Integrating AI in fighting advancing Alzheimer: diagnosis, prevention, treatment, monitoring, mechanisms, and clinical trials.

The application of artificial intelligence (AI) in neurology is a growing field offering opportunities to improve accuracy of diagnosis and treatment of complicated neuronal disorders, plus fostering a deeper understanding of the aetiologies of these diseases through AI-based analyses of large omics data. The most common neurodegenerative disease, Alzheimer's disease (AD), is characterized by brain accumulation of specific pathological proteins, accompanied by cognitive impairment. In this review, we summarize the latest progress on the use of AI in different AD-related fields, such as analysis of neuroimaging data enabling early and accurate AD diagnosis; prediction of AD progression, identification of patients at higher risk and evaluation of new treatments; improvement of the evaluation of drug response using AI algorithms to analyze patient clinical and neuroimaging data; the development of personalized AD therapies; and the use of AI-based techniques to improve the quality of daily life of AD patients and their caregivers.

Mild behavioral impairment in early Alzheimer's disease and its association with APOE and BDNF risk genetic polymorphisms.

BACKGROUND: Mild behavioral impairment (MBI) has been commonly reported in early Alzheimer's disease (AD) but rarely using biomarker-defined samples. It is also unclear whether genetic polymorphisms influence MBI in such individuals. We thus aimed to examine the association between the cognitive status of participants (amnestic mild cognitive impairment (aMCI-AD) vs cognitively normal (CN) older adults) and MBI severity. Within aMCI-AD, we further examined the association between APOE and BDNF risk genetic polymorphisms and MBI severity. METHODS: We included 62 aMCI-AD participants and 50 CN older adults from the Czech Brain Aging Study. The participants underwent neurological, comprehensive neuropsychological examination, APOE and BDNF genotyping, and magnetic resonance imaging. MBI was diagnosed with the Mild Behavioral Impairment Checklist (MBI-C), and the diagnosis was based on the MBI-C total score ≥ 7. Additionally, self-report instruments for anxiety (the Beck Anxiety Inventory) and depressive symptoms (the Geriatric Depression Scale-15) were administered. The participants were stratified based on the presence of at least one risk allele in genes for APOE (i.e., e4 carriers and non-carriers) and BDNF (i.e., Met carriers and non-carriers). We used linear regressions to examine the associations. RESULTS: MBI was present in 48.4% of the aMCI-AD individuals. Compared to the CN, aMCI-AD was associated with more affective, apathy, and impulse dyscontrol but not social inappropriateness or psychotic symptoms. Furthermore, aMCI-AD was related to more depressive but not anxiety symptoms on self-report measures. Within the aMCI-AD, there were no associations between APOE e4 and BDNF Met and MBI-C severity. However, a positive association between Met carriership and self-reported anxiety appeared. CONCLUSIONS: MBI is frequent in aMCI-AD and related to more severe affective, apathy, and impulse dyscontrol symptoms. APOE and BDNF polymorphisms were not associated with MBI severity separately; however, their combined effect warrants further investigation.

Prevalence Estimates of Amyloid Abnormality Across the Alzheimer Disease Clinical Spectrum.

