Data-Driven Differential Diagnosis of Dementia Using Multiclass Disease State Index Classifier

cCOG Web-Based Cognitive Assessment Tool

Cognitive testing is an essential part of clinical diagnostics and clinical trials in Alzheimer's disease. Digital cognitive tests hold a great opportunity to provide more versatile and cost-efficient patient pathways through flexible testing including at home. In this work, we describe a web-based cognitive test, cCOG, that can be used in screening, differential diagnosis, and monitoring the progression of neurodegenerative diseases.

Classification of neuroimaging data in Alzheimer's disease using particle swarm optimization: A systematic review

AIM

Particle swarm optimization (PSO) is an algorithm that involves the optimization of Non-linear and Multidimensional problems to reach the best solutions with minimal parameterization. This metaheuristic model has frequently been used in the Pathological domain. This optimization model has been used in diverse forms while predicting Alzheimer's disease. It is a robust algorithm that works on linear and multi-modal data while predicting Alzheimer's disease. PSO techniques have been in action for quite some time for detecting various diseases and this paper systematically reviews the papers on various kinds of PSO techniques.

METHODS

To perform the systematic review, PRISMA guidelines were followed and a Boolean search ("particle swarm optimization" OR "PSO") AND Neuroimaging AND (Alzheimer's disease prediction OR classification OR diagnosis) were performed. The query was run in 4-reputed databases: Google Scholar, Scopus, Science Direct, and Wiley publications.

RESULTS

For the final analysis, 10 papers were incorporated for qualitative and quantitative synthesis. PSO has shown a dominant character while handling the uni-modal as well as the multi-modal data while predicting the conversion from MCI to Alzheimer's. It can be seen from the table that almost all the 10 reviewed papers had MRI-driven data. The accuracy rate was accentuated while adding other modalities or Neurocognitive measures.

CONCLUSIONS

Through this algorithm, we are providing an opportunity to other researchers to compare this algorithm with other state-of-the-art algorithms, while seeing the classification accuracy, with the aim of early prediction and progression of MCI into Alzheimer's disease.

Interpretability of Clinical Decision Support Systems Based on Artificial Intelligence from Technological and Medical Perspective: A Systematic Review

Background

Artificial intelligence (AI) has developed rapidly, and its application extends to clinical decision support system (CDSS) for improving healthcare quality. However, the interpretability of AI-driven CDSS poses significant challenges to widespread application.

Objective

This study is a review of the knowledge-based and data-based CDSS literature regarding interpretability in health care. It highlights the relevance of interpretability for CDSS and the area for improvement from technological and medical perspectives.

Methods

A systematic search was conducted on the interpretability-related literature published from 2011 to 2020 and indexed in the five databases: Web of Science, PubMed, ScienceDirect, Cochrane, and Scopus. Journal articles that focus on the interpretability of CDSS were included for analysis. Experienced researchers also participated in manually reviewing the selected articles for inclusion/exclusion and categorization.

Results

Based on the inclusion and exclusion criteria, 20 articles from 16 journals were finally selected for this review. Interpretability, which means a transparent structure of the model, a clear relationship between input and output, and explainability of artificial intelligence algorithms, is essential for CDSS application in the healthcare setting. Methods for improving the interpretability of CDSS include ante-hoc methods such as fuzzy logic, decision rules, logistic regression, decision trees for knowledge-based AI, and white box models, post hoc methods such as feature importance, sensitivity analysis, visualization, and activation maximization for black box models. A number of factors, such as data type, biomarkers, human-AI interaction, needs of clinicians, and patients, can affect the interpretability of CDSS.

Conclusions

The review explores the meaning of the interpretability of CDSS and summarizes the current methods for improving interpretability from technological and medical perspectives. The results contribute to the understanding of the interpretability of CDSS based on AI in health care. Future studies should focus on establishing formalism for defining interpretability, identifying the properties of interpretability, and developing an appropriate and objective metric for interpretability; in addition, the user's demand for interpretability and how to express and provide explanations are also the directions for future research.

Optimizing cCOG, a Web-based tool, to detect dementia with Lewy Bodies

Introduction

Distinguishing dementia with Lewy bodies (DLB) from Alzheimer's disease (AD) is challenging due to overlapping presentations. We adapted a Web-based test tool, cCOG, by adding a visuospatial task and a brief clinical survey and assessed its ability to differentiate between DLB and AD.

