Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311453650> ?p ?o ?g. }
- W4311453650 abstract "Rationale and objectives Reproducibility of artificial intelligence (AI) research has become a growing concern. One of the fundamental reasons is the lack of transparency in data, code, and model. In this work, we aimed to systematically review the radiology and nuclear medicine papers on AI in terms of transparency and open science. Materials and Methods A systematic literature search was performed in PubMed to identify original research studies on AI. The search was restricted to studies published in Q1 and Q2 journals that are also indexed on the Web of Science. A random sampling of the literature was performed. Besides six baseline study characteristics, a total of five availability items were evaluated. Two groups of independent readers including eight readers participated in the study. Inter-rater agreement was analyzed. Disagreements were resolved with consensus. Results Following eligibility criteria, we included a final set of 194 papers. The raw data was available in about one-fifth of the papers (34/194; 18%). However, the authors made their private data available only in one paper (1/161; 1%). About one-tenth of the papers made their pre-modeling (25/194; 13%), modeling (28/194; 14%), or post-modeling files (15/194; 8%) available. Most of the papers (189/194; 97%) did not attempt to create a ready-to-use system for real-world usage. Data origin, use of deep learning, and external validation had statistically significantly different distributions. The use of private data alone was negatively associated with the availability of at least one item (p<0.001). Conclusion Overall rates of availability for items were poor, leaving room for substantial improvement. Reproducibility of artificial intelligence (AI) research has become a growing concern. One of the fundamental reasons is the lack of transparency in data, code, and model. In this work, we aimed to systematically review the radiology and nuclear medicine papers on AI in terms of transparency and open science. A systematic literature search was performed in PubMed to identify original research studies on AI. The search was restricted to studies published in Q1 and Q2 journals that are also indexed on the Web of Science. A random sampling of the literature was performed. Besides six baseline study characteristics, a total of five availability items were evaluated. Two groups of independent readers including eight readers participated in the study. Inter-rater agreement was analyzed. Disagreements were resolved with consensus. Following eligibility criteria, we included a final set of 194 papers. The raw data was available in about one-fifth of the papers (34/194; 18%). However, the authors made their private data available only in one paper (1/161; 1%). About one-tenth of the papers made their pre-modeling (25/194; 13%), modeling (28/194; 14%), or post-modeling files (15/194; 8%) available. Most of the papers (189/194; 97%) did not attempt to create a ready-to-use system for real-world usage. Data origin, use of deep learning, and external validation had statistically significantly different distributions. The use of private data alone was negatively associated with the availability of at least one item (p<0.001). Overall rates of availability for items were poor, leaving room for substantial improvement." @default.
- W4311453650 created "2022-12-26" @default.
- W4311453650 creator A5020961489 @default.
- W4311453650 creator A5021502056 @default.
- W4311453650 creator A5026473179 @default.
- W4311453650 creator A5031985958 @default.
- W4311453650 creator A5057316894 @default.
- W4311453650 creator A5059163661 @default.
- W4311453650 creator A5067516704 @default.
- W4311453650 creator A5074166234 @default.
- W4311453650 date "2022-12-01" @default.
- W4311453650 modified "2023-10-18" @default.
- W4311453650 title "Transparency in Artificial Intelligence Research: a Systematic Review of Availability Items Related to Open Science in Radiology and Nuclear Medicine" @default.
- W4311453650 cites W1825120118 @default.
- W4311453650 cites W2015265189 @default.
- W4311453650 cites W2077181076 @default.
- W4311453650 cites W2084341220 @default.
- W4311453650 cites W2105824687 @default.
- W4311453650 cites W2144981148 @default.
- W4311453650 cites W2166378641 @default.
- W4311453650 cites W2169512394 @default.
- W4311453650 cites W2228927609 @default.
- W4311453650 cites W2406493898 @default.
- W4311453650 cites W2414283705 @default.
- W4311453650 cites W2598446296 @default.
- W4311453650 cites W2787225861 @default.
- W4311453650 cites W2789242863 @default.
- W4311453650 cites W2791320132 @default.
- W4311453650 cites W2799424953 @default.
