{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,17]],"date-time":"2025-12-17T18:19:33Z","timestamp":1765995573502,"version":"build-2065373602"},"reference-count":52,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Clinical documentation, particularly the hospital discharge report (HDR), is essential for ensuring continuity of care, yet its preparation is time-consuming and places a considerable clinical and administrative burden on healthcare professionals. Recent advancements in Generative Artificial Intelligence (GenAI) and the use of prompt engineering in large language models (LLMs) offer opportunities to automate parts of this process, improving efficiency and documentation quality while reducing administrative workload. This study aims to design a digital system based on LLMs capable of automatically generating HDRs using information from clinical course notes and emergency care reports. The system was developed through iterative cycles, integrating various instruction flows and evaluating five different LLMs combined with prompt engineering strategies and agent-based architectures. Throughout the development, more than 60 discharge reports were generated and assessed, leading to continuous system refinement. In the production phase, 40 pneumology discharge reports were produced, receiving positive feedback from physicians, with an average score of 2.9 out of 4, indicating the system\u2019s usefulness, with only minor edits needed in most cases. The ongoing expansion of the system to additional services and its integration within a hospital electronic system highlights the potential of LLMs, when combined with effective prompt engineering and agent-based architectures, to generate high-quality medical content and provide meaningful support to healthcare professionals. Hospital discharge reports (HDRs) are pivotal for continuity of care but consume substantial clinician time. Generative AI systems based on large language models (LLMs) could streamline this process, provided they deliver accurate, multilingual, and workflow-compatible outputs. We pursued a three-stage, design-science approach. Proof-of-concept: five state-of-the-art LLMs were benchmarked with multi-agent prompting to produce sample HDRs and define the optimal agent structure. Prototype: 60 HDRs spanning six specialties were generated and compared with clinician originals using ROUGE with average scores compatible with specialized news summarizing models in Spanish and Catalan (lower scores). A qualitative audit of 27 HDR pairs showed recurrent divergences in medication dose (56%) and social context (52%). Pilot deployment: The AI-HDR service was embedded in the hospital\u2019s electronic health record. In the pilot, 47 HDRs were autogenerated in real-world settings and reviewed by attending physicians. Missing information and factual errors were flagged in 53% and 47% of drafts, respectively, while written assessments diminished the importance of these errors. An LLM-driven, agent-orchestrated pipeline can safely draft real-world HDRs, cutting administrative overhead while achieving clinician-acceptable quality, not without errors that require human supervision. Future work should refine specialty-specific prompts to curb omissions, add temporal consistency checks to prevent outdated data propagation, and validate time savings and clinical impact in multi-center trials.<\/jats:p>","DOI":"10.3390\/computers14060210","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T06:30:26Z","timestamp":1748413826000},"page":"210","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Leave as Fast as You Can: Using Generative AI to Automate and Accelerate Hospital Discharge Reports"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4142-083X","authenticated-orcid":false,"given":"Alex","family":"Trejo Ome\u00f1aca","sequence":"first","affiliation":[{"name":"Innex Labs, Carrer de Tarragona 10, 08800 Vilanova i la Geltr\u00fa, Spain"},{"name":"Departament d\u2019Enginyeria Gr\u00e0fica i Disseny, Escola Polit\u00e8cnica Superior d\u2019Enginyeria de Vilanova i la Geltr\u00fa (EPSEVG), Universitat Polit\u00e8cnica de Catalunya, Avinguda de V\u00edctor Balaguer 1, 08800 Vilanova i la Geltr\u00fa, Spain"}]},{"given":"Esteve","family":"Llargu\u00e9s Rocabruna","sequence":"additional","affiliation":[{"name":"Hospital