IMPORTANCE: One characteristic histopathological event in Alzheimer disease (AD) is cerebral amyloid aggregation, which can be detected by biomarkers in cerebrospinal fluid (CSF) and on positron emission tomography (PET) scans. Prevalence estimates of amyloid pathology are important for health care planning and clinical trial design. OBJECTIVE: To estimate the prevalence of amyloid abnormality in persons with normal cognition, subjective cognitive decline, mild cognitive impairment, or clinical AD dementia and to examine the potential implications of cutoff methods, biomarker modality (CSF or PET), age, sex, APOE genotype, educational level, geographical region, and dementia severity for these estimates. DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional, individual-participant pooled study included participants from 85 Amyloid Biomarker Study cohorts. Data collection was performed from January 1, 2013, to December 31, 2020. Participants had normal cognition, subjective cognitive decline, mild cognitive impairment, or clinical AD dementia. Normal cognition and subjective cognitive decline were defined by normal scores on cognitive tests, with the presence of cognitive complaints defining subjective cognitive decline. Mild cognitive impairment and clinical AD dementia were diagnosed according to published criteria. EXPOSURES: Alzheimer disease biomarkers detected on PET or in CSF. MAIN OUTCOMES AND MEASURES: Amyloid measurements were dichotomized as normal or abnormal using cohort-provided cutoffs for CSF or PET or by visual reading for PET. Adjusted data-driven cutoffs for abnormal amyloid were calculated using gaussian mixture modeling. Prevalence of amyloid abnormality was estimated according to age, sex, cognitive status, biomarker modality, APOE carrier status, educational level, geographical location, and dementia severity using generalized estimating equations. RESULTS: Among the 19 097 participants (mean [SD] age, 69.1 [9.8] years; 10 148 women [53.1%]) included, 10 139 (53.1%) underwent an amyloid PET scan and 8958 (46.9%) had an amyloid CSF measurement. Using cohort-provided cutoffs, amyloid abnormality prevalences were similar to 2015 estimates for individuals without dementia and were similar across PET- and CSF-based estimates (24%; 95% CI, 21%-28%) in participants with normal cognition, 27% (95% CI, 21%-33%) in participants with subjective cognitive decline, and 51% (95% CI, 46%-56%) in participants with mild cognitive impairment, whereas for clinical AD dementia the estimates were higher for PET than CSF (87% vs 79%; mean difference, 8%; 95% CI, 0%-16%; P = .04). Gaussian mixture modeling-based cutoffs for amyloid measures on PET scans were similar to cohort-provided cutoffs and were not adjusted. Adjusted CSF cutoffs resulted in a 10% higher amyloid abnormality prevalence than PET-based estimates in persons with normal cognition (mean difference, 9%; 95% CI, 3%-15%; P = .004), subjective cognitive decline (9%; 95% CI, 3%-15%; P = .005), and mild cognitive impairment (10%; 95% CI, 3%-17%; P = .004), whereas the estimates were comparable in persons with clinical AD dementia (mean difference, 4%; 95% CI, -2% to 9%; P = .18). CONCLUSIONS AND RELEVANCE: This study found that CSF-based estimates using adjusted data-driven cutoffs were up to 10% higher than PET-based estimates in people without dementia, whereas the results were similar among people with dementia. This finding suggests that preclinical and prodromal AD may be more prevalent than previously estimated, which has important implications for clinical trial recruitment strategies and health care planning policies.

Characteristics of subjective cognitive decline associated with amyloid positivity.

INTRODUCTION: The evidence for characteristics of persons with subjective cognitive decline (SCD) associated with amyloid positivity is limited. METHODS: In 1640 persons with SCD from 20 Amyloid Biomarker Study cohort, we investigated the associations of SCD-specific characteristics (informant confirmation, domain-specific complaints, concerns, feelings of worse performance) demographics, setting, apolipoprotein E gene (APOE) ε4 carriership, and neuropsychiatric symptoms with amyloid positivity. RESULTS: Between cohorts, amyloid positivity in 70-year-olds varied from 10% to 76%. Only older age, clinical setting, and APOE ε4 carriership showed univariate associations with increased amyloid positivity. After adjusting for these, lower education was also associated with increased amyloid positivity. Only within a research setting, informant-confirmed complaints, memory complaints, attention/concentration complaints, and no depressive symptoms were associated with increased amyloid positivity. Feelings of worse performance were associated with less amyloid positivity at younger ages and more at older ages. DISCUSSION: Next to age, setting, and APOE ε4 carriership, SCD-specific characteristics may facilitate the identification of amyloid-positive individuals.

Defining a Centiloid scale threshold predicting long-term progression to dementia in patients attending the memory clinic: an [18F] flutemetamol amyloid PET study.

