Jul 2026· International Conference Computing Methodologies and Communication· pp. 64-73· 0 citations· 16 references
Abstract
This paper discusses the creation and use of a Virtualized Multi-Role Hospital Care Platform that aims to fill the gap in preventative healthcare and remote medical consultation. Traditional healthcare systems sometimes have problems discovering chronic diseases early, managing them from a distance, and obtaining specialists to treat patients in remote areas. We recommend a full-stack solution that digitally copies hospital workflows for four primary roles: Patient, Doctor, Lab Assistant, and Admin. This will help fix these challenges. The platform combines four different Machine Learning (ML) models to predict diseases early and help individuals make decisions based on AI that can be explained. These models are mainly about assessing overall health, predicting skin cancer, predicting cardiovascular health, and prediciting the risk of liver cirrhosis. There are many layers of security in the system to keep private medical information safe. Security is enforced through CAPTCHA-verified login, JWT session management, OTP-gated patient record access. Telehealth consultations, digital lab report management, and real-time AI diagnostics all function together without any complications because they all use frontend and backend services. The findings of the model tests show that the platform might significantly lighten the load on healthcare infrastructure and enhance patient outcomes by allowing early intervention and remote access. They also show that the platform is quite good at making predictions.
Healthcare software prototypes usually have conversational help, scheduling, role-specific dashboards, and real-time data. Their evaluations focus more on feature lists than on failure modes. This paper reports a reproducible evaluation of safety and access control for Medicare. React, Node.js/Express, MongoDB, and socket.io. AI.IO educational health care platform. We froze a 20-prompt safety benchmark covering emergencies, first aid, medication use, mental health and general questions. We defined eight source-level security checks, including JSON Web Token middleware, role guards, appointment ownership, patient-only creation, password hashing, secret handling and Socket.IO room access. The baseline deterministic chatbot passed 7 out of 20 prompts (35%) and 5 out of 8 security checks. The dynamic loopback test also showed that an unauthenticated client could join the doctor telemetry room. Remediation introduced specific intent-matching, explicit high-risk routes, authenticated socket.io middleware, room-level role restrictions, and appointment ownership enforcement. Our final benchmark passed all 20 prompts and all eight source-level checks. The study does not claim clinical efficacy: no patient records, clinician participants, diagnostic model, or clinical outcomes were assessed. The Atlas network allowlist blocked database-backed exploitation and post-remediation dynamic socket tests, which were reported as unexecuted. Thus, the contribution is a transparent case study of how an ambitious student prototype can be transformed into a more testable, safety-aware system.
Kaustubha Khandagale, S. Bhosle, Akhilesh Kurhadkar et al.· DMPedia Lecture Notes in Com...· 0 citations
An AI-assisted healthcare kiosk, a web-based, fully offline system that provides automated disease prediction, medication recommendations, BMI assessment, cardiovascular risk evaluation, and doctor referrals without needing a permanent physician or internet connection is discussed.
Thanu Shree M. N, M. Vijayalakshmi· International Research Journ...· 0 citations
With the rapid development of artificial intelligence (AI), natural language processing (NLP), and mobile health technologies, remote healthcare services have significantly improved. Intelligent healthcare chatbots have emerged as an important tool for providing scalable, affordable, and continuous patient care outside clinical environments. These chatbots use conversational interfaces to deliver medical information, perform symptom checks, schedule appointments, remind patients about medications, provide mental health support, and offer personalized health education. The increasing workload in healthcare systems, shortage of healthcare professionals, and rising chronic diseases have accelerated the adoption of chatbot-based remote care solutions. This paper presents a comprehensive study of intelligent healthcare chatbots for supporting remote patients, including their architecture, features, integration with health information systems, and clinical applications. Modern chatbots employ machine learning models, deep learning-based NLP techniques, and medical knowledge bases to enable context-aware, adaptive, and personalized patient interactions. Healthcare chatbots also improve access to medical services, particularly in underserved and rural areas where healthcare facilities may be limited. The paper further discusses ethical, legal, and privacy concerns such as patient data protection, regulatory compliance, and potential algorithmic bias. Chatbot performance is evaluated using metrics like response accuracy, user satisfaction, task completion rate, and clinical relevance, highlighting their advantages over traditional telehealth methods. The proposed framework integrates multimodal data sources, real-time patient feedback, and active learning techniques to enhance clinical decision-making and patient engagement. Overall, intelligent healthcare chatbots can reduce response time, improve treatment adherence, and enhance patient experience. The study concludes that healthcare chatbots have strong potential to transform remote healthcare delivery while emphasizing the need for further research to improve clinical reliability and regulatory compliance.
Anita Verma· International Journal of Mod...· 0 citations
Abstract— Government hospitals provide medicines and treatment to patients based on proper diagnosis. These hospitals maintain both historical and current patient data in secure cloud-based systems, which helps doctors access accurate medical records anytime and ensures better continuity of care. In the proposed system, users can register with their personal details, and this information is stored in the admin-controlled database for secure access and management. The system also includes a feature that helps users locate nearby government hospitals using a predictive algorithm, which considers factors like location, urgency, and medical requirements. It provides detailed information about hospitals such as available doctors, specialists, departments, emergency services, and medicine availability. This improves transparency and helps patients make informed decisions quickly. The system further enhances patient experience by providing real-time updates on doctor availability, waiting time, and medicine stock. From an administrative perspective, it improves financial and operational efficiency by ensuring proper utilization of resources, reducing fraud and misuse, and optimizing supply chain and human resource management. Overall, the system aims to make government healthcare services more efficient, accessible, and patient-friendly through better data management and intelligent decision-making.
Karre Surya Prakash, Kaja Masthan, P. Rani· International Scientific Jou...· 0 citations
Artificial intelligence (AI) is supporting clinical decision-making processes in healthcare systems, personalizing patient care, and optimizing workflows. The aim of this narrative review is to examine the role of AI technologies in supporting physicians, nurses and physiotherapists, as well as to evaluate the barriers, ethical issues, and educational transformations associated with integration. Articles related to the topic were selected from Google Scholar, PubMed, and Scopus search databases using the keywords “Artificial intelligence, healthcare team, healthcare services, informatics,” without any restrictions on publication year. Findings show that clinical decision support systems increase diagnostic accuracy and, through personalized treatment planning, enhance treatment efficacy. In nursing, AI-supported monitoring systems improve patient safety while reducing administrative burden; in physiotherapy, robotic devices, wearable sensors, and machine learning-based movement analysis support rehabilitation. AI-based health education requires new competencies such as health, data, and human literacy. Key barriers include lack of algorithmic transparency, data privacy concerns, bias, and legal uncertainty regarding accountability. In conclusion, AI functions as “augmented intelligence” that complements rather than replaces healthcare professionals. Effective integration requires transparent infrastructures, clear legal boundaries, workforce training, and human-centered practices. Healthcare teams utilizing these AI-supported systems can maximize patient health outcomes.
Ramazan Demirer· İstanbul Gelişim Üniversites...· 0 citations
Emergency Surgery Hot Clinics provide ambulatory follow-up for patients with conditions such as cholecystitis, biliary colic, and unresolved abdominal pain. In our unit, appointment tracking relied on a ward-based register and informal spreadsheets, limiting accessibility and posing confidentiality risks. Patients frequently attended clinic with unresolved informational queries.
To improve patient journey, clinician workflow, and confidentiality within the Emergency Surgery Hot Clinic.
A clinician-led digital booking and patient-support application was developed and deployed via hotclinicdiary.co.uk. The platform includes a secure clinician login with a live booking calendar for eight daily Hot Clinic slots, replacing paper-based systems. A patient-facing interface provides condition-specific resources and an AI chatbot trained using NICE and WSES guidance. Access is via QR code.
The digital system improved visibility of clinic capacity, simplified booking, and enhanced confidentiality. The patient-support component addressed common informational queries, reducing clinician workload. The project received Clinical Governance approval and is awaiting Trust Information Governance approval.
This QIP demonstrates the feasibility of a low-cost digital solution to improve Emergency Surgery Hot Clinic workflows and patient experience.
Abdaal Munir, A. Gallucci, Anudeep Ladi· British Journal of Surgery· 0 citations
