A guide to optometrists for appraising and using artificial intelligence in clinical practice

References

• Rajpurohit DS, Seal R. Legal definition of artificial intelligence. Supremo Amic 2019; 10: 87–95.
   Google Scholar
• Wang C, Huang Q, Cheng M et al. Deep learning for camera autofocus. IEEE Trans Comput Imaging 2021; 7: 258–271. doi:10.1109/TCI.2021.3059497.
   Web of Science ®Google Scholar
• Herrmann C, Bowen RS, Wadhwa N et al. Learning to autofocus. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020. p. 2230–2239.
   Google Scholar
• Sadda SR, Nittala MG, Taweebanjongsin W et al. Quantitative assessment of the severity of diabetic retinopathy. Am J Ophthalmol 2020; 218: 342–352. doi:10.1016/j.ajo.2020.05.021.
   PubMed Web of Science ®Google Scholar
• Ting DSW, Pasquale LR, Peng L et al. Artificial intelligence and deep learning in ophthalmology. Br J Ophthalmol 2019; 103: 167–175. doi:10.1136/bjophthalmol-2018-313173.
   PubMed Web of Science ®Google Scholar
• Bayer A, Akman A. Artifacts and anatomic variations in optical coherence tomography. Turkish J Ophthalmol/Turk Oftalmol Derg 2020; 50: 99–106. doi:10.4274/tjo.galenos.2019.78000.
   PubMed Web of Science ®Google Scholar
• Charng J, Alam K, Swartz G et al. Deep learning: applications in retinal and optic nerve diseases. Clin Exp Optom 2022: 1–10. doi:10.1080/08164622.2022.2111201.
   PubMed Web of Science ®Google Scholar
• Zhou Y, Yu K, Wang M et al. Speckle noise reduction for OCT images based on image style transfer and conditional GAN. IEEE J Biomed Heal Informatics 2022; 26: 139–150. doi:10.1109/JBHI.2021.3074852.
   PubMed Web of Science ®Google Scholar
• Wang M, Zhu W, Yu K et al. Semi-supervised capsule cGAN for speckle noise reduction in retinal OCT images. IEEE Trans Med Imaging 2021; 40: 1168–1183. doi:10.1109/TMI.2020.3048975.
   PubMed Web of Science ®Google Scholar
• Grath OM, Sarfraz MW, Gupta A et al. Clinical utility of artificial intelligence algorithms to enhance wide-field optical coherence tomography angiography images. J Imaging 2021; 7: 32. doi:10.3390/jimaging7020032.
   PubMed Web of Science ®Google Scholar
• Liu Y, Carass A, He Y et al. Layer boundary evolution method for macular OCT layer segmentation. Biomed Opt Express 2019; 10: 1064–1080. doi:10.1364/BOE.10.001064.
   PubMed Web of Science ®Google Scholar
• Gao K, Kong W, Niu S et al. Automatic retinal layer segmentation in SD-OCT images with CSC guided by spatial characteristics. Multimed Tools Appl 2020; 79: 4417–4428. doi:10.1007/s11042-019-7395-9.
   Web of Science ®Google Scholar
• Cavichini M, An C, Bartsch DU et al. Artificial intelligence for automated overlay of fundus camera and scanning laser ophthalmoscope images. Transl Vis Sci Technol 2020; 9: 56. doi:10.1167/tvst.9.2.56.
   PubMed Web of Science ®Google Scholar
• Wang Y, Yu X, Wu C. Optic disc detection based on fully convolutional neural network and structured matrix decomposition. Multimed Tools Appl an Int J 2022; 81: 1–21. doi:10.1007/s11042-022-12235-1.
   PubMed Web of Science ®Google Scholar
• Yu X, Wang Y, Wang S et al. Fully convolutional network and visual saliency-based automatic optic disc detection in retinal fundus images. J Healthc Eng 2021; 2021: 3561134. doi:10.1155/2021/3561134.
