Accuracy of Biomarker Testing for Neuropathologically Defined Alzheimer Disease in Older Adults With Dementia

Development and validation of an automatic classification algorithm for the diagnosis of Alzheimer's disease using a high-performance interpretable deep learning network

OBJECTIVES

To develop and validate an automatic classification algorithm for diagnosing Alzheimer's disease (AD) or mild cognitive impairment (MCI).

METHODS AND MATERIALS

This study evaluated a high-performance interpretable network algorithm (TabNet) and compared its performance with that of XGBoost, a widely used classifier. Brain segmentation was performed using a commercially approved software. TabNet and XGBoost were trained on the volumes or radiomics features of 102 segmented regions for classifying subjects into AD, MCI, or cognitively normal (CN) groups. The diagnostic performances of the two algorithms were compared using areas under the curves (AUCs). Additionally, 20 deep learning-based AD signature areas were investigated.

RESULTS

Between December 2014 and March 2017, 161 AD, 153 MCI, and 306 CN cases were enrolled. Another 120 AD, 90 MCI, and 141 CN cases were included for the internal validation. Public datasets were used for external validation. TabNet with volume features had an AUC of 0.951 (95% confidence interval [CI], 0.947-0.955) for AD vs CN, which was similar to that of XGBoost (0.953 [95% CI, 0.951-0.955], p = 0.41). External validation revealed the similar performances of two classifiers using volume features (0.871 vs. 0.871, p = 0.86). Likewise, two algorithms showed similar performances with one another in classifying MCI. The addition of radiomics data did not improve the performance of TabNet. TabNet and XGBoost focused on the same 13/20 regions of interest, including the hippocampus, inferior lateral ventricle, and entorhinal cortex.

CONCLUSIONS

TabNet shows high performance in AD classification and detailed interpretation of the selected regions.

CLINICAL RELEVANCE STATEMENT

Using a high-performance interpretable deep learning network, the automatic classification algorithm assisted in accurate Alzheimer's disease detection using 3D T1-weighted brain MRI and detailed interpretation of the selected regions.

KEY POINTS

• MR volumetry data revealed that TabNet had a high diagnostic performance in differentiating Alzheimer's disease (AD) from cognitive normal cases, which was comparable with that of XGBoost. • The addition of radiomics data to the volume data did not improve the diagnostic performance of TabNet. • Both TabNet and XGBoost selected the clinically meaningful regions of interest in AD, including the hippocampus, inferior lateral ventricle, and entorhinal cortex.

Magneto-assisted enzymatic DNA walkers for simultaneous electrochemical detection of amyloid-beta oligomers and Tau

DNA walkers have been widely explored and applied as biosensor elements to detect disease-related biomarkers. Traditional interface-anchored DNA walkers typically have a fixed swing arm range and an orientation of the preset track, which might complicate the design of a sensor system and limit its application in more scenes. We propose a simple electrochemical aptasensor to accurately detect Alzheimer's disease (AD) based on a nicking enzyme-powered DNA walker. In this method, bifunctional magnetic nanoparticles are used to identify and capture Aβ oligomers (AβO) and Tau and release the DNA walker. As the DNA walker moves freely on the surface of the electrode, the nicking enzymes circularly cleave and release the two signal substrate chains, significantly amplifying the signal. It has been demonstrated that the constructed sensor can sensitively detect AβO and Tau, and the combined analysis of dual markers improves the accuracy of AD diagnosis. Furthermore, this method can distinguish normal individuals from AD patients in real cerebrospinal fluid samples. The excellent performance of this biosensor makes it promising for clinical applications in diagnosing AD patients and prognosis assessment.