General de Granollers, Avinguda Francesc Ribas s\/n, 08402 Granollers, Spain"}]},{"given":"Jonny","family":"Sloan","sequence":"additional","affiliation":[{"name":"Innex Labs, Carrer de Tarragona 10, 08800 Vilanova i la Geltr\u00fa, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9200-1976","authenticated-orcid":false,"given":"Michelle","family":"Catta-Preta","sequence":"additional","affiliation":[{"name":"Innex Labs, Carrer de Tarragona 10, 08800 Vilanova i la Geltr\u00fa, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1431-9349","authenticated-orcid":false,"given":"Jan","family":"Ferrer i Pic\u00f3","sequence":"additional","affiliation":[{"name":"Innex Labs, Carrer de Tarragona 10, 08800 Vilanova i la Geltr\u00fa, Spain"},{"name":"Departament d\u2019Enginyeria Gr\u00e0fica i Disseny, Escola T\u00e8cnica Superior d\u2019Enginyeria Industrial de Barcelona (ETSEIB), Universitat Polit\u00e8cnica de Catalunya, Avinguda Diagonal 647, 08028 Barcelona, Spain"}]},{"given":"Julio Cesar","family":"Alfaro Alvarez","sequence":"additional","affiliation":[{"name":"Hospital General de Granollers, Avinguda Francesc Ribas s\/n, 08402 Granollers, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1461-7381","authenticated-orcid":false,"given":"Toni","family":"Alonso Solis","sequence":"additional","affiliation":[{"name":"Hospital General de Granollers, Avinguda Francesc Ribas s\/n, 08402 Granollers, Spain"}]},{"given":"Eloy","family":"Lloveras Gil","sequence":"additional","affiliation":[{"name":"Hospital General de Granollers, Avinguda Francesc Ribas s\/n, 08402 Granollers, Spain"}]},{"given":"Xavier","family":"Serrano Vinaixa","sequence":"additional","affiliation":[{"name":"Hospital General de Granollers, Avinguda Francesc Ribas s\/n, 08402 Granollers, Spain"}]},{"given":"Daniela","family":"Velasquez Villegas","sequence":"additional","affiliation":[{"name":"Hospital General de Granollers, Avinguda Francesc Ribas s\/n, 08402 Granollers, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9526-7338","authenticated-orcid":false,"given":"Ramon","family":"Romeu Garcia","sequence":"additional","affiliation":[{"name":"Hospital General de Granollers, Avinguda Francesc Ribas s\/n, 08402 Granollers, Spain"}]},{"given":"Carles","family":"Rubies Feijoo","sequence":"additional","affiliation":[{"name":"Hospital General de Granollers, Avinguda Francesc Ribas s\/n, 08402 Granollers, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7416-8306","authenticated-orcid":false,"given":"Josep Maria","family":"Monguet i Fierro","sequence":"additional","affiliation":[{"name":"Innex Labs, Carrer de Tarragona 10, 08800 Vilanova i la Geltr\u00fa, Spain"},{"name":"Departament d\u2019Enginyeria Gr\u00e0fica i Disseny, Escola T\u00e8cnica Superior d\u2019Enginyeria Industrial de Barcelona (ETSEIB), Universitat Polit\u00e8cnica de Catalunya, Avinguda Diagonal 647, 08028 Barcelona, Spain"}]},{"given":"Beatriu","family":"Bayes Genis","sequence":"additional","affiliation":[{"name":"Hospital General de Granollers, Avinguda Francesc Ribas s\/n, 08402 Granollers, Spain"}]}],"member":"1968","published-online":{"date-parts":[[2025,5,28]]},"reference":[{"key":"ref_1","unstructured":"European Commission (2024). Guidelines on Hospital Discharge Report, European Commission."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1001\/jama.297.8.831","article-title":"Deficits in Communication and Information Transfer Between Hospital-Based and Primary Care Physicians: Implications for Patient Safety and Continuity of Care","volume":"297","author":"Kripalani","year":"2007","journal-title":"JAMA"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1046\/j.1525-1497.2002.10741.x","article-title":"Effect of Discharge Summary Availability during Post-Discharge Visits on Hospital Readmission","volume":"17","author":"Walraven","year":"2002","journal-title":"J. Gen. Intern. Med."},{"key":"ref_4","first-page":"1111","article-title":"Improving Continuity of Care via the Discharge Summary","volume":"2015","author":"Sakaguchi","year":"2015","journal-title":"AMIA Annu. Symp. Proc."