Installation

Unzip the DOSES archive to the folder of your choice. A folder named scripts will be generated containing the mixup files with the rules and the python post processing scripts. Additionally, there will be two complete_scripts: one .sh for those who want to run DOSES in Linux and one .bat for those who want to run it on Windows. Both scripts produce a final CSV file inside the parent folder.

Running DOSES:

Prerequisites: You need to have Python 2.7 installed and added to the path as well as MinorThird.

You can run the tool using the following line:

• Windows:
  • complete_script.bat. It takes three arguments
  • the path to the exe file of python e.g., C:\program files\python\python.exe,
  • the input file with the contained prescriptions in the necessary format,
  • and the path to the exe file of java e.g., c:\program file\java\jre\bin\java.exe
• Linux:
  • complete_script.sh
  • The input txt file has to be changed inside the script to that one of the user – original file is called common_dosages.txt.

DOSES should run on any Windows and Linux distribution that supports Python, but it has been tested on Windows 7 and 8 professional, and Linux openSUSE 10.2 (X86-64) only.

The post DOSES – installation guide appeared first on gnTEAM.

DOSES (DOSage Extraction System) extracts and represents free-text medication prescription instruction information in a structured form. In particular, it represents the variability and flexibility in drug directions by including minimum and maximum values for drug dosage, frequency and interval of administration, as well as optional choices. In order to comprehensively represent the information in medication prescriptions, DOSES identifies and represents in structure the following medication prescription dosage attributes:

• min/max dose number
• min/max dose frequency
• min/max dose interval
• dose unit
• optional dose

DOSES is implemented in MinorThird for the identification of the targeted dosage attributes, and Python for result post-processing and structured representation.

Currently, two versions are available for DOSES:

In DOSES v.1, the performance has been evaluated on a subset of CPRD (Clinical Practice Research Database) prescription records.

More details on the architecture and the performance can be found in.

• Karystianis, George, et al. “Modelling and extraction of variability in free-text medication prescriptions from an anonymised primary care electronic medical record research database.” BMC medical informatics and decision making 16.1 (2016): 1.

DOSES v.2 has been tailored and evaluated on a collection of patient records acquired from the UK Renal Registry (UKRR).

More details on the tailored version can be found in.

• Alfattni, Ghada, et al. “Integrating text analytics and statistical modelling to analyse the UK Renal Registry data.” Poster presented at: International Population Data Linkage Conference; 2016 AUGUST 24-26; Swansea, United Kingdom.

Contact George Christopher Karystianis, (karystianis@gmail) regarding any questions, bugs and/or suggestions.

The post DOSES appeared first on gnTEAM.