Longitudinal clinical simulation cohorts

<strong>Rotroff Lab</strong> <strong>2022-07-01</strong> This repository contains simulated datasets related to <code>Identification of Robust Deep Neural Network Models of Longitudinal Clinical Measurements</code> article published in <em>npj Digital Medicine</em> (2022). These datasets were simulated by manipulating shapes and magnitudes of clinical longitudinal measurements of random blood glucose tests, systolic blood pressure and BMI. Per clinical measurement type, 3168 datasets were generated. In half of these datasets, classes were defined by differences in shape (50%, N=1584) and in the other half, classes were defined by differences in magnitudes (50%, N=1584). The complete list of parameters manipulated is as follows: Effect Size: 0.25-2.75 Dispersion: 0.25-2.00 Noise: 0%, 10%, 25%, 50% Irregularity: Moderate (0-3 missing measurements) or High (2-5 missing measurements) For more information on the simulations, please refer to the Methods section of the paper. Please note that with the inclusion of class imbalance, the total number of cohorts increased to 12,672 in the paper. <strong>Parameter annotations</strong> The parameters are annotated in the file names as follows: _Simulated_Cohort_EffectSize_Dispersion_Noise_Irregularity_OverlapBetweenClasses.csv When <code>IrrNMP</code> is used for Irregularity, no irregularity is applied. <code>OverlapBetweenClasses</code> specifies the overlap between the two classes. <strong>Directory Structure</strong> The directory structure for each clinical measurement type is as follows: bmi_simulation (N=1056)mag_cohorts shape_cohorts <code>Simulation_Cohort_IDRandomNumber</code>: Random trajectory base 4 irregularity_cohorts other_cohorts <code>Simulation_Cohort_ID_RandomNumber</code>: Random trajectory base 5 irregularity_cohorts other_cohorts <code>Simulation_Cohort_ID_RandomNumber</code>: Random trajectory base 6 irregularity_cohorts other_cohorts glucose_simulation (1056)mag_cohorts shape_cohorts sbp_simulation (N=1056)mag_cohorts shape_cohorts <strong>Note:</strong> <code>irregularity_cohorts</code>: Effect sizes, dispersions and irregularity were manipulated in these files. <code>other_cohorts</code>: Effect sizes, dispersions and noise were manipulated in these files. <br> <br> Please cite the following paper and this dataset in your work: <br> H. Javidi, et al., Identification of Robust Deep Neural Network Models of Longitudinal Clinical Measurements, Nature Digital Medicine, 2022.