PURPOSE: To evaluate cerebral amyloid-ß(Aß) pathology in older adults with cognitive complaints, visual assessment of PET images is approved as the routine method for image interpretation. In research studies however, Aß-PET semi-quantitative measures are associated with greater risk of progression to dementia; but until recently, these measures lacked standardization. Therefore, the Centiloid scale, providing standardized Aß-PET semi-quantitation, was recently validated. We aimed to determine the predictive values of visual assessments and Centiloids in non-demented patients, using long-term progression to dementia as our standard of truth. METHODS: One hundred sixty non-demented participants (age, 54-86) were enrolled in a monocentric [18F] flutemetamol Aß-PET study. Flutemetamol images were interpreted visually following the manufacturers recommendations. SUVr values were converted to the Centiloid scale using the GAAIN guidelines. Ninety-eight persons were followed until dementia diagnosis or were clinically stable for a median of 6 years (min = 4.0; max = 8.0). Twenty-five patients with short follow-up (median = 2.0 years; min = 0.8; max = 3.9) and 37 patients with no follow-up were excluded. We computed ROC curves predicting subsequent dementia using baseline PET data and calculated negative (NPV) and positive (PPV) predictive values. RESULTS: In the 98 participants with long follow-up, Centiloid = 26 provided the highest overall predictive value = 87% (NPV = 85%, PPV = 88%). Visual assessment corresponded to Centiloid = 40, which predicted dementia with an overall predictive value = 86% (NPV = 81%, PPV = 92%). Inclusion of the 25 patients who only had a 2-year follow-up decreased the PPV = 67% (NPV = 88%), reflecting the many positive cases that did not progress to dementia after short follow-ups. CONCLUSION: A Centiloid threshold = 26 optimally predicts progression to dementia 6 years after PET. Visual assessment provides similar predictive value, with higher specificity and lower sensitivity. TRIAL REGISTRATION: Eudra-CT number: 2011-001756-12.

Czech Brain Aging Study (CBAS): prospective multicentre cohort study on risk and protective factors for dementia in the Czech Republic.

PURPOSE: Identification of demographic, physical/physiological, lifestyle and genetic factors contributing to the onset of dementia, specifically Alzheimer disease (AD), and implementation of novel methods for early diagnosis are important to alleviate prevalence of dementia globally. The Czech Brain Aging Study (CBAS) is the first large, prospective study to address these issues in Central/Eastern Europe by enrolling non-demented adults aged 55+ years, collecting a variety of personal and biological measures and tracking cognitive function over time. PARTICIPANTS: The CBAS recruitment was initiated in 2011 from memory clinics at Brno and Prague University Hospitals, and by the end of 2018, the study included 1228 participants. Annual follow-ups include collection of socioeconomic, lifestyle and personal history information, neurology, neuropsychology, laboratory, vital sign and brain MRI data. In a subset, biomarker assessment (cerebrospinal fluid (CSF) and amyloid positron emission tomography) and spatial navigation were performed. Participants were 69.7±8.1 years old and had 14.6±3.3 years of education at baseline, and 59% were women. By the end of 2018, 31% finished three and more years of follow-up; 9% converted to dementia. Apolipoprotein E status is available from 95% of the participants. The biological sample bank linked to CBAS database contained CSF, serum and DNA. FINDINGS TO DATE: Overall, the findings, mainly from cross-sectional analyses, indicate that spatial navigation is a promising marker of early AD and that it can be distinguished from other cognitive functions. Specificity of several standard memory tests for early AD pathology was assessed with implications for clinical practice. The relationship of various lifestyle factors to cognition and brain atrophy was reported. FUTURE PLANS: Recruitment is ongoing with secured funding. Longitudinal data analyses are currently being conducted. Proposals for collaboration on specific data from the database or biospecimen, as well as collaborations with similar cohort studies to increase sample size, are welcome. Study details are available online (www.cbas.cz).

Subjective Spatial Navigation Complaints - A Frequent Symptom Reported by Patients with Subjective Cognitive Decline, Mild Cognitive Impairment and Alzheimer's Disease.

