Dataset Information

Machine learning for comprehensive forecasting of Alzheimer's Disease progression.

ABSTRACT: Most approaches to machine learning from electronic health data can only predict a single endpoint. The ability to simultaneously simulate dozens of patient characteristics is a crucial step towards personalized medicine for Alzheimer's Disease. Here, we use an unsupervised machine learning model called a Conditional Restricted Boltzmann Machine (CRBM) to simulate detailed patient trajectories. We use data comprising 18-month trajectories of 44 clinical variables from 1909 patients with Mild Cognitive Impairment or Alzheimer's Disease to train a model for personalized forecasting of disease progression. We simulate synthetic patient data including the evolution of each sub-component of cognitive exams, laboratory tests, and their associations with baseline clinical characteristics. Synthetic patient data generated by the CRBM accurately reflect the means, standard deviations, and correlations of each variable over time to the extent that synthetic data cannot be distinguished from actual data by a logistic regression. Moreover, our unsupervised model predicts changes in total ADAS-Cog scores with the same accuracy as specifically trained supervised models, additionally capturing the correlation structure in the components of ADAS-Cog, and identifies sub-components associated with word recall as predictive of progression.

SUBMITTER: Fisher CK

PROVIDER: S-EPMC6754403 | biostudies-other | 2019 Sep

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Machine learning for comprehensive forecasting of Alzheimer's Disease progression.

Fisher Charles K CK Smith Aaron M AM Walsh Jonathan R JR

Scientific reports 20190920 1

Most approaches to machine learning from electronic health data can only predict a single endpoint. The ability to simultaneously simulate dozens of patient characteristics is a crucial step towards personalized medicine for Alzheimer's Disease. Here, we use an unsupervised machine learning model called a Conditional Restricted Boltzmann Machine (CRBM) to simulate detailed patient trajectories. We use data comprising 18-month trajectories of 44 clinical variables from 1909 patients with Mild Cog ...[more]

PMID: 31541187

Similar Datasets

Project description:Currently there are no reliable biomarkers for early detection of Alzheimer's disease (AD) at the preclinical stage. This study assessed the pupil light reflex (PLR) for focal red and blue light stimuli in central and peripheral retina in 125 cognitively normal middle age subjects (45-71 years old) at high risk for AD due to a family history of the disease (FH+), and 61 age-similar subjects with no family history of AD (FH-) using Chromatic Pupilloperimetry coupled with Machine Learning (ML). All subjects had normal ophthalmic assessment, and normal retinal and optic nerve thickness by optical coherence tomography. No significant differences were observed between groups in cognitive function and volumetric brain MRI. Chromatic pupilloperimetry-based ML models were highly discriminative in differentiating subjects with and without AD family history, using transient PLR for focal red (primarily cone-mediated), and dim blue (primarily rod-mediated) light stimuli. Features associated with transient pupil response latency (PRL) achieved Area Under the Curve Receiver Operating Characteristic (AUC-ROC) of 0.90 ± 0.051 (left-eye) and 0.87 ± 0.048 (right-eye). Parameters associated with the contraction arm of the rod and cone-mediated PLR were more discriminative compared to parameters associated with the relaxation arm and melanopsin-mediated PLR. Significantly shorter PRL for dim blue light was measured in the FH+ group in two test targets in the temporal visual field in right eye that had highest relative weight in the ML algorithm (mean ± standard error, SE 0.449 s ± 0.007 s vs. 0.478 s ± 0.010 s, p = 0.038). Taken together our study suggests that subtle focal changes in pupil contraction latency may be detected in subjects at high risk to develop AD, decades before the onset of AD clinical symptoms. The dendrites of melanopsin containing retinal ganglion cells may be affected very early at the preclinical stages of AD.

