Suchergebnisse - "GPT-4"

Performance of Microsoft Copilot in the Diagnostic Process of Pulmonary Embolism

Autoren: Arslan, Banu Sutasir, Mehmet Necmeddin Altinbilek, Ertugrul

Quelle: Western Journal of Emergency Medicine: Integrating Emergency Care with Population Health. 26(4)

Schlagwörter: Chatbot, GPT-4, copilot, pulmonary embolism, Artificial Intelligence, Emergency Medicine

Dateibeschreibung: application/pdf

Zugangs-URL: https://escholarship.org/uc/item/11s8f15j
https://escholarship.org/content/qt11s8f15j/qt11s8f15j.pdf

AI‐driven simplification of surgical reports in gynecologic oncology: A potential tool for patient education

Autoren: Maximilian Riedel Bastian Meyer Raphael Kfuri Rubens et al.

Quelle: Acta Obstet Gynecol Scand
Acta Obstetricia et Gynecologica Scandinavica, Vol 104, Iss 7, Pp 1373-1381 (2025)

Schlagwörter: surgery, Oncology, AI, GPT‐4, gynecology, RG1-991, ORIGINAL RESEARCH, ONCOLOGY, GPT-4, large language models, patient education, Gynecology and obstetrics, ddc

Dateibeschreibung: application/pdf

Zugangs-URL: https://pubmed.ncbi.nlm.nih.gov/40366215
https://doaj.org/article/70340d46d1ec4bfd80a4c2a83204c500
https://mediatum.ub.tum.de/doc/1791840/document.pdf

Development of a GPT-4–Powered Virtual Simulated Patient and Communication Training Platform for Medical Students to Practice Discussing Abnormal Mammogram Results With Patients: Multiphase Study

Autoren: Weisman, Dan Sugarman, Alanna Huang, Yue Ming et al.

Quelle: JMIR Formative Research. 9

Schlagwörter: 4203 Health Services and Systems (for-2020), 42 Health Sciences (for-2020), Bioengineering (rcdc), Clinical Research (rcdc), Women's Health (rcdc), Cancer (rcdc), Breast Cancer (rcdc), Biomedical Imaging (rcdc), Humans (mesh), Students, Medical (mesh), Female (mesh), Mammography (mesh), Patient Simulation (mesh), Communication (mesh), Physician-Patient Relations (mesh), Male (mesh), Breast Neoplasms (mesh), standardized patient, virtual simulated patient, artificial intelligence, AI, large language model, LLM, GPT-4, agent, communication skills training, abnormal mammography results, biopsy, Humans (mesh), Breast Neoplasms (mesh), Mammography (mesh), Communication (mesh), Physician-Patient Relations (mesh), Students, Medical (mesh), Patient Simulation (mesh), Female (mesh), Male (mesh), AI, GPT-4, LLM, abnormal mammography results, agent, artificial intelligence, biopsy, communication skills training, large language model, standardized patient, virtual simulated patient, Humans (mesh), Students, Medical (mesh), Female (mesh), Mammography (mesh), Patient Simulation (mesh), Communication (mesh), Physician-Patient Relations (mesh), Male (mesh), Breast Neoplasms (mesh), 32 Biomedical and clinical sciences (for-2020), 42 Health sciences (for-2020)

Dateibeschreibung: application/pdf

Zugangs-URL: https://escholarship.org/uc/item/0xp4z6q8
https://escholarship.org/content/qt0xp4z6q8/qt0xp4z6q8.pdf

Natural language interfaces for business intelligence at scale: A review

Autoren: Sura, Rajesh

Quelle: International Journal of Science and Research Archive. 15:1702-1711

Schlagwörter: Natural Language Interfaces, Business Intelligence, Conversational BI, Semantic Parsing, GPT-4, Data Analytics, NL2SQL, Transformer Models, Human-AI Interaction, SQL Generation

Evaluation of a context-aware chatbot using retrieval-augmented generation for answering clinical questions on medication-related osteonecrosis of the jaw

Autoren: David Steybe Philipp Poxleitner Suad Aljohani et al.

Quelle: Journal of Cranio-Maxillofacial Surgery. 53:355-360

Schlagwörter: Generative pre-trained transformer, Retrieval-augmented generation, Medication-related osteonecrosis of the jaw, GPT-4, Humans, Information Storage and Retrieval, Bisphosphonate-Associated Osteonecrosis of the Jaw, Large language models, Clinical practice guidelines

Zugangs-URL: https://pubmed.ncbi.nlm.nih.gov/39799075
https://hdl.handle.net/11370/634416a3-462b-4977-9b43-40fc599719d4
https://research.rug.nl/en/publications/634416a3-462b-4977-9b43-40fc599719d4
https://doi.org/10.1016/j.jcms.2024.12.009
https://epub.ub.uni-muenchen.de/126597/

From Bag-of-Words to Transformers: A Comparative Study for Text Classification in Healthcare Discussions in Social Media

Autoren: Enrico De Santis Alessio Martino Francesca Ronci et al.