Methods

We included 110 patients (n = 30 DLB, n = 32 AD dementia, and n = 48 controls with subjective cognitive decline (SCD)). Full cCOG comprises six cognitive subtasks and a survey addressing self-reported DLB core and autonomic features. First, we compared cCOG cognitive tasks to traditional neuropsychological tasks for all diagnostic groups and clinical questions to validated assessments of clinical features in DLB only. Then, we studied the performance of cCOG cognitive tasks and clinical questions, separately and combined, in differentiating diagnostic groups.

Results

cCOG cognitive tasks and clinical survey had moderate to strong correlations to standard neuropsychological testing (.61≤ r ^s ≤ .77) and to validated assessments of clinical features (.41≤ r ^s ≤ .65), except for fluctuations and REM-sleep behavior disorder (RBD) (r ^s = .32 and r ^s = .10). Full cCOG, including both cognitive tasks and brief survey had a diagnostic accuracy (acc) of 0.82 [95% CI 0.73-0.89], with good discrimination of DLB versus AD (acc 0.87 [0.76-0.95]) and DLB versus controls (acc 0.94 [0.86-0.98]).

Conclusion

We illustrated that cCOG aids in distinguishing DLB and AD patients by using remote assessment of cognition and clinical features. Our findings pave the way to a funneled, harmonized diagnostic process among memory clinics and, eventually, a more timely and accurate diagnosis of DLB and AD.

Computer-Aided Detection and Diagnosis of Neurological Disorder

Nowadays, neurological problems are more regular, representing a worry to pregnant ladies, guardians, healthy babies, and kids. Neurological problems emerge in a wide assortment of structures, each with its arrangement of beginnings, inconveniences, and results. The conclusion of neurological illnesses is an evolving concern and predominantly troublesome difficulty for current medication. Current diagnosis advancements (e.g., MRI and EEG) produce immense information (in proportion and aspect) as location, checking, and therapy of nervous system illnesses. As a common rule, investigation of that enormous clinical information is performed physically by specialists to distinguish and figure out the irregularities. It is a genuinely troublesome errand for an individual to collect, make due, investigate, and absorb enormous amounts of information through visible review. As an outcome, the specialist has been requesting electronic conclusion frameworks known as “computer-aided diagnosis” that can consequently identify the nervous system irregularities utilizing the essential clinical information. This framework further develops uniformity of findings, builds treatment outcomes, protects lives, and lessens price and time. As of late, few examinations have improved the computer-aided design frameworks for the executives of enormous clinical information for determination appraisal. This paper investigates the difficulties of tremendous clinical information giving. This article fundamentally evaluated and looked at the exhibition of existing AI and comprehensive learning approaches for identifying nervous system illnesses. A far-reaching piece of this concentration also shows different modalities and illness-determined datasets that identify and record pictures, signs, addresses, and so forth. Restricted related works are additionally summed up on nervous system illnesses, as this space has essentially less work zeroed in on illness and recognition rules. A portion of the standard assessment measurements is likewise introduced in this review for improved outcome examination.

Affinity scores: An individual-centric fingerprinting framework for neuropsychiatric disorders

Population-centric frameworks of biomarker identification for psychiatric disorders focus primarily on comparing averages between groups and assume that diagnostic groups are (1) mutually-exclusive, and (2) homogeneous. There is a paucity of individual-centric approaches capable of identifying individual-specific 'fingerprints' across multiple domains. To address this, we propose a novel framework, combining a range of biopsychosocial markers, including brain structure, cognition, and clinical markers, into higher-level 'fingerprints', capable of capturing intra-illness heterogeneity and inter-illness overlap. A multivariate framework was implemented to identify individualised patterns of brain structure, cognition and clinical markers based on affinity to other participants in the database. First, individual-level affinity scores defined each participant's "neighbourhood" across each measure based on variable-specific hop sizes. Next, diagnostic verification and classification algorithms were implemented based on multivariate affinity score profiles. To perform affinity-based classification, data were divided into training and test samples, and 5-fold nested cross-validation was performed on the training data. Affinity-based classification was compared to weighted K-nearest neighbours (KNN) classification. The framework was applied to the Australian Schizophrenia Research Bank (ASRB) dataset, which included data from individuals with chronic and treatment resistant schizophrenia and healthy controls. Individualised affinity scores provided a 'fingerprint' of brain structure, cognition, and clinical markers, which described the affinity of an individual to the representative groups in the dataset. Diagnostic verification capability was moderate to high depending on the choice of multivariate affinity metric. Affinity score-based classification achieved a high degree of accuracy in the training, nested cross-validation and prediction steps, and outperformed KNN classification in the training and test datasets. Affinity scores demonstrate utility in two keys ways: (1) Early and accurate diagnosis of neuropsychiatric disorders, whereby an individual can be grouped within a diagnostic category/ies that best matches their fingerprint, and (2) identification of biopsychosocial factors that most strongly characterise individuals/disorders, and which may be most amenable to intervention.

