Skip to main content

Mindstrong Digital Biomarker Model Fitting

Project description

This package uses Supervised Kernel Principal Components Analysis with cross validation to fit digital biomarker data to target measurements. The software was written by members of the Mindstrong Health Data Science team:

  • Paul Dagum, MD, PhD
  • Greg Ryslik, PhD, FCAS, MAAA
  • Bob Dougherty, PhD
  • Patrick Staples, PhD

Please contact us at

NOTE: If you use this software in your work, please cite the following paper:

Dagum, P. (2018) Digital biomarkers of cognitive function. npj Digital Medicine, issue 1, article 10. DOI: 10.1038/s41746-018-0018-4.


The easiest way to install the package is via easy_install or pip:

$ pip install mindstrong_biomarker_modelfit

This should also take care of the dependencies (numpy, scipy, pandas, and sklearn).


Simulated digital biomarker and target measure data are included with the project. To fit a model to these example data:

import numpy as np
import pandas as pd
import os
from mindstrong import mindstrong_modelfit as mindstrong

target_file = mindstrong.get_example_data('example_targets.csv')
feature_file = mindstrong.get_example_data('example_features.csv')
target_colname = 'target1'

# Load target data
target_df = pd.read_csv(target_file)
target_df.set_index('device_id', inplace=True)

# Load Feature Data
feature_df = pd.read_csv(feature_file).set_index(['device_id', 'targetDOY'])

# Cross Validated supervised kernel PCA model-fitting
cvdf, best_model = mindstrong.calculateCrossValidatedCorrelation(target_df,

# Print the final results

Project details

Release history Release notifications

This version


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for mindstrong, version 1.0
Filename, size File type Python version Upload date Hashes
Filename, size mindstrong-1.0.tar.gz (883.9 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page