Parkinson's disease - current treatment.

PURPOSE OF REVIEW: The purpose is to review the results and impact of recent studies for current and future treatment of both motor and non-motor symptoms in Parkinson's disease (PD). RECENT FINDINGS: New formulations of levodopa further optimize motor fluctuations, allowing for more on-time and less dyskinesia. On demand apomorphine continues to showcase itself as an effective and tolerable tool for treating motor off-periods. Though there are no clear treatment guidelines for PD-related constipation and sleep related disorders, several new agents for these non-motor symptoms show promising preliminary data. Expiratory muscle strength training may represent a useful and cost-effective strategy to alleviate oropharyngeal dysphagia associated with PD. There is evidence to suggest that the use of shorter pulse width and directional deep brain stimulation leads can results in a greater therapeutic window. SUMMARY: Though no interventions currently exist to significantly modify the disease progression of PD, new studies continue to give insight into optimal symptomatic management. Clinicians should be familiar with expanding the repertoire of tools available to treat the diverse range of symptoms and challenges associated with PD.

Global Epidemiology of Movement Disorders: Rare or Underdiagnosed?

In this manuscript, we review the epidemiology of movement disorders including Parkinson's disease (PD), atypical parkinsonism, essential tremor, dystonia, functional movement disorders, tic disorders, chorea, and ataxias. We emphasize age-, sex-, and geography-based incidence and prevalence, as well as notable trends including the rising incidence and prevalence of PD. Given the growing global interest in refining clinical diagnostic skills in recognizing movement disorders, we highlight some key epidemiological findings that may be of interest to clinicians and health systems tasked with diagnosing and managing the health of patients with movement disorders.

Mapping holmes tremor circuit using the human brain connectome.

OBJECTIVE: Holmes tremor is a debilitating movement disorder with limited treatment options. Lesions causing Holmes tremor can occur in multiple different brain locations, leaving the neuroanatomical substrate unclear. Here, we test whether lesion locations that cause Holmes tremor map to a connected brain circuit and whether this circuit might serve as a useful therapeutic target. METHODS: Case reports of Holmes tremor caused by focal brain lesions were identified through a systematic literature search. Connectivity between each lesion location and the rest of the brain was computed using resting state functional connectivity magnetic resonance imaging data from 1,000 healthy volunteers. Commonalities across lesion locations were identified. This Holmes tremor circuit was then compared to neurosurgical treatment targets and clinical efficacy. RESULTS: We identified 36 lesions causing Holmes tremor, which were scattered across multiple different brain regions. However, all lesion locations were connected to a common brain circuit with nodes in the red nucleus, thalamus, globus pallidus, and cerebellum. In cases with effective neurosurgical treatment, the treatment target was connected with the lesion location, indicating that a second hit to the same circuit might be beneficial. Commonly used deep brain stimulation targets such as the ventral intermediate nucleus and subthalamic nucleus fell outside our Holmes tremor circuit, whereas the globus pallidus target was close, consistent with published clinical response rates for these targets. INTERPRETATION: Lesions causing Holmes tremor are part of a single connected brain circuit that may serve as an improved therapeutic target. ANN NEUROL 2019;86:812-820.

Identifying therapeutic targets from spontaneous beneficial brain lesions.

Brain damage can occasionally result in paradoxical functional benefit, which could help identify therapeutic targets for neuromodulation. However, these beneficial lesions are rare and lesions in multiple different brain locations can improve the same symptom. Using a technique called lesion network mapping, we show that heterogeneous lesion locations resulting in tremor relief are all connected to common nodes in the cerebellum and thalamus, the latter of which is a proven deep brain stimulation target for tremor. These results suggest that lesion network mapping can identify the common substrate underlying therapeutic lesions and effective therapeutic targets. Ann Neurol 2018;83:153-157.

Clinical Impact of 123I-Ioflupane SPECT (DaTscan) in a Movement Disorder Center.

