Search

Background: The term progressive apraxia of speech (PAOS) is used to describe speakers presenting with isolated or dominant apraxia of speech in the context of a neurodegenerative syndrome, including primary progressive apraxia of speech (PPAOS) and dominant progressive apraxia of speech (DAOS), respectively. Its motor speech profile has been increasingly explored in the last decade, but description remains vague and very English oriented, although the effect of speakers' language on motor speech phenotypes is increasingly recognized. Although some studies suggest that speakers presenting with isolated PAOS (PPAOS) versus dominant PAOS with concomitant aphasia (DAOS) should be differentiated, distinct characteristics of the two presentations are unclear. Furthermore, a careful description of their clinical presentation in languages other than English is required. Aims: To describe the motor speech characteristics of Quebec French-speaking participants with prominent PAOS and to explore the communication profile of those presenting more specifically with isolated PAOS (PPAOS), and with dominant PAOS and concomitant aphasia (DAOS). Methods & Procedures: A thorough effort to recruit all speakers presenting with PAOS in the larger population areas of the province of Quebec was conducted over a 3-year span. A total of nine participants with PAOS (pwPAOS; PPAOS = 5, DAOS = 4) underwent a comprehensive language and motor speech assessment, and a cognitive screening. Their performance was compared with 30 matched healthy controls. Outcomes & Results: As a group, pwPAOS differed from healthy speakers on all acoustic and perceptual measures. The PPAOS and PAOS subgroups were similar on several measures, but participants from the PPAOS subgroup tended to perform better on articulatory measures and maximum speech rate tasks. Conclusions & Implications: This study provides an in-depth analysis of motor speech characteristics of PAOS in Quebec French speakers and adds further evidence for the differentiation of PPAOS and DAOS. Combining simple perceptual and acoustic analyses represent a promising approach to distinguish the two variants and identify treatment targets.

Background: Quantitative maps obtained with diffusion weighted (DW) imaging, such as fractional anisotropy (FA) –calculated by fitting the diffusion tensor (DT) model to the data,—are very useful to study neurological diseases. To fit this map accurately, acquisition times of the order of several minutes are needed because many noncollinear DW volumes must be acquired to reduce directional biases. Deep learning (DL) can be used to reduce acquisition times by reducing the number of DW volumes. We already developed a DL network named “oneminute FA,” which uses 10 DW volumes to obtain FA maps, maintaining the same characteristics and clinical sensitivity of the FA maps calculated with the standard method using more volumes. Recent publications have indicated that it is possible to train DL networks and obtain FA maps even with 4 DW input volumes, far less than the minimum number of directions for the mathematical estimation of the DT. Methods: Here we investigated the impact of reducing the number of DW input volumes to 4 or 7, and evaluated the performance and clinical sensitivity of the corresponding DL networks trained to calculate FA, while comparing results also with those using our one-minute FA. Each network training was performed on the human connectome project open-access dataset that has a high resolution and many DW volumes, used to fit a ground truth FA. To evaluate the generalizability of each network, they were tested on two external clinical datasets, not seen during training, and acquired on different scanners with different protocols, as previously done. Results: Using 4 or 7 DW volumes, it was possible to train DL networks to obtain FA maps with the same range of values as ground truth - map, only when using HCP test data; pathological sensitivity was lost when tested using the external clinical datasets: indeed in both cases, no consistent differences were found between patient groups. On the contrary, our “one-minute FA” did not suffer from the same problem. Conclusion: When developing DL networks for reduced acquisition times, the ability to generalize and to generate quantitative biomarkers that provide clinical sensitivity must be addressed. [ABSTRACT FROM AUTHOR]

Computed tomography (CT) arthrography is a quickly available imaging modality to investigate elbow disorders. Its excellent spatial resolution enables the detection of subtle pathologic changes of intra-articular structures, which makes this technique extremely valuable in a joint with very tiny chondral layers and complex anatomy of articular capsule and ligaments. Radiation exposure has been widely decreased with the novel CT scanners, thereby increasing the indications of this examination. The main applications of CT arthrography of the elbow are the evaluation of capsule, ligaments, and osteochondral lesions in both the settings of acute trauma, degenerative changes, and chronic injury due to repeated microtrauma and overuse. In this review, we discuss the normal anatomic findings, technical tips for injection and image acquisition, and pathologic findings that can be encountered in CT arthrography of the elbow, shedding light on its role in the diagnosis and management of different orthopedic conditions. We aspire to offer a roadmap for the integration of elbow CT arthrography into routine clinical practice, fostering improved patient outcomes and a deeper understanding of elbow pathologies. [ABSTRACT FROM AUTHOR]

