Machine learning for comprehensive forecasting of Alzheimer’s Disease progression

Fisher, Charles K.; Smith, Aaron; Walsh, Jonathan R.; Simon, Adam J.; Edgar, Chris; Jack, Clifford R.; Holtzman, David M.; Russell, David; Hill, Derek L. G.; Grosset, Donald; Wood, Fred B.; Vanderstichele, Hugo; Morris, John C.; Blennow, Kaj; Marek, Kenneth; Shaw, Leslie M.; Albert, Marilyn; Weiner, Michael D.; Fox, Nick; Aisen, Paul S.; Cole, Patricia E.; Petersen, Ronald C.; Sherer, Todd; Kubick, Wayne

doi:10.1038/s41598-019-49656-2

Cited by 157 publications

(118 citation statements)

References 39 publications

Supporting

Mentioning

117

Contrasting

Order By: Relevance

“…In recent models of disease progression or aging either the mortality is not considered, 15 or the models require longitudinal data, 48,49 or both. [50][51][52] Structurally, our model differs from others by using an explicit network describing pairwise interactions, and it uses this network to generate stochastic changes to their health state as they age until death -rather than capturing the dynamics with unobserved latent variables that are harder to interpret. Using discrete health states within our model allows us to simply compare with observed health states using maximum likelihood methods, and enables our success using cross-sectional data.…”

Section: Discussionmentioning

confidence: 99%

Generating synthetic aging trajectories with a weighted network model using cross-sectional data

Farrell

Mitnitski

Rockwood

et al. 2020

Preprint

View full text Add to dashboard Cite

We develop a computational model of human aging that generates individual health trajectories using a set of observed health attributes. Our model consists of a network of interacting health attributes that stochastically damage with age to form health deficits, leading to eventual mortality. We train and test the model for two different cross-sectional observational aging studies that include simple clinical indicators of health. In both studies, we find that the individuals generated from the model resemble the observed data in both health characteristics and mortality. Predicted average health trajectories and survival probabilities also agree with the observed data. Author summaryHuman aging is characterized by the individual accumulation of damage. In later life this damage often presents as laboratory abnormalities, diseases, or an impaired ability to carry out daily tasks and activities. This accumulated damage is also connected with an increased risk of mortality. We develop a model to generate realistic and detailed trajectories of health for aging individuals. Given individual health status at a given age, these predicted trajectories describe the likely conditions or disabilities the individual will have in the future. This provides a computational model of human aging that includes observable health features.February 14, 2020 1/15 many binary deficits to evaluate overall health provides measures that are strongly associated with both adverse health outcomes and mortality [5][6][7][8].Many recent attempts to generate or forecast individual trajectories of disease progression use longitudinal data. Current models can generate and forecast individual trajectories of disease progression [9][10][11], or jointly forecast both disease progression and survival [12,13]. Modeling aging more generally is less common.There are many limitations due to data availability when modeling aging. Typically large observational studies (10 4 + individuals) with linked mortality are cross-sectional (measuring variables only at study entry, with only irregular follow ups), have short censored survival outcomes, and have a lot of missing data. This complicates generating realistic health trajectories during aging. While a model forecasting general health trajectories during aging using cross-sectional data has been developed recently [14], it did not consider individual survival. Recent work used longitudinal data to build a model that describes the aging of mice with a single state variable, although doesn't incorporate survival or predictions of health trajectories [15]. Here, we present a model that can deal with the data limitations of cross-sectional data with censored survival information to generate individual aging trajectories that includes both health and survival.Our model is adapted from previous work modeling human aging with stochastic dynamics on a complex network [16][17][18], which was shown to capture population level aging phenomena, such as Gompertz' law of mortality [19]. This model is based on the intuit...

show abstract

Section: Discussionmentioning

confidence: 99%

Generating synthetic aging trajectories with a weighted network model using cross-sectional data

Farrell

Mitnitski

Rockwood

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…ML likewise appears promising for precision medicine: given the patients' extreme heterogeneity of symptoms, medication response, and prognosis, the implementation of ML to create computational models of disease development tackles patients' diverseness (Fisher et al, 2019). Over the years, researchers have devised a number of disease progression models for both MCI and AD, relying on clinical and imaging data (Mueller et al, 2005;Ito et al, 2011;Rogers et al, 2012;Moradi et al, 2015;Miotto et al, 2017;Samper-Gonzalez et al, 2017;Fisher et al, 2019). Previous applications of ML to clinical data have proven useful in predicting a single outcome (e.g., the likelihood of conversion from MCI to AD) (Fisher et al, 2019).…”

Section: A New Integrated Approach To MCI Assessmentmentioning

confidence: 99%

Digital Biomarkers for the Early Detection of Mild Cognitive Impairment: Artificial Intelligence Meets Virtual Reality

Cavedoni

Chirico

Pedroli

et al. 2020

Front. Hum. Neurosci.

