Blood group identification using Raspberry Pi
Create New

Blood group identification using Raspberry Pi

Project period

04/13/2017 - 05/12/2017




Blood group identification using Raspberry Pi
Blood group identification using Raspberry Pi

Determine blood type is essential before administering a blood transfusion, including in an emergency. Currently, these tests are performed manually by technicians, which can lead to human errors. Various systems have been developed to automate these tests, but none can perform the analysis in time for emergencies. This work aims to develop an automatic system to perform these tests in a short period, adapting to emergencies. To do so, it uses the slide test and image processing techniques using the Raspberry Pi. The image captured after the slide test is processed and detects the occurrence of agglutination. Next, the classification algorithm determines the blood type in the analysis. Finally, all the information is stored in a database. Thus, the system allows determining the blood type in emergencies very fastly.

Determining blood types is very important during an emergency before administering a blood transfusion. Presently, these tests are performed manually by technicians, which can lead to human errors. Determination of the blood types in a short period and without human errors is very much essential. This paper presents a new methodology for determining blood group by taking an image of blood sample content added chemicals such as Anitclonal A, B, D and by processing this image in raspberry pi 3 we can get the blood group. Phenotyping based on Raspberry pi and python 3.5 for detection of blood group using image processing. The image processing techniques such as thresholding and morphological operations are used for the basic operation of the images. By using the standalone system based on the raspberry pi we can easily take the image of the blood sample process it and the result will be shown on the LCD. Depending on the agglutination rate we can classify the blood group. Thus, the developed automated method determines the blood type using image processing techniques. The developed method is useful in an emergency and also used when several people are large. 

Why: Problem statement

Before performing a blood transfusion, it is necessary to perform certain tests that are properly standardized. One of these tests is the determination of blood type and this test is essential for the realization of a safe blood transfusion, to administer a blood type that is compatible with the type of receiver. However, there are certain emergencies which due to the risk of a patient's life, it is necessary to administer blood immediately. In these cases, as the tests currently available require moving the laboratory, it may not be time enough to determine the blood type and is administered blood type O negative considered universal donor and therefore provides less risk of incompatibility.
However, despite the risk of incompatibilities be less sometimes occur transfusion reactions that cause the death of a patient and it is essential to avoid them, administering blood based on the principle of the universal donor only in emergencies. Thus, the ideal would be to determine the blood type of the patient even in emergencies and administering compatible blood type from the first unit of blood transfusion. Secondly, the pre-transfusion tests are performed manually by a technician's analysis, which sometimes leads to the occurrence of human errors in procedures, reading, and interpreting of results. Since these human errors can translate into fatal consequences for the patient, being one of the most significant causes of fatal blood transfusions is extremely important to automate the procedure of these tests, the reading, and interpretation of the results.

How: Solution description

Blood group detection using fiber optics. In this technique, the transmitter is used to generate pulses of frequency 10KHZ. Then these pulses are fed to the Light Emitting Diode [LED], which converts electrical variations into optical variations. After that, the optical signals were launched into the fiber. Then it is fed to the blood sample and it is received by the receiver which converts the optical variations again into electrical variations. The observed electrical variations are different for all blood types. Due to the optical variations of different blood group, there will be corresponding voltage variation in the output of the photodetector. Thereby the blood groups (ABO) can be determined without using the antigen. But, the Rh (positive and negative) type of the blood group has not discussed.

  1. Classification of blood type by microscopic color images. In this semi-automated system, the blood group can be identified by microscopic color images. Initially, it performs image pre-processing by histogram equalization and color correction and then color space conversion for converting the RBC to HIS. Then, it extracts the color and texture feature of the images using the cumulative histogram and haralick method respectively. Then finally the corresponding person's blood group can be analyzed by using Support Vector Machine (SVM). In this system, the more skilled persons are needed to handle and it is tedious to do.
  2. Rapid Automated Blood Group Analysis with QCM Biosensors. In this type of analysis, protein A coating is provided on the gold surface of QCM biosensors for the immobilization of antibodies against blood group antigens A and B which permits the identification of the blood groups with two measurements. But for determining Rh factor one more experiment is needed. Here the computer and software are essential to detect the blood group. It also requires chemicals and reagents for the determination and that is expensive.
  3. Electronic data processing-assisted serial automation of current methods in blood group serology. The introduction of special centrifugal racks with a transparent bottom into the conventional typing of blood group in glass tubes facilitates the simultaneous work on and reading of a maximum of 32 complete ABO, Rhesus, and Kell typing in one series. As a result of the facts that it is unnecessary to label the individual tubes and that the pipetting of serum and erythrocyte suspension is done automatically and through the unmistakable classification of the samples using bar-coding, the manual work is reduced to about 50%. Even though it is useful but it is a semi-automated system. So the working personnel has some difficulties.
  4. A Prototype for Blood Typing Based on Image Processing,”the fourth International Conference on SensorDevice Technologies and Applications, Copyright (c) IARIA, 2013. Errors have occurred in blood transfusions since the technique began to be used. One requirement was the mandatory reporting of all fatalities linked to blood transfusion and donation. The humans will inevitably make errors and that the system design must be such that it decreases errors and detects residual errors that evade corrective procedures.


How is it different from competition

Two techniques are widely used for blood group analysis. Among these the most widely used one is the ABO technique. In this antigen A, antigen B and antigen D is used for analyzing the blood group. According to ABO and Rh blood grouping system, the person can belong to any one of the following blood groups: A positive, A Negative, B positive, B negative, AB positive, AB Negative, O positive, O Negative. While doing the blood group analysis by a manual process in laboratories, a drop of antigen is added with a drop of the blood sample and the technician has to wait for few seconds, to check whether the clumping reaction has occurred or not. Based on the level of the reaction occurred, an individual’s blood group can be identified by the technicians.

The blood has been taken and place a five drop of blood on the slide and then add an antigen (A, B & D), Bombay blood group and blood cell. Then the agglutination reaction occurs. After that, the image can be captured by the Raspberry pi camera.

Who are your customers

Common people and Government Hospitals

Project Phases and Schedule

  1. Designing and planning
  2. Hardware setup
  3. Interfacing the sensor components
  4. Programming
  5. Testing

Resources Required

Hardware Required: Raspberry Pi, RFID module, LDR, Wifi

Software Required: Python programming, Raspbian


Leave a Comment

Post a Comment