Pakistani students use AI for quick diagnosis

Two Pakistani students Muhammad Aleem and Rahul Raj have developed an artificial intelligence (AI) device to help diagnose coronavirus. Due to a shortage of test kits, the government intensifies efforts to combat the virus.

Who are the two young developers?

Muhammad Aleem, a final year student of Mechanical Engineering at GIKI. He is a firm believer that Industry 4.0 will revolutionize the world. This is what encouraged him to learn AI. Given his diverse expertise, he specializes in crossover projects integrating knowledge from a variety of fields. He has experience in working on smart cars, AI assistants, robotic surgery, and AI-capable medical research.

Rahul Raj is a final year computer science student at GIKI. He always fascinated by the concept of AI and Machine Learning (ML). He has worked on a number of ML projects related to autonomous driving, image and speech recognition, classification, and prediction. Rahul says his lifelong goal is to learn all about AI. So he can use his abilities to make the world a better place.

Muhammad Aleem said “the virus is still growing rapidly and our hospitals already overwhelmed. We have decided to turn to artificial intelligence. It will help to identify cases rapidly in the absence of testing kits.

The doctors are at the forefront of the fight against the Coronavirus. The government is moving fast to provide medical supplies. Aleem and his colleague Rahul Raj, have developed a technology to help doctors fight against the coronavirus. Aleem told, “The AI-based deep learning model we’ve developed from scratch is a computing tomography (CT) scan of the lungs with 92% confidence in detecting COVID-19. “

How does an AI detector help identify patients?

The AI detector may offer an alternative way to help diagnose coronavirus patients. The detector is based upon CT imaging of the chest. If CT scans are available, then it will take a time of 7-10 seconds to analyze and find out if the patient is COVID-19 positive. Detectors not only help to save time but also reduce the engagement of specialists such as radiologists.

Automatic analysis can help identify two things. If the person has tested positive or negative for the novel coronavirus, it can be confirmed with 92% confidence.

Secondly, based on medical imaging, it can help identify the exact status, effects, and severity of the damage to the lungs. The aim is to help doctors to diagnose quickly. So the patients can be instructed on the next course of action (such as quarantine or isolation). Since the detector relies on medical imaging, the biggest limitation is the cost of CT scans in Pakistan, which is around Rs 5,000-8,000, as well as the unavailability of diagnostic equipment.

Requests from the government for data and assistance

The AI detector is a profound learning model in which computers learn just like humans: from examples and actions. Aleem Explained that The more data (such as images and text) an algorithm can train, the more accurate it will be.
That is why the team is in dire need of health facilities and more data and support from the government. “Now we need more CT scans of the coronavirus, so we can improve the accuracy of the detector and begin testing.” The developers say the government’s support and endorsement could speed up the assessment as they are “committed to helping save Pakistanis in times of crisis.”

Aleem said, Some countries, such as China, are working on similar AI systems to diagnose coronavirus. However, the data or AI framework is not available as an open-source. The output of our system may be similar, but we have our own method for achieving results.