Quelle: IEEE Transactions on Emerging Topics in Computational Intelligence. 9:1063-1077

Schlagwörter: social networking (online), transformers, semantics, vectors, training, task analysis, support vector machines, embedding techniques, healthcare, natural language processing, social network analysis, text categorization, text mining, mistral, GPT-4, large language models, Embedding techniques, healthcare, natural language processing, social network analysis, text categorization, text mining, transformers, mistral, GPT-4, large language models

Dateibeschreibung: application/pdf

Prompt Engineering P2X Business Ecosystem with Generative AI

Autoren: Metso Lasse Ylä-Kujala Antti Sinkkonen Tiina et al.

Weitere Verfasser: Metso Lasse Ylä-Kujala Antti Sinkkonen Tiina et al.

Quelle: Procedia Computer Science. 256:20-27

Schlagwörter: Prompt Engineering, Power-to-X, Business Ecosystem, Sustainability, Generative AI, GPT-4, AI Data Visualization

Dateibeschreibung: fulltext

Zugangs-URL: https://lutpub.lut.fi/handle/10024/169175

GPT-4 shows comparable performance to human examiners in ranking open-text answers

Autoren: Abdullah Al Zubaer Michael Granitzer Stephan Geschwind et al.

Quelle: Scientific Reports, Vol 15, Iss 1, Pp 1-14 (2025)

Schlagwörter: Automated grading systems, Examination tasks, GPT-4, Inter-rater reliability, Open-text answers, Medicine, Science

Dateibeschreibung: electronic resource

Relation: https://doaj.org/toc/2045-2322

Zugangs-URL: https://doaj.org/article/470a4076584448ec91e57477fbc33da0

Evaluation of large language models (LLMs) on the mastery of knowledge and skills in the heating, ventilation and air conditioning (HVAC) industry

Autoren: Jie Lu Xiangning Tian Chaobo Zhang et al.

Quelle: Energy and Built Environment, Vol 6, Iss 5, Pp 875-892 (2025)

Schlagwörter: Large language model, ChatGPT, GPT-4, Artificial general intelligence, HVAC systems, Environmental technology. Sanitary engineering, TD1-1066, Building construction, TH1-9745

Dateibeschreibung: electronic resource

Relation: http://www.sciencedirect.com/science/article/pii/S2666123324000448; https://doaj.org/toc/2666-1233

Zugangs-URL: https://doaj.org/article/35220d2715904afbbbab10bb32e00d81

Evaluating and comparing student responses in examinations from the perspectives of human and artificial intelligence (GPT-4 and Gemini)

Autoren: Kubra Yildiz Domanic Sukran Baycan

Quelle: BMC Medical Education, Vol 25, Iss 1, Pp 1-6 (2025)

Schlagwörter: ChatGPT, GPT-4, Gemini, Artificial intelligence, Dental education, Assessment methods, Special aspects of education, LC8-6691, Medicine

Dateibeschreibung: electronic resource

Relation: https://doaj.org/toc/1472-6920

Zugangs-URL: https://doaj.org/article/4fb9baad619745eb9d84c0ddf49a960a

Un nouvel echoà l'intelligence artificielle dans l’enseignement de la langue Française

Autoren: Ifechukwude, Omilo Njosi , F.C.

Quelle: Abraka Humanities Review; Vol. 15 No. 2 (2025); 37-44

Schlagwörter: IA, langue française, processus d'enseignement, ChatGPT, GPT-4, AI, French language, teaching process, ChatGPT, GPT-4

Dateibeschreibung: application/pdf

Zugangs-URL: https://www.ajol.info/index.php/abraka/article/view/300676

Open Source Language Models Can Provide Feedback: Evaluating LLMs' Ability to Help Students Using GPT-4-As-A-Judge

Autoren: Charles Koutcheme Nicola Dainese Sami Sarsa et al.

Weitere Verfasser: Charles Koutcheme Nicola Dainese Sami Sarsa et al.

Quelle: Proceedings of the 2024 on Innovation and Technology in Computer Science Education V. 1. :52-58

Schlagwörter: FOS: Computer and information sciences, llm-as-a-judge, Computer Science - Artificial Intelligence, Zephyr, tekoäly, zephyr, korkeakouluopetus, chattibotit, Computer Science - Computers and Society, open source, avoin lähdekoodi, code llama, Computers and Society (cs.CY), large language models, 10. No inequality, Computer Science - Computation and Language, 9. Industry and infrastructure, automatic evaluation, 4. Education, palaute, gpt-4, automatic feedback, llms, Code Llama, programming feedback, LLM-as-a-judge, Artificial Intelligence (cs.AI), generative ai, generative AI, GPT-4, kielimallit, LLMs, ohjelmointi, Computation and Language (cs.CL)

Dateibeschreibung: application/pdf; fulltext

Zugangs-URL: http://arxiv.org/abs/2405.05253
http://urn.fi/URN:NBN:fi:jyu-202408075409
https://aaltodoc.aalto.fi/handle/123456789/130471

Using Large Language Models in the Diagnosis of Acute Cholecystitis: Assessing Accuracy and Guidelines Compliance

Autoren: Marta Goglia Arianna Cicolani Francesco Maria Carrano et al.