BACKGROUND/AIMS: The clinical diagnosis of degenerative forms of parkinsonism is imperfect, with past studies reporting a high rate of misdiagnosis by neurologists and movement disorder specialists, particularly early in the disease course. 123I-ioflupane SPECT (DaTscan) is a diagnostic neuroimaging tool used to distinguish essential tremor from tremor due to degenerative parkinsonisms. The present study expands upon prior studies of the clinical impact of DaTscan imaging in movement disorder centers by assessing quantitative estimates of diagnostic certainty, the impact on subsequent clinical decisions, and the degree to which the asymmetry in the results corresponds to laterality by clinical history and examination. METHODS: In a prospective, observational study of the impact of DaTscan imaging in a movement disorder center over the course of 18 months, 4 specialists completed a questionnaire at the time they ordered imaging and again within 1 month after imaging. RESULTS: Twenty-seven patients underwent DaTscan imaging; the result was normal in 4 cases (14.8%), abnormal in 22 cases (81.4%), and equivocal in 1 case (3.7%). In all cases of a normal result, the post-scan-predicted chance of degenerative parkinsonism decreased compared to the pre-scan prediction (p < 0.05), and in all cases of abnormal scan, the post-scan chance of degenerative parkinsonism increased or remained high (p < 0.0001). Clinical impacts were observed following imaging in a total of 24 patients (88.9%), including changes in medications for 18 patients and psychological impacts for 11 patients. Asymmetric clinical symptoms were corroborated based on the expected asymmetry of dopamine uptake deficits in 57.1% of the cases, were not present in 23.8%, and were opposite of expectations in 19.0% of the scans. CONCLUSION: DaTscan imaging results have an impact on physician's confidence in the diagnosis of parkinsonism and may also have a psychological impact on patients. DaTscan imaging may be a useful adjunct to clinical history and examination in selected patients.

Clinical and demographic characteristics related to onset site and spread of cervical dystonia.

BACKGROUND: Clinical characteristics of isolated idiopathic cervical dystonia such as onset site and spread to and from additional body regions have been addressed in single-site studies with limited data and incomplete or variable dissociation of focal and segmental subtypes. The objectives of this study were to characterize the clinical characteristics and demographics of isolated idiopathic cervical dystonia in the largest standardized multicenter cohort. METHODS: The Dystonia Coalition, through a consortium of 37 recruiting sites in North America, Europe, and Australia, recruited 1477 participants with focal (60.7%) or segmental (39.3%) cervical dystonia on examination. Clinical and demographic characteristics were evaluated in terms of the body region of dystonia onset and spread. RESULTS: Site of dystonia onset was: (1) focal neck only (78.5%), (2) focal onset elsewhere with later segmental spread to neck (13.3%), and (3) segmental onset with initial neck involvement (8.2%). Frequency of spread from focal cervical to segmental dystonia (22.8%) was consistent with prior reports, but frequency of segmental onset with initial neck involvement was substantially higher than the 3% previously reported. Cervical dystonia with focal neck onset, more than other subtypes, was associated with spread and tremor of any type. Sensory tricks were less frequent in cervical dystonia with segmental components, and segmental cervical onset occurred at an older age. CONCLUSIONS: Subgroups had modest but significant differences in the clinical characteristics that may represent different clinical entities or pathophysiologic subtypes. These findings are critical for design and implementation of studies to describe, treat, or modify disease progression in idiopathic isolated cervical dystonia. © 2016 International Parkinson and Movement Disorder Society.

Three-dimensional brain MRI for DBS patients within ultra-low radiofrequency power limits.