INTRODUCTION: Plasma biomarkers are promising tools for Alzheimer's disease (AD) diagnosis, but comparisons with more established biomarkers are needed. METHODS: We assessed the diagnostic performance of p‐tau181, p‐tau217, and p‐tau231 in plasma and CSF in 174 individuals evaluated by dementia specialists and assessed with amyloid‐PET and tau‐PET. Receiver operating characteristic (ROC) analyses assessed the performance of plasma and CSF biomarkers to identify amyloid‐PET and tau‐PET positivity. RESULTS: Plasma p‐tau biomarkers had lower dynamic ranges and effect sizes compared to CSF p‐tau. Plasma p‐tau181 (AUC = 76%) and p‐tau231 (AUC = 82%) assessments performed inferior to CSF p‐tau181 (AUC = 87%) and p‐tau231 (AUC = 95%) for amyloid‐PET positivity. However, plasma p‐tau217 (AUC = 91%) had diagnostic performance indistinguishable from CSF (AUC = 94%) for amyloid‐PET positivity. DISCUSSION: Plasma and CSF p‐tau217 had equivalent diagnostic performance for biomarker‐defined AD. Our results suggest that plasma p‐tau217 may help reduce the need for invasive lumbar punctures without compromising accuracy in the identification of AD. Highlights: p‐tau217 in plasma performed equivalent to p‐tau217 in CSF for the diagnosis of AD, suggesting the increased accessibility of plasma p‐tau217 is not offset by lower accuracy.p‐tau biomarkers in plasma had lower mean fold‐changes between amyloid‐PET negative and positive groups than p‐tau biomarkers in CSF.CSF p‐tau biomarkers had greater effect sizes than plasma p‐tau biomarkers when differentiating between amyloid‐PET positive and negative groups.Plasma p‐tau181 and plasma p‐tau231 performed worse than p‐tau181 and p‐tau231 in CSF for AD diagnosis. [ABSTRACT FROM AUTHOR]

We describe the case of a young woman affected by debilitating chorea and rapidly progressive cognitive decline. While her original diagnosis was multiple sclerosis, we performed a full instrumental and genetic assessement, though which we identified multiple genetic variants, including a novel variant of the APP gene. We propose some possible mechanisms by which such variants may contribute to neuroinflammation and ultimately lead to this devastating clinical course. [ABSTRACT FROM AUTHOR]

Introduction: [18F]AZD4694 is an amyloid beta (Aβ) imaging agent used in several observational studies and clinical trials. However, no studies have yet published data on longitudinal Aβ accumulation measured with [18F]AZD4694. Methods: We assessed 146 individuals who were evaluated with [18F]AZD4694 at baseline and 2‐year follow‐up. We calculated annual rates of [18F]AZD4694 change for clinically defined and biomarker‐defined groups Results: Cognitively unimpaired (CU) older adults displayed subtle [18F]AZD4694 standardized uptake value ratio (SUVR) accumulation over the follow‐up period. In contrast, Aβ positive CU older adults displayed higher annual [18F]AZD4694 SUVR increases. [18F]AZD4694 SUVR accumulation in Aβ positive mild cognitive impairment (MCI) and dementia was modest across the neocortex Discussion: Larger increases in [18F]AZD4694 SUVR were observed in CU individuals who had abnormal amyloid positron emission tomography levels at baseline. [18F]AZD4694 can be used to monitor Aβ levels in therapeutic trials as well as clinical settings, particularly prior to initiating anti‐amyloid therapies. [ABSTRACT FROM AUTHOR]