View full text Add to dashboard Cite

Elderly people affected by Mild Cognitive Impairment (MCI) usually report a perceived decline in cognitive functions that deeply impacts their quality of life. This subtle waning, although it cannot be diagnosable as dementia, is noted by caregivers on the basis of their relative's behaviors. Crucially, if this condition is also not detected in time by clinicians, it can easily turn into dementia. Thus, early detection of MCI is strongly needed. Classical neuropsychological measures-underlying a categorical model of diagnosis-could be integrated with a dimensional assessment approach involving Virtual Reality (VR) and Artificial Intelligence (AI). VR can be used to create highly ecologically controlled simulations resembling the daily life contexts in which patients' daily instrumental activities (IADL) usually take place. Clinicians can record patients' kinematics, particularly gait, while performing IADL (Digital Biomarkers). Then, Artificial Intelligence employs Machine Learning (ML) to analyze them in combination with clinical and neuropsychological data. This integrated computational approach would enable the creation of a predictive model to identify specific patterns of cognitive and motor impairment in MCI. Therefore, this new dimensional cognitive-behavioral assessment would reveal elderly people's neural alterations and impaired cognitive functions, typical of MCI and dementia, even in early stages for more time-sensitive interventions.

show abstract

“…This, in turn, leads to models biased toward specific disease stages (Ning et al, 2010). Various methods, such as complete data analysis (Xiang et al, 2013), imputation (Fisher et al, 2019), or analysis based on dichotomized data (Donohue et al, 2011), have been established to address censored data. Yet all of these methods may introduce error and impose complexities and biases on other integrative modeling steps, such as model interpretation, and thus need to be used with care (Prinja et al, 2010).…”

Section: Data Collectionmentioning

confidence: 99%

Challenges of Integrative Disease Modeling in Alzheimer's Disease

Khatami

Robinson

Birkenbihl

et al. 2020

Front. Mol. Biosci.

View full text Add to dashboard Cite

Dementia-related diseases like Alzheimer's Disease (AD) have a tremendous social and economic cost. A deeper understanding of its underlying pathophysiologies may provide an opportunity for earlier detection and therapeutic intervention. Previous approaches for characterizing AD were targeted at single aspects of the disease. Yet, due to the complex nature of AD, the success of these approaches was limited. However, in recent years, advancements in integrative disease modeling, built on a wide range of AD biomarkers, have taken a global view on the disease, facilitating more comprehensive analysis and interpretation. Integrative AD models can be sorted in two primary types, namely hypothetical models and data-driven models. The latter group split into two subgroups: (i) Models that use traditional statistical methods such as linear models, (ii) Models that take advantage of more advanced artificial intelligence approaches such as machine learning. While many integrative AD models have been published over the last decade, their impact on clinical practice is limited. There exist major challenges in the course of integrative AD modeling, namely data missingness and censoring, imprecise human-involved priori knowledge, model reproducibility, dataset interoperability, dataset integration, and model interpretability. In this review, we highlight recent advancements and future possibilities of integrative modeling in the field of AD research, showcase and discuss the limitations and challenges involved, and finally, propose avenues to address several of these challenges.

show abstract

Machine learning for comprehensive forecasting of Alzheimer’s Disease progression

Cited by 157 publications

References 39 publications

Generating synthetic aging trajectories with a weighted network model using cross-sectional data

Generating synthetic aging trajectories with a weighted network model using cross-sectional data

Digital Biomarkers for the Early Detection of Mild Cognitive Impairment: Artificial Intelligence Meets Virtual Reality

Challenges of Integrative Disease Modeling in Alzheimer's Disease

Contact Info

Product

Resources

About