Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204235144> ?p ?o ?g. }
- W3204235144 abstract "Epiretinal membrane (ERM) is a common ophthalmological disorder of high prevalence. Its symptoms include metamorphopsia, blurred vision, and decreased visual acuity. Early diagnosis and timely treatment of ERM is crucial to preventing vision loss. Although optical coherence tomography (OCT) is regarded as a de facto standard for ERM diagnosis due to its intuitiveness and high sensitivity, ophthalmoscopic examination or fundus photographs still have the advantages of price and accessibility. Artificial intelligence (AI) has been widely applied in the health care industry for its robust and significant performance in detecting various diseases. In this study, we validated the use of a previously trained deep neural network based-AI model in ERM detection based on color fundus photographs. An independent test set of fundus photographs was labeled by a group of ophthalmologists according to their corresponding OCT images as the gold standard. Then the test set was interpreted by other ophthalmologists and AI model without knowing their OCT results. Compared with manual diagnosis based on fundus photographs alone, the AI model had comparable accuracy (AI model 77.08% vs. integrated manual diagnosis 75.69%, χ2 = 0.038, P = 0.845, McNemar's test), higher sensitivity (75.90% vs. 63.86%, χ2 = 4.500, P = 0.034, McNemar's test), under the cost of lower but reasonable specificity (78.69% vs. 91.80%, χ2 = 6.125, P = 0.013, McNemar's test). Thus our AI model can serve as a possible alternative for manual diagnosis in ERM screening." @default.
- W3204235144 created "2021-10-11" @default.
- W3204235144 creator A5009314993 @default.
- W3204235144 creator A5015253950 @default.
- W3204235144 creator A5017139813 @default.
- W3204235144 creator A5025505139 @default.
- W3204235144 creator A5033695487 @default.
- W3204235144 creator A5066150985 @default.
- W3204235144 creator A5067153593 @default.
- W3204235144 creator A5069271615 @default.
- W3204235144 creator A5073216396 @default.
- W3204235144 date "2021-09-29" @default.
- W3204235144 modified "2023-09-28" @default.
- W3204235144 title "Artificial intelligence-based detection of epimacular membrane from color fundus photographs" @default.
- W3204235144 cites W1981474379 @default.
- W3204235144 cites W1987295636 @default.
- W3204235144 cites W2000401548 @default.
- W3204235144 cites W2013734026 @default.
- W3204235144 cites W2018888962 @default.
- W3204235144 cites W2041245941 @default.
- W3204235144 cites W2042622212 @default.
- W3204235144 cites W2046081148 @default.
- W3204235144 cites W2047129867 @default.
- W3204235144 cites W2056716070 @default.
- W3204235144 cites W2058090383 @default.
- W3204235144 cites W2058809611 @default.
- W3204235144 cites W2070121808 @default.
- W3204235144 cites W2072732294 @default.
- W3204235144 cites W2090893538 @default.
- W3204235144 cites W2091599444 @default.
- W3204235144 cites W2097117768 @default.
- W3204235144 cites W2113305774 @default.
- W3204235144 cites W2128019619 @default.
- W3204235144 cites W2128045502 @default.
- W3204235144 cites W2141860662 @default.
- W3204235144 cites W2230079542 @default.
- W3204235144 cites W2269131495 @default.
- W3204235144 cites W2466721823 @default.
- W3204235144 cites W2531409750 @default.
- W3204235144 cites W2557738935 @default.
- W3204235144 cites W2579138220 @default.
- W3204235144 cites W2598442119 @default.
- W3204235144 cites W2726915958 @default.
- W3204235144 cites W2729433380 @default.
- W3204235144 cites W2752604242 @default.
- W3204235144 cites W2758333670 @default.
- W3204235144 cites W2759091466 @default.
- W3204235144 cites W2772246530 @default.
- W3204235144 cites W2792026451 @default.
- W3204235144 cites W2796809202 @default.
- W3204235144 cites W2800012666 @default.
- W3204235144 cites W2892198691 @default.
- W3204235144 cites W2906751147 @default.
- W3204235144 cites W2907759749 @default.
- W3204235144 cites W2919115771 @default.
- W3204235144 cites W2962858109 @default.
- W3204235144 cites W2964350391 @default.
- W3204235144 cites W2970772642 @default.
- W3204235144 cites W2971891052 @default.
- W3204235144 cites W2975496140 @default.
- W3204235144 cites W3185043567 @default.
- W3204235144 doi "https://doi.org/10.1038/s41598-021-98510-x" @default.
- W3204235144 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/8481557" @default.
- W3204235144 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34588493" @default.
- W3204235144 hasPublicationYear "2021" @default.
- W3204235144 type Work @default.
- W3204235144 sameAs 3204235144 @default.
- W3204235144 citedByCount "2" @default.
- W3204235144 countsByYear W32042351442022 @default.
- W3204235144 countsByYear W32042351442023 @default.
- W3204235144 crossrefType "journal-article" @default.
- W3204235144 hasAuthorship W3204235144A5009314993 @default.
- W3204235144 hasAuthorship W3204235144A5015253950 @default.
- W3204235144 hasAuthorship W3204235144A5017139813 @default.
- W3204235144 hasAuthorship W3204235144A5025505139 @default.
- W3204235144 hasAuthorship W3204235144A5033695487 @default.
- W3204235144 hasAuthorship W3204235144A5066150985 @default.
- W3204235144 hasAuthorship W3204235144A5067153593 @default.
- W3204235144 hasAuthorship W3204235144A5069271615 @default.
- W3204235144 hasAuthorship W3204235144A5073216396 @default.
- W3204235144 hasBestOaLocation W32042351441 @default.
- W3204235144 hasConcept C105795698 @default.
- W3204235144 hasConcept C118487528 @default.
- W3204235144 hasConcept C119767625 @default.
- W3204235144 hasConcept C126838900 @default.
- W3204235144 hasConcept C151730666 @default.
- W3204235144 hasConcept C154945302 @default.
- W3204235144 hasConcept C169903167 @default.
- W3204235144 hasConcept C186282968 @default.
- W3204235144 hasConcept C2776391266 @default.
- W3204235144 hasConcept C2777267654 @default.
- W3204235144 hasConcept C2778257484 @default.
- W3204235144 hasConcept C2778348428 @default.
- W3204235144 hasConcept C2778818243 @default.
- W3204235144 hasConcept C2781242345 @default.
- W3204235144 hasConcept C2781325737 @default.
- W3204235144 hasConcept C33923547 @default.
- W3204235144 hasConcept C40993552 @default.
- W3204235144 hasConcept C41008148 @default.
- W3204235144 hasConcept C71924100 @default.