{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T20:47:02Z","timestamp":1776286022390,"version":"3.50.1"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T00:00:00Z","timestamp":1666569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Digit. Health"],"abstract":"<jats:p>In today\u2019s world it seems fair to say that extensive digital data sharing is the price we pay for the technological advances we have seen achieved as a result of AI systems analysing large quantities of data in a relatively short time. Where such AI is used in the realm of mental health, this data sharing poses additional challenges not just due to the sensitive nature of the data itself but also the potential vulnerability of the data donors themselves should there be a cybersecurity data breach. To address the problem, the AI community proposes to use synthetic text preserving only the salient properties of the original. Such text has potential to fill gaps in the textual data availability (e.g., rare conditions or under-represented groups) while reducing exposure. Our perspective piece is aimed to demystify the process of generating synthetic text, explain its algorithmic and ethical challenges, especially for the mental health domain, as well as most promising ways of overcoming them. We aim to promote better understanding and as a result acceptability of synthetic text outside the research community.<\/jats:p>","DOI":"10.3389\/fdgth.2022.1010202","type":"journal-article","created":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T04:35:31Z","timestamp":1666586131000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Leveraging the potential of synthetic text for AI in mental healthcare"],"prefix":"10.3389","volume":"4","author":[{"given":"Julia","family":"Ive","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,10,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1497","DOI":"10.1093\/jamia\/ocab031","article-title":"Robust suicide risk assessment on social media via deep adversarial learning","volume":"28","author":"Sawhney","year":"2021","journal-title":"J Am Med Inform Assoc"},{"key":"B2","volume-title":"Proceedings of the Seventh Workshop on Computational Linguistics and Clinical Psychology: Improving Access, Online","author":"Tsakalidis","year":""},{"key":"B3","volume-title":"Proceedings of the Eighth Workshop on Computational Linguistics and Clinical Psychology. Online","author":"Tsakalidis","year":"2022"},{"key":"B4","article-title":"Mental health helpline funded by royals shared users\u2019 conversations","author":"Das","year":"2022","journal-title":"Observer Mental Health"},{"key":"B5","volume-title":"Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, Vienna, Austria","author":"Abadi","year":""},{"key":"B6","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s00146-022-01433-y","article-title":"Will AI end privacy? How do we avoid an Orwellian future","volume":"1","author":"Walsh","year":"2022","journal-title":"AI Soc"},{"key":"B7","doi-asserted-by":"publisher","first-page":"2193","DOI":"10.1093\/JAMIA\/OCAB112","article-title":"Are synthetic clinical notes useful for real natural language processing tasks: a case study on clinical entity recognition","volume":"28","author":"Li","year":"2021","journal-title":"J Am Med Inform Assoc"},{"key":"B8","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-75178-4","volume-title":"Synthetic data for deep learning","author":"Nikolenko","year":"2021"},{"key":"B9","author":"Wei","year":""},{"key":"B10","author":"Feng","year":""},{"key":"B11","doi-asserted-by":"publisher","first-page":"S20","DOI":"10.1016\/J.JBI.2015.07.020","article-title":"Annotating longitudinal clinical narratives for de-identification: the 2014 i2b2\/UTHealth corpus","volume":"58","author":"Stubbs","year":"2015","journal-title":"J Biomed Inform"},{"key":"B12","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/J.KNOSYS.2017.01.032","article-title":"A semantic framework for noise addition with nominal data","volume":"122","author":"Rodriguez-Garcia","year":"2017","journal-title":"Knowledge-Based Syst"},{"key":"B13","author":"Keskar","year":"2019"},{"key":"B14","first-page":"8927","author":"Li","year":""},{"key":"B15","volume-title":"Speech, language processing: an introduction to natural language processing, computational linguistics\u201e speech recognition","author":"Jurafsky","year":"2021"},{"key":"B16","author":"Devlin","year":""},{"key":"B17","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020"},{"key":"B18","author":"Chen","year":""},{"key":"B19","doi-asserted-by":"publisher","first-page":"2287","DOI":"10.1093\/jamia\/ocab143","article-title":"A systematic review of automatic text summarization for biomedical literature, EHRs","volume":"28","author":"Wang","year":"2021","journal-title":"J Am Med Inform Assoc"},{"key":"B20","author":"Wu","year":""},{"key":"B21","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1038\/s41746-020-0267-x","article-title":"Generation, evaluation of artificial mental health records for natural language processing","volume":"3","author":"Ive","year":"2020","journal-title":"NPJ Digit Med"},{"key":"B22","volume-title":"Proceedings International Conference on Learning Representations","author":"Dathathri","year":"2020"},{"key":"B23","author":"Lester","year":""},{"key":"B24","volume-title":"Lecture Notes in Computer Science","author":"Dwork","year":""},{"key":"B25","author":"Ponomareva","year":""},{"key":"B26","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"B27","author":"Lin","year":""},{"key":"B28","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41551-021-00751-8","article-title":"Synthetic data in machine learning for medicine and healthcare","volume":"5","author":"Chen","year":"2021","journal-title":"Nat Biomed Engng"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41551-022-00898-y","article-title":"Shifting machine learning for healthcare from development to deployment and from models to data","volume":"2022","author":"Zhang","year":"2022","journal-title":"Nat Biomed Engng"},{"key":"B30","author":"Ribeiro","year":""},{"key":"B31","author":"Wiegreffe","year":""},{"key":"B32","author":"Lison","year":""},{"key":"B33","first-page":"171","article-title":"An economic analysis of privacy protection and statistical accuracy as social choices","volume-title":"Am Econ Rev","author":"Abowd","year":"2019"},{"key":"B34","author":"Meade","year":""}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2022.1010202\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T04:35:45Z","timestamp":1666586145000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2022.1010202\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,24]]},"references-count":34,"alternative-id":["10.3389\/fdgth.2022.1010202"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2022.1010202","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,24]]},"article-number":"1010202"}}