Background: Age‐related memory decline is well associated with hippocampal atrophy, although the specific role of hippocampal subfields in memory function has not been thoroughly investigated yet. In this study, we investigated the associations between hippocampal subfield volumes and free recall and recognition performances in verbal and visual memory tasks in older adults without dementia. Method: We selected 97 right‐handed participants without dementia aged 60 to 85, 42 males, from the Translational Biomarkers in Aging and Dementia (TRIAD) cohort. From T2‐weighted MRIs with 0.7*0.7*1mm voxel size, the hippocampi were segmented five subfields: 1) DG (DG); 2) CA2 with CA3 (CA2/CA3); 3) CA1; 4) strata radiatum, lacunosum and moleculare (SRLM); and 5) subiculum by using the MAGeT‐Brain algorithm. Memory was assessed with Rey Auditory Learning test for verbal free recall (RAVLT7) and recognition (RAVLT‐R), and with Aggie Figure Learning test for visual free recall (AFLT7) and recognition (AFLT‐R). Linear models were used to test the association between hippocampal subfield volumes and memory performances with age, sex and total intracranial volume as covariates (p<0.05, corrected for false discovery rate). Result: The volumes of bilateral CA1 and SRLM were significantly associated with RAVLT7 and RAVLT‐R. The right DG volume was significantly associated with AFLT7 and RAVLT7. AFLT7 was also associated with the volume of right CA2/CA3 while AFLT‐R was not associated with any hippocampal subfield (see Figures 1 & 2). Conclusion: Our results are consistent with the view that hippocampal subfields contribute differently to memory traces: CA1 for recollection that requires contextual information; the DG for pattern separation (creating new distinct representations of each stimulus); and CA3 for pattern completion (the recollection of a stimulus from a partial memory). Contextual information is more important when recollecting known words, while distinct and efficient encoding may be especially useful for search strategies inherent to free recall. Pattern completion could be particularly useful to efficiently recollect visual abstract figures based on visual features during free recall. Overall, this shows that hippocampal subfield segmentation offers a better understanding of their distinctive roles in cognition. [ABSTRACT FROM AUTHOR]

Background: To compare the performance of plasma p‐tau181, plasma‐NfL and FDG‐PET in the diagnosis of biological AD. Method: We included 787 participants (cognitively unimpaired (CU, n = 251), mild cognitive impairment (MCI, n = 412), and Alzheimer's dementia (AD, n = 124) from the ADNI database. Participants underwent measures of plasma p‐tau181, plasma‐NfL, CSF P‐tau181, [18F]FDG‐PET, amyloid‐PET and cognitive screening tests. ROC analyses were used to determine diagnostic accuracy of plasma P‐tau181, NfL and [18F]FDG‐PET using clinical diagnosis and core AD biomarkers (amyloid‐PET and CSF P‐tau181) as reference standards. We assessed whether plasma P‐tau181 and [18F]FDG‐PET diagnostic accuracies were significantly different with a bootstrap‐based test (pROC package in R). Second, correlations of [18F]FDG‐PET, plasma‐NfL, plasma P‐tau181 with P‐tau181 CSF, Aβ‐PET, and cognitive performance were evaluated. Correlation coefficients were compared via Cocor package, a statistical framework for comparing associations between intercorrelated measurements. Result: Across the total sample we observed that plasma P‐tau181, plasma‐NfL, and [18F]FDG‐PET were able to identify individuals with CSF evidence of AD as well as participants who are amyloid‐PET+. In the MCI group, plasma P‐tau181 outperformed [18F]FDG‐PET and plasma‐NfL in identifying AD pathophysiology measured via CSF P‐tau181 (p = 0.0007), and amyloid‐PET (p = 0.001). We also observed that both plasma P‐tau181, plasma‐NfL and [18F]FDG‐PET were associated with AD pathophysiology measured by core AD biomarkers (CSF and amyloid‐PET). However, [18F]FDG‐PET was more closely associated with cognitive outcomes than plasma P‐tau181 and plasma NfL (MoCA: p < 0.0001; MMSE: p< 0.0001; CDR‐SB: p < 0.0001) Conclusion: This study investigated the diagnostic properties of plasma P‐tau181 and two neurodegenerative biomarkers (plasma‐NfL and [18F]FDG‐PET) as well as their to identify biological AD. While plasma P‐tau181, plasma‐NfL concentrations and [18F]FDG‐PET were associated with AD pathophysiology measured by core AD biomarkers (CSF and amyloid‐PET), plasma P‐tau181 outperformed [18F]FDG‐PET and plasma‐NfL in identifying individuals with AD pathophysiology. However, we also observed that [18F]FDG‐PET was more strongly associated with neuropsychological assessments than plasma P‐tau181 and plasma‐NfL. Taken together, our study suggests that plasma P‐tau181 may aid in the evaluation of individuals by identifying those with underlying AD pathophysiology. [ABSTRACT FROM AUTHOR]