BACKGROUND: For patients with deep brain stimulators (DBS), local absorbed radiofrequency (RF) power is unknown and is much higher than what the system estimates. We developed a comprehensive, high-quality brain magnetic resonance imaging (MRI) protocol for DBS patients utilizing three-dimensional (3D) magnetic resonance sequences at very low RF power. METHODS: Six patients with DBS were imaged (10 sessions) using a transmit/receive head coil at 1.5 Tesla with modified 3D sequences within ultra-low specific absorption rate (SAR) limits (0.1 W/kg) using T2 , fast fluid-attenuated inversion recovery (FLAIR) and T1 -weighted image contrast. Tissue signal and tissue contrast from the low-SAR images were subjectively and objectively compared with routine clinical images of six age-matched controls. RESULTS: Low-SAR images of DBS patients demonstrated tissue contrast comparable to high-SAR images and were of diagnostic quality except for slightly reduced signal. CONCLUSIONS: Although preliminary, we demonstrated diagnostic quality brain MRI with optimized, volumetric sequences in DBS patients within very conservative RF safety guidelines offering a greater safety margin.

Neutrophil-to-lymphocyte ratio and longitudinal cognitive performance in Parkinson's disease.

OBJECTIVE: Previous studies have suggested a link between peripheral inflammation and cognitive outcomes in the general population and individuals with Parkinson's disease (PD). We sought to test the association between peripheral inflammation, measured by the neutrophil-to-lymphocyte ratio (NLR), cognitive performance, and mild cognitive impairment (MCI) status in individuals with PD. METHODS: A retrospective, longitudinal analysis was carried out using data from the Parkinson's Progression Markers Initiative (PPMI), including 422 participants with PD followed over 5 years. Cognitive performance was assessed using a neuropsychological battery including the Montreal Cognitive Assessment (MoCA) and tests of verbal learning, visuospatial function, processing speed, and executive function. Mixed-effect regression models were used to analyze the association between NLR, cognitive performance, and MCI status, controlling for age, sex, education, APOE genotype, and motor severity. RESULTS: There was a negative association between NLR and MoCA, even after adjusting for covariates (b = -0.12, p = 0.033). MoCA scores for individuals in the high NLR category exhibited a more rapid decline over time compared to the low NLR group (b = -0.16, p = 0.012). Increased NLR was associated with decreased performance across all cognitive domains. However, NLR was not associated with MCI status over 5 years of follow-up. INTERPRETATION: This study demonstrates a link between elevated NLR and cognitive performance in PD, but not with MCI status over 5 years. This suggests that NLR is more strongly associated with day-to-day cognitive performance than with incident MCI, but this requires further study in more heterogeneous cohorts.

Associations Among Tremor Amplitude, Activities of Daily Living, and Quality of Life in Patients with Essential Tremor.

Background: Essential tremor (ET) is a disabling syndrome consisting of tremor, primarily in the upper limbs. We assessed the correlation of The Essential Tremor Rating Assessment Scale (TETRAS) Performance Item 4 ratings of upper limb tremor with the TETRAS activities of daily living (ADL) subscale and with 2 quality of life (QoL) scales. Methods: This noninterventional, cross-sectional, point-in-time survey of neurologists(n = 60), primary care physicians (n = 38), and their patients with ET (n = 1,003) used real-world data collected through the Adelphi ET Disease Specific Programme™. Physician-reported measures (TETRAS Performance Item 4 and TETRAS ADL total) and patient-reported QoL measures (generic EuroQol-5 Dimension 5 Level [EQ-5D-5 L] and ET-specific Quality of Life in Essential Tremor Questionnaire (QUEST)) were assessed with bivariate and multivariable analyses. Sensitivity analyses were also conducted. Results: The bivariate association between TETRAS Performance Item 4 score and TETRAS ADL total score was high (Pearson r = 0.761, P < 0.001). The bivariate associations between TETRAS Performance Item 4 score and EQ-5D-5 L index score (r = -0.410, P < 0.001) and between TETRAS ADL total score and EQ-5D-5 L index score (r = -0.543, P < 0.001) were moderate. The bivariate associations between TETRAS Performance Item 4 score and QUEST total score (r = 0.457, P < 0.001), and between TETRAS ADL total score and QUEST total score (r = 0.630, P < 0.001) were also moderate. These associations were unaltered by the inclusion of covariates. Discussion: This study showed that greater tremor severity (TETRAS Performance Item 4) was positively correlated with ADL impairment (TETRAS ADL) and negatively associated with QoL (EQ-5D-5 L and QUEST). TETRAS Performance Item 4 score is a robust predictor of TETRAS ADL total score, and TETRAS Performance Item 4 and TETRAS ADL total scores were robust predictors of the 2 QoL scales. The results demonstrate the value of TETRAS scores as valid endpoints for future clinical trials. Highlights: This real-world study assessed TETRAS scores as predictors of impaired QoL in ET. TETRAS Performance Item 4 and ADL were associated with EQ-5D-5 L and QUEST. TETRAS scores may serve as valid endpoints for future clinical trials.

