{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T11:07:14Z","timestamp":1775041634531,"version":"3.50.1"},"reference-count":0,"publisher":"Canadian Urological Association Journal","issue":"8","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CUAJ"],"abstract":"<jats:p>Introduction: Patients rely on online searches for patient education materials (PEMs). PEMs are recommended to be written at or below a sixth-grade reading level but are regularly written at a college reading level. Using prompt engineering, we assess the information, misinformation, and readability of ChatGPT responses to urologic oncology questions.\nMethods: Forty-five questions relating to prostate, bladder, and kidney cancer were presented to ChatGPT (version 4o, OpenAI). Quality of health information was assessed using DISCERN (1 [low] to 5 [high]). Understandability and actionability were assessed using PEMAT-P (0 [low] -100% [high]). Misinformation was scored from 1 [no misinformation] to 5 [high misinformation]. Grade and reading level were calculated using the Flesch-Kincaid scale [5 (easy) to 16 (difficult), and 100-90 (5th grade level) to 10-0 (professional level), respectively]. Prompt engineering was then applied to responses and evaluated.\nResults: ChatGPT answers are highly accurate but too advanced of a reading level and lacked explanations of benefits, risks, visual aids, actionability, and citations. Using prompt engineering, DISCERN (3.42-4.47, p&lt;0.0001), PEMAT-P understandability (88.4-95.5%, p&lt;0.0001), and actionability (25.6-84.2%, p&lt;0.0001), grade reading level (10.5\uf02d5.3, p&lt;0.0001), and reading level (42 [college level] to 71.7 [7th grade], p&lt;0.0001), all significantly improved. Misinformation did not change significantly.\nConclusions: Using prompt engineering, ChatGPT provides highly accurate and understandable PEMs at a patient appropriate reading level and provides concrete resources for patient action. Urologists should understand prompt engineering and be involved in the development of artificial chatbots to optimize results.<\/jats:p>","DOI":"10.5489\/cuaj.9578","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T09:20:47Z","timestamp":1774948847000},"source":"Crossref","is-referenced-by-count":0,"title":["Optimizing ChatGPT"],"prefix":"10.5489","volume":"20","author":[{"given":"Mark N.","family":"Alshak","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michelle I.","family":"Higgins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Craig","family":"Cronin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William S.","family":"Azar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joseph G.","family":"Cheaib","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"Kates","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunil H.","family":"Patel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"3456","published-online":{"date-parts":[[2026,3,30]]},"container-title":["Canadian Urological Association Journal"],"original-title":[],"link":[{"URL":"https:\/\/cuaj.ca\/index.php\/journal\/article\/download\/9578\/6784","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/cuaj.ca\/index.php\/journal\/article\/download\/9578\/6783","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T09:20:50Z","timestamp":1775035250000},"score":1,"resource":{"primary":{"URL":"https:\/\/cuaj.ca\/index.php\/journal\/article\/view\/9578"}},"subtitle":["Applying prompt engineering to frequently asked questions in urologic oncology"],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":0,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,3,30]]}},"URL":"https:\/\/doi.org\/10.5489\/cuaj.9578","relation":{},"ISSN":["1920-1214","1911-6470"],"issn-type":[{"value":"1920-1214","type":"electronic"},{"value":"1911-6470","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,30]]}}}