{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T13:52:28Z","timestamp":1774965148904,"version":"3.50.1"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T00:00:00Z","timestamp":1709078400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T00:00:00Z","timestamp":1709078400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Bioinformatics Shared Resource of the Wake Forest Baptist Comprehensive Cancer Center\u2019s NCI Cancer Center Support Grant","award":["P30CA012197"],"award-info":[{"award-number":["P30CA012197"]}]},{"name":"Bioinformatics Shared Resource of the Wake Forest Baptist Comprehensive Cancer Center\u2019s NCI Cancer Center Support Grant","award":["P30CA012197"],"award-info":[{"award-number":["P30CA012197"]}]},{"name":"National Center for Advancing Translational Sciences, National Institutes of Health","award":["UL1TR001420"],"award-info":[{"award-number":["UL1TR001420"]}]},{"name":"National Center for Advancing Translational Sciences, National Institutes of Health","award":["UL1TR001420"],"award-info":[{"award-number":["UL1TR001420"]}]},{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["3R01CA272627-01A1S1"],"award-info":[{"award-number":["3R01CA272627-01A1S1"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007154","name":"Wake Forest University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007154","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Healthc Inform Res"],"published-print":{"date-parts":[[2024,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Deep learning (DL) has gained prominence in healthcare for its ability to facilitate early diagnosis, treatment identification with associated prognosis, and varying patient outcome predictions. However, because of highly variable medical practices and unsystematic data collection approaches, DL can unfortunately exacerbate biases and distort estimates. For example, the presence of sampling bias poses a significant challenge to the efficacy and generalizability of any statistical model. Even with DL approaches, selection bias can lead to inconsistent, suboptimal, or inaccurate model results, especially for underrepresented populations. Therefore, without addressing bias, wider implementation of DL approaches can potentially cause unintended harm. In this paper, we studied a novel method for bias reduction that leverages the frequency domain transformation via the Gerchberg-Saxton and corresponding impact on the outcome from a racio-ethnic bias perspective.<\/jats:p>","DOI":"10.1007\/s41666-024-00163-8","type":"journal-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T14:02:00Z","timestamp":1709128920000},"page":"225-243","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Improving Equity in Deep Learning Medical Applications with the Gerchberg-Saxton Algorithm"],"prefix":"10.1007","volume":"8","author":[{"given":"Seha","family":"Ay","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Cardei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anne-Marie","family":"Meyer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Umit","family":"Topaloglu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,28]]},"reference":[{"key":"163_CR1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1002\/minf.201501008","volume":"35","author":"E Gawehn","year":"2015","unstructured":"Gawehn E et al (2015) Deep learning in drug discovery. Mol Inf 35:3\u201314","journal-title":"Mol Inf"},{"key":"163_CR2","doi-asserted-by":"crossref","unstructured":"Tekke\u015fin AI (2019) Artificial Intelligence in Healthcare: Past, Present and Future. Anatol J Cardiol","DOI":"10.14744\/AnatolJCardiol.2019.28661"},{"key":"163_CR3","doi-asserted-by":"crossref","unstructured":"Zhou SK et al (2021) A review of deep learning in medical imaging: imaging traits, technology trends, case studies with progress highlights, and future promises. Proc IEEE 109","DOI":"10.1109\/JPROC.2021.3054390"},{"key":"163_CR4","doi-asserted-by":"crossref","unstructured":"Rayan RA et al (2021) Deep learning for health and medicine. Deep Learn Personalized Healthc Serv.","DOI":"10.1515\/9783110708127-001"},{"key":"163_CR5","doi-asserted-by":"crossref","unstructured":"Mehrabi N et al (2021) A survey on bias and fairness in machine learning. ACM Comput Surv 54","DOI":"10.1145\/3457607"},{"key":"163_CR6","doi-asserted-by":"crossref","unstructured":"Sharma