Background: Several recent studies have provided evidence for high diagnostic performance of plasma biomarkers for AD, with Area Under the Curve values sometimes exceeding 90%. However, positive and negative predictive values are rarely reported yet are critical for interpreting individual‐level screening test results. Method: We determined positive and negative predictive values of plasma biomarkers (p‐tau181, p‐tau217, p‐tau231, GFAP and NfL) for biological AD (A+T+, determined either with PET or CSF) in the TRIAD, WRAP, ALFA+, BIODEGMAR, ADNI and McGill memory clinic cohorts (total n = 2219). We also determined positive and negative predictive values for specific clinical scenarios: MCI and mild AD – two populations that may benefit from disease‐modifying therapies in AD. Prevalence estimates of biological AD in these groups were taken from the Mayo Clinic Study of Aging. Result: P‐tau217 had the highest positive and negative predictive values of all biomarkers in all cohorts, with above 80% positive and negative predictive values. In individuals with MCI, an etiologically heterogeneous syndrome, plasma p‐tau217 had sufficiently high performance to rule out biological AD in differential diagnosis. In mild AD dementia, plasma p‐tau217 could rule in biological AD, but follow‐up with PET/CSF will likely be needed to confirm the absence of AD. Conclusion: Plasma biomarkers have the potential to be used as stand‐alone diagnostic tools in specific clinical scenarios. In MCI, a negative plasma p‐tau217 could rule out AD as a cause of cognitive impairment, but a positive result should be followed up with PET/CSF. In mild AD dementia, a positive plasma p‐tau217 result can rule in biological AD, but a negative result should be followed up with PET/CSF. [ABSTRACT FROM AUTHOR]

Background and Objectives In older adults, executive functions are important for daily-life function and mobility. Evidence suggests that the relationship between cognition and mobility is dynamic and could vary according to individual factors, but whether cardiorespiratory fitness reduces the age-related increase of interdependence between mobility and cognition remains unexplored. Research Design and Methods One hundred eighty-nine participants (aged 50–87) were divided into 3 groups according to their age: middle-aged (MA; <65), young older adults (YOA; 65–74), and old older adults (OOA; ≥75). Participants performed Timed Up and Go and executive functioning assessments (Oral Trail Making Test and Phonologic verbal fluency) remotely by videoconference. Participants completed the Matthews questionnaire to estimate their cardiorespiratory fitness (VO2 max in ml/min/kg). A 3-way moderation was used to address whether cardiorespiratory fitness interacts with age to moderate the relationship between cognition and mobility. Results Results showed that the cardiorespiratory fitness × age interaction moderated the association between executive functioning and mobility (β = −0.05; p =.048; R 2 = 17.6; p <.001). At lower levels of physical fitness (<19.16 ml/min/kg), executive functioning significantly influenced YOA's mobility (β = −0.48, p =.004) and to a greater extent OOA's mobility (β = −0.96, p =.002). Discussion and Implications Our results support the idea of a dynamic relationship between mobility and executive functioning during aging and suggest that physical fitness could play a significant role in reducing their interdependency. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) phenotypes might result from differences in selective vulnerability. Evidence from preclinical models suggests that tau pathology has cell-to-cell propagation properties. Therefore, here, we tested the cell-to-cell propagation framework in the amnestic, visuospatial, language, and behavioral/dysexecutive phenotypes of AD. We report that each AD phenotype is associated with a distinct network-specific pattern of tau aggregation, where tau aggregation is concentrated in brain network hubs. In all AD phenotypes, regional tau load could be predicted by connectivity patterns of the human brain. Furthermore, regions with greater connectivity displayed similar rates of longitudinal tau accumulation in an independent cohort. Connectivity-based tau deposition was not restricted to a specific vulnerable network but was rather a general property of brain organization, linking selective vulnerability and transneuronal spreading models of neurodegeneration. Together, this study indicates that intrinsic brain connectivity provides a framework for tau aggregation across diverse phenotypic manifestations of AD. Determining behavior by following tau: Although some of the symptoms of Alzheimer's disease (AD) are conserved among patients, multiple phenotypes exist, including amnestic, visuospatial, language, and behavioral/dysexecutive. Understanding the mechanisms mediating the different behavioral phenotypes will help the development of specific treatments. Here, Therriault and colleagues studied the pattern of tau pathology spreading in multiple cohorts of patients with different phenotypes and showed that each phenotype was associated with a specific connectivity-based pattern of tau aggregation. The results suggest that intrinsic brain connectivity drives tau aggregation pattern, thus determining the behavioral phenotype of the disease. [ABSTRACT FROM AUTHOR]

