{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:44:49Z","timestamp":1782845089769,"version":"3.54.5"},"reference-count":76,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIRx Med"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Artificial intelligence (AI) has evolved through various trends, with different subfields gaining prominence over time. Currently, conversational AI\u2014particularly generative AI\u2014is at the forefront. Conversational AI models are primarily focused on text-based tasks and are commonly deployed as chatbots. Recent advancements by OpenAI have enabled the integration of external, independently developed models, allowing chatbots to perform specialized, task-oriented functions beyond general language processing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to develop a smart chatbot that integrates large language models from OpenAI with specialized domain-specific models, such as those used in medical image diagnostics. The system leverages transfer learning via Google\u2019s Teachable Machine to construct image-based classifiers and incorporates a diabetes detection model developed in TensorFlow.js. A key innovation is the chatbot\u2019s ability to extract relevant parameters from user input, trigger the appropriate diagnostic model, interpret the output, and deliver responses in natural language. The overarching goal is to demonstrate the potential of combining large language models with external models to build multimodal, task-oriented conversational agents.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Two image-based models were developed and integrated into the chatbot system. The first analyzes chest X-rays to detect viral and bacterial pneumonia. The second uses optical coherence tomography images to identify ocular conditions such as drusen, choroidal neovascularization, and diabetic macular edema. Both models were incorporated into the chatbot to enable image-based medical query handling. In addition, a text-based model was constructed to process physiological measurements for diabetes prediction using TensorFlow.js. The architecture is modular; new diagnostic models can be added without redesigning the chatbot, enabling straightforward functional expansion.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The findings demonstrate effective integration between the chatbot and the diagnostic models, with only minor deviations from expected behavior. Additionally, a stub function was implemented within the chatbot to schedule medical appointments based on the severity of a patient\u2019s condition, and it was specifically tested with the optical coherence tomography and X-ray models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study demonstrates the feasibility of developing advanced AI systems\u2014including image-based diagnostic models and chatbot integration\u2014by leveraging AI as a service. It also underscores the potential of AI to enhance user experiences in bioinformatics, paving the way for more intuitive and accessible interfaces in the field. Looking ahead, the modular nature of the chatbot allows for the integration of additional diagnostic models as the system evolves.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/56090","type":"journal-article","created":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T13:45:08Z","timestamp":1756388708000},"page":"e56090-e56090","source":"Crossref","is-referenced-by-count":3,"title":["Development of a Conversational Artificial Intelligence\u2013Based Web Application for Medical Consultations: Prototype Study"],"prefix":"10.2196","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5786-0306","authenticated-orcid":false,"given":"Jorge Guerra","family":"Pires","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"issue":"2","key":"R1","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1167\/tvst.9.2.45","article-title":"Current challenges and barriers to real-world artificial intelligence adoption for the healthcare system, provider, and the patient","volume":"9","author":"Singh","journal-title":"Trans Vis Sci Tech"},{"key":"R2","unstructured":"Pires JG . An informal survey presents the gap between computer and medical doctors and biologists. Theoretical and Mathematical Biology (Medium Blog). 