Search

Adherence to positive airway pressure treatment is crucial in managing obstructive sleep apnoea (OSA). However, the need for continuous usage poses a significant challenge. Introducing AI-supported educational programs offers a unique opportunity. These programs can facilitate the creation of interactive learning paths for patients, providing personalized information and practical advice based on their health conditions. The goal is to develop a personalized educational platform leveraging AI to improve adherence, therapeutic efficacy, and quality of life for patients with OSA. [ABSTRACT FROM AUTHOR]

Artificial intelligence algorithms are increasingly finding their way into the diagnosis, early treatment, prevention and monitoring of chronic respiratory diseases. Diagnosis of asthma often requires the use of various instrumental and laboratory investigations for better framing and phenotyping, including analysis of the fraction of exhaled nitric oxide (FeNO) for profiling eosinophilic inflammation and the forced oscillation technique (FOT), which plays a role not codified by guidelines. This project aims to develop a new predictive model for the early diagnosis of asthma by modelling data from the analysis of FeNO and FOT combined with clinical, laboratory and spirometric data using machine learning algorithms [ABSTRACT FROM AUTHOR]

Chatbots are innovative technological tools useful in managing bronchial asthma. The aim of the present study is to develop a Chatbot that helps asthmatic patients in understanding the severity of their condition and explore new treatment options, including biological drugs. The Chatbot will be based on an algorithm composed of questions selected through a Delphi process, to assess the clinical probability of severe and/or uncontrolled asthma. The Chatbot, thanks to artificial intelligence, will also be able to rephrase questions for better patient understanding, provide guidance on treatments, and direct patients to the nearest centers for severe asthma care. The Chatbot will be tested in a pilot project in Tuscany, offering personalized support to patients with severe asthma who may benefit from biological drugs. [ABSTRACT FROM AUTHOR]

Severe asthma presents significant management challenges, requiring a highly personalized diagnostic and therapeutic approach. Our study aims to explore the potential of volatile organic compounds (VOCs) in exhaled air as biomarkers useful for endotyping severe asthma patients. Using a device for collecting VOCs from the alveolar portion of the exhaled breath and using advanced analytical approaches, we aim to identify possible distinctive metabolic patterns related to the severity of pathology and the response to different treatments. By integrating clinical and biological data with machine learning techniques, we aim to define disease phenotypes and develop predictive algorithms for increasingly personalized management of severe asthma. [ABSTRACT FROM AUTHOR]

Background. Eosinophilic diseases require an integrated approach. Recent data highlight the complexity of these syndromes underlying the importance of multidisciplinary approach. The implementation of multidisciplinary team is limited by the shortage of health resources. Aim. To develop predictive algorithms and optimize the multidisciplinary management of patients with eosinophilic disease. Methods. Predictive statistics and artificial intelligence tools will be performed to select the tests required for understanding the patient’s main pathologic area and to personalize his diagnostic-therapeutic approach. Expected results. New technologies, significantly speeding up the access to care, will be useful for both the patient with eosinophilic disease and the clinicians involved in the multidisciplinary team. [ABSTRACT FROM AUTHOR]