S et al (2020) Data augmentation for discrimination prevention and bias disambiguation. AAAI\/ACM Conf AI Ethics Soc (AIES '20)","DOI":"10.1145\/3375627.3375865"},{"key":"163_CR7","doi-asserted-by":"publisher","first-page":"23","DOI":"10.5220\/0011531400003523","volume":"2022","author":"V Kumar","year":"2022","unstructured":"Kumar V et al (2022) Data augmentation for reliability and fairness in counselling quality classification. Scarce Data Artif Intell Healthc (SDAIH) 2022:23\u201328","journal-title":"Scarce Data Artif Intell Healthc (SDAIH)"},{"key":"163_CR8","unstructured":"Iosifidis V, Ntoutsi E (2018) Dealing with bias via data augmentation in supervised learning scenarios. Jo Bates Paul D. Clough Robert J\u00e4schke"},{"key":"163_CR9","unstructured":"Li X et al (2021) Estimating and improving fairness with adversarial learning. arXiv 1"},{"key":"163_CR10","doi-asserted-by":"crossref","unstructured":"Zhang BH et al (2018) Mitigating unwanted biases with adversarial learning. 2018 AAAI\/ACM Conference on AI, Ethics, and Society","DOI":"10.1145\/3278721.3278779"},{"key":"163_CR11","doi-asserted-by":"publisher","first-page":"884","DOI":"10.1038\/s42256-023-00697-3","volume":"5","author":"J Yang","year":"2023","unstructured":"Yang J et al (2023) Algorithmic fairness and bias mitigation for clinical machine learning with deep reinforcement learning. Nat Mach Intell 5:884\u2013894","journal-title":"Nat Mach Intell"},{"key":"163_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2016.35","volume":"3","author":"AE Johnson","year":"2016","unstructured":"Johnson AE et al (2016) MIMIC-III, a freely accessible critical care database. Sci Data 3:1\u20139","journal-title":"Sci Data"},{"key":"163_CR13","doi-asserted-by":"crossref","unstructured":"Velichkovska B et al (2022) Vital signs as a source of racial bias. medRxiv","DOI":"10.1101\/2022.02.03.22270291"},{"key":"163_CR14","unstructured":"Smith A et al (2022) Reducing racial bias in a critical care mortality prediction model. arXiv"},{"key":"163_CR15","first-page":"237","volume":"35","author":"RW Gerchberg","year":"1972","unstructured":"Gerchberg RW, Saxton WO (1972) A practical algorithm for the determination of the phase from image and diffraction plane pictures. Optik 35:237\u2013246","journal-title":"Optik"},{"key":"163_CR16","doi-asserted-by":"crossref","unstructured":"Zhao T, Chi Y (2020) Modified Gerchberg\u2013Saxton (G-S) algorithm and its application. Entropy","DOI":"10.3390\/e22121354"},{"key":"163_CR17","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1088\/1367-2630\/7\/1\/117","volume":"7","author":"G Whyte","year":"2005","unstructured":"Whyte G, Courtial J (2005) Experimental demonstration of holographic three-dimensional light shaping using a Gerchberg Saxton algorithm. New J Phys 7:117","journal-title":"New J Phys"},{"key":"163_CR18","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.phycom.2017.02.008","volume":"25","author":"M Li","year":"2017","unstructured":"Li M, Li Y, Han J (2017) Gerchberg-Saxton algorithm-based phase correction in optical wireless communication. Phys Commun 25:323\u2013327","journal-title":"Phys Commun"},{"key":"163_CR19","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1364\/OL.21.000842","volume":"21","author":"Z Zalevsky","year":"1996","unstructured":"Zalevsky Z, Dorsch RG, Mendlovic D (1996) Gerchberg-Saxton algorithm applied in the fractional Fourier or the Fresnel domain. Opt Lett 21:842\u2013844","journal-title":"Opt Lett"},{"key":"163_CR20","doi-asserted-by":"publisher","first-page":"D31","DOI":"10.1364\/JOSAA.36.000D31","volume":"36","author":"T Latychevskaia","year":"2019","unstructured":"Latychevskaia T (2019) Iterative phase retrieval for digital holography: tutorial. J Opt Soc Am 36:D31\u2013D40","journal-title":"J Opt Soc Am"},{"key":"163_CR21","unstructured":"Lundberg S, Lee S-I (2017) A unified approach to interpreting model predictions. arXiv"},{"key":"163_CR22","first-page":"198","volume":"20","author":"J Ren","year":"2019","unstructured":"Ren J et al (2019) Modulation signal recognition based on information entropy and ensemble learning. Entropy (Basel) 20:198","journal-title":"Entropy (Basel)"},{"key":"163_CR23","doi-asserted-by":"publisher","DOI":"10.1145\/3194770.3194776","volume-title":"Fairness definitions explained","author":"S Verma","year":"2018","unstructured":"Verma S, Rubin J (2018) Fairness definitions explained. ACM, International Workshop on Software Fairness"},{"key":"163_CR24","unstructured":"Barocas S, Hardt M, Narayanan A (2018) Fairness and machine learning"},{"key":"163_CR25","doi-asserted-by":"crossref","unstructured":"Chouldechova A (2017) Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. arXiv","DOI":"10.1089\/big.2016.0047"},{"key":"163_CR26","doi-asserted-by":"crossref","unstructured":"Dwork C et al (2012) Fairness through awareness. 