The use of neuroimaging techniques in the early and differential diagnosis of dementia

Dementia is a leading cause of disability and death worldwide. At present there is no disease modifying treatment for any of the most common types of dementia such as Alzheimer's disease (AD), Vascular dementia, Lewy Body Dementia (LBD) and Frontotemporal dementia (FTD). Early and accurate diagnosis of dementia subtype is critical to improving clinical care and developing better treatments. Structural and molecular imaging has contributed to a better understanding of the pathophysiology of neurodegenerative dementias and is increasingly being adopted into clinical practice for early and accurate diagnosis. In this review we summarise the contribution imaging has made with particular focus on multimodal magnetic resonance imaging (MRI) and positron emission tomography imaging (PET). Structural MRI is widely used in clinical practice and can help exclude reversible causes of memory problems but has relatively low sensitivity for the early and differential diagnosis of dementia subtypes. 18F-fluorodeoxyglucose PET has high sensitivity and specificity for AD and FTD, while PET with ligands for amyloid and tau can improve the differential diagnosis of AD and non-AD dementias, including recognition at prodromal stages. Dopaminergic imaging can assist with the diagnosis of LBD. The lack of a validated tracer for α-synuclein or TAR DNA-binding protein 43 (TDP-43) imaging remain notable gaps, though work is ongoing. Emerging PET tracers such as 11C-UCB-J for synaptic imaging may be sensitive early markers but overall larger longitudinal multi-centre cross diagnostic imaging studies are needed.

Development and validation of a deep-broad ensemble model for early detection of Alzheimer's disease

Introduction

Alzheimer's disease (AD) is a chronic neurodegenerative disease of the brain that has attracted wide attention in the world. The diagnosis of Alzheimer's disease is faced with the difficulties of insufficient manpower and great difficulty. With the intervention of artificial intelligence, deep learning methods are widely used to assist clinicians in the early recognition of Alzheimer's disease. And a series of methods based on data input with different dimensions have been proposed. However, traditional deep learning models rely on expensive hardware resources and consume a lot of training time, and may fall into the dilemma of local optima.

Methods

In recent years, broad learning system (BLS) has provided researchers with new research ideas. Based on the three-dimensional residual convolution module and BLS, a novel broad-deep ensemble model based on BLS is proposed for the early detection of Alzheimer's disease. The Alzheimer's Disease Neuroimaging Initiative (ADNI) MRI image dataset is used to train the model and then we compare the performance of proposed model with previous work and clinicians' diagnosis.

Results

The result of experiments demonstrate that the broad-deep ensemble model is superior to previously proposed related works, including 3D-ResNet and VoxCNN, in accuracy, sensitivity, specificity and F1.

Discussion

The proposed broad-deep ensemble model is effective for early detection of Alzheimer's disease. In addition, the proposed model does not need the pre-training process of its depth module, which greatly reduces the training time and hardware dependence.

Aβ42 treatment of the brain side reduced the level of flotillin from endothelial cells on the blood side via FGF-2 signaling in a blood-brain barrier model

Our previous study showed that the flotillin level is decreased in the blood of patients with Alzheimer's disease (AD) when compared to that of patients with non-AD and vascular dementia; however, the molecular mechanism remains to be determined. In this study, to elucidate whether Aβ accumulation in the brain has an effect on the blood flotillin level, we used our previously established blood-brain barrier (BBB) culture model using microvascular endothelial cells obtained from human induced pluripotent stem cells (iBMECs) and astrocytes prepared from rat cortex. In this BBB model with iBMECs plated on the upper compartment (blood side) and astrocytes plated on the lower compartment (brain side), the trans-endothelial electrical resistance values are high (over 1500 Ωm²) and stable during experiments. We found that the addition of Aβ42 (0.5 and 2 µM) to the brain side significantly reduced the level of flotillin secreted by iBMECs on the blood side. The level of basic fibroblast growth factor (FGF-2) in the brain side was significantly reduced by Aβ42 treatment, and was accompanied by a reduction in the level of phosphorylation of the fibroblast growth factor receptor in iBMECs. The brain-side Aβ42 treatment-induced reduction of flotillin secretion into the blood side was restored in a dose-dependent manner by the addition of FGF-2 into the brain side. These results indicated that Aβ accumulation in the brain side reduced FGF-2 release from astrocytes, which attenuated FGF-2-mediated iBMECs signaling via the FGF-2 receptor, and thereby reduced flotillin secretion from iBMECs on the blood side. Our findings revealed a novel signaling pathway crossing the BBB from the brain side to the blood side, which is different from the classical intramural periarterial drainage or lymphatic-system-to-blood pathway.