2021. URL: https:\/\/medium.com\/theoretical-and-mathematical-biology\/an-informal-survey-presents-the-gap-between-computer-and-medical-doctors-and-biologists-ca8816051739 [Accessed 26-09-2025]"},{"key":"R3","doi-asserted-by":"crossref","unstructured":"Pires JG . Data science using openai: testing their new capabilities focused on data science. Qeios. Preprint posted online on Jan 29, 2024. [doi: 10.32388\/76QMHB.2]","DOI":"10.32388\/76QMHB.2"},{"key":"R4","doi-asserted-by":"crossref","unstructured":"Pires JG . SnakeChat: a conversational-AI based app for snake classification. Qeios. Preprint posted online on Nov 23, 2023. [doi: 10.32388\/Y13B20]","DOI":"10.32388\/1PA11N"},{"issue":"2","key":"R5","doi-asserted-by":"publisher","first-page":"1647","DOI":"10.3390\/su15021647","article-title":"RoboDoc: smart robot design dealing with contagious patients for essential vitals amid COVID-19 pandemic","volume":"15","author":"Khan","journal-title":"Sustainability"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3233\/FRL-200002","article-title":"RoboDoc: critical ethical issues to consider for the design and development of a robotic doctor experience","volume":"1","author":"Edmond","journal-title":"FRL"},{"issue":"9","key":"R7","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1093\/jamia\/ocy072","article-title":"Conversational agents in healthcare: a systematic review","volume":"25","author":"Laranjo","journal-title":"J Am Med Inform Assoc"},{"issue":"4","key":"R8","doi-asserted-by":"publisher","first-page":"1009","DOI":"10.1093\/jamia\/ocae015","article-title":"Question answering systems for health professionals at the point of care-a systematic review","volume":"31","author":"Kell","journal-title":"J Am Med Inform Assoc"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","DOI":"10.1186\/s12903-025-05732-w","article-title":"Artificial intelligence-based chatbot assistance in clinical decision-making for medically complex patients in oral surgery: a comparative study","volume":"25","author":"\u015ei\u015fman","journal-title":"BMC Oral Health"},{"key":"R10","doi-asserted-by":"crossref","unstructured":"Wolfram S . ChatGPT gets its \u201cWolfram superpowers\u201d. Stephen Wolfram. Mar 23, 2023. URL: https:\/\/writings.stephenwolfram.com\/2023\/03\/chatgpt-gets-its-wolfram-superpowers\/ [Accessed 26-09-2025]","DOI":"10.31855\/7325963b-c14"},{"key":"R11","unstructured":"McGinley L . AI hasn\u2019t killed radiology, but it is changing it. The Washington Post. Apr 2025. URL: https:\/\/www.washingtonpost.com\/health\/2025\/04\/ 05\/ai-machine-learning-radiology-software\/?utm_source=chatgpt.com [Accessed 26-09-2025]"},{"issue":"5","key":"R12","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","journal-title":"Cell"},{"key":"R13","doi-asserted-by":"crossref","unstructured":"Pires JG . Machine learning in medicine using JavaScript: building web apps using TensorFlow.js for interpreting biomedical datasets. medRxiv. Preprint posted online on Dec 21, 2023. [doi: 10.1101\/2023.06.21.23291717]","DOI":"10.1101\/2023.06.21.23291717"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.20935\/AL5792","article-title":"Innovating with Biomathematics: the challenge of building user-friendly interfaces for computational biology","author":"Pires","journal-title":"Academia Letters"},{"key":"R15","unstructured":"Health informatics. Wikipedia. 