3rd Innovations in Theoretical Computer Science Conference, p. 214\u2013226","DOI":"10.1145\/2090236.2090255"}],"container-title":["Journal of Healthcare Informatics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41666-024-00163-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41666-024-00163-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41666-024-00163-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,26]],"date-time":"2024-04-26T12:15:43Z","timestamp":1714133743000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41666-024-00163-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,28]]},"references-count":26,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["163"],"URL":"https:\/\/doi.org\/10.1007\/s41666-024-00163-8","relation":{},"ISSN":["2509-4971","2509-498X"],"issn-type":[{"value":"2509-4971","type":"print"},{"value":"2509-498X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,28]]},"assertion":[{"value":"14 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The research presented in this manuscript titled \u201cImproving Equity in Deep Learning Medical Applications with the Gerchberg-Saxton Algorithm\u201d utilizes the MIMIC-III dataset, which is created by the Massachusetts Institute of Technology (MIT) and publicly available at physionet.org. The MIMIC-III dataset consists of de-identified human vital signs data collected from patients admitted to the Beth Israel Deaconess Medical Center.This research study does not involve the subjecting of animals or humans to any interventions or procedures. Instead, it relies solely on the analysis of the pre-existing MIMIC-III dataset for scientific investigation. The dataset has been made publicly available by MIT for research purposes, and all identifying information has been anonymized to ensure privacy and confidentiality.As the MIMIC-III dataset is openly accessible and contains de-identified information, the research team acknowledges and adheres to the following ethical considerations:1. Confidentiality: The research team will strictly adhere to data protection and confidentiality protocols. The dataset utilized in this study has been previously de-identified to safeguard the privacy of the individuals whose data is included.2. Informed Consent: Since no new data will be collected from individuals for this study, obtaining informed consent is not applicable. The MIMIC-III dataset has been released with the understanding that it will be used for scientific research purposes while maintaining confidentiality.3. Beneficence and Non-Maleficence: The study will be conducted with the principles of beneficence and non-maleficence in mind. All analyses will be carried out responsibly, aiming to generate valuable scientific insights while minimizing any potential harm or negative consequences.4. Compliance with Regulations: This research complies with all relevant laws, regulations, and guidelines pertaining to the use of publicly available datasets. The study adheres to the policies and terms of use set forth by the custodians of the MIMIC-III dataset.5. Acknowledgement: The custodians of the MIMIC-III dataset, including the Massachusetts Institute of Technology, will be duly acknowledged for their efforts in data collection and sharing. Proper citation and attribution will be provided in accordance with the dataset\u2019s documentation and usage guidelines.By utilizing the MIMIC-III dataset, this research contributes to advancing knowledge in the field of bias mitigation in AI-powered healthcare solutions without subjecting any animals or humans to additional procedures or interventions. The findings presented in this manuscript are solely derived from the analysis of the publicly available dataset, adhering to ethical principles and regulations.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}}]}}