Skip to main content
100%

Gist e5affea97473980182b59a9d4efb945e

✓ Published0🌍 Public
Aakeshavan
Last edited May 3, 2016
Created on May 3, 2016

This example visualizes the relationship between brain connectivity measures and disability in multiple sclerosis patients. It fits ordinary least squares regression models predicting the EDSS score from diffusion imaging metrics and demographic covariates across each brain connection, then displays the resulting p-values and R-squared values in a table. The code uses pandas for data handling, statsmodels' `ols` API for the regression models, and seaborn with pylab inline for plotting.

AI-generated description

Similar vizzes

Loading thumbnail…

Gist 65e3c6b08f24fc0f33141f71ce37e702

This example visualizes the relationship between imaging-derived connectivity metrics and clinical measures in multiple sclerosis patients by computing global efficiency from weighted brain graphs. The notebook applies PCA to combine multiple imaging features per connection, then calculates efficiency values for each subject using the Brain Connectivity Toolbox (bct.efficiency_wei). The resulting efficiency dataframe is merged with demographic and clinical data using pandas, with Seaborn and matplotlib available for plotting, though the visualization output itself is not displayed.

Aakeshavan
79% match
Loading thumbnail…

Gist 1e296721b61bae725016

This visualization displays functional connectivity between brain regions as a circular node-link diagram, with edges colored by PLS regression coefficients relating resting-state fMRI correlations to disability scores (EDSS) in multiple sclerosis patients. The code converts correlation values to z-scores via Fisher transform, then applies PLSRegression to extract predictive components. Using MNE-Python’s `circular_layout` and `plot_connectivity_circle`, it arranges region names around a ring, styles nodes with seaborn color palettes, and encodes edge weights through a custom colormap with a colorbar. The underlying data is loaded from a CSV of freesurfer parcellations and connectivity metrics.

Aakeshavan
79% match
Loading thumbnail…

Gist 5c928c271ee8dd212aef9236c69ed525

The example shows a PCA-based analysis of neuroimaging and clinical data from a multiple sclerosis dataset, displaying how imaging-derived features relate to demographic and clinical variables. It computes principal components from diffusion and magnetization transfer metrics, then explores correlations with clinical measures like EDSS and timed walk. The notebook uses pandas for data handling, scikit-learn's PCA and RandomForestRegressor for modeling, and statsmodels for statistical testing, with seaborn and matplotlib providing visualization support.

Aakeshavan
79% match
Loading thumbnail…

Gist 9556811

This example simulates brain volume and disability data for healthy controls and multiple sclerosis patients across two sites, generating synthetic datasets with site-specific EDSS distributions. It uses Python with statsmodels and matplotlib via prettyplotlib to plot the simulated distributions, including scatterplots and regression fits that illustrate relationships between age, brain volume, and EDSS scores. The visualization is part of a Vue-based gallery, but the core computation and plotting rely on numpy and statsmodels for statistical simulation and visualization.

Aakeshavan
78% match
Loading thumbnail…

Gist fd5980c016748347a3ed

This visualization displays correlation plots of spinal cord measurements from a multiple sclerosis dataset, including metrics like cord area, gray matter, and white matter at different spinal levels, alongside clinical scores (EDSS). The analysis uses pandas to load the data and seaborn to generate the plots, with a white background, Set1 color palette, and talk-context styling. Dark red and dark blue colors distinguish the plots, which examine relationships between structural measurements and disability scores.

Aakeshavan
76% match
Loading thumbnail…

Gist 9557217

This example simulates brain-volume measurements for healthy controls and multiple-sclerosis patients across two scan protocols, using synthetic data generated with NumPy and Statsmodels. It shows how measurement noise and protocol-related biases affect the relationship between age, disability scores, and brain volume. The visualization displays the simulated distributions and calibration results, with matplotlib and prettyplotlib rendering static plots. The code relies on inline plotting via `%pylab` and custom utility functions for distribution and calibration analysis, though no interactive or WebGL output is present in the provided notebook cells.

Aakeshavan
73% match
Loading thumbnail…

Gist 9614007

This visualization demonstrates simulated brain volume (BV) measurements across healthy controls (HC) and multiple sclerosis (MS) patients, generated with a custom Python function. The simulation models two distinct "sites" or protocols, each with its own disease severity distribution (EDSS-like scores) and age-dependent brain volume trends. Parameters include group sizes (50 HC, 250 MS), age ranges, disease severity mixture distributions, and linear relationships between age, disability, and brain volume with added noise. The example includes a plot of the simulated disability scores for both sites, created using matplotlib inline in an IPython notebook. Built with the Vue framework, the visualization highlights how simulated data can be used to explore statistical estimation and model assumptions in neuroimaging studies.

Aakeshavan
73% match
Loading thumbnail…

Gist 9633197

This example demonstrates a simulated data analysis workflow for studying brain volume (BV) differences between healthy controls (HC) and multiple sclerosis (MS) patients across two sites. The notebook defines a synthetic data generator that creates age, disability (EDSS), and brain volume measurements for healthy controls and MS patients under two different scanning protocols, then calibrates measurements between the two sites. Using ordinary least squares regression via the `statsmodels` library, it fits models relating brain volume to age and disease severity, then applies a calibration transformation to harmonize measurements across sites. The visualization likely shows scatter plots of the simulated data with regression lines, illustrating the calibration process and residual patterns. The example demonstrates a statistical approach to cross-site calibration of imaging biomarkers in the presence of disease-related effects.

Aakeshavan
72% match