Search

The use of artificial intelligence in geriatrics is very promising and relevant, as the diagnosis of a geriatric patient is a complex, experience-based, and time-consuming process that involves a variety of questionnaires and subjective and inaccurate patient responses. This paper proposes the explainable artificial intelligence-based (XAI) clinical decision support system (CDSS) to assess nutrition-related factors (symptoms) and to determine the likelihood of geriatric patient health risks associated with four syndromes: malnutrition, oropharyngeal dysphagia, dehydration, and eating disorders in dementia. The proposed system’s prototype was tested under real conditions at the geriatric department of Lithuanian University of Health Sciences Kaunas Hospital. The subjects of this study were 83 geriatric patients with various health conditions. The assessments of the nutritional status and syndromes of the patients provided by the CDSS were compared with the diagnoses of the physicians obtained using standard assessment methods. The results show that proposed CDSS can efficiently diagnose nutrition-related geriatric syndromes with high accuracy: 87.95% for malnutrition, 87.95% for oropharyngeal dysphagia, 90.36% for eating disorders in dementia, and 86.75% for dehydration. The research confirms that the proposed XAI-based CDSS is an effective tool, able to assess nutrition-related health risk factors and their dependencies and, in some cases, makes even a more accurate decision than a less experienced physician.

This paper addresses the issues of decision-making methods and their usage capabilities for intelligent control based on resident’s habits. Learning from the behaviour of the resident is essential for the system to adapt and provide intelligent control based on behaviour patterns. Different homes have different conditions and habits which have to be taken into account for the intelligent system to be useful. However, even deeply ingrained habits are subject to change over time. Therefore, an intelligent system has to respond to changing and diverse environment. Various decision-making methods have the potential of a number of benefits in providing intelligent control for the Smart home systems. In this paper, concurrent decision-making methods, including Artificial Neural Networks, Fuzzy Logic, Linear Programing and Bayesian, are employed with particular algorithms in order to provide control based on resident’s habits. These approaches are tested and compared within experimental scenarios for intelligent lightning control., Straipsnyje tiriamos spendimo priėmimo metodų taikymo galimybės sprendžiant intelektualiojo valdymo uždavinius, paremtus gyvenamojo namo gyventojo įpročiais. Tam, kad sistema galėtų atlikti adaptaciją ir pateikti intelektualųjį valdymą pagal elgsenos įpročius, reikia mokytis iš gyventojo elgsenos. Tačiau reikia įvertinti ir tai, jog net ir labiausiai įsisenėję įpročiai gali kisti laike. Todėl intelektuali valdymo sistema privalo reaguoti į kintančią ir dinamišką aplinką. Siekiant pateikti gyventojo įpročiais paremtą intelektualųjį valdymą, šiame darbe buvo taikyti skirtingi metodai: dirbtiniai neuroniniai tinklai, neraiškioji logika, tiesinis programavimas ir Bajeso metodas, kuriais remiantis buvo pasiūlyti atitinkami sprendimo priėmimo algoritmai. Sukurti eksperimentiniai scenarijai, kurie leido ištestuoti, palyginti ir patikrinti pasiūlytų algoritmų tinkamumą gyvenamojo namo intelektualiajam valdymui, pvz., namo apšvietimo valdymui, remiantis pastoviais ir kintančiais gyventojo valdymo įpročiais.