Pink Tech Design, an IT innovation company, has recently developed an artificial intelligence (AI) algorithm to classify x-rays of patients as being COVID-19 positive. With the development being successful, it can pre-screen patients who need the confirmatory tests.
The pandemic has caused a devastating effect. Hence, it is extremely critical to detect positive cases as early as possible to control the spread of the virus further. It is evident that application of advanced AI techniques combined with radiological imaging can be assistive to overcome many challenges in accurate and early detection of this disease.
Once the company gets the access to a dataset of COVID-19 positive and negative x-rays released by Kaggle which is the subsidiary of Google, the world's largest data science community with powerful tools and resources the scientists process the data and train their COVID-19 detector with Keras and TensorFlow.
After many optimisations, the model gave 90% accuracy with a sensitivity of 0.8 and specificity of 1.0. Though these are initial results, the development has made it clear that x-rays and CT (computed tomography) scans can be an equally effective method to detect COVID-19 as well as present greater detail and accuracy in the results.
Speaking about the development, Dr. Kanav Kahol, CEO, Pink Tech Design said, “The project has led us to some extremely promising results and we are keen to build on this success rapidly to help in the fight against the virus. The AI model employed in the study is able to predict results with great accuracy. However, our research team continues to strive for even more robust and reliable results.