[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-542036-105":59,"doc-detail-542036-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","artificial-intelligence-versus-human-touch-can-artificial-intelligence-accurately-generate-a-literature-review-on-laser-technologies","Artificial intelligence versus human touch: can artificial intelligence accurately generate a literature review on laser technologies?","","Purpose: compare open-source AI Large Language Models (LLMs) against human authors in generating a systematic review (SR) on pulsed-Thulium:YAG (p-Tm:YAG) laser for lithotripsy. Methods: five SRs were produced; Human-SR served as ground truth. Four LLMs (ChatGPT3.5, Vercel, Claude, Mistral-7b) generated LLM-SRs via a fixed prompt and were reformatted for blinding. Nine endourologic participants assessed accuracy using a 10-checkpoint proforma and composite quality/clarity/rank scores. Results: Human-SR showed higher objective and subjective accuracy than LLM-SRs; ChatGPT3.5 performed best. Conclusion: LLM accuracy on technical medical topics is lower than key opinion leaders, but human supervision may improve practice.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/artificial-intelligence-versus-human-touch-can-artificial-intelligence-accurately-generate-a-literature-review-on-laser-technologies/542036/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/artificial-intelligence-versus-human-touch-can-artificial-intelligence-accurately-generate-a-literature-review-on-laser-technologies/542036.png","ImageObject",300,407,{"name":92,"@type":93},"WPS_1786070896","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-15","2026-10-10",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"How were the human and AI systematic reviews compared?","Question",{"text":112,"@type":113},"Five manuscripts were compared, with a Human-SR on p-Tm:YAG serving as ground truth. Four LLMs generated SRs from a fixed prompt, then outputs were reformatted to enable blinding.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which models were used to generate the LLM-based systematic reviews?",{"text":117,"@type":113},"The LLM-SRs were generated using four open-source LLMs: ChatGPT3.5, Vercel, Claude, and Mistral-7b.",{"name":119,"@type":110,"acceptedAnswer":120},"What were the main findings on accuracy between LLMs and human authors?",{"text":121,"@type":113},"Human-SR was more accurate than LLM-SRs in both objective and subjective assessments. Overall LLM-SRs did not significantly differ, though ChatGPT3.5 showed the highest subjective and objective scores.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},542036,1791772722,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144,"preview_page_count":19,"preview_urls":145},549768072016,"https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d","World Journal of Urology (2024) 42:598  \n[https://doi.org/10.1007/s00345-024-05311-8](https://doi.org/10.1007/s00345-024-05311-8)  \nArtificial intelligence versus human touch: can artificial intelligence accurately generate a literature review on laser technologies?  \nFrédéric Panthier1,2,3,4 · Hugh Crawford‑Smith1 · Eduarda Alvarez1,5 · Alberto Melchionna1 · Daniela Velinova1 · Ikran Mohamed1 · Siobhan Price1 · Simon Choong1 · Vimoshan Arumuham1 · Sian Allen1 · Olivier Traxer2,3,4 · Daron Smith1,6,7  \nReceived: 10 June 2024 / Accepted: 4 October 2024 / Published online: 28 October 2024  \n© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024  \nAbstract  \nPurpose To compare the accuracy of open-source Artificial Intelligence (AI) Large Language Models (LLM) against human authors to generate a systematic review (SR) on the new pulsed-Thulium:YAG (p-Tm:YAG) laser.  \nMethods Five manuscripts were compared. The Human-SR on p-Tm:YAG (considered to be the “ground truth”) was written by independent certified endourologists with expertise in lasers, accepted in a peer-review pubmed-indexed journal (but not yet available online, and therefore not accessible to the LLMs) . The query to the AI LLMs was: “write a systematic review on pulsed-Thulium:YAG laser for lithotripsy” which was submitted to four LLMs (ChatGPT3.5/Vercel/Claude/Mistral-7b) . The LLM-SR were uniformed and Human-SR reformatted to fit the general output appearance, to ensure blindness. Nine participants with various levels of endourological expertise (three Clinical Nurse Specialist nurses, Urology Trainees and Consultants) objectively assessed the accuracy of the five SRs using a bespoke 10 “checkpoint” proforma. A subjective assessment was recorded using a composite score including quality (0–10), clarity (0–10) and overall manuscript rank (1–5) . Results The Human-SR was objectively and subjectively more accurate than LLM-SRs (96 ± 7% and 86.8 ± 8.2% respectively; p \u003C 0.001) . The LLM-SRs did not significantly differ but ChatGPT3.5 presented greater subjective and objective accuracy scores (62.4 ± 15% and 29 ± 28% respectively; p >0.05). Quality and clarity assessments were significantly impacted by SR type but not the expertise level (p \u003C 0.001 and >0.05, respectively) .  \nConclusions LLM generated data on highly technical topics present a lower accuracy than Key Opinion Leaders. LLMs, especially ChatGPT3.5, with human supervision could improve our practice.  \nKeywords Artificial intelligence · Machine learning · Neural network · Urinary stones · Laser · Lithotripsy  \nIntroduction  \nArtificial intelligence (AI) was born in the early 1950s with Alan Turing’s machine and provocative question: “can machines think?”. It now includes several fields intending to train a machine to perform specific tasks (Machine Learning, ML) [1] . Deep Learning (DL) is a subcategory of ML with particular efficiency for learning and detecting text or images, and which has spread recently among medical applications. Generative AI and especially Large Language Models (LLMs) and “chatbots” allow queries through user/ chat interfaces for data retrieval or production. LLMs provide structured responses using text recognition, database  \nExtended author information available on the last page of the article  \nsearching and compilation, and enhance their performances by reinforcement learning, a “reward-based” method [2] .  \nAlthough peer-review journals do not accept manuscripts that have been produced by a Generative AI chatbot, LLMs are under evaluation in various scientific and educational fields and especially within medicine. The question“how accurate could LLM-generated text be on this medical topic?” is complex and requires dedicated evaluations through each specific field of research. Laser technologies for surgical applications is an area of practice that could help our appreciation and understanding of the current performance of LLMs.  \nKi","cbCaidSO5iDN11dN","https://ap.wps.com/l/cbCaidSO5iDN11dN","pdf",747122,"English","# Abstract\n## Purpose\n## Methods\n## Results\n## Conclusions\n# Introduction\n## Background on AI and LLMs\n## Laser technologies for lithotripsy\n# Methods\n## Study design","[{\"question\":\"How were the human and AI systematic reviews compared?\",\"answer\":\"Five manuscripts were compared, with a Human-SR on p-Tm:YAG serving as ground truth. Four LLMs generated SRs from a fixed prompt, then outputs were reformatted to enable blinding.\"},{\"question\":\"Which models were used to generate the LLM-based systematic reviews?\",\"answer\":\"The LLM-SRs were generated using four open-source LLMs: ChatGPT3.5, Vercel, Claude, and Mistral-7b.\"},{\"question\":\"What were the main findings on accuracy between LLMs and human authors?\",\"answer\":\"Human-SR was more accurate than LLM-SRs in both objective and subjective assessments. Overall LLM-SRs did not significantly differ, though ChatGPT3.5 showed the highest subjective and objective scores.\"}]","Artificial intelligence versus human touch: can artificial intelligence accurately generate a literature review on laser technologies? | PDF",1791668952,25,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/d989f6dfecd0e039263c8af539edc04b.webp",983,1305,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/f46311e3201647f0ba2a022d0a7f28a1.webp",982,1304,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/d659f11e0f24245b1dc7469e6ec8c345.webp",981,1303,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/9e4da95d179142ee69fdf0cd8760b144.webp",980,1301]