PMID- 38343243
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20240422
LR  - 20240426
IS  - 2948-2933 (Electronic)
IS  - 2948-2925 (Print)
IS  - 2948-2925 (Linking)
VI  - 37
IP  - 2
DP  - 2024 Apr
TI  - Diagnostic Performance of Artificial Intelligence in Detection of Primary 
      Malignant Bone Tumors: a Meta-Analysis.
PG  - 766-777
LID - 10.1007/s10278-023-00945-3 [doi]
AB  - We aim to conduct a meta-analysis on studies that evaluated the diagnostic 
      performance of artificial intelligence (AI) algorithms in the detection of 
      primary bone tumors, distinguishing them from other bone lesions, and comparing 
      them with clinician assessment. A systematic search was conducted using a 
      combination of keywords related to bone tumors and AI. After extracting 
      contingency tables from all included studies, we performed a meta-analysis using 
      random-effects model to determine the pooled sensitivity and specificity, 
      accompanied by their respective 95% confidence intervals (CI). Quality assessment 
      was evaluated using a modified version of Transparent Reporting of a 
      Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) and 
      Prediction Model Study Risk of Bias Assessment Tool (PROBAST). The pooled 
      sensitivities for AI algorithms and clinicians on internal validation test sets 
      for detecting bone neoplasms were 84% (95% CI: 79.88) and 76% (95% CI: 64.85), 
      and pooled specificities were 86% (95% CI: 81.90) and 64% (95% CI: 55.72), 
      respectively. At external validation, the pooled sensitivity and specificity for 
      AI algorithms were 84% (95% CI: 75.90) and 91% (95% CI: 83.96), respectively. The 
      same numbers for clinicians were 85% (95% CI: 73.92) and 94% (95% CI: 89.97), 
      respectively. The sensitivity and specificity for clinicians with AI assistance 
      were 95% (95% CI: 86.98) and 57% (95% CI: 48.66). Caution is needed when 
      interpreting findings due to potential limitations. Further research is needed to 
      bridge this gap in scientific understanding and promote effective implementation 
      for medical practice advancement.
CI  - (c) 2024. The Author(s) under exclusive licence to Society for Imaging Informatics 
      in Medicine.
FAU - Salehi, Mohammad Amin
AU  - Salehi MA
AD  - School of Medicine, Tehran University of Medical Sciences, Pour Sina St, 
      Keshavarz Blvd, Tehran, 1417613151, Iran.
FAU - Mohammadi, Soheil
AU  - Mohammadi S
AD  - School of Medicine, Tehran University of Medical Sciences, Pour Sina St, 
      Keshavarz Blvd, Tehran, 1417613151, Iran. soheil.mhm@gmail.com.
FAU - Harandi, Hamid
AU  - Harandi H
AD  - School of Medicine, Tehran University of Medical Sciences, Pour Sina St, 
      Keshavarz Blvd, Tehran, 1417613151, Iran.
FAU - Zakavi, Seyed Sina
AU  - Zakavi SS
AD  - School of Medicine, Tabriz University of Medical Sciences, Tabriz, Iran.
FAU - Jahanshahi, Ali
AU  - Jahanshahi A
AD  - School of Medicine, Guilan University of Medical Sciences, Rasht, Iran.
FAU - Shahrabi Farahani, Mohammad
AU  - Shahrabi Farahani M
AD  - Medical Students Research Committee, Shahed University, Tehran, Iran.
FAU - Wu, Jim S
AU  - Wu JS
AD  - Department of Radiology, Beth Israel Deaconess Medical Center, Harvard Medical 
      School, 330 Brookline Avenue, Boston, MA, 02215, USA.
LA  - eng
PT  - Journal Article
PT  - Review
DEP - 20240112
PL  - Switzerland
TA  - J Imaging Inform Med
JT  - Journal of imaging informatics in medicine
JID - 9918663679206676
SB  - IM
PMC - PMC11031503
OTO - NOTNLM
OT  - Artificial intelligence
OT  - Bone malignancies
OT  - Bone tumor
OT  - Deep learning
OT  - Machine learning
COIS- The authors declare no competing interests.
EDAT- 2024/02/12 15:42
MHDA- 2024/02/12 15:43
PMCR- 2024/01/12
CRDT- 2024/02/12 02:33
PHST- 2023/08/01 00:00 [received]
PHST- 2023/10/12 00:00 [accepted]
PHST- 2023/10/04 00:00 [revised]
PHST- 2024/02/12 15:43 [medline]
PHST- 2024/02/12 15:42 [pubmed]
PHST- 2024/02/12 02:33 [entrez]
PHST- 2024/01/12 00:00 [pmc-release]
AID - 10.1007/s10278-023-00945-3 [pii]
AID - 945 [pii]
AID - 10.1007/s10278-023-00945-3 [doi]
PST - ppublish
SO  - J Imaging Inform Med. 2024 Apr;37(2):766-777. doi: 10.1007/s10278-023-00945-3. 
      Epub 2024 Jan 12.