2024. URL: https:\/\/en.wikipedia.org\/wiki\/Health_informatics [Accessed 02-03-2024]"},{"key":"R16","unstructured":"Kahneman D Sibony O Sunstein CR . Noise. Little, Brown Spark; 2021. ISBN: 0316451401"},{"key":"R17","doi-asserted-by":"crossref","unstructured":"Meehl PE . Clinical Versus Statistical Prediction: A Theoretical Analysis and A Review of the Evidence. University of Minnesota Press; 1954. [doi: 10.1037\/11281-000] ISBN: 0963878492","DOI":"10.1037\/11281-000"},{"key":"R18","unstructured":"Brown TB Mann B Ryder N Subbiah M Kaplan J Dhariwal P et al. Language models are few-shot learners. Presented at: Proceedings of the 34th International Conference on Neural Information Processing Systems; Dec 6-12, 2020; Red Hook, NY. 2020.[doi: 10.5555\/3495724.3495883]"},{"issue":"7639","key":"R19","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","journal-title":"Nature New Biol"},{"key":"R20","unstructured":"Kaplan J McCandlish S Henighan T Brown TB Chess B Child R et al. Scaling laws for neural language models. Preprint posted online on Jan 23, 2020. 10.48550\/arXiv.2001.08361"},{"key":"R21","unstructured":"OpenAI. Function calling. 2024. URL: https:\/\/platform.openai.com\/docs\/guides\/function-calling\/function-calling [Accessed 26-09-2025]"},{"key":"R22","unstructured":"Bookings introduction. URL: https:\/\/dev.wix.com\/docs\/velo\/apis\/wix-bookings-backend\/bookings\/introduction [Accessed 08-10-2025]"},{"key":"R23","unstructured":"Google Calendar API overview. URL: https:\/\/developers.google.com\/workspace\/calendar\/api\/guides\/overview [Accessed 08-10-2025]"},{"key":"R24","unstructured":"Heroku | Robodoc. URL: https:\/\/robodoc.herokuapp.com\/#\/tools\/diabetes [Accessed 08-10-2025]"},{"key":"R25","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2021.624259","article-title":"Galaxy and MEAN stack to create a user-friendly workflow for the rational optimization of cancer chemotherapy","volume":"12","author":"Pires","journal-title":"Front Genet"},{"key":"R26","unstructured":"Pires JG . What are the challenges that you will face when using JavaScript libraries in Angular. JavaScript in Plain English. 2021. URL: https:\/\/javascript.plainenglish.io\/ what-javascript-has-to-do-with-angular-6fdd45fd30b7 [Accessed 26-09-2025]"},{"key":"R27","unstructured":"Pires JG . Python, JavaScript is on your snake tail! IdeaCoding Lab. 2022. URL: https:\/\/medium.com\/ideacoding-lab\/python-javascript-is-on-you-snake-tail-eb1509b7e4cc [Accessed 26-09-2025]"},{"issue":"3","key":"R28","doi-asserted-by":"publisher","first-page":"80","DOI":"10.5335\/rbca.v15i3.15028","article-title":"SnakeFace: a transfer learning based app for snake classification","volume":"15","author":"Pires","journal-title":"RBCA"},{"key":"R29","unstructured":"OpenAI API Reference. URL: https:\/\/platform.openai.com\/docs\/api-reference\/introduction [Accessed 08-10-2025]"},{"key":"R30","unstructured":"Angular \u2014 What is Angular? URL: https:\/\/angular.dev\/overview [Accessed 08-10-2025]"},{"key":"R31","unstructured":"TensorFlow.js. URL: https:\/\/www.tensorflow.org\/js [Accessed 08-10-2025]"},{"key":"R32","unstructured":"Heroku. URL: https:\/\/devcenter.heroku.com\/categories\/reference [Accessed 08-10-2025]"},{"key":"R33","unstructured":"Jorge Guerra Pires. GitHub. URL: https:\/\/github.com\/JorgeGuerraPires [Accessed 08-10-2025]"},{"key":"R34","unstructured":"Jorge Guerra Pires. Amazon. URL: https:\/\/www.amazon.com\/stores\/Jorge-Guerra-Pires\/author\/B09QJXMG1F?ref=ap_rdr&isDramIntegrated=true&shoppingPortalEnabled=true [Accessed 08-10-2025]"},{"key":"R35","unstructured":"Jorge Guerra Pires. Udemy. URL: https:\/\/www.udemy.com\/user\/jorge-guerra-pires\/?srsltid=AfmBOoorCGgMP0CHEEjzzf29PyCv-dFHhLcGH9-kV-EwriOAR3ua6022 [Accessed 08-10-2025]"},{"key":"R36","unstructured":"OpenAI | Model optimization. URL: https:\/\/platform.openai.com\/docs\/guides\/model-optimization [Accessed 08-10-2025]"},{"issue":"8","key":"R37","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1011319","article-title":"Ten quick tips for harnessing the power of ChatGPT in computational biology","volume":"19","author":"Lubiana","journal-title":"PLoS