Quelle: The American Surgeon™. 91:967-977

Schlagwörter: gpt-4, tokyo guidelines, acute cholecystitis, clinical decision support, gemini advanced, large language models

Dateibeschreibung: application/pdf

Zugangs-URL: https://pubmed.ncbi.nlm.nih.gov/40072889
https://hdl.handle.net/11573/1738657
https://doi.org/10.1177/00031348251323719

Breaking the Programming Language Barrier: Multilingual Prompting to Empower Non-Native English Learners

Autoren: James Prather Brent N Reeves Paul Denny et al.

Weitere Verfasser: James Prather Brent N Reeves Paul Denny et al.

Quelle: Proceedings of the 27th Australasian Computing Education Conference. :74-84

Schlagwörter: LLM, FOS: Computer and information sciences, Computer Science - Artificial Intelligence, GPT, Prompt Problems, Computer Science - Human-Computer Interaction, Human-Computer Interaction (cs.HC), GitHub, Computer Science - Computers and Society, Large Language Models, Non-Native English Speakers, Artificial Intelligence, Computers and Society (cs.CY), Copilot, HCI, OpenAI, GenAI, Introductory Programming, Codex, ChatGPT, Artificial Intelligence (cs.AI), AI, Novice Programming, GPT-4, Automatic Code Generation, CS1

Dateibeschreibung: application/pdf

Zugangs-URL: http://arxiv.org/abs/2412.12800
https://aaltodoc.aalto.fi/handle/123456789/137040

Comparative Analysis of ChatGPT and Human Expertise in Diagnosing Primary Liver Carcinoma: A Focus on Gross Morphology

Autoren: Prakasit Sa-ngiamwibool Thiyaphat Laohawetwanit

Quelle: Siriraj Medical Journal, Vol 77, Iss 2 (2025)

Schlagwörter: Cholangiocarcinoma, Artificial intelligence, ChatGPT, Hepatocellular carcinoma, GPT-4, Medicine, Liver cancer

Zugangs-URL: https://doaj.org/article/114bf4415b4d48d88257430e826016b4

Assessing the Capabilities of Generative Pretrained Transformer-4 in Addressing Open-Ended Inquiries of Oral Cancer

Autoren: Kaiyuan Ji Jing Han Guangtao Zhai et al.

Quelle: Int Dent J
International Dental Journal, Vol 75, Iss 1, Pp 158-165 (2025)

Schlagwörter: Artificial intelligence, Oral health, Scientific Research Report, Education tool, GPT-4, Oral cancer, Dentistry, RK1-715

Zugangs-URL: https://pubmed.ncbi.nlm.nih.gov/39098480
https://doaj.org/article/a918a6cd36ce4b398ca060d570e3128d

Large Language Models in side-channel cryptanalysis

Autoren: Witold Waligóra

Quelle: International Journal of Electronics and Telecommunications, Vol vol. 71, Iss No 2, Pp 437-442 (2025)

Schlagwörter: side-channel analysis, gpt-4, Telecommunication, large language models, Electrical engineering. Electronics. Nuclear engineering, TK5101-6720, TK1-9971

Exploring the Impact of Large Language Models on Disease Diagnosis

Autoren: Ibrahim Almubark

Quelle: IEEE Access, Vol 13, Pp 8225-8238 (2025)

Schlagwörter: ChatGPT, GPT-4, health care applications, GPT-3.5, Electrical engineering. Electronics. Nuclear engineering, Large language models, BARD, TK1-9971

Zugangs-URL: https://doaj.org/article/fd5be9bc24d245e3a7649d9d69e245d7

Evaluating ChatGPT-4’s correctness in patient-focused informing and awareness for atrial fibrillation

Autoren: Ivan Zeljkovic Matea Novak Ana Jordan et al.

Quelle: Heart Rhythm O2

Schlagwörter: Experimental, GPT-4, Patient Informing Atrial fibrillation Large language models AI in health care

Zugangs-URL: https://pubmed.ncbi.nlm.nih.gov/40224268
https://www.sciencedirect.com/science/article/pii/S2666501824003301
https://doi.org/10.1016/j.hroo.2024.10.005

Case study identification with GPT-4 and implications for mapping studies

Autoren: Petersen, Kai

Quelle: Information and Software Technology. 171

Schlagwörter: Case study, Data extraction, GPT-4, Systematic mapping studies, Data mining, Extraction, Case-studies, Code smell, Mapping studies, Performance, Mapping

Dateibeschreibung: electronic

Zugangs-URL: https://urn.kb.se/resolve?urn=urn:nbn:se:bth-26102
https://doi.org/10.1016/j.infsof.2024.107452