Project description:The emergence of new technologies to synthesize and analyze big data with high-performance computing has increased our capacity to more accurately predict crop yields. Recent research has shown that machine learning (ML) can provide reasonable predictions faster and with higher flexibility compared to simulation crop modeling. However, a single machine learning model can be outperformed by a "committee" of models (machine learning ensembles) that can reduce prediction bias, variance, or both and is able to better capture the underlying distribution of the data. Yet, there are many aspects to be investigated with regard to prediction accuracy, time of the prediction, and scale. The earlier the prediction during the growing season the better, but this has not been thoroughly investigated as previous studies considered all data available to predict yields. This paper provides a machine leaning based framework to forecast corn yields in three US Corn Belt states (Illinois, Indiana, and Iowa) considering complete and partial in-season weather knowledge. Several ensemble models are designed using blocked sequential procedure to generate out-of-bag predictions. The forecasts are made in county-level scale and aggregated for agricultural district and state level scales. Results show that the proposed optimized weighted ensemble and the average ensemble are the most precise models with RRMSE of 9.5%. Stacked LASSO makes the least biased predictions (MBE of 53 kg/ha), while other ensemble models also outperformed the base learners in terms of bias. On the contrary, although random k-fold cross-validation is replaced by blocked sequential procedure, it is shown that stacked ensembles perform not as good as weighted ensemble models for time series data sets as they require the data to be non-IID to perform favorably. Comparing our proposed model forecasts with the literature demonstrates the acceptable performance of forecasts made by our proposed ensemble model. Results from the scenario of having partial in-season weather knowledge reveals that decent yield forecasts with RRMSE of 9.2% can be made as early as June 1st. Moreover, it was shown that the proposed model performed better than individual models and benchmark ensembles at agricultural district and state-level scales as well as county-level scale. To find the marginal effect of each input feature on the forecasts made by the proposed ensemble model, a methodology is suggested that is the basis for finding feature importance for the ensemble model. The findings suggest that weather features corresponding to weather in weeks 18-24 (May 1st to June 1st) are the most important input features.

Project description:BackgroundDiverse modeling approaches viz. neural networks and multiple regression have been followed to date for disease prediction in plant populations. However, due to their inability to predict value of unknown data points and longer training times, there is need for exploiting new prediction softwares for better understanding of plant-pathogen-environment relationships. Further, there is no online tool available which can help the plant researchers or farmers in timely application of control measures. This paper introduces a new prediction approach based on support vector machines for developing weather-based prediction models of plant diseases.ResultsSix significant weather variables were selected as predictor variables. Two series of models (cross-location and cross-year) were developed and validated using a five-fold cross validation procedure. For cross-year models, the conventional multiple regression (REG) approach achieved an average correlation coefficient (r) of 0.50, which increased to 0.60 and percent mean absolute error (%MAE) decreased from 65.42 to 52.24 when back-propagation neural network (BPNN) was used. With generalized regression neural network (GRNN), the r increased to 0.70 and %MAE also improved to 46.30, which further increased to r = 0.77 and %MAE = 36.66 when support vector machine (SVM) based method was used. Similarly, cross-location validation achieved r = 0.48, 0.56 and 0.66 using REG, BPNN and GRNN respectively, with their corresponding %MAE as 77.54, 66.11 and 58.26. The SVM-based method outperformed all the three approaches by further increasing r to 0.74 with improvement in %MAE to 44.12. Overall, this SVM-based prediction approach will open new vistas in the area of forecasting plant diseases of various crops.ConclusionOur case study demonstrated that SVM is better than existing machine learning techniques and conventional REG approaches in forecasting plant diseases. In this direction, we have also developed a SVM-based web server for rice blast prediction, a first of its kind worldwide, which can help the plant science community and farmers in their decision making process. The server is freely available at http://www.imtech.res.in/raghava/rbpred/.

Dataset Information

Machine learning for comprehensive forecasting of Alzheimer's Disease progression.

Publications

Machine learning for comprehensive forecasting of Alzheimer's Disease progression.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets