Author Archives: semlab

AI based calorie intake estimation and activity tracking has been developed and integrated in FitSprite Nutrition mobile app. An insight generator has been developed for FitSprite Nutrition mobile app to create insights for physical activity. Research area(s) AI for food … Read More

Ambient Listening is specifically designed and adapted for the eating disorder use case. It is voice recognition technology that uses Generative AI to listen to, interpret and analyze conversations between patients and providers. It can be used for one-on-one and … Read More

A non-invasive Neurosity BCI was beta-tested for depression support, and a neurogame was developed to actively influence brain activity. LLMs were tested on a Materna server and locally to support therapists diagnostically. The LLMs were benchmarked and a function for … Read More

HealthTalk.ai is a secure, cloud-based medical speech recognition solution that streamlines doctor-patient communication. It provides real-time transcription focused on medical terminology, automates clinical data integration, and generates standardized medical reports. By reducing administrative burdens, addressing staff shortages, and improving archiving … Read More

LLMs can be offered to support therapists with detailed data and medical guidelines. Non-invasive BCI that is easy to attach with dry electrodes and without medical intervention.  Software that is OSS and interoperable. Research area(s) Neuroinformatics, data science, LLM engineering, cognitive … Read More

The methodology assesses RAG answer quality using LLM-as-a-judge prompts, focusing on groundedness and completeness as core reliability criteria. Answers are evaluated strictly against the retrieved context used for generation. Groundedness is checked at the sentence level and aggregated conservatively using … Read More

The method assesses question caching by matching new queries to a question database to determine whether a validated answer can be safely reused. Duplicate detection is strict, requiring exact intent equivalence; any change in intent or detail is treated as … Read More

Continue AI into healthcare with ITEA project Medical GPT Revolutionizing Healthcare with Ethical AI. Partners: Semlab, Philips, 5M, TUE, ISEP, SESTRK, NP Istanbul. Technical features Large Language Models (LLM) tools have made significant advancements in the healthcare industry, but European … Read More

The Patient App records usage and health data and delivers dynamic, personalised e‑learning modules. Therapists adjust content via a dashboard, while progress, PHQ‑9 results and self‑reflection data are reported back clearly. The app includes quiz‑based assessments, automatic reminders and data‑efficient … Read More

This standards-compliant IoT wearable platform collects and structures physiological and activity data for digital health ecosystems. Unlike closed consumer devices, it features an interoperable architecture with modular backend APIs for seamless integration into B2B healthcare and analytics systems. The platform … Read More

An AI-supported clinical decision support platform has been developed to help differentiate Bipolar Disorder and Unipolar Major Depressive Disorder using MRI data and structured clinical information. The system integrates with hospital infrastructures and allows clinicians to initiate secure AI-based analyses … Read More