<em>ALZUMERIC</em>: A decision support system for diagnosis and monitoring of cognitive impairment

Abstract

Internet of things and smart cities are becoming a reality. Nowadays, more and more devices are interconnected and in order to deal with this new situation, data processing speeds are increasing to keep the pace. Smart devices like tablets and smartphones are accessible to a wide part of society in developed countries, and Internet connections for data exchange make it possible to handle large volumes of information in less time. This new reality has opened up the possibility of developing client-server architectures focused on clinical diagnosis in real time and at a very low cost. This paper illustrates the design and implementation of the ALZUMERIC system that is oriented to the diagnosis of Alzheimer’s disease (AD). It is a platform where the medical specialist can gather voice samples through non-invasive methods from patients with and without mild cognitive impairment (MCI), and the system automatically parameterizes the input signal to make a diagnose proposal. Although this type of impairment produces a cognitive loss, it is not severe enough to interfere with daily life. The present approach is based on the description of speech pathologies with regard to the following profiles: phonation, articulation, speech quality, analysis of the emotional response, language perception, and complex dynamics of the system. Privacy, confidentiality and information security have also been taken into consideration, as well as possible threats that the system could suffer, so this first prototype of services offered by ALZUMERIC has been targeted to a predetermined number of medical specialists.

Artificial Intelligence, Speech, and Language Processing Approaches to Monitoring Alzheimer’s Disease: A Systematic Review

“…The comparison groups are based on diagnosis groups, which in turn are established with the results of such assessments. Therefore, papers lacking that information do not specify their criteria for group assignment [ 60, 61, 75, 79, 80, 82–85 ]. This could be problematic, since the field currently revolves around diagnostic categories, trying to identify such categories through speech data.…”

“…Among other monologue studies, eight work with speech obtained through cognitive tests, frequently verbal fluency tasks. Only two papers rely on truly spontaneous and natural monologues, prompted with an open question instead of a picture description [ 60, 65 ].…”

“…The most frequently encountered data modality, apart from speech and language, is structured data related to cognitive examinations, largely dominated by MMSE and verbal fluency scores. Another modality is video, which is available in some datasets such as CCC [ 10, 98 ], AZTITXIKI [ 79 ], AZTIAHORE [ 60, 80 ], IVA [ 12, 85 ], or the one in Tanaka et al. [ 94 ], although it is not included in their analysis.…”

“…As expected, a number of studies (41%) were conducted through English. However, there is a fair amount of papers using data in a variety of languages, including: Italian [ 91 ], Portuguese [ 57, 90 ], Chinese and Taiwanese [ 82 ], French [ 50, 69, 77, 96, 102 ], Hungarian [ 62, 63, 99 ], Spanish [ 83, 89, 100 ], Swedish [ 7, 59, 87 ], Japanese [ 64, 71, 94 ], Turkish [ 84 ], Persian [ 65 ], Greek [ 61, 88 ], German [ 68, 74 ], or reported as multilingual [ 60, 79, 80 ].…”

Technological Features of Internet of Things in Medicine: A Systematic Mapping Study

“…The cloud has some shortcomings in handling big data such as response delays and network loads [132]. Due to the exploding volume of data collected from IoT devices, it Hosseini et al [102] Spanakis et al [41] Jara et al [121] Rivera et al [114] García et al [97] Pai et al [39] Stradolini et al [56] Lizarduy et al [100] Choi et al [26] Figure 9: Security methods used in studies [26,39,41,56,68,79,80,94,97,100,102,108,112,114,116,121].…”