Simulated Data for Patient Time Series Record Linkage

This simulated dataset constitutes two files (after decompression), namely: <b>sim_ergo_1600.<code>csv</code></b> and <b>sim_pat_1600</b><code><b>.csv</b>.</code><code><br></code><code>1. <code><b>ergo.csv</b></code> contains heart rate timeseries data for 1600 patients' ergometric tests. For each patient, 20 different ergometric tests were simulated. Each row in this file constitutes three field values: <code><i>Ergo_ID</i></code>, <i>Heart Rate</i> (BPM), and <code><i>timestamp</i></code>.<br><code><br></code></code><code><code>2. <b>pat.csv</b></code> contains only four sample readings from each of the patient's 20 ergometric tests. Each row contains three values: <i>patient_ID</i>, <i>Heart Rate</i>, and <i>timestamp</i>. <br></code><br>The goal is to link patients (identified by their patient_ID in the <code><b>pat.csv</b></code> file) to their corresponding ergometric tests (identified by their <i>Ergo_ID</i> in the <code><b>ergo.csv</b></code> file). This is done solely on matching the timestamp-value pairs from both files.<br><br>The timeseries record linkage task described above is efficiently accomplished by the proposed <b>tslink2</b> algorithm. <b>tslink2</b> is implemented in <i>C++</i> and is publicly availabe at <i>https://github.com/ahmsoliman/tslink2</i><i><br></i>Data is simulated such that correctly linked/matched identifiers follow the following formula:<i><br></i><i>|</i><i>Ergo_ID - </i><i>patient_ID|</i><i> mod 10⁴ == 0</i><br><i><br></i>The above formula is useful in evaluating the linkage algorithm performance.