Design and Feasibility Analysis of a Smartphone-Based Digital Cognitive Assessment Study in the Framingham Heart Study.

BACKGROUND: Smartphone-based digital technology is increasingly being recognized as a cost-effective, scalable, and noninvasive method of collecting longitudinal cognitive and behavioral data. Accordingly, a state-of-the-art 3-year longitudinal project focused on collecting multimodal digital data for early detection of cognitive impairment was developed. METHODS AND RESULTS: A smartphone application collected 2 modalities of cognitive data, digital voice and screen-based behaviors, from the FHS (Framingham Heart Study) multigenerational Generation 2 (Gen 2) and Generation 3 (Gen 3) cohorts. To understand the feasibility of conducting a smartphone-based study, participants completed a series of questions about their smartphone and app use, as well as sensory and environmental factors that they encountered while completing the tasks on the app. Baseline data collected to date were from 537 participants (mean age=66.6 years, SD=7.0; 58.47% female). Across the younger participants from the Gen 3 cohort (n=455; mean age=60.8 years, SD=8.2; 59.12% female) and older participants from the Gen 2 cohort (n=82; mean age=74.2 years, SD=5.8; 54.88% female), an average of 76% participants agreed or strongly agreed that they felt confident about using the app, 77% on average agreed or strongly agreed that they were able to use the app on their own, and 81% on average rated the app as easy to use. CONCLUSIONS: Based on participant ratings, the study findings are promising. At baseline, the majority of participants are able to complete the app-related tasks, follow the instructions, and encounter minimal barriers to completing the tasks independently. These data provide evidence that designing and collecting smartphone application data in an unsupervised, remote, and naturalistic setting in a large, community-based population is feasible.

Validation of a New Patient-Reported Outcome Measure of the Functional Impact of Essential Tremor on Activities of Daily Living.

Background: The Essential Tremor Rating Assessment Scale (TETRAS) is a popular scale for essential tremor (ET), but its activities of daily living (ADL) and performance (P) subscales are based on a structured interview and physical exam. No patient-reported outcome (PRO) scale for ET has been developed according to US regulatory guidelines. Objective: Develop and validate a TETRAS PRO subscale. Methods: Fourteen items, rated 0-4, were derived from TETRAS ADL and structured cognitive interviews of 18 ET patients. Convergent validity analyses of TETRAS PRO versus TETRAS ADL, TETRAS-P, and the Quality of Life in Essential Tremor Questionnaire (QUEST) were computed for 67 adults with ET or ET plus. Test-retest reliability was computed at intervals of 1 and 30 days. The influence of mood (Hospital Anxiety and Depression Scale, HADS) and coping behaviors (Essen Coping Questionnaire, ECQ) was examined with multiple linear regression. Results: TETRAS PRO was strongly correlated (r > 0.7) with TETRAS ADL, TETRAS-P, and QUEST and exhibited good to excellent reliability (Cronbach alpha 95%CI = 0.853-0.926; 30-day test-retest intraclass correlation 95%CI = 0.814-0.921). The 30-day estimate of minimum detectable change (MDC) was 6.6 (95%CI 5.2-8.0). TETRAS-P (rsemipartial = 0.607), HADS depression (rsemipartial = 0.384), and the coping strategy of information seeking and exchange of experiences (rsemipartial = 0.176) contributed statistically to TETRAS PRO in a multiple linear regression (R2 = 0.67). Conclusions: TETRAS PRO is a valid and reliable scale that is influenced strongly by tremor severity, moderately by mood (depression), and minimally by coping skills. The MDC for TETRAS PRO is probably sufficient to detect clinically important change.

