Barnard, Leland R

Abstract Nerve conduction F-wave studies contain crucial information about subclinical motor dysfunction that can be used to diagnose patients with amyotrophic lateral sclerosis (ALS). However, F-wave responses are highly variable in morphology, making waveform interpretation challenging. Artificial intelligence techniques can extract time–frequency features to provide new insights into ALS diagnosis and prognosis. A retrospective analysis was performed on F-wave responses from 46 802 patients. Discrete wavelet transforms were applied to time-series waveform responses after stimulating ulnar, median, fibular and tibial nerves. Wavelet coefficient statistics, onset age, sex and body mass index were features for training a Gradient Boosting Machine model on 40 095 patients (5329 diagnosed with motor neuron disease). Model performance was tested on responses from 689 ALS patients meeting Gold Coast criteria and 689 age- and sex-matched controls. An exploratory analysis examined model performance on cohorts of patients with inclusion body myositis, cervical radiculopathy, lumbar radiculopathy or peripheral neuropathy, which can mimic ALS symptoms. Factors affecting survival were estimated through Cox proportional hazards regression. The model trained using wavelet features on the full waveform had 90% recall, 87% precision and 88% accuracy. Similar model performance was measured using features from only the M-wave or F-wave. Classification probabilities for ALS patients were statistically different from the diagnoses mimicking ALS symptoms (P < 0.001, ANOVA, Tukey’s post hoc test). Higher model classification probabilities of ALS, older age at onset, and family history of ALS alone or with frontotemporal dementia were factors decreasing survival. Longer diagnostic delay and upper limb onset site were factors increasing survival. Model scores two standard deviations below the mean had 4 months increased survival (two standard deviations below had 3 months decreased survival). Artificial intelligence techniques extracted important information from F-wave responses to estimate a patient’s likelihood of ALS and their survival risks. Although the model can make predictions at a specific decision threshold as presented here, the true strength of such a model lies in its ability to provide probabilities about whether a patient is likely to have ALS in comparison to other mimicking diagnoses, such as inclusion body myositis, cervical or lumbar radiculopathy or peripheral neuropathy. These probabilities provide clinicians with additional information that they can use to make the final diagnosis with greater confidence and precision. Integrating such a model into the clinical workflow could help clinicians to diagnose ALS sooner and manage treatment based on estimated survival, which might improve outcomes and the quality of life of patients.

AbstractBackgroundMany proposed clinical decision support systems (CDSS) require multiple disparate data elements as input, which makes implementation difficult, and furthermore have a black‐box nature leading to low interpretability. Fluorodeoxyglucose Positron Emission Tomography (FDG‐PET) is an established modality for the diagnosis of dementia, and a CDSS that uses only an FDG‐PET image to produce a reliable and understandable result would ease both of these challenges to clinical application.MethodA deep variational autoencoder (VAE) was used to extract a latent representation of each image through prior training from FDG‐PET brain images (n=2000). This unsupervised VAE has a novel graph convolutional architecture that makes it applicable to masked template space images. A logistic regression model was used to classify each image. A parametric study of the latent space revealed the imaging features that were used in the logistic regression model to differentiate each class. A separate dataset of participants labeled with their clinical diagnosis (n=1239) was used to assess the logistic regression model’s diagnostic accuracy of cognitively unimpaired (CU) (n=679) and between common dementia subtypes: Alzheimer’s disease (AD) (n=310), Lewy body dementia (DLB) (n=151), and behavioral variant frontotemporal dementia (bvFTD) (n=99). The logistic regression classifier was evaluated using receiver‐operator characteristic (ROC‐AUC) curves.ResultROC‐AUC curves for CU and each dementia subtype are illustrated in Figure 1a. A k nearest neighbors model was used to develop a graphical representation of the latent space where nodes are images and edges are drawn between nearest neighbors, illustrated in Figure 1b. The graph of the latent space demonstrates a comparison between dementia subtypes and CU images.ConclusionIn this study, we developed a proof‐of‐concept VAE that can achieve differential diagnosis with 84.8% balanced accuracy. The model architecture provides visual interpretability, and shows that the hippocampi, parietal lobes, and cerebellum, were useful for distinguishing AD, the frontal lobe, posterior cingulate cortex, and hippocampi were useful for distinguishing DLB, and prefrontal pole, subcortical structures, and occipital lobe were useful for distinguishing bvFTD. These regions of metabolism align with clinical pathology and metabolic patterns.