Diagnostic performance of hippocampal volumetry in Alzheimer's disease or mild cognitive impairment: a meta-analysis

OBJECTIVE

To evaluate the diagnostic performance of hippocampal volumetry for Alzheimer's disease (AD) or mild cognitive impairment (MCI).

METHODS

The MEDLINE and Embase databases were searched for articles that evaluated the diagnostic performance of hippocampal volumetry in differentiating AD or MCI from normal controls, published up to March 6, 2022. The quality of the articles was evaluated by the QUADAS-2 tool. A bivariate random-effects model was used to pool sensitivity, specificity, and area under the curve. Sensitivity analysis and meta-regression were conducted to explain study heterogeneity. The diagnostic performance of entorhinal cortex volumetry was also pooled.

RESULTS

Thirty-three articles (5157 patients) were included. The pooled sensitivity and specificity for AD were 82% (95% confidence interval [CI], 77-86%) and 87% (95% CI, 82-91%), whereas those for MCI were 60% (95% CI, 51-69%) and 75% (95% CI, 67-81%), respectively. No difference in the diagnostic performance was observed between automatic and manual segmentation (p = 0.11). MMSE scores, study design, and the reference standard being used were associated with study heterogeneity (p < 0.01). Subgroup analysis demonstrated a higher diagnostic performance of entorhinal cortex volumetry for both AD (pooled sensitivity: 88% vs. 79%, specificity: 92% vs. 89%, p = 0.07) and MCI (pooled sensitivity: 71% vs. 55%, specificity: 83% vs. 68%, p = 0.06).

CONCLUSIONS

Our meta-analysis demonstrated good diagnostic performance of hippocampal volumetry for AD or MCI. Entorhinal cortex volumetry might have superior diagnostic performance to hippocampal volumetry. However, due to a small number of studies, the diagnostic performance of entorhinal cortex volumetry is yet to be determined.

KEY POINTS

• The pooled sensitivity and specificity of hippocampal volumetry for Alzheimer's disease were 82% and 87%, whereas those for mild cognitive impairment were 60% and 75%, respectively. • No significant difference in the diagnostic performance was observed between automatic and manual segmentation. • Subgroup analysis demonstrated superior diagnostic performance of entorhinal cortex volumetry for AD (pooled sensitivity: 88%, specificity: 92%) and MCI (pooled sensitivity: 71%, specificity: 83%).

Biofluid Biomarkers of Alzheimer’s Disease: Progress, Problems, and Perspectives

Since the establishment of the biomarker-based A-T-N (Amyloid/Tau/Neurodegeneration) framework in Alzheimer’s disease (AD), the diagnosis of AD has become more precise, and cerebrospinal fluid tests and positron emission tomography examinations based on this framework have become widely accepted. However, the A-T-N framework does not encompass the whole spectrum of AD pathologies, and problems with invasiveness and high cost limit the application of the above diagnostic methods aimed at the central nervous system. Therefore, we suggest the addition of an “X” to the A-T-N framework and a focus on peripheral biomarkers in the diagnosis of AD. In this review, we retrospectively describe the recent progress in biomarkers based on the A-T-N-X framework, analyze the problems, and present our perspectives on the diagnosis of AD.

Associations of Fully Automated CSF and Novel Plasma Biomarkers With Alzheimer Disease Neuropathology at Autopsy

OBJECTIVE

To study CSF biomarkers of Alzheimer disease (AD) analyzed by fully automated Elecsys immunoassays compared to neuropathologic gold standards and to compare their accuracy to plasma phosphorylated tau (p-tau181) measured with a novel single molecule array method.

