<?xml version="1.0"?><rdf:RDF xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:edm="http://www.europeana.eu/schemas/edm/" xmlns:wgs84_pos="http://www.w3.org/2003/01/geo/wgs84_pos" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:rdaGr2="http://rdvocab.info/ElementsGr2" xmlns:oai="http://www.openarchives.org/OAI/2.0/" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:ore="http://www.openarchives.org/ore/terms/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:dcterms="http://purl.org/dc/terms/"><edm:WebResource rdf:about="http://www.dlib.si/stream/URN:NBN:SI:DOC-7PYPGFMK/b228b6bd-dfbc-4eb4-96a9-4a33aa073b4b/PDF"><dcterms:extent>552 KB</dcterms:extent></edm:WebResource><edm:WebResource rdf:about="http://www.dlib.si/stream/URN:NBN:SI:DOC-7PYPGFMK/48ea00dd-c068-436a-9fe7-d4c320e05e90/TEXT"><dcterms:extent>40 KB</dcterms:extent></edm:WebResource><edm:TimeSpan rdf:about="2005-2025"><edm:begin xml:lang="en">2005</edm:begin><edm:end xml:lang="en">2025</edm:end></edm:TimeSpan><edm:ProvidedCHO rdf:about="URN:NBN:SI:DOC-7PYPGFMK"><dcterms:isPartOf rdf:resource="https://www.dlib.si/details/URN:NBN:SI:spr-8ER5ZBJN" /><dcterms:issued>2025</dcterms:issued><dc:creator>Horvat, Nejc</dc:creator><dc:creator>Knez, Lea</dc:creator><dc:creator>Kodrič, Ana</dc:creator><dc:format xml:lang="sl">številka:5</dc:format><dc:format xml:lang="sl">letnik:76</dc:format><dc:format xml:lang="sl">str. 303-312</dc:format><dc:identifier>ISSN:2536-4316</dc:identifier><dc:identifier>COBISSID_HOST:266043395</dc:identifier><dc:identifier>URN:URN:NBN:SI:doc-7PYPGFMK</dc:identifier><dc:language>sl</dc:language><dc:publisher xml:lang="sl">Slovensko farmacevtsko društvo</dc:publisher><dcterms:isPartOf xml:lang="sl">Farmacevtski vestnik</dcterms:isPartOf><dc:subject xml:lang="en">artificial intelligence</dc:subject><dc:subject xml:lang="sl">ChatGPT</dc:subject><dc:subject xml:lang="en">clinical pharmacy</dc:subject><dc:subject xml:lang="sl">Farmacija</dc:subject><dc:subject xml:lang="sl">klinična farmacija</dc:subject><dc:subject xml:lang="en">large language models</dc:subject><dc:subject xml:lang="en">medication review</dc:subject><dc:subject xml:lang="sl">pregled zdravljenja z zdravili</dc:subject><dc:subject xml:lang="sl">Umetna inteligenca</dc:subject><dc:subject xml:lang="sl">veliki jezikovni modeli</dc:subject><dcterms:temporal rdf:resource="2005-2025" /><dc:title xml:lang="sl">Uporabnost velikega jezikovnega modela ChatGPT pri obravnavi kliničnih primerov pacientov| Usefulness of the large language model ChatGPT in the evaluation of clinical patient cases|</dc:title><dc:description xml:lang="sl">Opportunities for using large language models are emerging in healthcare, including pharmacy. To evaluate ChatGPT’s (version GPT 3.5, march 2023) usefulness in clinical pharmacy, five clinical pharmacists assessed its performance on clinical cases. ChatGPT demonstrated utility in identifying basic issues, such as drug interactions and adverse effects, but its responses were often overly general or incorrect. Answer accuracy was 29% for general questions and only 19% for specific ones, with frequent lack of context reducing their practical value. While pharmacists found the responses linguistically clear, they criticised the lack of comprehensiveness and reasoning. Opinions on using artificial intelligence in clinical practice were mixed; some recognised its potential for supporting decision-making, while others emphasised its limited accuracy and lack of professional judgement. Although ChatGPT can assist in clinical decisions, it currently cannot replace the professional judgement of a pharmacist</dc:description><dc:description xml:lang="sl">Na področju zdravstva, vključno s farmacijo, se pojavljajo možnosti uporabe velikih jezikovnih modelov, zato smo želeli oceniti uporabnost ChatGPT v klinični farmaciji. Pet kliničnih farmacevtk je ocenjevalo uspešnost ChatGPT (verzija GPT 3.5, marec 2023) pri obravnavi kliničnih primerov. ChatGPT se je izkazal kot uporaben pri prepoznavanju osnovnih težav, kot so interakcije med zdravili in neželeni učinki, vendar so bili odgovori včasih preveč splošni ali napačni. Pri splošnih vprašanjih je bila pravilnost odgovorov 29 %, pri specifičnih vprašanjih pa le 19 %, pri čemer je pogosto izostal kontekstualni vidik, kar je zmanjšalo uporabnost odgovorov. Klinične farmacevtke so odgovore ocenile kot jasne in jezikovno ustrezne, vendar so opozorile na pomanjkanje celovitosti in argumentacije. Mnenja o uporabi umetne inteligence v klinični praksi so bila deljena, saj so nekatere klinične farmacevtke prepoznale njen potencial pri podpori odločanju, druge pa so izpostavile omejeno pravilnost in pomanjkanje strokovne presoje. Čeprav ChatGPT lahko podpira klinične odločitve, trenutno še ne more nadomestiti strokovne presoje farmacevta</dc:description><edm:type>TEXT</edm:type><dc:type xml:lang="sl">znanstveno časopisje</dc:type><dc:type xml:lang="en">journals</dc:type><dc:type rdf:resource="http://www.wikidata.org/entity/Q361785" /></edm:ProvidedCHO><ore:Aggregation rdf:about="http://www.dlib.si/?URN=URN:NBN:SI:DOC-7PYPGFMK"><edm:aggregatedCHO rdf:resource="URN:NBN:SI:DOC-7PYPGFMK" /><edm:isShownBy rdf:resource="http://www.dlib.si/stream/URN:NBN:SI:DOC-7PYPGFMK/b228b6bd-dfbc-4eb4-96a9-4a33aa073b4b/PDF" /><edm:rights rdf:resource="http://creativecommons.org/licenses/by-nc/4.0/" /><edm:provider>Slovenian National E-content Aggregator</edm:provider><edm:intermediateProvider xml:lang="en">National and University Library of Slovenia</edm:intermediateProvider><edm:dataProvider xml:lang="sl">Slovensko farmacevtsko društvo</edm:dataProvider><edm:object rdf:resource="http://www.dlib.si/streamdb/URN:NBN:SI:DOC-7PYPGFMK/maxi/edm" /><edm:isShownAt rdf:resource="http://www.dlib.si/details/URN:NBN:SI:DOC-7PYPGFMK" /></ore:Aggregation></rdf:RDF>