A Tensorized Multitask Deep Learning Network for Progression Prediction of Alzheimer’s Disease

With the advances in machine learning for the diagnosis of Alzheimer’s disease (AD), most studies have focused on either identifying the subject’s status through classification algorithms or on predicting their cognitive scores through regression methods, neglecting the potential association between these two tasks. Motivated by the need to enhance the prospects for early diagnosis along with the ability to predict future disease states, this study proposes a deep neural network based on modality fusion, kernelization, and tensorization that perform multiclass classification and longitudinal regression simultaneously within a unified multitask framework. This relationship between multiclass classification and longitudinal regression is found to boost the efficacy of the final model in dealing with both tasks. Different multimodality scenarios are investigated, and complementary aspects of the multimodal features are exploited to simultaneously delineate the subject’s label and predict related cognitive scores at future timepoints using baseline data. The main intent in this multitask framework is to consolidate the highest accuracy possible in terms of precision, sensitivity, F1 score, and area under the curve (AUC) in the multiclass classification task while maintaining the highest similarity in the MMSE score as measured through the correlation coefficient and the RMSE for all time points under the prediction task, with both tasks, run simultaneously under the same set of hyperparameters. The overall accuracy for multiclass classification of the proposed KTMnet method is 66.85 ± 3.77. The prediction results show an average RMSE of 2.32 ± 0.52 and a correlation of 0.71 ± 5.98 for predicting MMSE throughout the time points. These results are compared to state-of-the-art techniques reported in the literature. A discovery from the multitasking of this consolidated machine learning framework is that a set of hyperparameters that optimize the prediction results may not necessarily be the same as those that would optimize the multiclass classification. In other words, there is a breakpoint beyond which enhancing further the results of one process could lead to the downgrading in accuracy for the other.

Dual-Task Gait as a Predictive Tool for Cognitive Impairment in Older Adults: A Systematic Review

The use of the dual-task model as a cognitive-motor interface has been extensively investigated in cross-sectional studies as a training task in cognitive impairment. However, few existing longitudinal studies prove the usefulness of this tool as a clinical marker of cognitive impairment in older people. What is the evidence in prospective studies about dual-task gait as a predictor of cognitive impairment in older adults? This study aims to review and discuss the current state of knowledge in prospective studies on the use of dual-task gait as a predictive tool for cognitive impairment in older adults. The methodology used was a systematic review, according to the PRISMA criteria for the search, summarize and report. A search in 3 databases (Pubmed, Web of Science, and Scopus) was carried out until April 2021. The search terms used were: "(gait OR walking) AND (cognitive decline) AND (dual-task) AND (follow-up OR longitudinal OR long-term OR prospective OR cohort OR predict)." We included prospective research articles with older people with cognitive evaluation at the beginning and the end of the follow-up and dual-task gait paradigm as initial evaluation associated with the presentation of cognitive impairment prediction using any dual-task gait parameters. After exclusion criteria, 12 studies were reviewed. The results indicate that eight studies consider dual-task gait parameters a useful cognitive-motor tool, finding that some of the evaluated parameters of dual-task gait significantly correlate with cognitive impairment over time. The most promising DT parameters associated with cognitive impairment prediction seem to be gait speed, speed cost, DT time, numbers of words during DT, among others. In sum, this study reviews the variety of dual-task gait parameters and their relevance as a simple tool for early cognitive impairment screening, opening a diagnostic window for the screening of cognitive impairment in older people.

Assessing the Views of Professionals, Patients, and Care Partners Concerning the Use of Computer Tools in Memory Clinics: International Survey Study

Background

Computer tools based on artificial intelligence could aid clinicians in memory clinics in several ways, such as by supporting diagnostic decision-making, web-based cognitive testing, and the communication of diagnosis and prognosis.