METHODS

We studied antemortem Elecsys-derived CSF biomarkers in 45 individuals who underwent standardized postmortem assessments of AD and non-AD neuropathologic changes at autopsy. In a subset of 26 participants, we also analyzed antemortem levels of plasma p-tau181 and neurofilament light (NfL). Reference biomarker values were obtained from 146 amyloid-PET-negative healthy controls (HC).

RESULTS

All CSF biomarkers clearly distinguished pathology-confirmed AD dementia (n = 27) from HC (area under the curve [AUC] 0.86-1.00). CSF total tau (t-tau), p-tau181, and their ratios with β-amyloid1-42 (Aβ1-42) also accurately distinguished pathology-confirmed AD from non-AD dementia (n = 8; AUC 0.94-0.97). In pathology-specific analyses, intermediate to high Thal amyloid phases were best detected by CSF Aβ1-42 (AUC [95% confidence interval] 0.91 [0.81-1]), while intermediate to high scores for Consortium to Establish a Registry for Alzheimer's Disease neuritic plaques and Braak tau stages were best detected by CSF p-tau181 (AUC 0.89 [0.79-0.99] and 0.88 [0.77-0.99], respectively). Optimal Elecsys biomarker cutoffs were derived at 1,097, 229, and 19 pg/mL for Aβ1-42, t-tau, and p-tau181. In the plasma subsample, both plasma p-tau181 (AUC 0.91 [0.86-0.96]) and NfL (AUC 0.93 [0.87-0.99]) accurately distinguished those with pathology-confirmed AD (n = 14) from HC. However, only p-tau181 distinguished AD from non-AD dementia cases (n = 4; AUC 0.96 [0.88-1.00]) and showed a similar, although weaker, pathologic specificity for neuritic plaques (AUC 0.75 [0.52-0.98]) and Braak stage (AUC 0.71 [0.44-0.98]) as CSF p-tau181.

CONCLUSION

Elecsys-derived CSF biomarkers detect AD neuropathologic changes with very high discriminative accuracy in vivo. Preliminary findings support the use of plasma p-tau181 as an easily accessible and scalable biomarker of AD pathology.

CLASSIFICATION OF EVIDENCE

This study provides Class II evidence that fully automated CSF t-tau and p-tau181 measurements discriminate between autopsy-confirmed AD and other dementias.

Treatment of canine cognitive dysfunction with novel butyrylcholinesterase inhibitor

Canine cognitive dysfunction (CCD) is common in aged dogs and has many similarities with Alzheimer’s disease. Unfortunately, like Alzheimer’s disease, CCD cannot be cured. In the present study, we treated dogs with CCD with our newly developed and characterized butyrylcholinesterase inhibitor (BChEi). Seventeen dogs were randomized into two groups (treated with BChEi and untreated) and followed for 6 months at regular check-ups. The dogs’ cognitive status was determined by a Canine Dementia Scale (CADES) questionnaire and two cognitive tests. In dogs with moderate cognitive impairment, treatment caused significant improvement in the clinical rating of cognitive abilities and the performance-based tests of cognitive functioning when compared to the untreated group (p < 0.001). Dogs treated with BChEi showed markedly improved cognitive function with enhanced quality of life. No side effects were observed in the treated dogs with moderate cognitive impairment. According to the results of this preliminary study, there is an indication that novel BChEi may be a promising drug for the treatment of CCD in dogs and may be an interesting candidate for the treatment of Alzheimer's disease in humans. However, further clinical studies are needed to confirm this.