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Pal, K., Bahrainian, S.A., Mercurio, L., and Eickhoff, C. (2023). Neural Summarization of Electronic Health Records. arXiv.","DOI":"10.2196\/preprints.49544"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1161\/CIRCOUTCOMES.114.001227","article-title":"Hospital Variation in Quality of Discharge Summaries for Patients Hospitalized With Heart Failure Exacerbation","volume":"8","author":"Dzara","year":"2015","journal-title":"Circ. Cardiovasc. Qual. Outcomes"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1002","DOI":"10.1007\/s11606-009-1057-y","article-title":"Adequacy of Hospital Discharge Summaries in Documenting Tests with Pending Results and Outpatient Follow-up Providers","volume":"24","author":"Were","year":"2009","journal-title":"J. Gen. Intern. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1995","DOI":"10.1093\/jamia\/ocad177","article-title":"A Method to Automate the Discharge Summary Hospital Course for Neurology Patients","volume":"30","author":"Hartman","year":"2023","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"753","DOI":"10.7326\/M16-0961","article-title":"Allocation of Physician Time in Ambulatory Practice: A Time and Motion Study in 4 Specialties","volume":"165","author":"Sinsky","year":"2016","journal-title":"Ann. Intern. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"50","DOI":"10.7326\/M18-0139","article-title":"Physician Burnout in the Electronic Health Record Era: Are We Ignoring the Real Cause?","volume":"169","author":"Downing","year":"2018","journal-title":"Ann. Intern. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1055\/s-0044-1787007","article-title":"Toward Alleviating Clinician Documentation Burden: A Scoping Review of Burden Reduction Efforts","volume":"15","author":"Sloss","year":"2024","journal-title":"Appl. Clin. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1136\/jamia.2010.007237","article-title":"Data from Clinical Notes: A Perspective on the Tension between Structure and Flexible Documentation","volume":"18","author":"Rosenbloom","year":"2011","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1038\/s41746-020-0221-y","article-title":"An Overview of Clinical Decision Support Systems: Benefits, Risks, and Strategies for Success","volume":"3","author":"Sutton","year":"2020","journal-title":"Npj Digit. Med."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2817","DOI":"10.1007\/s00330-023-10213-1","article-title":"ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports","volume":"34","author":"Jeblick","year":"2023","journal-title":"Eur. Radiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1055\/a-2281-7092","article-title":"A Survey of Clinicians\u2019 Views of the Utility of Large Language Models","volume":"15","author":"Spotnitz","year":"2024","journal-title":"Appl. Clin. Inform."},{"key":"ref_16","unstructured":"Sahota, P. (2025, March 01). How We\u2019re Using Generative AI to Support Outpatient Care in Peru. Front. Tech Hub, Available online: https:\/\/www.frontiertechhub.org\/insights\/avatr-generative-ai-learnings-in-project-empatia."},{"key":"ref_17","first-page":"216","article-title":"A Day-to-Day Approach for Automating the Hospital Course Section of the Discharge Summary","volume":"2022","author":"Hartman","year":"2022","journal-title":"AMIA Summits Transl. Sci. Proc."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e240357","DOI":"10.1001\/jamanetworkopen.2024.0357","article-title":"Generative Artificial Intelligence to Transform Inpatient Discharge Summaries to Patient-Friendly Language and Format","volume":"7","author":"Zaretsky","year":"2024","journal-title":"JAMA Netw. Open"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1177\/00912174241284730","article-title":"Application of AI in the Creation of Discharge Summaries in Psychiatric Clinics","volume":"60","author":"Janota","year":"2025","journal-title":"Int. J. Psychiatry Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"BJGPO.2023.0116","DOI":"10.3399\/BJGPO.2023.0116","article-title":"Transforming Healthcare Documentation: Harnessing the Potential of AI to Generate Discharge Summaries","volume":"8","author":"Clough","year":"2024","journal-title":"BJGP Open"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"152","DOI":"10.2340\/17453674.2024.40182","article-title":"ChatGPT-4 Generates Orthopedic Discharge Documents Faster than Humans Maintaining Comparable Quality: A Pilot Study of 6 Cases","volume":"95","author":"Rosenberg","year":"2024","journal-title":"Acta Orthop."