Objective

This study aims to identify the preferences as well as the main barriers and facilitators related to using computer tools in memory clinics for all end users, that is, clinicians, patients, and care partners.

Methods

Between July and October 2020, we sent out invitations to a web-based survey to clinicians using the European Alzheimer’s Disease Centers network and the Dutch Memory Clinic network, and 109 clinicians participated (mean age 45 years, SD 10; 53/109, 48.6% female). A second survey was created for patients and care partners. They were invited via Alzheimer Europe, Alzheimer’s Society United Kingdom, Amsterdam Dementia Cohort, and Amsterdam Aging Cohort. A total of 50 patients with subjective cognitive decline, mild cognitive impairment, or dementia (mean age 73 years, SD 8; 17/34, 34% female) and 46 care partners (mean age 65 years, SD 12; 25/54, 54% female) participated in this survey.

Results

Most clinicians reported a willingness to use diagnostic (88/109, 80.7%) and prognostic (83/109, 76.1%) computer tools. User-friendliness (71/109, 65.1%); Likert scale mean 4.5, SD 0.7), and increasing diagnostic accuracy (76/109, 69.7%; mean 4.3, SD 0.7) were reported as the main factors stimulating the adoption of a tool. Tools should also save time and provide clear information on reliability and validity. Inadequate integration with electronic patient records (46/109, 42.2%; mean 3.8, SD 1.0) and fear of losing important clinical information (48/109, 44%; mean 3.7, SD 1.2) were most frequently indicated as barriers. Patients and care partners were equally positive about the use of computer tools by clinicians, both for diagnosis (69/96, 72%) and prognosis (73/96, 76%). In addition, most of them thought favorably regarding the possibility of using the tools themselves.

Conclusions

This study showed that computer tools in memory clinics are positively valued by most end users. For further development and implementation, it is essential to overcome the technical and practical barriers of a tool while paying utmost attention to its reliability and validity.

Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer's disease

Background

Although convolutional neural networks (CNNs) achieve high diagnostic accuracy for detecting Alzheimer’s disease (AD) dementia based on magnetic resonance imaging (MRI) scans, they are not yet applied in clinical routine. One important reason for this is a lack of model comprehensibility. Recently developed visualization methods for deriving CNN relevance maps may help to fill this gap as they allow the visualization of key input image features that drive the decision of the model. We investigated whether models with higher accuracy also rely more on discriminative brain regions predefined by prior knowledge.

Methods

We trained a CNN for the detection of AD in N = 663 T1-weighted MRI scans of patients with dementia and amnestic mild cognitive impairment (MCI) and verified the accuracy of the models via cross-validation and in three independent samples including in total N = 1655 cases. We evaluated the association of relevance scores and hippocampus volume to validate the clinical utility of this approach. To improve model comprehensibility, we implemented an interactive visualization of 3D CNN relevance maps, thereby allowing intuitive model inspection.

Results

Across the three independent datasets, group separation showed high accuracy for AD dementia versus controls (AUC ≥ 0.91) and moderate accuracy for amnestic MCI versus controls (AUC ≈ 0.74). Relevance maps indicated that hippocampal atrophy was considered the most informative factor for AD detection, with additional contributions from atrophy in other cortical and subcortical regions. Relevance scores within the hippocampus were highly correlated with hippocampal volumes (Pearson’s r ≈ −0.86, p < 0.001).

Conclusion

The relevance maps highlighted atrophy in regions that we had hypothesized a priori. This strengthens the comprehensibility of the CNN models, which were trained in a purely data-driven manner based on the scans and diagnosis labels. The high hippocampus relevance scores as well as the high performance achieved in independent samples support the validity of the CNN models in the detection of AD-related MRI abnormalities. The presented data-driven and hypothesis-free CNN modeling approach might provide a useful tool to automatically derive discriminative features for complex diagnostic tasks where clear clinical criteria are still missing, for instance for the differential diagnosis between various types of dementia.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13195-021-00924-2.