Shifting From Active to Passive Monitoring of Alzheimer Disease: The State of the Research.

Most research using digital technologies builds on existing methods for staff-administered evaluation, requiring a large investment of time, effort, and resources. Widespread use of personal mobile devices provides opportunities for continuous health monitoring without active participant engagement. Home-based sensors show promise in evaluating behavioral features in near real time. Digital technologies across these methodologies can detect precise measures of cognition, mood, sleep, gait, speech, motor activity, behavior patterns, and additional features relevant to health. As a neurodegenerative condition with insidious onset, Alzheimer disease and other dementias (AD/D) represent a key target for advances in monitoring disease symptoms. Studies to date evaluating the predictive power of digital measures use inconsistent approaches to characterize these measures. Comparison between different digital collection methods supports the use of passive collection methods in settings in which active participant engagement approaches are not feasible. Additional studies that analyze how digital measures across multiple data streams can together improve prediction of cognitive impairment and early-stage AD are needed. Given the long timeline of progression from normal to diagnosis, digital monitoring will more easily make extended longitudinal follow-up possible. Through the American Heart Association-funded Strategically Focused Research Network, the Boston University investigative team deployed a platform involving a wide range of technologies to address these gaps in research practice. Much more research is needed to thoroughly evaluate limitations of passive monitoring. Multidisciplinary collaborations are needed to establish legal and ethical frameworks for ensuring passive monitoring can be conducted at scale while protecting privacy and security, especially in vulnerable populations.

Comparing Cognitive Tests and Smartphone-Based Assessment in 2 US Community-Based Cohorts.

BACKGROUND: Smartphone-based cognitive assessments have emerged as promising tools, bridging gaps in accessibility and reducing bias in Alzheimer disease and related dementia research. However, their congruence with traditional neuropsychological tests and usefulness in diverse cohorts remain underexplored. METHODS AND RESULTS: A total of 406 FHS (Framingham Heart Study) and 59 BHS (Bogalusa Heart Study) participants with traditional neuropsychological tests and digital assessments using the Defense Automated Neurocognitive Assessment (DANA) smartphone protocol were included. Regression models investigated associations between DANA task digital measures and a neuropsychological global cognitive Z score (Global Cognitive Score [GCS]), and neuropsychological domain-specific Z scores. FHS participants' mean age was 57 (SD, 9.75) years, and 44% (179) were men. BHS participants' mean age was 49 (4.4) years, and 28% (16) were men. Participants in both cohorts with the lowest neuropsychological performance (lowest quartile, GCS1) demonstrated lower DANA digital scores. In the FHS, GCS1 participants had slower average response times and decreased cognitive efficiency scores in all DANA tasks (P<0.05). In BHS, participants in GCS1 had slower average response times and decreased cognitive efficiency scores for DANA Code Substitution and Go/No-Go tasks, although this was not statistically significant. In both cohorts, GCS was significantly associated with DANA tasks, such that higher GCS correlated with faster average response times (P<0.05) and increased cognitive efficiency (all P<0.05) in the DANA Code Substitution task. CONCLUSIONS: Our findings demonstrate that smartphone-based cognitive assessments exhibit concurrent validity with a composite measure of traditional neuropsychological tests. This supports the potential of using smartphone-based assessments in cognitive screening across diverse populations and the scalability of digital assessments to community-dwelling individuals.

