Download PDFOpen PDF in browser

Architectural Design of Medical Test Scanner Machine for Mass Medical Tests Scanning, Results Recording and Visualisation

EasyChair Preprint 8356

8 pagesDate: June 22, 2022

Abstract

In medical laboratories, many tests are taken in order to be analysed for providing better treatment to patients. During the times of rise of epidemics and pandemics, a mass testing approach for screening the spread of diseases in the population is used. Currently, it takes many hours for health workers to manually record tests’ results in systems or logbooks. Based on object recognition with computer vision techniques, the OCR engine, and data analysis techniques, an efficient novel approach to design the Medical Test Scanner machine has been successfully achieved. The machine is designed to scan different RDT types for invalid, negative and positive results for a single or many patients at time. The results with the same patient identification number are clustered to be recorded on a single patient, and results with the same test type are clustered to be recorded on respective test types. As the RDT types are not predefined, all the existing and the future RDTs can be monitored due to the machine automatically recording the patient ID, the RDT types and their results dynamically. This machine can be used extensively in laboratories and in times of rise of epidemics and pandemics as it eases the work of health workers in recording and assessing the test results, laboratory tests management, mass testing, and screening the spread of diseases.

Keyphrases: Optical Character Recognition, computer vision, medical test scanner, python tesseract, rapid diagnostic test

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:8356,
  author    = {Josue Uwimana},
  title     = {Architectural Design of Medical Test Scanner Machine for Mass Medical Tests Scanning, Results Recording and Visualisation},
  howpublished = {EasyChair Preprint 8356},
  year      = {EasyChair, 2022}}
Download PDFOpen PDF in browser