Comput Biol"},{"issue":"6","key":"R38","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.40922","article-title":"Artificial intelligence (AI) chatbots in medicine: a supplement, not a substitute","volume":"15","author":"Altamimi","journal-title":"Cureus"},{"key":"R39","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2023.1199058","article-title":"ChatGPT outperforms humans in emotional awareness evaluations","volume":"14","author":"Elyoseph","journal-title":"Front Psychol"},{"issue":"5","key":"R40","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1016\/j.jpurol.2023.05.018","article-title":"ChatGPT and large language model (LLM) chatbots: the current state of acceptability and a proposal for guidelines on utilization in academic medicine","volume":"19","author":"Kim","journal-title":"J Pediatr Urol"},{"issue":"6","key":"R41","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1001\/jamainternmed.2023.1835","article-title":"How chatbots and large language model artificial intelligence systems will reshape modern medicine: fountain of creativity or Pandora\u2019s box?","volume":"183","author":"Li","journal-title":"JAMA Intern Med"},{"issue":"1","key":"R42","doi-asserted-by":"publisher","DOI":"10.1136\/leader-2023-000797","article-title":"ChatGPT and generative AI chatbots: challenges and opportunities for science, medicine and medical leaders","volume":"8","author":"Loh","journal-title":"BMJ Lead"},{"issue":"5","key":"R43","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/j.revmed.2023.04.001","article-title":"Chatbots and internal medicine: future opportunities and challenges","volume":"44","author":"Galland","journal-title":"Rev Med Interne"},{"issue":"4","key":"R44","doi-asserted-by":"publisher","first-page":"2137","DOI":"10.1007\/s00405-023-08381-3","article-title":"Performance of artificial intelligence chatbots in sleep medicine certification board exams: ChatGPT versus Google Bard","volume":"281","author":"Cheong","journal-title":"Eur Arch Otorhinolaryngol"},{"issue":"4","key":"R45","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1016\/S1470-2045(19)30142-1","article-title":"Artificial intelligence, chatbots, and the future of medicine","volume":"20","author":"Greene","journal-title":"Lancet Oncol"},{"key":"R46","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-0280-0","article-title":"Chatbots in the fight against the COVID-19 pandemic","volume":"3","author":"Miner","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R47","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0901-1","article-title":"Strategies to reduce diagnostic errors: a systematic review","volume":"19","author":"Abimanyi-Ochom","journal-title":"BMC Med Inform Decis Mak"},{"issue":"5","key":"R48","doi-asserted-by":"publisher","first-page":"403","DOI":"10.47470\/0044-197X-2023-67-5-403-410","article-title":"Chatbots is the modern reality of consulting in medicine","volume":"67","author":"Aksenova","journal-title":"Zdravoohran Ross Fed"},{"key":"R49","unstructured":"Product Hunt | Robodoc. URL: https:\/\/www.producthunt.com\/products\/robodoc\/launches\/robodoc?comment=3125845 [Accessed 08-10-2025]"},{"issue":"1","key":"R50","doi-asserted-by":"publisher","first-page":"38","DOI":"10.26512\/gs.v11i1.28626","article-title":"Alguns insights em Startups um novo paradigma para a tr\u00edplice alian\u00e7a ci\u00eancia, tecnologia e inova\u00e7\u00e3o [Article in Portuguese]","volume":"11","author":"Pires","journal-title":"Rev G&S"},{"issue":"1","key":"R51","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-46995-z","article-title":"Evaluation of the performance of GPT-3.5 and GPT-4 on the Polish Medical Final Examination","volume":"13","author":"Roso\u0142","journal-title":"Sci Rep"},{"issue":"11","key":"R52","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1093\/clinchem\/hvad106","article-title":"AI chatbots in clinical laboratory medicine: