{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T23:10:50Z","timestamp":1786662650021,"version":"build-2736575974"},"reference-count":21,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/100005196","name":"Bureau of Justice Assistance","doi-asserted-by":"publisher","award":["15PBJA-23-GG-02335-COAP"],"award-info":[{"award-number":["15PBJA-23-GG-02335-COAP"]}],"id":[{"id":"10.13039\/100005196","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>This study presents a protocol that integrates conversational artificial intelligence into qualitative data analysis to support rapid, decision-oriented descriptive analysis in public health settings. The protocol was developed during an applied project with Hamilton County Public Health that analyzed interviews with the next of kin of overdose decedents to inform local strategies. The objective is to describe the protocol, its safeguards for data familiarization and human verification, and its practical application in a real-world case.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Evaluators designed and tested manual coding, intentional artificial intelligence-assisted coding, and conversational artificial intelligence within ATLAS.ti, selecting the conversational approach for the protocol. The protocol requires a mandatory pre-analysis familiarization phase that includes reading a stratified subset of transcripts and drafting immersion memos. Analysts then pose structured natural language queries tied to prespecified research questions. All outputs are treated as proposals and undergo required human verification, including confirmation of quoted evidence and contextual review. Theme-level benchmarking compared independent human synthesis with conversational artificial intelligence outputs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Conversational artificial intelligence produced rapid descriptive findings anchored to verifiable text, enabling efficient auditing through embedded links. Theme-level comparison showed conceptual overlap between human and artificial intelligence outputs, with transparent documentation of areas of divergence. The protocol supported rapid training of local personnel and sustained in-house analysis capacity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The protocol formalizes a pragmatic workflow for question-led, top-down descriptive analysis using conversational artificial intelligence with mandatory human oversight. It is not intended to replace interpretive or theory-generating approaches but offers a transparent and scalable option for time sensitive, decision-focused qualitative work.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076261435085","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T08:38:44Z","timestamp":1774341524000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":2,"title":["Transforming qualitative research: The AQUATIC approach to AI-driven data analysis"],"prefix":"10.1177","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5454-399X","authenticated-orcid":false,"given":"Sam","family":"Belkin","sequence":"first","affiliation":[{"name":"Voinovich School of Leadership and Public Service, Ohio University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacob","family":"White","sequence":"additional","affiliation":[{"name":"Voinovich School of Leadership and Public Service, Ohio University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cale G.","family":"Burke","sequence":"additional","affiliation":[{"name":"Voinovich School of Leadership and Public Service, Ohio University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma","family":"Cepek","sequence":"additional","affiliation":[{"name":"Voinovich School of Leadership and Public Service, Ohio University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"e_1_3_5_2_2","doi-asserted-by":"publisher","DOI":"10.5465\/amle.2015.0016"},{"key":"e_1_3_5_3_2","doi-asserted-by":"publisher","DOI":"10.1177\/1094428115574858"},{"key":"e_1_3_5_4_2","volume-title":"Research capacity at a local government level (REC@LL): mapping review and rapid systematic review","author":"Hock E","year":"2020","unstructured":"Hock E, Scope A, Booth A. Research capacity at a local government level (REC@LL): mapping review and rapid systematic review. Sheffield, UK: University of Sheffield\u2019s School of Health and Related Research, 2020."},{"key":"e_1_3_5_5_2","first-page":"21","article-title":"Knowledge translation strategies to improve the use of evidence in public health decision making in local government: intervention design and implementation plan","volume":"8","author":"Armstrong R","year":"2013","unstructured":"Armstrong R, Waters E, Dobbins M, et al. Knowledge translation strategies to improve the use of evidence in public health decision making in local government: intervention design and implementation plan. Implementation Sci Comm 2013; 8: 21.","journal-title":"Implementation Sci Comm"},{"key":"e_1_3_5_6_2","doi-asserted-by":"publisher","DOI":"10.1093\/eurpub\/cku038"},{"key":"e_1_3_5_7_2","doi-asserted-by":"publisher","DOI":"10.1108\/JHOM-02-2020-0043"},{"key":"e_1_3_5_8_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12961-024-01162-2"},{"key":"e_1_3_5_9_2","doi-asserted-by":"publisher","DOI":"10.4324\/9780203506714"},{"key":"e_1_3_5_10_2","volume-title":"Case study research and applications: design and methods","author":"Yin RK","year":"2017","unstructured":"Yin RK. Case study research and applications: design and methods. Thousand Oaks, CA: Sage, 2017."},{"key":"e_1_3_5_11_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781003503538"},{"key":"e_1_3_5_12_2","doi-asserted-by":"publisher","DOI":"10.1177\/10944281211060710"},{"key":"e_1_3_5_13_2","doi-asserted-by":"publisher","DOI":"10.5465\/amj.2018.4004"},{"key":"e_1_3_5_14_2","doi-asserted-by":"publisher","DOI":"10.1002\/sdr.1772"},{"key":"e_1_3_5_15_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-025-02961-5"},{"key":"e_1_3_5_16_2","doi-asserted-by":"publisher","DOI":"10.1111\/beer.12645"},{"key":"e_1_3_5_17_2","doi-asserted-by":"publisher","DOI":"10.15658\/rev.electron.educ.pedagog20.05040604"},{"key":"e_1_3_5_18_2","first-page":"1","article-title":"\u201cIn minutes instead of weeks\u201d: discursive constructions of generative AI and qualitative data analysis","volume":"31","author":"Paulus T","year":"2024","unstructured":"Paulus T, Marone V. \u201cIn minutes instead of weeks\u201d: discursive constructions of generative AI and qualitative data analysis. Qual Inq 2024; 31: 1\u20138.","journal-title":"Qual Inq"},{"key":"e_1_3_5_19_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13677-023-00578-5"},{"key":"e_1_3_5_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113047"},{"key":"e_1_3_5_21_2","first-page":"3929","article-title":"Retrieval augmented language model pre-training","author":"Guu K","year":"2020","unstructured":"Guu K, Lee Z, Tung P, et al. Retrieval augmented language model pre-training. Proc Mach Learn Res 2020: 3929\u20133938.","journal-title":"Proc Mach Learn Res"},{"key":"e_1_3_5_22_2","volume-title":"CARE: structure for crafting AI prompts","author":"Moran K","year":"2024","unstructured":"Moran K. CARE: structure for crafting AI prompts. Raleigh, NC: NNGroup, 2024. https:\/\/www.nngroup.com\/articles\/careful-prompts\/."}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261435085","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261435085","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261435085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:56:30Z","timestamp":1777398990000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261435085"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":21,"alternative-id":["10.1177\/20552076261435085"],"URL":"https:\/\/doi.org\/10.1177\/20552076261435085","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261435085"}}