Fractional anisotropy (FA) is a quantitative map sensitive to microstructural properties of tissues in vivo and it is extensively used to study the healthy and pathological brain. This map is classically calculated by model fitting (standard method) and requires many diffusion weighted (DW) images for data quality and unbiased readings, hence needing the acquisition time of several minutes. Here, we adapted the U-net architecture to be generalized and to obtain good quality FA from DW volumes acquired in 1minute. Our network requires 10 input DW volumes (hence fast acquisition), is robust to the direction of application of the diffusion gradients (hence generalized), and preserves/improves map quality (hence good quality maps). We trained the network on the human connectome project (HCP) data using the standard model-fitting method on the entire set of DW directions to extract FA (ground truth). We addressed the generalization problem, i.e., we trained the network to be applicable, without retraining, to clinical datasets acquired on different scanners with different DW imaging protocols. The network was applied to two different clinical datasets to assess FA quality and sensitivity to pathology in temporal lobe epilepsy and multiple sclerosis, respectively. For HCP data, when compared to the ground truth FA, the FA obtained from 10 DW volumes using the network was significantly better (p < 10-4) than the FA obtained using the standard pipeline. For the clinical datasets, the network FA retained the same microstructural characteristics as the FA calculated with all DW volumes using the standard method. At the subject level, the comparison between white matter (WM) ground truth FA values and network FA showed the same distribution; at the group level, statistical differences of WM values detected in the clinical datasets with the ground truth FA were reproduced when using values from the network FA, i.e., the network retained sensitivity to pathology. In conclusion, the proposed network provides a clinically availablemethod to obtain FA froma generic set of 10 DW volumes acquirable in 1minute, augmenting data quality compared to direct model fitting, reducing the possibility of bias from sub-sampled data, and retaining FA pathological sensitivity, which is very attractive for clinical applications. [ABSTRACT FROM AUTHOR]

Brain pathologies are characterized by microscopic changes in neurons and synapses that reverberate into large scale networks altering brain dynamics and functional states. An important yet unresolved issue concerns the impact of patients' excitation/inhibition profiles on neurodegenerative diseases including Alzheimer's Disease, Frontotemporal Dementia, and Amyotrophic Lateral Sclerosis. In this work, we used The Virtual Brain (TVB) simulation platform to simulate brain dynamics in healthy and neurodegenerative conditions and to extract information about the excitatory/inhibitory balance in single subjects. The brain structural and functional connectomes were extracted from 3T-MRI (Magnetic Resonance Imaging) scans and TVB nodes were represented by a Wong-Wang neural mass model endowing an explicit representation of the excitatory/inhibitory balance. Simulations were performed including both cerebral and cerebellar nodes and their structural connections to explore cerebellar impact on brain dynamics generation. The potential for clinical translation of TVB derived biophysical parameters was assessed by exploring their association with patients' cognitive performance and testing their discriminative power between clinical conditions. Our results showed that TVB biophysical parameters differed between clinical phenotypes, predicting higher global coupling and inhibition in Alzheimer's Disease and stronger N-methyl-D-aspartate (NMDA) receptor-dependent excitation in Amyotrophic Lateral Sclerosis. These physio-pathological parameters allowed us to perform an advanced analysis of patients' conditions. In backward regressions, TVB-derived parameters significantly contributed to explain the variation of neuropsychological scores and, in discriminant analysis, the combination of TVB parameters and neuropsychological scores significantly improved the discriminative power between clinical conditions. Moreover, cluster analysis provided a unique description of the excitatory/inhibitory balance in individual patients. Importantly, the integration of cerebro-cerebellar loops in simulations improved TVB predictive power, i.e., the correlation between experimental and simulated functional connectivity in all pathological conditions supporting the cerebellar role in brain function disrupted by neurodegeneration. Overall, TVB simulations reveal differences in the excitatory/inhibitory balance of individual patients that, combined with cognitive assessment, can promote the personalized diagnosis and therapy of neurodegenerative diseases. [ABSTRACT FROM AUTHOR]

Background. The neural correlates of training-induced improvements of cognitive functions after brain damage remain still scarcely understood. In the specific case of aphasia, although several investigations have addressed the issue [...]