- W4311453650 cites W2799873608 @default.
- W4311453650 cites W2913997948 @default.
- W4311453650 cites W2921613140 @default.
- W4311453650 cites W2945270037 @default.
- W4311453650 cites W2962850237 @default.
- W4311453650 cites W2968126678 @default.
- W4311453650 cites W2968631110 @default.
- W4311453650 cites W2971563774 @default.
- W4311453650 cites W2997449172 @default.
- W4311453650 cites W3004306740 @default.
- W4311453650 cites W3004476491 @default.
- W4311453650 cites W3008058947 @default.
- W4311453650 cites W3011403448 @default.
- W4311453650 cites W3013294478 @default.
- W4311453650 cites W3045772401 @default.
- W4311453650 cites W3084171410 @default.
- W4311453650 cites W3088267623 @default.
- W4311453650 cites W3138291572 @default.
- W4311453650 cites W3161335554 @default.
- W4311453650 cites W3215875675 @default.
- W4311453650 cites W4304481303 @default.
- W4311453650 cites W585341442 @default.
- W4311453650 doi "https://doi.org/10.1016/j.acra.2022.11.030" @default.
- W4311453650 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36526532" @default.
- W4311453650 hasPublicationYear "2022" @default.
- W4311453650 type Work @default.
- W4311453650 citedByCount "2" @default.
- W4311453650 countsByYear W43114536502023 @default.
- W4311453650 crossrefType "journal-article" @default.
- W4311453650 hasAuthorship W4311453650A5020961489 @default.
- W4311453650 hasAuthorship W4311453650A5021502056 @default.
- W4311453650 hasAuthorship W4311453650A5026473179 @default.
- W4311453650 hasAuthorship W4311453650A5031985958 @default.
- W4311453650 hasAuthorship W4311453650A5057316894 @default.
- W4311453650 hasAuthorship W4311453650A5059163661 @default.
- W4311453650 hasAuthorship W4311453650A5067516704 @default.
- W4311453650 hasAuthorship W4311453650A5074166234 @default.
- W4311453650 hasConcept C105795698 @default.
- W4311453650 hasConcept C132964779 @default.
- W4311453650 hasConcept C142724271 @default.
- W4311453650 hasConcept C154945302 @default.
- W4311453650 hasConcept C19527891 @default.
- W4311453650 hasConcept C199360897 @default.
- W4311453650 hasConcept C2522767166 @default.
- W4311453650 hasConcept C2778149293 @default.
- W4311453650 hasConcept C2780233690 @default.
- W4311453650 hasConcept C3020774429 @default.
- W4311453650 hasConcept C33923547 @default.
- W4311453650 hasConcept C38652104 @default.
- W4311453650 hasConcept C41008148 @default.
- W4311453650 hasConcept C71924100 @default.
- W4311453650 hasConcept C95190672 @default.
- W4311453650 hasConceptScore W4311453650C105795698 @default.
- W4311453650 hasConceptScore W4311453650C132964779 @default.
- W4311453650 hasConceptScore W4311453650C142724271 @default.
- W4311453650 hasConceptScore W4311453650C154945302 @default.
- W4311453650 hasConceptScore W4311453650C19527891 @default.
- W4311453650 hasConceptScore W4311453650C199360897 @default.
- W4311453650 hasConceptScore W4311453650C2522767166 @default.
- W4311453650 hasConceptScore W4311453650C2778149293 @default.
- W4311453650 hasConceptScore W4311453650C2780233690 @default.
- W4311453650 hasConceptScore W4311453650C3020774429 @default.
- W4311453650 hasConceptScore W4311453650C33923547 @default.
- W4311453650 hasConceptScore W4311453650C38652104 @default.
- W4311453650 hasConceptScore W4311453650C41008148 @default.
- W4311453650 hasConceptScore W4311453650C71924100 @default.
- W4311453650 hasConceptScore W4311453650C95190672 @default.
- W4311453650 hasLocation W43114536501 @default.
- W4311453650 hasLocation W43114536502 @default.
- W4311453650 hasOpenAccess W4311453650 @default.
- W4311453650 hasPrimaryLocation W43114536501 @default.