PowerShell-based novel framework for Big health data analysis

An obvious feature of the big data is overload. When we are held up in the Lake of big data, it is necessary to filter the most meaningful information [Khan et al. (ICCWAMTIP 2018:232–236, 2018), (Int J Inf Technol 12(2):409–417, 2020)]. The key element is segmentation, which involves the breakdown of the dataset into smaller ones. MIMIC-III (Medical Information Mart for Intensive Care III), an open critical care database, comprises data flow that encompasses patient information during whole hospital length of stay, i.e., from the beginning of hospital admission to patients’ discharge from the hospital. As MIMIC III stores a large volume of shared data, selecting useful data using traditional data mining approach to tailor academic research would be time consuming and resource demanding. Herein, we introduced a robust Windows build-in tool known as PowerShell, which is used to segment the big data into a practical dataset. Since the PowerShell script is open on the platform to demonstrate its use for further public research, we would present the step-by-step operation here to help readers grab a general idea of its mechanism.