Introduction: Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia.Methods: We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases.Results: A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort.Discussion: The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice.Highlights: There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias

Alzheimer’s disease (AD) and frontotemporal dementia (FTD) are the most common neurodegenerative early-onset dementias. Despite the fact that both conditions have a very distinctive clinical pattern, they present with an overlap in their cognitive and behavioral features that may lead to misdiagnosis or delay in diagnosis. The current review intends to summarize briefly the main differences at the clinical, neuropsychological, and behavioral levels, in an attempt to suggest which aspects would facilitate an adequate diagnosis in a clinical setting, especially in Latin American and low- and middle-income countries, where the resources needed for a differential diagnosis (such as MRI or biomarkers) are not always available. A timely diagnosis of AD and FTD have significant implications for the medical management and quality of life of patients and careers.

Background: Information and communication technology (ICT) has become an increasingly important part of daily life. The ability to use technology is becoming essential for autonomous functioning in society. Current functional scales for patients with cognitive impairment do not evaluate the use of technology. The objective of this study was to develop and validate a new version of the Activities of Daily Living Questionnaire (ADLQ) that incorporates an ICT subscale. Method: A new technology-based subscale was incorporated into the Spanish version of the ADLQ (SV-ADLQ), entitled the Technology version of the ADLQ (T-ADLQ). The T-ADLQ was administered to 63 caregivers of dementia patients, 21 proxies of mild cognitive impairment patients and 44 proxies of normal elderly subjects (mean age of the sample ± SD: 73.5 ± 8.30 years). We analysed the convergent validity, internal consistency, reliability cut-off point, sensitivity and specificity of the T-ADLQ. The results of the T-ADLQ were compared to the SV-ADLQ. Results: The T-ADLQ showed significant correlations with the Mini-Mental State Examination (MMSE), the Frontal Assessment Battery (FAB) as well as other measures of functional impairment and dementia severity (MMSE: r = –0.70; FAB: r = –0.65; Functional Assessment Questionnaire: r = 0.77; Instrumental Activities of Daily Living Scale: r = –0.75; Clinical Dementia Rating Scale: r = 0.72; p < 0.001). The T-ADLQ showed a good reliability with a relatively high Cronbach’s α-coefficient (Cronbach’s α = 0.861). When considering a functional impairment cut-off point greater than 29.25%, the sensitivity and specificity of the T-ADLQ were 82 and 90%, respectively. The area under the receiver-operating characteristic curve was 0.937 for the T-ADLQ and 0.932 for the original version of the test. Conclusions: The T-ADLQ revealed adequate indicators of validity and reliability for the functional assessment of activities of daily living in dementia patients. However, the inclusion of technology items in the T-ADLQ did not improve the performance of the scale, which may reflect the lack of widespread use of technology by elderly individuals. Thus, although it appeared reasonable to add technology use questions to the ADLQ, our experience suggested that this has to be done cautiously, since the sensitivity of these additional items could vary in different populations. The T-ADLQ needs to be validated in a different population of dementia subjects.

Caring for a person with dementia is associated with well-documented increases in burden and distress and decreases in mental health and wellbeing. Studies assessing burden in caregivers of patients with dementia and its determinants are scarce in Latin America. The main objective of this study was to assess the extent and the determinants of burden in informal primary caregivers of patients with dementia in Chile. A descriptive study was conducted using clinically validated scales to assess dementia characteristics and to measure caregiver variables. Family socio-demographic characteristics and functional status, patient functional dependency and behavioral disturbances, and caregiver psychiatric morbidity were analyzed as independent variables to determine caregiver burden. Two hundred and ninety-two informal caregivers were included. There were more female (80%) than male caregivers, consisting mainly of daughters and spouses of the patients. Severe burden was reported in 63% of the caregivers, and 47% exhibited psychiatric morbidity. Burden was associated with caregiver psychiatric distress, family dysfunction, severity of neuropsychiatric symptoms and functional disability, but neither patient age, gender, nor socioeconomic status impacted burden. Our results underscore the importance of assessing the consequences of dementia in both caregivers and patients in order to evaluate the real biopsychosocial impact of dementia, as well as the importance of planning appropriate and effective public health interventions in Latin American countries. In addition, interventions targeting caregiver psychological distress, caregiver familial dysfunction, patient neuropsychiatric disorders, and patient functional disability could potentially diminish caregiver burden.

