Literature DB >> 32857270

[Artificial intelligence in ophthalmology : Guidelines for physicians for the critical evaluation of studies].

Maximilian Pfau1,2, Guenther Walther3, Leon von der Emde4, Philipp Berens5,6, Livia Faes7,8, Monika Fleckenstein9, Tjebo F C Heeren8, Karsten Kortüm10,11, Sandrine H Künzel4, Philipp L Müller4,5, Peter M Maloca8,12,13, Sebastian M Waldstein14,15, Maximilian W M Wintergerst4, Steffen Schmitz-Valckenberg4,9, Robert P Finger4, Frank G Holz4.   

Abstract

BACKGROUND: Empirical models have been an integral part of everyday clinical practice in ophthalmology since the introduction of the Sanders-Retzlaff-Kraff (SRK) formula. Recent developments in the field of statistical learning (artificial intelligence, AI) now enable an empirical approach to a wide range of ophthalmological questions with an unprecedented precision.
OBJECTIVE: Which criteria must be considered for the evaluation of AI-related studies in ophthalmology?
MATERIAL AND METHODS: Exemplary prediction of visual acuity (continuous outcome) and classification of healthy and diseased eyes (discrete outcome) using retrospectively compiled optical coherence tomography data (50 eyes of 50 patients, 50 healthy eyes of 50 subjects). The data were analyzed with nested cross-validation (for learning algorithm selection and hyperparameter optimization).
RESULTS: Based on nested cross-validation for training, visual acuity could be predicted in the separate test data-set with a mean absolute error (MAE, 95% confidence interval, CI of 0.142 LogMAR [0.077; 0.207]). Healthy versus diseased eyes could be classified in the test data-set with an agreement of 0.92 (Cohen's kappa). The exemplary incorrect learning algorithm and variable selection resulted in an MAE for visual acuity prediction of 0.229 LogMAR [0.150; 0.309] for the test data-set. The drastic overfitting became obvious on comparison of the MAE with the null model MAE (0.235 LogMAR [0.148; 0.322]).
CONCLUSION: Selection of an unsuitable measure of the goodness-of-fit, inadequate validation, or withholding of a null or reference model can obscure the actual goodness-of-fit of AI models. The illustrated pitfalls can help clinicians to identify such shortcomings.

Entities:  

Keywords:  Automated analysis; Deep learning; Empirical approach; Machine-learning; Statistical learning

Mesh:

Year:  2020        PMID: 32857270     DOI: 10.1007/s00347-020-01209-z

Source DB:  PubMed          Journal:  Ophthalmologe        ISSN: 0941-293X            Impact factor:   1.059


  21 in total

1.  Acuity VEP: improved with machine learning.

Authors:  Michael Bach; Sven P Heinrich
Journal:  Doc Ophthalmol       Date:  2019-06-11       Impact factor: 2.379

2.  Reporting of artificial intelligence prediction models.

Authors:  Gary S Collins; Karel G M Moons
Journal:  Lancet       Date:  2019-04-20       Impact factor: 79.321

3.  Prediction of Anti-VEGF Treatment Requirements in Neovascular AMD Using a Machine Learning Approach.

Authors:  Hrvoje Bogunovic; Sebastian M Waldstein; Thomas Schlegl; Georg Langs; Amir Sadeghipour; Xuhui Liu; Bianca S Gerendas; Aaron Osborne; Ursula Schmidt-Erfurth
Journal:  Invest Ophthalmol Vis Sci       Date:  2017-06-01       Impact factor: 4.799

4.  Diagnostic tests 3: receiver operating characteristic plots.

Authors:  D G Altman; J M Bland
Journal:  BMJ       Date:  1994-07-16

5.  Selection bias in gene extraction on the basis of microarray gene-expression data.

Authors:  Christophe Ambroise; Geoffrey J McLachlan
Journal:  Proc Natl Acad Sci U S A       Date:  2002-04-30       Impact factor: 11.205

Review 6.  [Artificial intelligence in ophthalmology : Guidelines for physicians for the critical evaluation of studies].

Authors:  Maximilian Pfau; Guenther Walther; Leon von der Emde; Philipp Berens; Livia Faes; Monika Fleckenstein; Tjebo F C Heeren; Karsten Kortüm; Sandrine H Künzel; Philipp L Müller; Peter M Maloca; Sebastian M Waldstein; Maximilian W M Wintergerst; Steffen Schmitz-Valckenberg; Robert P Finger; Frank G Holz
Journal:  Ophthalmologe       Date:  2020-10       Impact factor: 1.059

Review 7.  Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement.