The role of the immune system in Alzheimer's disease

Alzheimer's disease (AD) is the most common neurodegenerative disorder where the accumulation of amyloid plaques and the formation of tau tangles are the prominent pathological hallmarks. Increasing preclinical and clinical studies have revealed that different components of the immune system may act as important contributors to AD etiology and pathogenesis. The recognition of misfolded Aβ and tau by immune cells can trigger a series of complex immune responses in AD, and then lead to neuroinflammation and neurodegeneration. In parallel, genome-wide association studies have also identified several immune related loci associated with increased - risk of AD by interfering with the function of immune cells. Other immune related factors, such as impaired immunometabolism, defective meningeal lymphatic vessels and autoimmunity might also be involved in the pathogenesis of AD. Here, we review the data showing the alterations of immune cells in the AD trajectory and seek to demonstrate the crosstalk between the immune cell dysfunction and AD pathology. We then discuss the most relevant research findings in regards to the influences of gene susceptibility of immune cells for AD. We also consider impaired meningeal lymphatics, immunometabolism and autoimmune mechanisms in AD. In addition, immune related biomarkers and immunotherapies for AD are also mentioned in order to offer novel insights for future research.

Improvement in depressive symptoms after antiretroviral therapy initiation in people with HIV in Rakai, Uganda

Depression is common following HIV infection and often improves after ART initiation. We aimed to identify distinct dimensions of depression that change following ART initiation in persons with HIV (PWH) with minimal comorbidities (e.g., illicit substance use) and no psychiatric medication use. We expected that dimensional changes in improvements in depression would differ across PWH. In an observational cohort in Rakai, Uganda, 312 PWH (51% male; mean age = 35.6 years) completed the Center for Epidemiologic Studies-Depression (CES-D) scale before and up to 2 years after ART initiation. Twenty-two percent were depressed (CES-D scores ≥ 16) pre-ART that decreased to 8% after ART. All CES-D items were used in a latent class analysis to identify subgroups with similar change phenotypes. Two improvement phenotypes were identified: affective-symptom improvement (n = 58, 19%) and mixed-symptom improvement (effort, appetite, irritability; n = 41, 13%). The affect-improvement subgroup improved on the greatest proportion of symptoms (76%). A third subgroup was classified as no-symptom changes (n = 213, 68%) as they showed no difference is symptom manifestation from baseline (93% did not meet depression criteria) to post-ART. Factors associated with subgroup membership in the adjusted regression analysis included pre-ART self-reported functional capacity, CD4 count, underweight BMI, hypertension, female sex(P's < 0.05). In a subset of PWH with CSF, subgroup differences were seen on Aβ-42, IL-13, and IL-12. Findings support that depression generally improves following ART initiation; however, when improvement is seen the patterns of symptom improvement differ across PWH. Further exploration of this heterogeneity and its biological underpinning is needed to evaluate potential therapeutic implications of these differences.

On the prevention and treatment of Alzheimer's disease: Control the promoters and look beyond the brain

Alzheimer's disease (AD) is a progressive incurable neurodegenerative disease of the brain afflicting a third of the population aged 85 and older. Pathologic hallmarks include extracellular plaques of amyloid-beta (Aß), intraneuronal neurofibrillary tangles of hyperphosphorylated tau protein, synaptic destruction, neuronal death, and brain atrophy. Neuroinflammation, mediated by microglia, is a central component of the disease, and is intricately connected with peripheral inflammation. The clinical manifestations include progressive memory loss and eventual death. The present treatment of AD is largely ineffective. Nearly all AD is late-onset and presents age 65 or older, and the most common genetic risk factor is carriage of an apolipoprotein (APO) E4 allele, seen in about 25% of the general population. Individuals carrying an APOE4 allele produce more Aß and clear it less efficiently from the brain throughout life. There has been accumulating pathologic and clinical evidence that microbes, particularly the herpes simplex virus (HSV), is a causative factor for AD, most notable in carriers of the APOE4 allele. Eighty percent of the adult population harbors HSV and it resides in the trigeminal ganglion in latent state throughout life, but periodically reactivates, traveling antegrade resulting in herpes labialis and traveling retrograde into the brain leading to neuroinflammation. Functioning as an antimicrobial peptide, Aß inactivates HSV and the recurring process culminates in a buildup of Aß plaque and other hallmarks of AD over time. Periodontal disease exists in 20-50% of the adult population and is also a causative factor for AD. Accordingly, bacteria causing periodontal disease and their byproducts can enter the brain directly via the trigeminal nerve or indirectly through the bloodstream, resulting in AD pathology over time. There are many other promoters of AD, particularly inflammatory conditions outside of the brain, that can be mitigated. Small trials are finally in progress testing antimicrobial drugs for the prevention and treatment of AD. In the meantime, a more proactive approach to the prevention and treatment of AD is posited, with an emphasis on prevention, since the pathologic underpinnings of the disease start decades before the clinical manifestations. Individuals can be stratified in risk categories using family history, periodontal disease presence, APOE4 carriage, and HSV IgG positivity. Moderate- and high-risk individuals can be treated safely with various preventive measures and appropriate antimicrobial agents as discussed. Importantly, the proposed treatments are concordant with the accepted practice of medicine, and if utilized, could significantly decrease AD prevalence.