Objective: This study sought to analyze the psychometric properties and diagnostic accuracy of the Chilean version of the INECO Frontal Screening (IFS-Ch) in a sample of dementia patients and control Methods: After adapting the instrument to the Chilean context and obtaining content validity evidence through expert consultation, the IFS-Ch was administered to 31 dementia patients and 30 control subjects together with other executive assessments (Frontal Assessment Battery [FAB], Modified version of the Wisconsin Card Sorting Test [MCST], phonemic verbal fluencies [letters A and P] and semantic verbal fluency [animals]) and global cognitive efficiency tests (Mini mental State Examination [MMSE] and Addenbrooke's Cognitive Examination-Revised [ACE-R]). Caregivers of dementia patients and proxies of control subjects were interviewed with instruments measuring dysexecutive symptoms (Dysexecutive Questionnaire [DEX]), dementia severity (Clinical Dementia Rating Scale [CDR]) and functional status in activities of daily living (Activities of Daily Living Scale [IADL] and Technology-Activities of Daily Living Questionnaire [T-ADLQ]). Convergent and discriminant validity, internal consistency reliability, cut-off points, sensitivity and specificity for the IFS-Ch were estimated. Results: Evidence of content validity was obtained. Evidence of convergent validity was also found showing significant correlations (p<0.05) between the IFS-Ch and the other instruments measuring: executive functions (FAB, r=0.935; categories achieved in the MCST, r=0.791; perseverative errors in the MCST, r= -0.617; animal verbal fluency, r=0.728; A verbal fluency, r=0.681; and P verbal fluency, r=0.783), dysexecutive symptoms in daily living (DEX, r= -0.494), dementia severity (CDR, r= -0.75) and functional status in activities of daily living (T-ADLQ, r= -0.745; IADL, r=0.717). Regarding reliability, a Cronbach's alpha coefficient of 0.905 was obtained. For diagnostic accuracy, a cut-off point of 18 points (sensitivity=0.903; specificity=0.867) and an area under curve of 0.951 were estimated to distinguish between patients with dementia and control subjects. Discussion: The IFS-Ch showed acceptable psychometric properties, supported by evidence of validity and reliability for its use in the measurement of executive functions in patients with dementia. The diagnostic accuracy of the IFS-Ch for detecting dementia patients was also considered acceptable.

The Neuropsychiatric Inventory Questionnaire (NPI-Q) is an informant-based instrument that measures the presence and severity of 12 Neuropsychiatric Symptoms (NPS) in patients with dementia, as well as informant distress. Objective: To measure the psychometric properties of the NPI-Q and the prevalence of NPS in patients with Alzheimer's disease (AD) in Chile. Methods: 53 patients with AD were assessed. Subjects were divided into two different groups: mild AD (n=26) and moderate AD (n=27). Convergent validity was estimated by correlating the outcomes of the NPI-Q with Neuropsychiatric Inventory (NPI) scores and with a global cognitive efficiency test (Addenbrooke's Cognitive Examination - Revised - ACE-R). Reliability of the NPI-Q was analysed by calculating its internal consistency. Prevalence of NPS was estimated with both the NPI and NPI-Q. Results: Positive and significant correlations were observed between the NPI-Q, the NPI, and the ACE-R (r=0.730; p<0.01 and 0.315; p<0.05 respectively). The instrument displayed an adequate level of reliability (Cronbach's alpha=0.783). The most prevalent NPS were apathy/indifference (62.3%) and dysphoria/depression (58.5%). Conclusion: The NPI-Q exhibited acceptable validity and reliability indicators for patients with AD in Chile, indicating that it is a suitable instrument for the routine assessment of NPS in clinical practice.