Technical and clinical validation of commercial automated volumetric MRI tools for dementia diagnosis-a systematic review

Developments in neuroradiological MRI analysis offer promise in enhancing objectivity and consistency in dementia diagnosis through the use of quantitative volumetric reporting tools (QReports). Translation into clinical settings should follow a structured framework of development, including technical and clinical validation steps. However, published technical and clinical validation of the available commercial/proprietary tools is not always easy to find and pathways for successful integration into the clinical workflow are varied. The quantitative neuroradiology initiative (QNI) framework highlights six necessary steps for the development, validation and integration of quantitative tools in the clinic. In this paper, we reviewed the published evidence regarding regulatory-approved QReports for use in the memory clinic and to what extent this evidence fulfils the steps of the QNI framework. We summarize unbiased technical details of available products in order to increase the transparency of evidence and present the range of reporting tools on the market. Our intention is to assist neuroradiologists in making informed decisions regarding the adoption of these methods in the clinic. For the 17 products identified, 11 companies have published some form of technical validation on their methods, but only 4 have published clinical validation of their QReports in a dementia population. Upon systematically reviewing the published evidence for regulatory-approved QReports in dementia, we concluded that there is a significant evidence gap in the literature regarding clinical validation, workflow integration and in-use evaluation of these tools in dementia MRI diagnosis.

Gait Disturbances are Associated with Increased Cognitive Impairment and Cerebrospinal Fluid Tau Levels in a Memory Clinic Cohort

Background:

Gait analysis with accelerometers is a relatively inexpensive and easy to use method to potentially support clinical diagnoses of Alzheimer’s disease and other dementias. It is not clear, however, which gait features are most informative and how these measures relate to Alzheimer’s disease pathology.

Objective:

In this study, we tested if calculated features of gait 1) differ between cognitively normal subjects (CN), mild cognitive impairment (MCI) patients, and dementia patients, 2) are correlated with cerebrospinal fluid (CSF) biomarkers related to Alzheimer’s disease, and 3) predict cognitive decline.

Methods:

Gait was measured using tri-axial accelerometers attached to the fifth lumbar vertebra (L5) in 58 CN, 58 MCI, and 26 dementia participants, while performing a walk and dual task. Ten gait features were calculated from the vertical L5 accelerations, following principal component analysis clustered in four domains, namely pace, rhythm, time variability, and length variability. Cognitive decline over time was measured using MMSE, and CSF biomarkers were available in a sub-group.

Results:

Linear mixed models showed that dementia patients had lower pace scores than MCI patients and CN subjects (p < 0.05). In addition, we found associations between the rhythm domain and CSF-tau, especially in the dual task. Gait was not associated with CSF Aβ₄₂ levels and cognitive decline over time as measured with the MMSE.

Conclusion:

These findings suggest that gait — particularly measures related to pace and rhythm — are altered in dementia and have a direct link with measures of neurodegeneration.

Evaluation of machine learning algorithms for health and wellness applications: A tutorial

Research on decision support applications in healthcare, such as those related to diagnosis, prediction, treatment planning, etc., has seen strongly growing interest in recent years. This development is thanks to the increase in data availability as well as to advances in artificial intelligence and machine learning research and access to computational resources. Highly promising research examples are published daily. However, at the same time, there are some unrealistic, often overly optimistic, expectations and assumptions with regard to the development, validation and acceptance of such methods. The healthcare application field introduces requirements and potential pitfalls that are not immediately obvious from the 'general data science' viewpoint. Reliable, objective, and generalisable validation and performance assessment of developed data-analysis methods is one particular pain-point. This may lead to unmet schedules and disappointments regarding true performance in real-life with as result poor uptake (or non-uptake) at the end-user side. It is the aim of this tutorial to provide practical guidance on how to assess performance reliably and efficiently and avoid common traps especially when dealing with application for health and wellness settings. Instead of giving a list of do's and don't s, this tutorial tries to build a better understanding behind these issues and presents both the most relevant performance evaluation criteria as well as approaches how to compute them. Along the way, we will indicate common mistakes and provide references discussing various topics more in-depth.