Assessment of Wearable Device Adherence for Monitoring Physical Activity in Older Adults: Pilot Cohort Study.

Background: Physical activity has emerged as a modifiable behavioral factor to improve cognitive function. However, research on adherence to remote monitoring of physical activity in older adults is limited. Objective: This study aimed to assess adherence to remote monitoring of physical activity in older adults within a pilot cohort from objective user data, providing insights for the scalability of such monitoring approaches in larger, more comprehensive future studies. Methods: This study included 22 participants from the Boston University Alzheimer's Disease Research Center Clinical Core. These participants opted into wearing the Verisense watch as part of their everyday routine during 14-day intervals every 3 months. Eighteen continuous physical activity measures were assessed. Adherence was quantified daily and cumulatively across the follow-up period. The coefficient of variation was used as a key metric to assess data consistency across participants over multiple days. Day-to-day variability was estimated by calculating intraclass correlation coefficients using a 2-way random-effects model for the baseline, second, and third days. Results: Adherence to the study on a daily basis outperformed cumulative adherence levels. The median proportion of adherence days (wearing time surpassed 90% of the day) stood at 92.1%, with an IQR spanning from 86.9% to 98.4%. However, at the cumulative level, 32% (7/22) of participants in this study exhibited lower adherence, with the device worn on fewer than 4 days within the requested initial 14-day period. Five physical activity measures have high variability for some participants. Consistent activity data for 4 physical activity measures might be attainable with just a 3-day period of device use. Conclusions: This study revealed that while older adults generally showed high daily adherence to the wearable device, consistent usage across consecutive days proved difficult. These findings underline the effectiveness of wearables in monitoring physical activity in older populations and emphasize the ongoing necessity to simplify usage protocols and enhance user engagement to guarantee the collection of precise and comprehensive data.

Machine Learning in Clinical Trials: A Primer with Applications to Neurology.

We reviewed foundational concepts in artificial intelligence (AI) and machine learning (ML) and discussed ways in which these methodologies may be employed to enhance progress in clinical trials and research, with particular attention to applications in the design, conduct, and interpretation of clinical trials for neurologic diseases. We discussed ways in which ML may help to accelerate the pace of subject recruitment, provide realistic simulation of medical interventions, and enhance remote trial administration via novel digital biomarkers and therapeutics. Lastly, we provide a brief overview of the technical, administrative, and regulatory challenges that must be addressed as ML achieves greater integration into clinical trial workflows.

Large Language Models in Neurology Research and Future Practice.

Recent advancements in generative artificial intelligence, particularly using large language models (LLMs), are gaining increased public attention. We provide a perspective on the potential of LLMs to analyze enormous amounts of data from medical records and gain insights on specific topics in neurology. In addition, we explore use cases for LLMs, such as early diagnosis, supporting patient and caregivers, and acting as an assistant for clinicians. We point to the potential ethical and technical challenges raised by LLMs, such as concerns about privacy and data security, potential biases in the data for model training, and the need for careful validation of results. Researchers must consider these challenges and take steps to address them to ensure that their work is conducted in a safe and responsible manner. Despite these challenges, LLMs offer promising opportunities for improving care and treatment of various neurologic disorders.

American Football Play and Parkinson Disease Among Men.