Ethical Considerations in Dementia Diagnosis and Care: AAN Position Statement

Alzheimer disease and other dementias present unique practical challenges for patients, their families, clinicians, and health systems. These challenges reflect not only the growing public health effect of dementia in an aging global population, but also more specific ethical complexities including early loss of patients' capacity to make decisions regarding their own care, the stigma often associated with a dementia diagnosis, the difficulty of balancing concern for patients' welfare with respect for patients' remaining independence, and the effect on the physical, emotional, and financial well-being of family caregivers. Caring for patients with dementia requires respecting patient autonomy while acknowledging progressively diminishing decisional capacity and continuing to provide care in accordance with other core ethical principles (beneficence, justice, and nonmaleficence). Whereas these ethical principles remain unchanged, neurologists must reconsider how to apply them given changes across multiple domains including our understanding of disease, clinical and legal tools for addressing manifestations of illness, our expanding awareness of the crucial role of family caregivers in providing care and maintaining patient quality of life, and societal conceptions of dementia and individuals' personal expectations for aging. This revision to the American Academy of Neurology's 1996 position statement summarizes ethical considerations that often arise in caring for patients with dementia; although it addresses how such considerations influence patient management, it is not a clinical practice guideline.

Brain SPECT as a Biomarker of Neurodegeneration in Dementia in the Era of Molecular Imaging: Still a Valid Option?

Biomarkers are playing a progressively leading role in both clinical practice and scientific research in dementia. Although amyloid and tau biomarkers have gained ground in the clinical community in recent years, neurodegeneration biomarkers continue to play a key role due to their ability to identify different patterns of brain involvement that sign the transition between asymptomatic and symptomatic stages of the disease with high sensitivity and specificity. Both ¹⁸F-FDG positron emission tomography (PET) and perfusion single photon emission computed tomography (SPECT) have proved useful to reveal the functional alterations underlying various neurodegenerative diseases. Although the focus of nuclear neuroimaging has shifted to PET, the lower cost and wider availability of SPECT make it a still valid alternative for the study of patients with dementia. This review discusses the principles of both techniques, compares their diagnostic performance for the diagnosis of neurodegenerative diseases and highlights the role of SPECT to characterize patients from low- and middle-income countries, where special care of additional costs is particularly needed to meet the new recommendations for the diagnosis and characterization of patients with dementia.

Comparison of the clinical impact of 2-[18F]FDG-PET and cerebrospinal fluid biomarkers in patients suspected of Alzheimer's disease

Background

The two biomarkers 2-[¹⁸F]FDG-PET and cerebrospinal fluid biomarkers are both recommended to support the diagnosis of Alzheimer’s disease. However, there is a lack of knowledge for the comparison of the two biomarkers in a routine clinical setting.

