Mobile and pervasive computing technologies and the future of Alzheimer’s clinical trials

Doraiswamy, P. Murali; Narayan, Vaibhav A.; Manji, Husseini K.

doi:10.1038/s41746-017-0008-y

Cited by 141 publications

(95 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In many cases, modern machine learning algorithms have been remarkably successful in taking a large set of predictors (e.g., phenotypes)—each weakly associated with the outcome (e.g., PD)—and combining them into a single, strong predictive model. 28 Indeed, several algorithms have been developed to predict the risk of developing PD using data derived from clinical tests, olfaction tests, genotyping arrays, and online tests and surveys. 8,29,30 Models based on data from online surveys or electronic health records can be used for low-cost population-wide screening, and may be a valuable tool for prioritizing individuals with a high probability of developing PD for research purposes.…”

Section: Discussionmentioning

confidence: 99%

The Parkinson’s phenome—traits associated with Parkinson’s disease in a broadly phenotyped cohort

Heilbron

Noyce

Fontanillas

et al. 2019

npj Parkinsons Dis.

View full text Add to dashboard Cite

In order to systematically describe the Parkinson’s disease phenome, we performed a series of 832 cross-sectional case-control analyses in a large database. Responses to 832 online survey-based phenotypes including diseases, medications, and environmental exposures were analyzed in 23andMe research participants. For each phenotype, survey respondents were used to construct a cohort of Parkinson’s disease cases and age-matched and sex-matched controls, and an association test was performed using logistic regression. Cohorts included a median of 3899 Parkinson’s disease cases and 49,808 controls, all of European ancestry. Highly correlated phenotypes were removed and the novelty of each significant association was systematically assessed (assigned to one of four categories: known, likely, unclear, or novel). Parkinson’s disease diagnosis was associated with 122 phenotypes. We replicated 27 known associations and found 23 associations with a strong a priori link to a known association. We discovered 42 associations that have not previously been reported. Migraine, obsessive-compulsive disorder, and seasonal allergies were associated with Parkinson’s disease and tend to occur decades before the typical age of diagnosis for Parkinson’s disease. The phenotypes that currently comprise the Parkinson’s disease phenome have mostly been explored in relatively small purpose-built studies. Using a single large dataset, we have successfully reproduced many of these established associations and have extended the Parkinson’s disease phenome by discovering novel associations. Our work paves the way for studies of these associated phenotypes that explore shared molecular mechanisms with Parkinson’s disease, infer causal relationships, and improve our ability to identify individuals at high-risk of Parkinson’s disease.

show abstract

Section: Discussionmentioning

confidence: 99%

The Parkinson’s phenome—traits associated with Parkinson’s disease in a broadly phenotyped cohort

Heilbron

Noyce

Fontanillas

et al. 2019

npj Parkinsons Dis.

View full text Add to dashboard Cite

show abstract

“…Active data collection occurs when a user is prompted to perform a measurement and/or enter a metric value, e.g., a digital e-assessment cognitive test that probes memory on a tablet to detect AD, 3 or a prompted voice test that probes vocal cord tremor to detect PD. 4 These measurements are usually targeted at addressing specific metrics that have previously been correlated with the disease.…”

Section: Mobile and Wearable Device- Derived Datamentioning

confidence: 99%

Digital biomarkers for Alzheimer’s disease: the mobile/wearable devices opportunity

et al. 2019

View full text Add to dashboard Cite

Alzheimer’s Disease (AD) represents a major and rapidly growing burden to the healthcare ecosystem. A growing body of evidence indicates that cognitive, behavioral, sensory, and motor changes may precede clinical manifestations of AD by several years. Existing tests designed to diagnose neurodegenerative diseases, while well-validated, are often less effective in detecting deviations from normal cognitive decline trajectory in the earliest stages of the disease. In the quest for gold standards for AD assessment, there is a growing interest in the identification of readily accessible digital biomarkers, which harness advances in consumer grade mobile and wearable technologies. Topics examined include a review of existing early clinical manifestations of AD and a path to the respective sensor and mobile/wearable device usage to acquire domain-centric data towards objective, high frequency and passive digital phenotyping.

show abstract

“…The existing literature was scrutinized to determine which methods have already been proven to deliver solid solutions. We do not use deep learning methods, which are very popular, and have been used in recent research [20,21] dealing with similar outcomes. Such techniques are very suitable for complex features, such as pixels in images, but they are not useful for standard tabular datasets as in this study.…”

Section: Resultsmentioning

confidence: 99%

“…We have found only a few prior hospital-wide studies predicting in-hospital mortality at admission in the literature [20]. One study using deep learning as technique and extracting the data from EHRs into a specific format achieved an AUCROC of 0.90.…”

Section: Plos Onementioning

confidence: 99%

Using structured pathology data to predict hospital-wide mortality at admission

et al. 2020

View full text Add to dashboard Cite

Early prediction of in-hospital mortality can improve patient outcome. Current prediction models for in-hospital mortality focus mainly on specific pathologies. Structured pathology data is hospital-wide readily available and is primarily used for e.g. financing purposes. We aim to build a predictive model at admission using the International Classification of Diseases (ICD) codes as predictors and investigate the effect of the self-evident DNR ("Do Not Resuscitate") diagnosis codes and palliative care codes. We compare the models using ICD-10-CM codes with Risk of Mortality (RoM) and Charlson Comorbidity Index (CCI) as predictors using the Random Forests modeling approach. We use the Present on Admission flag to distinguish which diagnoses are present on admission. The study is performed in a single center (Ghent University Hospital) with the inclusion of 36 368 patients, all discharged in 2017. Our model at admission using ICD-10-CM codes (AUCROC = 0.9477) outperforms the model using RoM (AUCROC = 0.8797 and CCI (AUCROC = 0.7435). We confirmed that DNR and palliative care codes have a strong impact on the model resulting in a decrease of 7% for the ICD model (AUCROC = 0.8791) at admission. We therefore conclude that a model with a sufficient predictive performance can be derived from structured pathology data, and if real-time available, can serve as a prerequisite to develop a practical clinical decision support system for physicians.

show abstract

Mobile and pervasive computing technologies and the future of Alzheimer’s clinical trials

Cited by 141 publications

References 27 publications

The Parkinson’s phenome—traits associated with Parkinson’s disease in a broadly phenotyped cohort

The Parkinson’s phenome—traits associated with Parkinson’s disease in a broadly phenotyped cohort

Digital biomarkers for Alzheimer’s disease: the mobile/wearable devices opportunity

Using structured pathology data to predict hospital-wide mortality at admission

Contact Info

Product

Resources

About