   PubMed Web of Science ®Google Scholar
• Huang Y, Zhong Z, Yuan J et al. Efficient and robust optic disc detection and fovea localization using region proposal network and cascaded network. Biomed Signal Process Control 2020; 60: 60. doi:10.1016/j.bspc.2020.101939.
   Web of Science ®Google Scholar
• Raman R, Srinivasan S, Virmani S et al. Fundus photograph-based deep learning algorithms in detecting diabetic retinopathy. Eye (Lond) 2019; 33: 97–109. doi:10.1038/s41433-018-0269-y.
   PubMed Web of Science ®Google Scholar
• Milea D, Najjar RP, Jiang Z et al. Artificial intelligence to detect papilledema from ocular fundus photographs. N Engl J Med 2020; 382: 1687–1695. Epub ahead of print 2020. doi:10.1056/nejmoa1917130.
   PubMed Web of Science ®Google Scholar
• Benjamens S, Dhunnoo P, Meskó B. The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database. NPJ Digit Med 2020; 3: 118. doi:10.1038/s41746-020-00324-0.
   PubMed Web of Science ®Google Scholar
• Ghassemi M, Oakden-Rayner L, Beam AL. The false hope of current approaches to explainable artificial intelligence in health care. Lancet Digit Heal 2021; 3: e745–750. doi:10.1016/S2589-7500(21)00208-9.
   PubMedGoogle Scholar
• Scheetz J, Rothschild P, McGuinness M et al. A survey of clinicians on the use of artificial intelligence in ophthalmology, dermatology, radiology and radiation oncology. Sci Rep 2021; 11: 5193. doi:10.1038/s41598-021-84698-5.
   PubMed Web of Science ®Google Scholar
• Loyola-González O. Black-box vs. white-box: understanding their advantages and weaknesses from a practical point of view. IEEE Access 2019; 7: 154096–154113. doi:10.1109/ACCESS.2019.2949286.
   Web of Science ®Google Scholar
• Wadden JJ. What kind of artificial intelligence should we want for use in healthcare decision-making applications? Can J Bioeth 2021 Jun 1; 4: 94–100. Epub ahead of print. doi:10.7202/1077636ar.
   Google Scholar
• Islam M, Ahmed M, Barua S et al. A systematic review of explainable artificial intelligence in terms of different application domains and tasks. Appl Sci 2022; 12: 1353. doi:10.3390/app12031353.
   Google Scholar
• Wang F, Kaushal R, Khullar D. Should health care demand interpretable artificial intelligence or accept ‘black box’ medicine? Ann Intern Med 2020; 172: 59–60. doi:10.7326/M19-2548.
   PubMed Web of Science ®Google Scholar
• Lippmann R. An introduction to computing with neural nets. IEEE ASSP Mag 1987; 4: 4–22. doi:10.1109/MASSP.1987.1165576.
   Google Scholar
• Yang L, Song Q, Fan Z et al. Rethinking the activation function in lightweight network. Multimed Tools Appl an Int J 2022; 82: 1–17. doi:10.1007/s11042-022-13217-z.
   Web of Science ®Google Scholar
• He K, Zhang X, Ren S et al. Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016. p. 770–778.
   Google Scholar
• Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images. Toronto (ON), Canada: University of Toronto; 2009.
   Google Scholar
• Alexander D. Neural networks : history and applications. New York (NY/USA): Nova Science Publishers, Inc; 2020.
   Google Scholar
• Li G, Wang J, Shen H-W et al. CNNPruner: pruning convolutional neural networks with visual analytics. IEEE Trans Vis Comput Graph 2021; 27: 1364–1373. doi:10.1109/TVCG.2020.3030461.
   PubMed Web of Science ®Google Scholar
• Fukushima K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern 1980; 36: 193–202. doi:10.1007/BF00344251.
   PubMed Web of Science ®Google Scholar
• Ting D, Lee A, Wong TY. Artificial intelligence research in ophthalmology: guidance on understanding, appraising, and reading an article. Ophthalmology 2019 Sep 1; 126: 1475–1479. Epub ahead of print. doi:10.1016/j.ophtha.2019.09.014.