Objective

The aim was to compare the clinical impact of 2-[¹⁸F]FDG-PET and cerebrospinal fluid biomarkers on diagnosis, prognosis, and patient management in patients suspected of Alzheimer’s disease.

Methods

Eighty-one patients clinically suspected of Alzheimer’s disease were retrospectively included from the Copenhagen Memory Clinic. As part of the clinical work-up all patients had a standard diagnostic program examination including MRI and ancillary investigations with 2-[¹⁸F]FDG-PET and cerebrospinal fluid biomarkers. An incremental study design was used to evaluate the clinical impact of the biomarkers. First, the diagnostic evaluation was based on the standard diagnostic program, then the diagnostic evaluation was revised after addition of either cerebrospinal fluid biomarkers or 2-[¹⁸F]FDG-PET. At each diagnostic evaluation, two blinded dementia specialists made a consensus decision on diagnosis, prediction of disease course, and change in patient management. Confidence in the decision was measured on a visual analogue scale (0–100). After 6 months, the diagnostic evaluation was performed with addition of the other biomarker. A clinical follow-up after 12 months was used as reference for diagnosis and disease course.

Results

The two biomarkers had a similar clinical value across all diagnosis when added individually to the standard diagnostic program. However, for the correctly diagnosed patient with Alzheimer’s disease cerebrospinal fluid biomarkers had a significantly higher impact on diagnostic confidence (mean scores±SD: 88±11 vs. 82±11, p = 0.046) and a significant reduction in the need for ancillary investigations (23 vs. 18 patients, p = 0.049) compared to 2-[¹⁸F]FDG-PET.

Conclusion

The two biomarkers had similar clinical impact on diagnosis, but cerebrospinal fluid biomarkers had a more significant value in corroborating the diagnosis of Alzheimer’s disease compared to 2-[¹⁸F]FDG-PET.

Diagnose it yourself: will there be a home test kit for Alzheimer's disease?

Alzheimer's disease is the most common neurodegenerative process leading to dementia. To date, there is no curative approach; thus, establishing a diagnosis as early as possible is necessary to implement preventive measures. However, today's gold standard for diagnosing Alzheimer's disease is high in both cost and effort and is not readily available. This defines the need for low-effort and economic alternatives that give patients low-threshold access to testing systems at their general practitioners or even at home for an independent retrieval of a biologic specimen. This perspective gives an overview of established and novel approaches in the field and speculates on the future of test strategies eventually technically implementable at home.

Diagnostic Accuracy of Amyloid versus 18 F-Fluorodeoxyglucose Positron Emission Tomography in Autopsy-Confirmed Dementia

OBJECTIVE

The purpose of this study was to compare the diagnostic accuracy of antemortem 11 C-Pittsburgh compound B (PIB) and 18 F-fluorodeoxyglucose (FDG) positron emission tomography (PET) versus autopsy diagnosis in a heterogenous sample of patients.

METHODS

One hundred one participants underwent PIB and FDG PET during life and neuropathological assessment. PET scans were visually interpreted by 3 raters blinded to clinical information. PIB PET was rated as positive or negative for cortical retention, whereas FDG scans were read as showing an Alzheimer disease (AD) or non-AD pattern. Neuropathological diagnoses were assigned using research criteria. Majority visual reads were compared to intermediate-high AD neuropathological change (ADNC).

RESULTS

One hundred one participants were included (mean age = 67.2 years, 41 females, Mini-Mental State Examination = 21.9, PET-to-autopsy interval = 4.4 years). At autopsy, 32 patients showed primary AD, 56 showed non-AD neuropathology (primarily frontotemporal lobar degeneration [FTLD]), and 13 showed mixed AD/FTLD pathology. PIB showed higher sensitivity than FDG for detecting intermediate-high ADNC (96%, 95% confidence interval [CI] = 89-100% vs 80%, 95% CI = 68-92%, p = 0.02), but equivalent specificity (86%, 95% CI = 76-95% vs 84%, 95% CI = 74-93%, p = 0.80). In patients with congruent PIB and FDG reads (77/101), combined sensitivity was 97% (95% CI = 92-100%) and specificity was 98% (95% CI = 93-100%). Nine of 24 patients with incongruent reads were found to have co-occurrence of AD and non-AD pathologies.