Detecting Amyloid Positivity in Elderly With Increased Risk of Cognitive Decline

The importance of early interventions in Alzheimer's disease (AD) emphasizes the need to accurately and efficiently identify at-risk individuals. Although many dementia prediction models have been developed, there are fewer studies focusing on detection of brain pathology. We developed a model for identification of amyloid-PET positivity using data on demographics, vascular factors, cognition, APOE genotype, and structural MRI, including regional brain volumes, cortical thickness and a visual medial temporal lobe atrophy (MTA) rating. We also analyzed the relative importance of different factors when added to the overall model. The model used baseline data from the Finnish Geriatric Intervention Study to Prevent Cognitive Impairment and Disability (FINGER) exploratory PET sub-study. Participants were at risk for dementia, but without dementia or cognitive impairment. Their mean age was 71 years. Participants underwent a brain 3T MRI and PiB-PET imaging. PiB images were visually determined as positive or negative. Cognition was measured using a modified version of the Neuropsychological Test Battery. Body mass index (BMI) and hypertension were used as cardiovascular risk factors in the model. Demographic factors included age, gender and years of education. The model was built using the Disease State Index (DSI) machine learning algorithm. Of the 48 participants, 20 (42%) were rated as Aβ positive. Compared with the Aβ negative group, the Aβ positive group had a higher proportion of APOE ε4 carriers (53 vs. 14%), lower executive functioning, lower brain volumes, and higher visual MTA rating. AUC [95% CI] for the complete model was 0.78 [0.65-0.91]. MRI was the most effective factor, especially brain volumes and visual MTA rating but not cortical thickness. APOE was nearly as effective as MRI in improving detection of amyloid positivity. The model with the best performance (AUC 0.82 [0.71-0.93]) was achieved by combining APOE and MRI. Our findings suggest that combining demographic data, vascular risk factors, cognitive performance, APOE genotype, and brain MRI measures can help identify Aβ positivity. Detecting amyloid positivity could reduce invasive and costly assessments during the screening process in clinical trials.

Potential New Approaches for Diagnosis of Alzheimer's Disease and Related Dementias

Dementia is an umbrella term-caused by a large number of specific diagnoses, including several neurodegenerative disorders. Alzheimer's disease (AD) is now the most common cause of dementia in advanced countries, while dementia due to neurosyphilis was the leading cause a century ago. Many challenges remain for diagnosing dementia definitively. Some of these include variability of early symptoms and overlap with similar disorders, as well as the possibility of combined, or mixed, etiologies in some cases. Newer technologies, including the incorporation of PET neuroimaging and other biomarkers (genomics and proteomics), are being incorporated into revised diagnostic criteria. However, the application of novel diagnostic methods at clinical sites is plagued by many caveats including availability and access. This review surveys new diagnostic methods as well as remaining challenges-for clinical care and clinical research.

Evaluating 2-[18F]FDG-PET in differential diagnosis of dementia using a data-driven decision model

•

Addition of 2-[¹⁸F]FDG-PET to common diagnostic tests improved the accuracy for DLB and FTD.

•

Two new 2-[¹⁸F]FDG-PET biomarkers demonstrated specific disease patterns for DLB and FTD.

•

Different combinations of diagnostic tests were valuable for each subtype of dementia.

2-[¹⁸F]fluoro-2-deoxy-d-glucose positron emission tomography (2-[¹⁸F]FDG-PET) has an emerging supportive role in dementia diagnostic as distinctive metabolic patterns are specific for Alzheimer's disease (AD), dementia with Lewy bodies (DLB) and frontotemporal dementia (FTD). Previous studies have demonstrated that a data-driven decision model based on the disease state index (DSI) classifier supports clinicians in the differential diagnosis of dementia by using different combinations of diagnostic tests and biomarkers. Until now, this model has not included 2-[¹⁸F]FDG-PET data.

The objective of the study was to evaluate 2-[¹⁸F]FDG-PET biomarkers combined with commonly used diagnostic tests in the differential diagnosis of dementia using the DSI classifier.

We included data from 259 subjects diagnosed with AD, DLB, FTD, vascular dementia (VaD), and subjective cognitive decline from two independent study cohorts. We also evaluated three 2-[¹⁸F]FDG-PET biomarkers (anterior vs. posterior index (API-PET), occipital vs. temporal index, and cingulate island sign) to improve the classification accuracy for both FTD and DLB.

We found that the addition of 2-[¹⁸F]FDG-PET biomarkers to cognitive tests, CSF and MRI biomarkers considerably improved the classification accuracy for all pairwise comparisons of DLB (balanced accuracies: DLB vs. AD from 64% to 77%; DLB vs. FTD from 71% to 92%; and DLB vs. VaD from 71% to 84%). The two 2-[¹⁸F]FDG-PET biomarkers, API-PET and occipital vs. temporal index, improved the accuracy for FTD and DLB, especially as compared to AD. Moreover, different combinations of diagnostic tests were valuable to differentiate specific subtypes of dementia.