Authors:  Gary S Collins; Johannes B Reitsma; Douglas G Altman; Karel G M Moons
Journal:  BMJ       Date:  2015-01-07

8.  Mesopic and Dark-Adapted Two-Color Fundus-Controlled Perimetry in Choroidal Neovascularization Secondary to Age-Related Macular Degeneration.

Authors:  Leon von der Emde; Maximilian Pfau; Sarah Thiele; Philipp T Möller; Ruth Hassenrik; Monika Fleckenstein; Frank G Holz; Steffen Schmitz-Valckenberg
Journal:  Transl Vis Sci Technol       Date:  2018-01-09       Impact factor: 3.283

9.  Artificial intelligence for morphology-based function prediction in neovascular age-related macular degeneration.

Authors:  Leon von der Emde; Maximilian Pfau; Chantal Dysli; Sarah Thiele; Philipp T Möller; Moritz Lindner; Matthias Schmid; Monika Fleckenstein; Frank G Holz; Steffen Schmitz-Valckenberg
Journal:  Sci Rep       Date:  2019-07-31       Impact factor: 4.379

10.  Clinically applicable deep learning for diagnosis and referral in retinal disease.

Authors:  Jeffrey De Fauw; Joseph R Ledsam; Bernardino Romera-Paredes; Stanislav Nikolov; Nenad Tomasev; Sam Blackwell; Harry Askham; Xavier Glorot; Brendan O'Donoghue; Daniel Visentin; George van den Driessche; Balaji Lakshminarayanan; Clemens Meyer; Faith Mackinder; Simon Bouton; Kareem Ayoub; Reena Chopra; Dominic King; Alan Karthikesalingam; Cían O Hughes; Rosalind Raine; Julian Hughes; Dawn A Sim; Catherine Egan; Adnan Tufail; Hugh Montgomery; Demis Hassabis; Geraint Rees; Trevor Back; Peng T Khaw; Mustafa Suleyman; Julien Cornebise; Pearse A Keane; Olaf Ronneberger
Journal:  Nat Med       Date:  2018-08-13       Impact factor: 53.440

View more
  5 in total

Review 1.  [Artificial intelligence in ophthalmology : Guidelines for physicians for the critical evaluation of studies].

Authors:  Maximilian Pfau; Guenther Walther; Leon von der Emde; Philipp Berens; Livia Faes; Monika Fleckenstein; Tjebo F C Heeren; Karsten Kortüm; Sandrine H Künzel; Philipp L Müller; Peter M Maloca; Sebastian M Waldstein; Maximilian W M Wintergerst; Steffen Schmitz-Valckenberg; Robert P Finger; Frank G Holz
Journal:  Ophthalmologe       Date:  2020-10       Impact factor: 1.059

2.  Inferred retinal sensitivity in recessive Stargardt disease using machine learning.

Authors:  Philipp L Müller; Alexandru Odainic; Tim Treis; Philipp Herrmann; Adnan Tufail; Frank G Holz; Maximilian Pfau
Journal:  Sci Rep       Date:  2021-01-14       Impact factor: 4.379

3.  Reliability of Retinal Pathology Quantification in Age-Related Macular Degeneration: Implications for Clinical Trials and Machine Learning Applications.

Authors:  Philipp L Müller; Bart Liefers; Tim Treis; Filipa Gomes Rodrigues; Abraham Olvera-Barrios; Bobby Paul; Narendra Dhingra; Andrew Lotery; Clare Bailey; Paul Taylor; Clarisa I Sánchez; Adnan Tufail
Journal:  Transl Vis Sci Technol       Date:  2021-03-01       Impact factor: 3.283

Review 4.  AI-based structure-function correlation in age-related macular degeneration.

Authors:  Leon von der Emde; Maximilian Pfau; Frank G Holz; Monika Fleckenstein; Karsten Kortuem; Pearse A Keane; Daniel L Rubin; Steffen Schmitz-Valckenberg
Journal:  Eye (Lond)       Date:  2021-03-25       Impact factor: 3.775

5.  [Interdisciplinary communication: ophthalmologists' letters to practices specializing in diabetic patients].

Authors:  Lydia Stock; Daniel Roeck; Andreas Fritsche; Tjalf Ziemssen; Focke Ziemssen
Journal:  Ophthalmologe       Date:  2021-04       Impact factor: 1.059

  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.