print) Linking ISSN: 01003984 NLM ISO Abbreviation: Radiol Bras Subsets: PubMed not MEDLINE |
| أسماء مطبوعة: | Original Publication: Rio De Janeiro : Colegio Brasileiro De Radiologia |
| مستخلص: | Objective: To describe the accuracy of HealthVCF, a software product that uses artificial intelligence, in the detection of incidental moderate-to-severe vertebral compression fractures (VCFs) on chest and abdominal computed tomography scans. Materials and Methods: We included a consecutive sample of 899 chest and abdominal computed tomography scans of patients 51-99 years of age. Scans were retrospectively evaluated by the software and by two specialists in musculoskeletal imaging for the presence of VCFs with vertebral body height loss > 25%. We compared the software analysis with that of a general radiologist, using the evaluation of the two specialists as the reference. Results: The software showed a diagnostic accuracy of 89.6% (95% CI: 87.4-91.5%) for moderate-to-severe VCFs, with a sensitivity of 73.8%, a specificity of 92.7%, and a negative predictive value of 94.8%. Among the 145 positive scans detected by the software, the general radiologist failed to report the fractures in 62 (42.8%), and the algorithm detected additional fractures in 38 of those scans. Conclusion: The software has good accuracy for the detection of moderate-to-severe VCFs, with high specificity, and can increase the opportunistic detection rate of VCFs by radiologists who do not specialize in musculoskeletal imaging. |
| References: | Osteoporos Int. 2006 Dec;17(12):1726-33. (PMID: 16983459) Ther Adv Musculoskelet Dis. 2021 Jul 10;13:1759720X211024029. (PMID: 34290831) Radiology. 2013 Jul;268(1):120-6. (PMID: 23449956) Lancet. 1999 Mar 13;353(9156):878-82. (PMID: 10093980) J Bone Miner Res. 1993 Sep;8(9):1137-48. (PMID: 8237484) PLoS One. 2017 May 22;12(5):e0178209. (PMID: 28542552) Radiology. 2017 Sep;284(3):788-797. (PMID: 28301777) AJR Am J Roentgenol. 2004 Oct;183(4):949-58. (PMID: 15385286) Osteoporos Int. 2016 Mar;27(3):1131-1136. (PMID: 26419470) World J Radiol. 2010 Oct 28;2(10):399-404. (PMID: 21161025) Arch Osteoporos. 2017 Dec;12(1):71. (PMID: 28785996) Osteoporos Int. 1999;10(3):214-21. (PMID: 10525713) J Intern Med. 2015 Jun;277(6):650-61. (PMID: 25832448) Lancet. 2011 Apr 9;377(9773):1276-87. (PMID: 21450337) Arq Bras Endocrinol Metabol. 2014 Jul;58(5):434-43. (PMID: 25166033) Eur Radiol. 2014 Apr;24(4):872-80. (PMID: 24425527) J Gerontol A Biol Sci Med Sci. 2013 Oct;68(10):1236-42. (PMID: 23833201) Am Fam Physician. 2001 Mar 1;63(5):897-904, 908. (PMID: 11261866) Eur Radiol. 2008 Aug;18(8):1696-702. (PMID: 18418607) Eur J Radiol. 2009 Jan;69(1):179-83. (PMID: 17913429) |
| فهرسة مساهمة: | Keywords: Artificial intelligence; Fractures; Lumbar vertebrae/diagnostic imaging; Osteoporosis; Spinal fractures/diagnostic imaging; Thoracic vertebrae/diagnostic imaging; compression/diagnostic imaging Local Abstract: [Publisher, Portuguese] Descrever a acurácia do software HealthVCF na detecção incidental de fraturas compressivas de corpos vertebrais moderadas a graves em exames de tomografia computadorizada do tórax e abdome. [Publisher, Portuguese] Foram incluídos 899 exames consecutivos de pacientes com idades entre 51 e 99 anos. As imagens foram retrospectivamente avaliadas pelo software e por dois radiologistas especializados em musculoesquelético que investigaram fraturas compressivas de corpos vertebrais com perda da altura somática > 25%. A análise comparativa foi realizada entre o software e um radiologista geral, usando a avaliação do especialista como referência. [Publisher, Portuguese] O software apresentou uma acurácia de 89,6% (IC 95%: 87,4–91,5%) para fraturas compressivas moderadas a graves, com sensibilidade de 73,8%, especificidade de 92,7% e valor preditivo negativo de 94,8%. Entre as 145 tomografias positivas detectadas pelo software, o radiologista geral deixou de relatar as fraturas em 62 (42,8%) e o algoritmo detectou fraturas adicionais em 38 dessas tomografias. [Publisher, Portuguese] O software possui boa acurácia na detecção de fraturas compressivas moderadas a graves, com alta especificidade, podendo aumentar a taxa de detecção oportunística dessas fraturas por radiologistas não especializados em musculoesquelético. |
| تواريخ الأحداث: | Date Created: 20240712 Latest Revision: 20240714 |
| رمز التحديث: | 20240714 |
| مُعرف محوري في PubMed: | PMC11235064 |
| DOI: | 10.1590/0100-3984.2023.0102 |
| PMID: | 38993956 |
| قاعدة البيانات: | MEDLINE |
Full Text Finder | تدمد: | 0100-3984 |
|---|---|
| DOI: | 10.1590/0100-3984.2023.0102 |