In conclusion, this study demonstrated that the addition of 2-[¹⁸F]FDG-PET to commonly used diagnostic tests provided complementary information that may help clinicians in diagnosing patients, particularly for differentiating between patients with FTD, DLB, and AD.

Impact of a Clinical Decision Support Tool on Dementia Diagnostics in Memory Clinics: The PredictND Validation Study

BACKGROUND

Determining the underlying etiology of dementia can be challenging. Computer- based Clinical Decision Support Systems (CDSS) have the potential to provide an objective comparison of data and assist clinicians.

OBJECTIVES

To assess the diagnostic impact of a CDSS, the PredictND tool, for differential diagnosis of dementia in memory clinics.

METHODS

In this prospective multicenter study, we recruited 779 patients with either subjective cognitive decline (n=252), mild cognitive impairment (n=219) or any type of dementia (n=274) and followed them for minimum 12 months. Based on all available patient baseline data (demographics, neuropsychological tests, cerebrospinal fluid biomarkers, and MRI visual and computed ratings), the PredictND tool provides a comprehensive overview and analysis of the data with a likelihood index for five diagnostic groups; Alzheimer´s disease, vascular dementia, dementia with Lewy bodies, frontotemporal dementia and subjective cognitive decline. At baseline, a clinician defined an etiological diagnosis and confidence in the diagnosis, first without and subsequently with the PredictND tool. The follow-up diagnosis was used as the reference diagnosis.

RESULTS

In total, 747 patients completed the follow-up visits (53% female, 69±10 years). The etiological diagnosis changed in 13% of all cases when using the PredictND tool, but the diagnostic accuracy did not change significantly. Confidence in the diagnosis, measured by a visual analogue scale (VAS, 0-100%) increased (ΔVAS=3.0%, p<0.0001), especially in correctly changed diagnoses (ΔVAS=7.2%, p=0.0011).

CONCLUSION

Adding the PredictND tool to the diagnostic evaluation affected the diagnosis and increased clinicians' confidence in the diagnosis indicating that CDSSs could aid clinicians in the differential diagnosis of dementia.

Selection of memory clinic patients for CSF biomarker assessment can be restricted to a quarter of cases by using computerized decision support, without compromising diagnostic accuracy

INTRODUCTION

An accurate and timely diagnosis for Alzheimer's disease (AD) is important, both for care and research. The current diagnostic criteria allow the use of CSF biomarkers to provide pathophysiological support for the diagnosis of AD. How these criteria should be operationalized by clinicians is unclear. Tools that guide in selecting patients in which CSF biomarkers have clinical utility are needed. We evaluated computerized decision support to select patients for CSF biomarker determination.

METHODS

We included 535 subjects (139 controls, 286 Alzheimer's disease dementia, 82 frontotemporal dementia and 28 vascular dementia) from three clinical cohorts. Positive (AD like) and negative (normal) CSF biomarker profiles were simulated to estimate whether knowledge of CSF biomarkers would impact (confidence in) diagnosis. We applied these simulated CSF values and combined them with demographic, neuropsychology and MRI data to initiate CSF testing (computerized decision support approach). We compared proportion of CSF measurements and patients diagnosed with sufficient confidence (probability of correct class ≥0.80) based on an algorithm with scenarios without CSF (only neuropsychology, MRI and APOE), CSF according to the appropriate use criteria (AUC) and CSF for all patients.

RESULTS

The computerized decision support approach recommended CSF testing in 140 (26%) patients, which yielded a diagnosis with sufficient confidence in 379 (71%) of all patients. This approach was more efficient than CSF in none (0% CSF, 308 (58%) diagnosed), CSF selected based on AUC (295 (55%) CSF, 350 (65%) diagnosed) or CSF in all (100% CSF, 348 (65%) diagnosed).

CONCLUSIONS

We used a computerized decision support with simulated CSF results in controls and patients with different types of dementia. This approach can support clinicians in making a balanced decision in ordering additional biomarker testing. Computer-supported prediction restricts CSF testing to only 26% of cases, without compromising diagnostic accuracy.