INTERPRETATION

In our sample enriched for younger onset cognitive impairment, PIB-PET had higher sensitivity than FDG-PET for intermediate-high ADNC, with similar specificity. When both modalities are congruent, sensitivity and specificity approach 100%, whereas mixed pathology should be considered when PIB and FDG are incongruent. ANN NEUROL 2021;89:389-401.

Matching Clinical Diagnosis and Amyloid Biomarkers in Alzheimer's Disease and Frontotemporal Dementia

BACKGROUND

The aims of this study were to compare the diagnostic accuracy, sensitivity, specificity, and positive and negative predictive values (PPV, NPV) of different cerebrospinal fluid (CSF) amyloid biomarkers and amyloid-Positron Emission Tomography (PET) in patients with a clinical diagnosis of Alzheimer's disease (AD) and Frontotemporal Dementia (FTD); to compare concordance between biomarkers; and to provide an indication of their use and interpretation.

METHODS

We included 148 patients (95 AD and 53 FTD), who underwent clinical evaluation, neuropsychological assessment, and at least one amyloid biomarker (CSF analysis or amyloid-PET). Thirty-six patients underwent both analyses. One-hundred-thirteen patients underwent Apolipoprotein E (ApoE) genotyping.

RESULTS

Amyloid-PET presented higher diagnostic accuracy, sensitivity, and NPV than CSF Aβ_1-42 but not Aβ_42/40 ratio. Concordance between CSF biomarkers and amyloid-PET was higher in FTD patients compared to AD cases. None of the AD patients presented both negative Aβ biomarkers.

CONCLUSIONS

CSF Aβ_42/40 ratio significantly increased the diagnostic accuracy of CSF biomarkers. On the basis of our current and previous data, we suggest a flowchart to guide the use of biomarkers according to clinical suspicion: due to the high PPV of both amyloid-PET and CSF analysis including Aβ_42/40, in cases of concordance between at least one biomarker and clinical diagnosis, performance of the other analysis could be avoided. A combination of both biomarkers should be performed to better characterize unclear cases. If the two amyloid biomarkers are both negative, an underlying AD pathology can most probably be excluded.

Utility of MemTrax and Machine Learning Modeling in Classification of Mild Cognitive Impairment

Background:

The widespread incidence and prevalence of Alzheimer’s disease and mild cognitive impairment (MCI) has prompted an urgent call for research to validate early detection cognitive screening and assessment.

Objective:

Our primary research aim was to determine if selected MemTrax performance metrics and relevant demographics and health profile characteristics can be effectively utilized in predictive models developed with machine learning to classify cognitive health (normal versus MCI), as would be indicated by the Montreal Cognitive Assessment (MoCA).

Methods:

We conducted a cross-sectional study on 259 neurology, memory clinic, and internal medicine adult patients recruited from two hospitals in China. Each patient was given the Chinese-language MoCA and self-administered the continuous recognition MemTrax online episodic memory test on the same day. Predictive classification models were built using machine learning with 10-fold cross validation, and model performance was measured using Area Under the Receiver Operating Characteristic Curve (AUC). Models were built using two MemTrax performance metrics (percent correct, response time), along with the eight common demographic and personal history features.

Results:

Comparing the learners across selected combinations of MoCA scores and thresholds, Naïve Bayes was generally the top-performing learner with an overall classification performance of 0.9093. Further, among the top three learners, MemTrax-based classification performance overall was superior using just the top-ranked four features (0.9119) compared to using all 10 common features (0.8999).

Conclusion:

MemTrax performance can be effectively utilized in a machine learning classification predictive model screening application for detecting early stage cognitive impairment.