{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T23:50:09Z","timestamp":1791503409943,"version":"4.3.4"},"reference-count":19,"publisher":"Georg Thieme Verlag KG","issue":"04","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Appl Clin Inform"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Background Open foundation models designed for on-device and edge deployment, exemplified by the Qwen 3.5 small series (March 2, 2026) and Gemma 4 (April 2, 2026), challenge the default of routing all clinical natural language processing through commercial cloud application programming interfaces (APIs).<\/jats:p>\n                  <jats:p>Objectives This study aimed to examine the implications of these models for clinical informatics, for clinical informaticians, healthcare chief information officers, governance committees and NLP researchers.<\/jats:p>\n                  <jats:p>Methods Narrative (non-systematic) perspective. We summarized the technical advances of both releases and situated them within the 2024 to 2026 peer-reviewed evidence on locally deployed clinical large language models. We searched PubMed, Scopus and Google Scholar (January 2024 to June 2026) and added citation tracking.<\/jats:p>\n                  <jats:p>Results Both releases narrow the gap between local and frontier cloud capability for structured extraction and template-based documentation. The existing evidence comes from 3 to 70 billion parameter models on institutional servers. Clinical benchmarks at 0.8 to 4 billion parameters are absent. Hallucination, quantization, endpoint security, liability and unvalidated multimodal and multilingual claims remain open concerns. Frontier cloud models retain clear advantages for complex clinical reasoning.<\/jats:p>\n                  <jats:p>Conclusion For a defined subset of tasks, cloud-by-default may no longer be the most defensible choice. The field needs reporting standards, governance and liability frameworks, task-appropriate routing, and edge-aware benchmarks.<\/jats:p>","DOI":"10.1055\/a-2969-1166","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T23:05:26Z","timestamp":1790723126000},"page":"882-888","source":"Crossref","is-referenced-by-count":0,"title":["From Cloud to Pocket: Frontier Edge Foundation Models and the Future of Clinical Informatics"],"prefix":"10.1055","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5578-3481","authenticated-orcid":false,"given":"Ravi","family":"Shankar","sequence":"additional","affiliation":[{"name":"Clinical Research and Innovation Office, Tan Tock Seng Hospital, Singapore","place":["Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"194","published-online":{"date-parts":[[2026,10,8]]},"reference":[{"key":"ref1","volume-title":"Gemma 4: Byte for Byte, the Most Capable Open Models","author":"Google DeepMind","year":"2026"},{"key":"ref2","volume-title":"Bring State-of-the-Art Agentic Skills to the Edge with Gemma 4","author":"Google AI Edge Team","year":"2026"},{"key":"ref3","volume-title":"Closer to the Edge and On-Device with Gemma 4","author":"A Srivastava","year":"2026"},{"key":"ref4","volume-title":"Qwen 3.5: Towards Native Multimodal Agents","author":"Qwen Team","year":"2026"},{"key":"ref5","volume-title":"Qwen 3.5 Small Model Series Release","author":"Alibaba | Qwen Team","year":"2026"},{"issue":"02","key":"ref7","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1145\/3733702","article-title":"Generative AI at the edge: challenges and opportunities","volume":"23","author":"V J Reddi","year":"2025","journal-title":"ACM Queue"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3724420","article-title":"Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models","author":"X Wang","year":"2025","journal-title":"ACM Comput Surv"},{"issue":"01","key":"ref9","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1038\/s41746-024-01233-2","article-title":"Privacy-preserving large language models for structured medical information retrieval","volume":"7","author":"I C Wiest","year":"2024","journal-title":"NPJ Digit Med"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"e64544","DOI":"10.2196\/64544","article-title":"Using large language models to automate data extraction from surgical pathology reports: retrospective cohort study","volume":"9","author":"D Lee","year":"2025","journal-title":"JMIR Form Res"},{"issue":"01","key":"ref11","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1038\/s43856-025-00808-8","article-title":"Comprehensive testing of large language models for extraction of structured data in pathology","volume":"5","author":"B Grothey","year":"2025","journal-title":"Commun Med"},{"issue":"01","key":"ref12","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1038\/s41698-025-01103-4","article-title":"A software pipeline for medical information extraction with large language models, open source and suitable for oncology","volume":"9","author":"I C Wiest","year":"2025","journal-title":"npj Precis Oncol"},{"issue":"05","key":"ref13","doi-asserted-by":"crossref","first-page":"ooaf109","DOI":"10.1093\/jamiaopen\/ooaf109","article-title":"Leveraging open-source large language models for clinical information extraction in resource-constrained settings","volume":"8","author":"L Builtjes","year":"2025","journal-title":"JAMIA Open"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"1538277","DOI":"10.3389\/fcomp.2025.1538277","article-title":"Intelligent data analysis in edge computing with large language models: applications, challenges, and future directions","volume":"7","author":"X Wang","year":"2025","journal-title":"Front Comput Sci"},{"issue":"01","key":"ref16","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1038\/s41598-025-30150-x","article-title":"Edge-AI integrated secure wireless IoT architecture for real time healthcare monitoring and federated anomaly detection","volume":"16","author":"M Prabha","year":"2025","journal-title":"Sci Rep"},{"issue":"12","key":"ref17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of hallucination in natural language generation","volume":"55","author":"Z Ji","year":"2023","journal-title":"ACM Comput Surv"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"10088","DOI":"10.52202\/075280-0441","article-title":"Qlora: Efficient finetuning of quantized LLMs","volume":"36","author":"T Dettmers","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"issue":"07","key":"ref19","doi-asserted-by":"crossref","first-page":"2405","DOI":"10.1038\/s41591-026-04431-5","article-title":"General-purpose large language models outperform specialized clinical AI tools on medical benchmarks","volume":"32","author":"K Vishwanath","year":"2026","journal-title":"Nat Med"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"e71916","DOI":"10.2196\/71916","article-title":"Implementing large language models in health care: clinician-focused review with interactive guideline","volume":"27","author":"H Li","year":"2025","journal-title":"J Med Internet Res"},{"issue":"12","key":"ref21","doi-asserted-by":"crossref","first-page":"2371","DOI":"10.1109\/JAS.2025.125540","article-title":"Advancing healthcare with large language models: techniques and application","volume":"12","author":"Z Hu","year":"2025","journal-title":"IEEE CAA J Autom Sin"}],"container-title":["Applied Clinical Informatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/www.thieme-connect.de\/products\/ejournals\/pdf\/10.1055\/a-2969-1166.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T23:11:00Z","timestamp":1791501060000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.thieme-connect.de\/DOI\/DOI?10.1055\/a-2969-1166"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":19,"journal-issue":{"issue":"04","published-online":{"date-parts":[[2026,8,14]]},"published-print":{"date-parts":[[2026,8]]}},"URL":"https:\/\/doi.org\/10.1055\/a-2969-1166","archive":["Portico","CLOCKSS"],"relation":{},"ISSN":["1869-0327"],"issn-type":[{"value":"1869-0327","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9,29]]},"published":{"date-parts":[[2026,8]]}}}