CLINIKIOSK-An innovative technology to expand health care access

CLINIKIOSK-An innovative technology to expand health care access | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 18 December 2025 V1 Latest version Share on CLINIKIOSK-An innovative technology to expand health care access Author : Ela Adhikari 0009-0004-6673-6050 [email protected] Authors Info & Affiliations https://doi.org/10.22541/au.176607126.64748589/v1 339 views 83 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract Background: Healthcare systems across the world face escalating gaps in access due to workforce shortages, facility closures, and long wait times, disproportionately affecting marginalized and rural populations. Digital health innovations, especially AI-powered tools, offer opportunities to broaden access, yet existing health chatbots are constrained by rule-based design, lack of multilingual support, minimal personalization, and lack of empathetic communication. To address these gaps, we propose to develop CliniKiosk, a multilingual, customizable, retrieval-augmented, GPT-based digital health kiosk designed to deliver real-time, evidence-based, and culturally sensitive guidance. To assess the feasibility of developing CliniKiosk and evaluate its accuracy, empathy, explainability and evidence-based guidance, we will compare its performance with that of other contemporary large language models (LLMs). Methods: CliniKiosk was engineered as a modular platform integrating a React front-end, a Supabase-managed backend with Row Level Security, and a four-component agentic conversational architecture (Medical Router, Planner, Executor, and Manager). Audio input was implemented through Whisper-1, and multilingual output was supported via i18next. A Retrieval-Augmented Generation (RAG) pipeline connected to PubMed, CrossRef, 2 ClinicalTrials.gov, AHA, ACP, and NICE guidelines was developed. We generated a clinicianverified dataset of 500 simulated patient cases representing diverse demographics, health-literacy levels, organ systems, conditions, and clinical complexities. CliniKiosk was benchmarked against GPT-4o, Claude 3 Opus, Mixtral 8×7B, and Gemma 3 12B using standardized prompts. Accuracy metrics were compared via χ² tests and pairwise two-proportion z-tests; empathy, explainability, and lexical diversity were assessed using ANOVA and Welch t-tests with Holm correction. Results: Triage accuracy was high across all models (88.6% for CliniKiosk) with only modest differences. Differential-diagnosis accuracy exceeded 92% for all models with no significant differences (p=0.865). Final-diagnosis accuracy was lower for CliniKiosk (76.0%) compared with other LLMs. CliniKiosk achieved comparable treatment-recommendation accuracy (84.5%) to Mixtral and Gemma, though GPT-4o and Claude Opus performed significantly better (p<0.0001). Notably, CliniKiosk achieved the highest empathy score (3.98/4) and strong explainability, outperforming most comparator models. Lexical diversity was moderate and appropriate for users with lower health literacy. Conclusions: CliniKiosk demonstrates that a domain-specific, multilingual RAG-based kiosk can deliver empathetic, evidence-based guidance with performance approaching general-purpose LLMs. With real-world validation and integration of point-of-care diagnostics, CliniKiosk has the potential to improve healthcare access, particularly in underserved communities. Supplementary Material File (clinikiosk-an innovative technology to expand health care access.pdf) Download 659.90 KB Information & Authors Information Version history V1 Version 1 18 December 2025 Copyright This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License Keywords artificial intelligence clinikiosk digital healthbot healthcare multilingual rural Authors Affiliations Ela Adhikari 0009-0004-6673-6050 [email protected] Basis Oro Valley High School, Oro Valley View all articles by this author Metrics & Citations Metrics Article Usage 339 views 83 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Ela Adhikari. CLINIKIOSK-An innovative technology to expand health care access. Authorea . 18 December 2025. DOI: https://doi.org/10.22541/au.176607126.64748589/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.176607126.64748589/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9fedb00278cd06f7',t:'MTc3OTMwNDcwOQ=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();