Impact of a clinical decision support tool on prediction of progression in early-stage dementia: a prospective validation study

Background

In clinical practice, it is often difficult to predict which patients with cognitive complaints or impairment will progress or remain stable. We assessed the impact of using a clinical decision support system, the PredictND tool, to predict progression in patients with subjective cognitive decline (SCD) and mild cognitive impairment (MCI) in memory clinics.

Methods

In this prospective multicenter study, we included 429 patients with SCD (n = 230) and MCI (n = 199) (female 54%, age 67 ± 9, MMSE 28 ± 2) and followed them for at least 12 months. Based on all available patient baseline data (demographics, cognitive tests, cerebrospinal fluid biomarkers, and MRI), the PredictND tool provides a comprehensive overview of the data and a classification defining the likelihood of progression. At baseline, a clinician defined an expected follow-up diagnosis and estimated the level of confidence in their prediction using a visual analogue scale (VAS, 0–100%), first without and subsequently with the PredictND tool. As outcome measure, we defined clinical progression as progression from SCD to MCI or dementia, and from MCI to dementia. Correspondence between the expected and the actual clinical progression at follow-up defined the prognostic accuracy.

Results

After a mean follow-up time of 1.7 ± 0.4 years, 21 (9%) SCD and 63 (32%) MCI had progressed. When using the PredictND tool, the overall prognostic accuracy was unaffected (0.4%, 95%CI − 3.0%; + 3.9%; p = 0.79). However, restricting the analysis to patients with more certain classifications (n = 203), we found an increase of 3% in the accuracy (95%CI − 0.6%; + 6.5%; p = 0.11). Furthermore, for this subgroup, the tool alone showed a statistically significant increase in the prognostic accuracy compared to the evaluation without tool (6.4%, 95%CI 2.1%; 10.7%; p = 0.004). Specifically, the negative predictive value was high. Moreover, confidence in the prediction increased significantly (∆VAS = 4%, p < .0001).

Conclusions

Adding the PredictND tool to the clinical evaluation increased clinicians’ confidence. Furthermore, the results indicate that the tool has the potential to improve prediction of progression for patients with more certain classifications.

Electronic supplementary material

The online version of this article (10.1186/s13195-019-0482-3) contains supplementary material, which is available to authorized users.

Computer-assisted prediction of clinical progression in the earliest stages of AD

Introduction

Individuals with subjective cognitive decline (SCD) are at increased risk for clinical progression. We studied how combining different diagnostic tests can help to identify individuals who are likely to show clinical progression.

Methods

We included 674 patients with SCD (46% female, 64 ± 9 years, Mini-Mental State Examination 28 ± 2) from three memory clinic cohorts. A multivariate model based on the Disease State Index classifier incorporated the available baseline tests to predict progression to MCI or dementia over time. We developed and internally validated the model in one cohort and externally validated it in the other cohorts.

Results

After 2.9 ± 2.0 years, 151(22%) patients showed clinical progression. Overall performance of the classifier when combining cognitive tests, magnetic resonance imagining, and cerebrospinal fluid showed a balanced accuracy of 74.0 ± 5.5, with high negative predictive value (93.3 ± 2.8).

Discussion

We found that a combination of diagnostic tests helps to identify individuals at risk of progression. The classifier had particularly good accuracy in identifying patients who remained stable.

Evaluating combinations of diagnostic tests to discriminate different dementia types

Introduction

We studied, using a data-driven approach, how different combinations of diagnostic tests contribute to the differential diagnosis of dementia.

Methods

In this multicenter study, we included 356 patients with Alzheimer's disease, 87 frontotemporal dementia, 61 dementia with Lewy bodies, 38 vascular dementia, and 302 controls. We used a classifier to assess accuracy for individual performance and combinations of cognitive tests, cerebrospinal fluid biomarkers, and automated magnetic resonance imaging features for pairwise differentiation between dementia types.

Results

Cognitive tests had good performance in separating any type of dementia from controls. Cerebrospinal fluid optimally contributed to identifying Alzheimer's disease, whereas magnetic resonance imaging features aided in separating vascular dementia, dementia with Lewy bodies, and frontotemporal dementia. Combining diagnostic tests increased the accuracy, with balanced accuracies ranging from 78% to 97%.

Discussion

Different diagnostic tests have their distinct roles in differential diagnostics of dementias. Our results indicate that combining different diagnostic tests may increase the accuracy further.