   PubMed Web of Science ®Google Scholar
• LeCun Y, Boser B, Denker JS et al. Backpropagation applied to handwritten zip code recognition. Neural Comput 1989; 1: 541–551. doi:10.1162/neco.1989.1.4.541.
   Web of Science ®Google Scholar
• Demšar J, Zupan B, Palagi PM. Hands-on training about overfitting. PLoS Comput Biol 2021; 17: e1008671. doi:10.1371/journal.pcbi.1008671.
   PubMed Web of Science ®Google Scholar
• Nikolaienko T, Gurbych O, Druchok M. Complex machine learning model needs complex testing: examining predictability of molecular binding affinity by a graph neural network. J Comput Chem 2022; 43: 728–739. doi:10.1002/jcc.26831.
   PubMed Web of Science ®Google Scholar
• Farag HH, Said LAA, Rizk MRM et al. Hyperparameters optimization for ResNet and Xception in the purpose of diagnosing COVID-19. J Intell Fuzzy Syst 2021; 41: 3555–3571. doi:10.3233/JIFS-210925.
   Web of Science ®Google Scholar
• Szegedy C, Ioffe S, Vanhoucke V et al. Inception-v4, Inception-ResNet and the impact of residual connections on learning. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. AAAI Press; 2017. p. 4278–4284.
   Google Scholar
• Szegedy C, Vanhoucke V, Ioffe S et al. Rethinking the inception architecture for computer vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Computer Vision and Pattern Recognition (CVPR), 2016 IEEE Conference on 2016. p. 2818–2826.
   Google Scholar
• Li T, Gao Y, Wang K et al. Diagnostic assessment of deep learning algorithms for diabetic retinopathy screening. Inf Sci (Ny) 2019; 501: 511–522. doi:10.1016/j.ins.2019.06.011.
   Web of Science ®Google Scholar
• Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. In: Fleet D, Pajdla T, and Schiele B et al., editors. Cham: Springer International Publishing; 2014. p. 818–833.
   Google Scholar
• Selvaraju RR, Cogswell M, Das A et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis 2020; 128: 336–359. doi:10.1007/s11263-019-01228-7.
   Web of Science ®Google Scholar
• Korot E, Pontikos N, Liu X et al. Predicting sex from retinal fundus photographs using automated deep learning. Sci Rep 2021; 11: 10286. doi:10.1038/s41598-021-89743-x.
   PubMed Web of Science ®Google Scholar
• Yamashita T, Terasaki H, Tanaka M et al. Factors in color fundus photographs that can be used by humans to determine sex of individuals. Transl Vis Sci Technol 2020 Jan 1; 9: 4. Epub ahead of print. doi:10.1167/tvst.9.2.4.
   PubMedGoogle Scholar
• Poplin R, Varadarajan AV, Blumer K et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat Biomed Eng 2018; 2: 158–164. doi:10.1038/s41551-018-0195-0.
   PubMed Web of Science ®Google Scholar
• Wan A, Dunlap L, Ho D et al. NBDT: neural-backed decision tree. In: International Conference on Learning Representations. 2021. https://openreview.net/forum?id=mCLVeEpplNE.
   Google Scholar
• Krizhevsky A, Hinton G. Learning multiple layers of features from tiny images.
   Google Scholar
• Webster CS, Taylor S, Thomas C et al. Social bias, discrimination and inequity in healthcare: mechanisms, implications and recommendations. BJA Educ 2022; 22: 131–137. doi:10.1016/j.bjae.2021.11.011.
   PubMed Web of Science ®Google Scholar
• Wilson BN, Murase JE, Sliwka D et al. Bridging racial differences in the clinical encounter: how implicit bias and stereotype threat contribute to health care disparities in the dermatology clinic. Int J Women’s Dermatology 2021; 7: 139–144. doi:10.1016/j.ijwd.2020.12.013.
   PubMedGoogle Scholar
• Kleinberg J, Ludwig J, Mullainathan S et al. Discrimination in the age of algorithms. J Leg Anal 2018; 10: 1–62. doi:10.1093/jla/laz001.