},{"key":"ref_22","unstructured":"Demner-Fushman, D., Ananiadou, S., Thompson, P., and Ondov, B. (2024, January 20). Experiments in Automated Generation of Discharge Summaries in Italian. Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024, Turin, Italy."},{"key":"ref_23","unstructured":"de Salut, D. (2012). Implantaci\u00f3 del Conjunt M\u00ednim B\u00e0sic de Dades d\u2019Atenci\u00f3 Prim\u00e0ria (CMBD-AP) i d\u2019Urg\u00e8ncies (CMBD-UR)(06\/2012), Scientia."},{"key":"ref_24","unstructured":"Henriksen, K., Battles, J.B., Keyes, M.A., and Grady, M.L. (2008). Documentation of Mandated Discharge Summary Components in Transitions from Acute to Subacute Care. Advances in Patient Safety: New Directions and Alternative Approaches (Vol. 2: Culture and Redesign), Agency for Healthcare Research and Quality (US)."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Tang, B., Chen, Q., Wang, X., and Yan, J. (2019, January 18\u201321). A Study on Automatic Generation of Chinese Discharge Summary. Proceedings of the 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), San Diego, CA, USA.","DOI":"10.1109\/BIBM47256.2019.8983293"},{"key":"ref_26","unstructured":"Taylor, A. (2025, March 01). How Real-World Businesses Are Transforming with AI\u2014with More than 140 New Stories. Off. Microsoft Blog, Available online: https:\/\/blogs.microsoft.com\/blog\/2025\/04\/22\/https-blogs-microsoft-com-blog-2024-11-12-how-real-world-businesses-are-transforming-with-ai\/."},{"key":"ref_27","unstructured":"O\u2019Brien, M., and Parvini, S. (2025, March 01). In 2024, Artificial Intelligence Was All About Putting AI Tools to Work. Assoc. Press News, Available online: https:\/\/apnews.com\/article\/ai-artificial-intelligence-0b6ab89193265c3f60f382bae9bbabc9."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1111\/jpim.12602","article-title":"Innovative Idea Generation in Problem Finding: Abductive Reasoning, Cognitive Impediments, and the Promise of Artificial Intelligence","volume":"38","author":"Garbuio","year":"2021","journal-title":"J. Prod. Innov. Manag."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2050312118822927","DOI":"10.1177\/2050312118822927","article-title":"Grounded Theory Research: A Design Framework for Novice Researchers","volume":"7","author":"Birks","year":"2019","journal-title":"SAGE Open Med."},{"key":"ref_30","unstructured":"Brown, T. (2025, March 01). Harvard Business Review. Available online: https:\/\/readings.design\/PDF\/Tim%20Brown,%20Design%20Thinking.pdf."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"44","DOI":"10.22215\/timreview\/1049","article-title":"The Design-Driven Living Lab: A New Approach to Exploring Solutions to Complex Societal Challenges","volume":"7","author":"Brankaert","year":"2017","journal-title":"Technol. Innov. Manag. Rev."},{"key":"ref_32","first-page":"1","article-title":"From NASA to EU: The Evolution of the TRL Scale in Public Sector Innovation","volume":"22","year":"2017","journal-title":"Innov. J."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"25148625","DOI":"10.2307\/25148625","article-title":"Design Science in Information Systems Research","volume":"28","author":"Hevner","year":"2004","journal-title":"MIS Q."},{"key":"ref_34","unstructured":"Zhou, D., Sch\u00e4rli, N., Hou, L., Wei, J., Scales, N., Wang, X., Schuurmans, D., Cui, C., Bousquet, O., and Le, Q. (2022). Least-to-Most Prompting Enables Complex Reasoning in Large Language Models. arXiv."},{"key":"ref_35","unstructured":"Hao, Y., Sun, Y., Dong, L., Han, Z., Gu, Y., and Wei, F. (2022). Structured Prompting: Scaling In-Context Learning to 1000 Examples. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Jung, J., Qin, L., Welleck, S., Brahman, F., Bhagavatula, C., Bras, R.L., and Choi, Y. (2022). Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations. arXiv.","DOI":"10.18653\/v1\/2022.emnlp-main.82"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Shortliffe, E.H., and Cimino, J.J. (2014). Biomedical Informatics: Computer Applications in Health Care and Biomedicine, Springer.","DOI":"10.1007\/978-1-4471-4474-8"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1188\/14.ONF.545-547","article-title":"The Use of Triangulation in Qualitative Research","volume":"41","author":"Carter","year":"2014","journal-title":"Oncol. Nurs. Forum"},{"key":"ref_39","first-page":"275","article-title":"A Triangulation Approach for Design Research","volume":"Volume 2","author":"Wang","year":"2009","journal-title":"Proceedings of the ICED 09 17th International Conference on Engineering Design"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"102571","DOI":"10.1016\/j.jocs.2025.102571","article-title":"Assessing the effectiveness of ROUGE as unbiased metric in Extractive vs. Abstractive summarization techniques","volume":"87","author":"Barbella","year":"2025","journal-title":"J. Comput. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"van Zandvoort, D., Wiersema, L., Huibers, T., van Dulmen, S., and Brinkkemper, S. (2023). Enhancing Summarization Performance through Transformer-Based Prompt Engineering in Automated Medical Reporting. arXiv.","DOI":"10.5220\/0012422600003657"},{"key":"ref_42","unstructured":"Lin, C.-Y., and Och, F. (2004, January 2\u20134). Looking for a Few Good Metrics: ROUGE and Its Evaluation. Proceedings of the NTCIR Workshop, Tokyo, Japan."},{"key":"ref_43","unstructured":"Auss\u00f3, S., Berenguer, A., Aznar, J., Ravent\u00f3s, C., G\u00f3mez, V., and Bretones, M. (2025). Guia de Bones Pr\u00e0ctiques per al Desenvolupament d\u2019Eines d\u2019IA Generativa en Salut. Grans Models de Llenguatge (LLM), Fundaci\u00f3 TIC Salut Social, Generalitat de Ctalunya."},{"key":"ref_44","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., and Artzi, Y. (2019). BERTScore: Evaluating Text Generation with BERT. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Rei, R., Stewart, C., Farinha, A.C., and Lavie, A. (2020, January 16\u201320). COMET: A Neural Framework for MT Evaluation. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"ref_46","unstructured":"Saggion, H., Torres-Moreno, J.-M., da Cunha, I., and SanJuan, E. (2010, January 23\u201327). Multilingual Summarization Evaluation without Human Models. Proceedings of the 23rd International Conference on Computational Linguistics: Posters, Beijing, China."},{"key":"ref_47","unstructured":"Zhang, J., Zhao, Y., Saleh, M., and Liu, P.J. (2020, January 3\u201318). PEGASUS: Pre-Training with Extracted Gap-Sentences for Abstractive Summarization. Proceedings of the 37th International Conference on Machine Learning, Online."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Ahuir, V., Hurtado, L.-F., Gonz\u00e1lez, J.\u00c1., and Segarra, E. (2021). NASca and NASes: Two Monolingual Pre-Trained Models for Abstractive Summarization in Catalan and Spanish. Appl. Sci., 11.","DOI":"10.3390\/app11219872"},{"key":"ref_49","unstructured":"Toutanova, K., Rumshisky, A., Zettlemoyer, L., Hakkani-Tur, D., Beltagy, I., Bethard, S., Cotterell, R., Chakraborty, T., and Zhou, Y. (2021, January 6\u201311). What\u2019s in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Ando, K., Komachi, M., Okumura, T., Horiguchi, H., and Matsumoto, Y. (2022, January 8\u201310). Is In-Hospital Meta-Information Useful for Abstractive Discharge Summary Generation?. Proceedings of the 2022 International Conference on Technologies and Applications of Artificial Intelligence (TAAI), Taichung, Taiwan.","DOI":"10.1109\/TAAI57707.2022.00034"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Irugalbandara, C., Mahendra, A., Daynauth, R., Arachchige, T.K., Dantanarayana, J., Flautner, K., Tang, L., Kang, Y., and Mars, J. (2024, January 5\u20137). Scaling Down to Scale Up: A Cost-Benefit Analysis of Replacing OpenAI\u2019s LLM with Open Source SLMs in Production. Proceedings of the 2024 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), Indianapolis, IN, USA.","DOI":"10.1109\/ISPASS61541.2024.00034"},{"key":"ref_52","unstructured":"Lohn, A.J. (2023). Scaling AI. Cost and Perfomance of AI at the Leading Edge, Center for Security and Emerging Technology."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/6\/210\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:42:00Z","timestamp":1760031720000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/6\/210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,28]]},"references-count":52,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["computers14060210"],"URL":"https:\/\/doi.org\/10.3390\/computers14060210","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2025,5,28]]}}}