Importance: Parkinsonism and Parkinson disease (PD) are known to result from repetitive head impacts from boxing. Repetitive head impacts from American football may also be associated with increased risk of neurodegenerative pathologies that cause parkinsonism, yet in vivo research on the association between football play and PD is scarce and limited by small samples and equivocal findings. Objective: To evaluate the association between football participation and self-reported parkinsonism or PD diagnosis. Design, Setting, and Participants: This cross-sectional study leveraged data from the online Fox Insight study. Participants completed online questionnaires and self-reported whether they currently had a diagnosis of Parkinson disease or parkinsonism by a physician or other health care professional. In November 2020, the Boston University Head Impact Exposure Assessment was launched for data collection on repetitive head impacts. Data used for this manuscript were obtained from the Fox Insight database on June 9, 2022. A total of 1875 men who endorsed playing any organized sport were included. Former athletes were divided into those who participated in football (n = 729 [38.9%]) and those who participated in other sports (reference group). Exposures: Self-reported participation in football, duration and level of football play, age at first exposure. Main Outcomes and Measures: Logistic regression tested associations between PD status and history of football play, duration of football play, highest level played, and age at first exposure, controlling for age, education, history of diabetes or heart disease, body mass index, history of traumatic brain injury with loss of consciousness, and family history of PD. Results: In this sample of 1875 men (mean [SD] age, 67.69 [9.84] years) enriched for parkinsonism or PD (n = 1602 [85.4%]), 729 (38.9%) played football (mean [SD] duration, 4.35 [2.91] years). History of playing football was associated with higher odds of having a parkinsonism or PD diagnosis (odds ratio [OR], 1.61; 95% CI, 1.19-2.17). Among the entire sample, longer duration of play was associated with higher odds of having a parkinsonism or PD diagnosis (OR, 1.12; 95% CI, 1.06-1.19). Among football players, longer duration of football play (OR, 1.12; 95% CI, 1.02-1.23) and higher level of play (OR, 2.93; 95% CI, 1.28-6.73) were associated with higher odds of having parkinsonism or PD. Conclusions and Relevance: In this cross-sectional study of participants enriched for PD, participation in football was associated with higher odds of having a reported parkinsonism or PD diagnosis.

Does essential tremor increase risk of cognitive impairment and dementia? Yes.

Essential Tremor (ET), by definition, is a disorder of movement. Yet over the years, epidemiologic, clinical, pathologic, and neuroimaging studies have converged to reveal a cognitive side of ET. The cognitive symptoms in ET are heterogeneous and are likely to reflect heterogeneous underlying mechanisms. In this chapter, we review and synthesize a diverse set of studies from both population-based settings to cohorts with more detailed investigations into cognition to consider the various mechanisms by which cognitive symptoms may emerge in a subset of individuals with ET. As part of our analysis, we consider questions surrounding ET diagnosis and the possibility of comorbid disease as potential factors that, upon closer examination, appear to strengthen the argument in favor of ET as a risk factor for dementia. Importantly, we also consider the clinical relevance of cognitive impairment in ET. While ET is not universally characterized by significant cognitive deficits, the data from epidemiological, cognitive, neuroimaging, and postmortem neuropathologic studies converge to reveal an increased risk for cognitive impairment and dementia among individuals with ET. We conclude by offering directions for future research, and a neurocognitive framework with which to consider existing findings and to use in the design of novel studies dedicated to clarifying the basis, nature, and course of cognitive impairments in ET.

Multimodal deep learning for Alzheimer's disease dementia assessment.

Worldwide, there are nearly 10 million new cases of dementia annually, of which Alzheimer's disease (AD) is the most common. New measures are needed to improve the diagnosis of individuals with cognitive impairment due to various etiologies. Here, we report a deep learning framework that accomplishes multiple diagnostic steps in successive fashion to identify persons with normal cognition (NC), mild cognitive impairment (MCI), AD, and non-AD dementias (nADD). We demonstrate a range of models capable of accepting flexible combinations of routinely collected clinical information, including demographics, medical history, neuropsychological testing, neuroimaging, and functional assessments. We then show that these frameworks compare favorably with the diagnostic accuracy of practicing neurologists and neuroradiologists. Lastly, we apply interpretability methods in computer vision to show that disease-specific patterns detected by our models track distinct patterns of degenerative changes throughout the brain and correspond closely with the presence of neuropathological lesions on autopsy. Our work demonstrates methodologies for validating computational predictions with established standards of medical diagnosis.