The ongoing global health challenge posed by diabetes necessitates a critical understanding of all generated data streamed from sensors. To address this, our study presents a robust fuzzy logic-based descriptive analysis of glucose sensor data. This analysis is embedded within the context of an innovative architecture designed to support multi-patient monitoring, with the goal of assisting healthcare professionals in their daily tasks and providing essential decision-making tools. Our novel approach, captures and interprets complex data patterns from glucose sensors, and also introduces the capability of creating high-quality linguistic summaries, to highlight the most relevant phenomena through the use of natural language (NL). These descriptions facilitate clear communication between healthcare professionals and people with diabetes, enhancing a deeper understanding of intricate data patterns and promoting collaboration in diabetes care. A comparative evaluation between our proposal and the one obtained using GPT-4 underscores the sustainability, effectiveness and efficiency of our methodology, positioning it as a new standard for empowering diabetic patients in terms of care and prevention, contributing to their progress and well-being.
Diabetes is a global health concern, affecting millions of adults worldwide and exhibiting a growing prevalence. Managing the disease highly relies on continuous glucose monitoring, yet the dense and complex nature of electronic devices data streams poses significant challenges for efficient interpretation. Large Language Models are being widely applied across different domains for their ability to generate human-like text, but still fall short in producing accurate and meaningful text from raw data. To address this limitation, this study proposes a fine-tuning methodology tailored specifically to glucose data, but scalable to other expert-guided domains, enabling the models to generate concise, relevant and safe summaries, bridging the gap between raw data and efficient medical attention. This study introduces a novel continuous glucose monitoring framework that involves fine-tuned GPT models using structured datasets generated through an expert-guided data modeling based on Fuzzy Logic and prompt engineering for task contextualization. A new evaluation methodology is defined to assess the performance of the Large Language Models across different critical domains where expert knowledge is fundamental to characterize temporally dependent data and ensure valuable insights. Fine-tuned GPT-4o achieved the highest performance, with an average score of 96% across all metrics. GPT-4o-mini followed with 76% score, while GPT-3.5 scored 72%. The use of fuzzy knowledge-based prompts proved more effective in scenarios with full data availability, or in scenarios with a simplified data availability when the models are not fine-tuned; domain-guided prompts improved output relevance and stability in fine-tuned models with less data availability. These results indicate the capability of our methods to align Large Language Models with the task of generating human-like text from raw data, highlighting their potential to manage diabetes by complex glucose patterns interpretation, alleviating the burden on healthcare systems.
Treatment adherence in chronic diseases is addressed here as a measurable construct that can be formally defined and computed from heterogeneous IoT data streams. The central contribution of this work lies in establishing a mathematical formulation of adherence that integrates both explicit treatment-related activities and behavioural indicators derived from sensor observations. The methodology specifies how raw data from wearables, BLE beacons, and ambient devices can be transformed into clinically meaningful activities through fuzzy logic, enabling the representation of uncertainty, temporal variability, and partial evidence. This framework also accommodates activity labels generated by machine learning models, providing a mechanism to adapt their outputs—originally expressed as probabilistic or categorical predictions—into fuzzy memberships suitable for adherence computation. By unifying sensor-driven activity extraction and model-based activity recognition under a common fuzzy representation, the proposed formulation delivers a coherent pathway for calculating adherence across multiple dimensions and contexts, thereby supporting robust and interpretable evaluation of patient behaviour. By integrating these elements, the methodology provides a comprehensive and interpretable profile of adherence, moving from isolated measures to a unified characterisation of patient behaviour. The framework enables healthcare professionals and patients to better monitor progress, anticipate risks, and support long-term disease management.
Background: Unwanted loneliness and social isolation in older adults are public health problems with negative effects on physical and mental health. The usual assessment tools, based on self-report questionnaires, have limitations in capturing these phenomena continuously and objectively. Objective: We aimed to critically analyze recent scientific evidence on the use of passive sensor technologies combined with artificial intelligence for the detection of unwanted loneliness and social isolation in older adults. Methods: Studies were reviewed in databases (PubMed, Scopus, Web of Science, and IEEE Xplore) that used wearable devices, environmental sensors in the home, smartphones, and multimodal fusion approaches. This systematic review was conducted following the PRISMA 2020 guidelines. Results: Behavioral variables derived from passive monitoring, such as mobility, time away from home, sleep patterns, and digital interactions, are consistently associated with measures of loneliness and social isolation. Likewise, artificial intelligence models based on the combination of multiple data sources show better predictive performance than unimodal approaches. Conclusions: Sensor-based technologies can complement traditional assessment methods, although their practical application requires overcoming challenges related to methodological validation, user acceptance, and ethical considerations.