foundations and trends","volume":"69","author":"Yang","journal-title":"Clin Chem"},{"key":"R53","doi-asserted-by":"crossref","unstructured":"Matsoukas C Haslum JF Sorkhei M Soderberg M Smith K . What makes transfer learning work for medical images: feature reuse & other factors. Presented at: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR); Jun 18-24, 2022; New Orleans, LA. [doi: 10.1109\/CVPR52688.2022.00901]","DOI":"10.1109\/CVPR52688.2022.00901"},{"key":"R54","doi-asserted-by":"crossref","unstructured":"Tang H Cen X . A survey of transfer learning applied in medical image recognition. Presented at: 2021 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA); Aug 27-28, 2021:94-97; Dalian, China. [doi: 10.1109\/AEECA52519.2021.9574368]","DOI":"10.1109\/AEECA52519.2021.9574368"},{"key":"R55","doi-asserted-by":"crossref","unstructured":"Wang Y . A new classification method for COVID-19 CT images based on transfer learning and attention mechanism. Presented at: 2022 16th ICME International Conference on Complex Medical Engineering (CME); Nov 4-7, 2022:236-240; Zhongshan, China. [doi: 10.1109\/CME55444.2022.10063276]","DOI":"10.1109\/CME55444.2022.10063276"},{"issue":"5","key":"R56","doi-asserted-by":"publisher","first-page":"1761","DOI":"10.18280\/ts.390534","article-title":"Investigating transfer learning performances of deep learning models for classification of GPR B-scan images","volume":"39","author":"Dikmen","journal-title":"TS"},{"key":"R57","doi-asserted-by":"crossref","unstructured":"Aftab MO Javed Awan M Khalid S Javed R Shabir H . Executing spark BigDL for leukemia detection from microscopic images using transfer learning. Presented at: 2021 1st International Conference on Artificial Intelligence and Data Analytics (CAIDA); Apr 6-7, 2021; Riyadh, Saudi Arabia. [doi: 10.1109\/CAIDA51941.2021.9425264]","DOI":"10.1109\/CAIDA51941.2021.9425264"},{"issue":"2","key":"R58","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.3233\/JIFS-219273","article-title":"COVID-19 detection with X-ray images by using transfer learning","volume":"43","author":"Mahanty","journal-title":"Journal of Intelligent & Fuzzy Systems"},{"issue":"7","key":"R59","doi-asserted-by":"publisher","first-page":"7236","DOI":"10.1007\/s11227-020-03572-9","article-title":"Classification of brain tumors from MR images using deep transfer learning","volume":"77","author":"Polat","journal-title":"J Supercomput"},{"issue":"1","key":"R60","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-99015-3","article-title":"Detection and analysis of COVID-19 in medical images using deep learning techniques","volume":"11","author":"Yang","journal-title":"Sci Rep"},{"key":"R61","unstructured":"Khan A . Radiology is embracing generative AI to streamline productivity\u2014and not to replace doctors. Business Insider. Jun 2025. URL: https:\/\/www.businessinsider.com\/radiology-embraces-generative-ai-to-streamline-productivity-2025-6 [Accessed 26-09-2025]"},{"key":"R62","doi-asserted-by":"crossref","unstructured":"Prusty S Patnaik S Dash SK . ResNet50V2: a transfer learning model to predict pneumonia with chest X-ray images. Presented at: 2022 International Conference on Machine Learning, Computer Systems and Security (MLCSS); Aug 5-6, 2022; Bhubaneswar, India. [doi: 10.1109\/MLCSS57186.2022.00046]","DOI":"10.1109\/MLCSS57186.2022.00046"},{"issue":"2","key":"R63","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/IJEHMC.20220701.oa2","article-title":"Utilization of transfer learning model in detecting COVID-19 cases from chest X-ray images","volume":"13","author":"Jawahar","journal-title":"International Journal of E-Health and Medical Communications"},{"issue":"1","key":"R64","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1109\/JAS.2020.1003393","article-title":"Automatic detection of COVID-19 infection using chest X-ray images through transfer learning","volume":"8","author":"Ohata","journal-title":"IEEE\/CAA