Abstract Background Many proposed clinical decision support systems (CDSS) require multiple disparate data elements as input, which makes implementation difficult, and furthermore have a black‐box nature leading to low interpretability. Fluorodeoxyglucose Positron Emission Tomography (FDG‐PET) is an established modality for the diagnosis of dementia, and a CDSS that uses only an FDG‐PET image to produce a reliable and understandable result would ease both of these challenges to clinical application. Method A deep variational autoencoder (VAE) was used to extract a latent representation of each image through prior training from FDG‐PET brain images (n=2000). This unsupervised VAE has a novel graph convolutional architecture that makes it applicable to masked template space images. A logistic regression model was used to classify each image. A parametric study of the latent space revealed the imaging features that were used in the logistic regression model to differentiate each class. A separate dataset of participants labeled with their clinical diagnosis (n=1239) was used to assess the logistic regression model’s diagnostic accuracy of cognitively unimpaired (CU) (n=679) and between common dementia subtypes: Alzheimer’s disease (AD) (n=310), Lewy body dementia (DLB) (n=151), and behavioral variant frontotemporal dementia (bvFTD) (n=99). The logistic regression classifier was evaluated using receiver‐operator characteristic (ROC‐AUC) curves. Result ROC‐AUC curves for CU and each dementia subtype are illustrated in Figure 1a. A k nearest neighbors model was used to develop a graphical representation of the latent space where nodes are images and edges are drawn between nearest neighbors, illustrated in Figure 1b. The graph of the latent space demonstrates a comparison between dementia subtypes and CU images. Conclusion In this study, we developed a proof‐of‐concept VAE that can achieve differential diagnosis with 84.8% balanced accuracy. The model architecture provides visual interpretability, and shows that the hippocampi, parietal lobes, and cerebellum, were useful for distinguishing AD, the frontal lobe, posterior cingulate cortex, and hippocampi were useful for distinguishing DLB, and prefrontal pole, subcortical structures, and occipital lobe were useful for distinguishing bvFTD. These regions of metabolism align with clinical pathology and metabolic patterns.

AbstractObjectivePrion disease classically presents with rapidly progressive dementia, leading to death within months of diagnosis. Advances in diagnostic testing have improved recognition of patients with atypical presentations and protracted disease courses, raising key questions surrounding the relationship between patterns of neurodegeneration and survival. We assessed the contribution of fluorodeoxyglucose (FDG‐PET) imaging for this purpose.MethodsFDG‐PET were performed in 40 clinic patients with prion disease. FDG‐PET images were projected onto latent factors generated in an external dataset to yield patient‐specific eigenvalues. Eigenvalues were input into a clustering algorithm to generate data‐driven clusters, which were compared by survival time.ResultsMedian age at FDG‐PET was 65.3 years (range 23–85). Median time from FDG‐PET to death was 3.7 months (range 0.3–19.0). Four data‐driven clusters were generated, termed “Neocortical” (n = 7), “Transitional” (n = 12), “Temporo‐parietal” (n = 13), and “Deep nuclei” (n = 6). Deep nuclei and transitional clusters had a shorter survival time than the neocortical cluster. Subsequent analyses suggested that this difference was driven by greater hypometabolism of deep nuclei relative to neocortical areas. FDG‐PET‐patterns were not associated with demographic (age and sex) or clinical (CSF total‐tau, 14‐3‐3) variables.InterpretationGreater hypometabolism within deep nuclei relative to neocortical areas associated with more rapid decline in patients with prion disease and vice versa. FDG‐PET informs large‐scale network physiology and may inform the relationship between spreading pathology and survival in patients with prion disease. Future studies should consider whether FDG‐PET may enrich multimodal prion disease prognostication models.

Abstract Electrophysiologic disturbances due to neurodegenerative disorders such as Alzheimer’s disease and Lewy Body disease are detectable by scalp EEG and can serve as a functional measure of disease severity. Traditional quantitative methods of EEG analysis often require an a-priori selection of clinically meaningful EEG features and are susceptible to bias, limiting the clinical utility of routine EEGs in the diagnosis and management of neurodegenerative disorders. We present a data-driven tensor decomposition approach to extract the top 6 spectral and spatial features representing commonly known sources of EEG activity during eyes-closed wakefulness. As part of their neurologic evaluation at Mayo Clinic, 11 001 patients underwent 12 176 routine, standard 10–20 scalp EEG studies. From these raw EEGs, we developed an algorithm based on posterior alpha activity and eye movement to automatically select awake-eyes-closed epochs and estimated average spectral power density (SPD) between 1 and 45 Hz for each channel. We then created a three-dimensional (3D) tensor (record × channel × frequency) and applied a canonical polyadic decomposition to extract the top six factors. We further identified an independent cohort of patients meeting consensus criteria for mild cognitive impairment (30) or dementia (39) due to Alzheimer’s disease and dementia with Lewy Bodies (31) and similarly aged cognitively normal controls (36). We evaluated the ability of the six factors in differentiating these subgroups using a Naïve Bayes classification approach and assessed for linear associations between factor loadings and Kokmen short test of mental status scores, fluorodeoxyglucose (FDG) PET uptake ratios and CSF Alzheimer’s Disease biomarker measures. Factors represented biologically meaningful brain activities including posterior alpha rhythm, anterior delta/theta rhythms and centroparietal beta, which correlated with patient age and EEG dysrhythmia grade. These factors were also able to distinguish patients from controls with a moderate to high degree of accuracy (Area Under the Curve (AUC) 0.59–0.91) and Alzheimer’s disease dementia from dementia with Lewy Bodies (AUC 0.61). Furthermore, relevant EEG features correlated with cognitive test performance, PET metabolism and CSF AB42 measures in the Alzheimer’s subgroup. This study demonstrates that data-driven approaches can extract biologically meaningful features from population-level clinical EEGs without artefact rejection or a-priori selection of channels or frequency bands. With continued development, such data-driven methods may improve the clinical utility of EEG in memory care by assisting in early identification of mild cognitive impairment and differentiating between different neurodegenerative causes of cognitive impairment.