BACKGROUND: Great effort has been put into developing simple and feasible tools capable to detect Alzheimer's disease (AD) in its early clinical stage. Spatial navigation impairment occurs very early in AD and is detectable even in the stage of mild cognitive impairment (MCI). OBJECTIVE: The aim was to describe the frequency of self-reported spatial navigation complaints in patients with subjective cognitive decline (SCD), amnestic and non-amnestic MCI (aMCI, naMCI) and AD dementia and to assess whether a simple questionnaire based on these complaints may be used to detect early AD. METHOD: In total 184 subjects: patients with aMCI (n=61), naMCI (n=27), SCD (n=63), dementia due to AD (n=20) and normal controls (n=13) were recruited. The subjects underwent neuropsychological examination and were administered a questionnaire addressing spatial navigation complaints. Responses to the 15 items questionnaire were scaled into four categories (no, minor, moderate and major complaints). RESULTS: 55% of patients with aMCI, 64% with naMCI, 68% with SCD and 72% with AD complained about their spatial navigation. 38-61% of these complaints were moderate or major. Only 33% normal controls expressed complaints and none was ranked as moderate or major. The SCD, aMCI and AD dementia patients were more likely to express complaints than normal controls (p's<0.050) after adjusting for age, education, sex, depressive symptoms (OR for SCD=4.00, aMCI=3.90, AD dementia=7.02) or anxiety (OR for SCD=3.59, aMCI=3.64, AD dementia=6.41). CONCLUSION: Spatial navigation complaints are a frequent symptom not only in AD, but also in SCD and aMCI and can potentially be detected by a simple and inexpensive questionnaire.

Scopolamine disrupts place navigation in rats and humans: a translational validation of the Hidden Goal Task in the Morris water maze and a real maze for humans.

RATIONALE: Development of new drugs for treatment of Alzheimer's disease (AD) requires valid paradigms for testing their efficacy and sensitive tests validated in translational research. OBJECTIVES: We present validation of a place-navigation task, a Hidden Goal Task (HGT) based on the Morris water maze (MWM), in comparable animal and human protocols. METHODS: We used scopolamine to model cognitive dysfunction similar to that seen in AD and donepezil, a symptomatic medication for AD, to assess its potential reversible effect on this scopolamine-induced cognitive dysfunction. We tested the effects of scopolamine and the combination of scopolamine and donepezil on place navigation and compared their effects in human and rat versions of the HGT. Place navigation testing consisted of 4 sessions of HGT performed at baseline, 2, 4, and 8 h after dosing in humans or 1, 2.5, and 5 h in rats. RESULTS: Scopolamine worsened performance in both animals and humans. In the animal experiment, co-administration of donepezil alleviated the negative effect of scopolamine. In the human experiment, subjects co-administered with scopolamine and donepezil performed similarly to subjects on placebo and scopolamine, indicating a partial ameliorative effect of donepezil. CONCLUSIONS: In the task based on the MWM, scopolamine impaired place navigation, while co-administration of donepezil alleviated this effect in comparable animal and human protocols. Using scopolamine and donepezil to challenge place navigation testing can be studied concurrently in animals and humans and may be a valid and reliable model for translational research, as well as for preclinical and clinical phases of drug trials.

Calretinin and parvalbumin immunoreactive interneurons in the retrosplenial cortex of the rat brain: Qualitative and quantitative analyses.

The retrosplenial cortex (RSC) is a mesocortical region broadly involved with memory and navigation. It shares many characteristics with the perirhinal cortex (PRC), both of which appear to be significantly involved in the spreading of epileptic activity. We hypothesized that RSC possesses an interneuronal composition similar to that of PRC. To prove the hypothesis we studied the general pattern of calretinin (CR) and parvalbumin (PV) immunoreactivity in the RSC of the rat brain, its optical density as well as the morphological features and density of CR- and PV-immunoreactive (CR+ and PV+) interneurons. We also analyzed the overall neuronal density on Nissl-stained sections in RSC. Finally, we compared our results with our earlier analysis of PRC (Barinka et al., 2012). Compared to PRC, RSC was observed to have a higher intensity of PV staining and lower intensity of CR staining of neuropil. Vertically-oriented bipolar neurons were the most common morphological type among CR+ neurons. The staining pattern did not allow for a similarly detailed analysis of somatodendritic morphology of PV+ neurons. RSC possessed lower absolute (i.e., neurons/mm(3)) and relative (i.e., percentage of the overall neuronal population) densities of CR+ neurons and similar absolute and lower relative densities of PV+ neurons relative to PRC. CR: PV neuronal ratio in RSC (1:2 in area 29 and 1:2.2 in area 30) differed from PRC (1:1.2 in area 35 and 1:1.7 in area 36). In conclusion, RSC, although similar in many aspects to PRC, differs strikingly in the interneuronal composition relative to PRC.