J Autom Sinica"},{"key":"R65","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/9437538","article-title":"A novel COVID-19 diagnosis support system using the stacking approach and transfer learning technique on chest X-ray images","volume":"2021","author":"Hamida","journal-title":"J Healthc Eng"},{"key":"R66","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2022.945892","article-title":"Prevention and treatment of ventilator-associated pneumonia in COVID-19","volume":"13","author":"Deng","journal-title":"Front Pharmacol"},{"issue":"1","key":"R67","doi-asserted-by":"publisher","first-page":"1765","DOI":"10.37506\/ijfmt.v15i1.13666","article-title":"ACO-based type 2 diabetes detection using artificial neural networks","volume":"15","journal-title":"Indian Journal of Forensic Medicine & Toxicology"},{"key":"R68","doi-asserted-by":"crossref","unstructured":"Haritha R Sureshbabu D Sammulal P . Diabetes detection using principal component analysis and neural networks. In: Santosh KC Hegadi RS , editors. Recent Trends in Image Processing and Pattern Recognition. Springer Singapore; 2019:270-285. [doi: 10.1007\/978-981-13-9184-2_24]","DOI":"10.1007\/978-981-13-9184-2_24"},{"issue":"19","key":"R69","doi-asserted-by":"publisher","first-page":"9435","DOI":"10.3390\/app12199435","article-title":"Towards explainable deep neural networks for the automatic detection of diabetic retinopathy","volume":"12","author":"Alghamdi","journal-title":"Appl Sci (Basel)"},{"key":"R70","doi-asserted-by":"crossref","unstructured":"Ahmed DW Hashim FA Salem NM . Diabetic retinopathy detection using convolutional neural networks. Presented at: 2023 33rd International Conference on Computer Theory and Applications (ICCTA); Dec 16-18, 2023:240-245; Alexandria, Egypt. [doi: 10.1109\/ICCTA60978.2023.10969372]","DOI":"10.1109\/ICCTA60978.2023.10969372"},{"issue":"21-22","key":"R71","doi-asserted-by":"publisher","DOI":"10.1002\/pmic.202400005","article-title":"Open-source large language models in action: a bioinformatics chatbot for PRIDE database","volume":"24","author":"Bai","journal-title":"Proteomics"},{"key":"R72","unstructured":"Stern J . GPT-4 has the memory of a goldfish. The Atlantic. 2023. URL: https:\/\/www.theatlantic.com\/technology\/archive\/2023\/03\/gpt-4-has-memory-context-window\/673426\/ [Accessed 26-09-2025]"},{"key":"R73","unstructured":"Raveendran C . Gemini 15 - breaking the token limits to create a new future. LinkedIn. 2024. URL: https:\/\/www.linkedin.com\/pulse\/gemini-15-breaking-token-limits-create-new-future-raveendran-i4jqc [Accessed 26-09-2025]"},{"key":"R74","doi-asserted-by":"crossref","unstructured":"Zhao H Chen H Yang F Liu N Deng H Cai H et al. Explainability for large language models: a survey. arXiv. Preprint posted online on Sep 2, 2023. [doi: 10.48550\/arXiv.2309.01029]","DOI":"10.1145\/3639372"},{"key":"R75","doi-asserted-by":"crossref","unstructured":"Weidinger L Uesato J Rauh M et al. Taxonomy of risks posed by language models. Presented at: FAccT \u201922; Jun 21-24, 2022:214-229; Seoul, Republic of Korea. Jun 21, 2022.[doi: 10.1145\/3531146.3533088]","DOI":"10.1145\/3531146.3533088"},{"issue":"1","key":"R76","doi-asserted-by":"publisher","DOI":"10.1038\/s44172-025-00453-y","article-title":"Explainability in the age of large language models for healthcare","volume":"4","author":"Mesinovic","journal-title":"Commun Eng"}],"container-title":["JMIRx Med"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/xmed.jmir.org\/2025\/1\/e56090","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:44:46Z","timestamp":1782841486000},"score":1,"resource":{"primary":{"URL":"https:\/\/xmed.jmir.org\/2025\/1\/e56090"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":76,"URL":"https:\/\/doi.org\/10.2196\/56090","relation":{},"ISSN":["2563-6316"],"issn-type":[{"value":"2563-6316","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,15]]},"article-number":"v6i2e56090"}}