Background: Episodic memory decline is a hallmark of cognitive impairment due to Alzheimer's Disease (AD). Literature has consistently indicated that delayed recall is compromised early in the disease. Recognition memory seems disrupted at late stages, although findings are mixed. Recent PET studies have demonstrated that the presence of tau in the medial temporal lobe (MTL) relates to early deterioration of delayed recall, but no PET studies have assessed how recognition memory relates to tau. We sought to investigate this relationship across the Braak staging continuum. Method: Tau PET ([18F]‐MK6240) was acquired for 140 cognitively unimpaired elderly (CU), 54 MCI patients and 33 AD patients. Participants were segregated into Braak stages, based on in vivo PET neuroimaging of tau. Episodic memory was assessed using RAVLT delayed recall and recognition tests. MRI were segmented into probabilistic grey (GM) and white (WM) maps, non‐linearly registered to the ADNI template using Dartel and smoothed with an 8mm FWHM gaussian kernel. Independent samples t‐tests or their nonparametric counterparts were conducted to evaluate differences in memory scores by Braak stage. Voxel‐wise linear regression models were applied, using VoxelStats, with either delayed recall or recognition scores as dependent variables and tau PET as a predictor. Global amyloid, age, sex, education and APOE genotype were entered as covariates. Results: Pairwise comparisons revealed that recognition memory is spared in early Braak stages. Voxel‐wise analyses in the whole sample unveiled that delayed recall and recognition memory relate to tau in virtually the same cortical areas. However, the strength of the relationships widely varied by memory type. Tau‐PET in anterior MTL and posterior hippocampus shows stronger associations with delayed recall, while tau binding in lateral temporal, temporooccipital and posterior areas exhibits stronger associations with recognition memory. Conclusion: Our findings support the differentiation between delayed recall and recognition across the AD spectrum. Relationships between delayed recall and tau in the MTL are in concordance with previous research. Moreover, the contrast in the strength of the associations between memory and tau aggregation further supports the notion that delayed recall is already impaired in early Braak stages while recognition is damaged in later Braak stages. [ABSTRACT FROM AUTHOR]

Background: TRACE4AD (DeepTrace Technologies s.r.l, Italy) is a machine learning‐based software‐as‐medical device able to predict the conversion to Alzheimer's disease (AD) dementia of subjects at risk within 24‐months exploiting automatic processing of T1‐weighted MPRAGE brain MRI study and neuropsychological tests. TRACE4AD provides a report with the predicted individual risk of conversion to AD dementia, specific cognitive deficits, and suggestions supporting neurologists in diagnosis and characterization, prognosis, and decision‐making. We tested TRACE4AD in the clinical setting in its ability, at baseline, to: a) predict amnestic Mild Cognitive Impairment (MCI) conversion to AD dementia within 24‐months; b) characterize cognitive deficits; c) support neurologists' decision‐making. Method: We retrospectively included 92 subjects (mean age 73.12±7.6, 46% female): 32 patients from two Italian centers where TRACE4AD was implemented after user training; and 60 subjects from the ADNI dataset. All patients had a brain MPRAGE study at baseline, 77/92 patients (83.7%) also performed a neuropsychological assessment at baseline, 75/92 patients (81.5%) had a stable clinical diagnosis at 24‐month. TRACE4AD extracted the gray matter map from MPRAGE and used it (combined with cognitive measures when available) to make inferences. Reference standards were: a) the neurologist's clinical diagnosis at 24‐months, b) the neuropsychological assessment at the baseline, c) the agreement with the neuro exam and intervention decision time and type defined by neurologists at the baseline. Result: TRACE4AD accurately predicted conversion to AD dementia in 93.3% of patients based on the MRI, and in 96.6% based on MRI and cognitive measures. Cognitive deficits were found in agreement with the neuropsychological assessment for all patients except one who presented with major depression. We found disagreement between the neurologist's decision at baseline and the tool in only two patients, defined with normal cognition by the neurologist and predicted at high risk of AD dementia conversion by the tool. TRACE4AD supported neurologists' decision by 12 months in 15/17 patients for the prompt decision at baseline. Conclusion: TRACE4AD is promising, safe, and effective in supporting neurologists in the clinical practice of MCI across different centers. [ABSTRACT FROM AUTHOR]