   Web of Science ®Google Scholar
• Bradshaw TJ, Boellaard R, Dutta J et al. Nuclear medicine and artificial intelligence: best practices for algorithm development. J Nucl Med 2022; 63: 500 LP–510. doi:10.2967/jnumed.121.262567.
   Web of Science ®Google Scholar
• Korot E, Gonçalves MB, Khan SM et al. Clinician-driven artificial intelligence in ophthalmology: resources enabling democratization. Curr Opin Ophthalmol 2021; 32: 445–451. doi:10.1097/ICU.0000000000000785.
   PubMed Web of Science ®Google Scholar
• Gordon MO, Beiser JA, Brandt JD et al. The ocular hypertension treatment study: baseline factors that predict the onset of primary open-angle glaucoma. Arch Ophthalmol (Chicago, Ill 1960) 2002; 120: 714–720. doi:10.1001/archopht.120.6.714.
   PubMed Web of Science ®Google Scholar
• Gerry P, Johnson K. Cup-to-disc ratios of aboriginal and non-aboriginal youths. Clin Exp Optom 2006; 89: 306–309. doi:10.1111/j.1444-0938.2006.00047.x.
   PubMed Web of Science ®Google Scholar
• Landers JA, Henderson TR, Craig JE. Optic nerve head parameters of an indigenous population living within Central Australia. Clin Experiment Ophthalmol 2006; 34: 852–856. doi:10.1111/j.1442-9071.2006.01344.x.
   PubMed Web of Science ®Google Scholar
• Chan HHL, Ong DN, Kong YXG et al. Glaucomatous optic neuropathy evaluation (GONE) project: the effect of monoscopic versus stereoscopic viewing conditions on optic nerve evaluation. Am J Ophthalmol 2014; 157: 936–944. doi:10.1016/j.ajo.2014.01.024.
   PubMed Web of Science ®Google Scholar
• Vihanninjoki K, Burk ROW, Teesalu P et al. Optic disc biomorphometry with the Heidelberg retina tomograph at different reference levels. Acta Ophthalmol Scand 2002; 80: 47–53. doi:10.1034/j.1600-0420.2002.800110.x.
   PubMedGoogle Scholar
• Deshpande G, Gupta R, Bawankule P et al. Structural evaluation of preperimetric and perimetric glaucoma. Indian J Ophthalmol 2019; 67: 1843–1849. doi:10.4103/ijo.IJO_1955_18.
   PubMed Web of Science ®Google Scholar
• Blumen Ohana E, Blumen MB, Bluwol E et al. Primary open angle glaucoma and snoring: prevalence of OSAS. Eur Ann Otorhinolaryngol Head Neck Dis 2010; 127: 159–164. doi:10.1016/j.anorl.2010.07.003.
   PubMed Web of Science ®Google Scholar
• Khandgave TP, Puthran N, Ingole AB et al. The assessment of sleep apnoea as a risk factor in glaucoma. J Clin Diagnostic Res 2013; 7: 1391–1393. doi:10.7860/JCDR/2013/5383.3147.
   PubMedGoogle Scholar
• Tufail A, Rudisill C, Egan C et al. Automated diabetic retinopathy image assessment software: diagnostic accuracy and cost-effectiveness compared with human graders. Ophthalmology 2017; 124: 343–351. doi:10.1016/j.ophtha.2016.11.014.
   PubMed Web of Science ®Google Scholar
• Therapeutic Goods Administration. How the TGA regulates software-based medical devices. 2021. https://www.tga.gov.au/sites/default/files/how-tga-regulates-software-based-medical-devices.pdf.
   Google Scholar
• Korot E, Guan Z, Ferraz D et al. Code-free deep learning for multi-modality medical image classification. Nat Mach Intell 2021; 3: 288–298. doi:10.1038/s42256-021-00305-2.
   Google Scholar
• Harvey HB, Gowda V. How the FDA regulates AI. Acad Radiol 2020; 27: 58–61. doi:10.1016/j.acra.2019.09.017.
   PubMed Web of Science ®Google Scholar