Home Healthcare AI Outperforms Some Doctors in Diagnosing Childhood illnesses

AI Outperforms Some Doctors in Diagnosing Childhood illnesses

Diagnosing an illness calls for the need to connect the dots and ingest a lot of information.

AI might be ideal for handling such a task, and recent tests have shown that a single system can outperform some doctors in diagnosing children’s diseases.

Kang Zhang together with his colleagues at the San Diego-based University of California used medical records to train an AI.

The records were drawn from 1.3 million patient visits at a leading medical center in Guangzhou, China.

All the patients were all below 18 years and visited their physician between January 2016 and January 2017.

READ MORE: AI Outperforms Doctors in Cervical Cancer Detection

Patients’ medical charts composed of laboratory test results and text written by physicians.

To assist the artificial intelligence (AI), Zhang and his colleagues had human physicians interpret medical records in a bid to recognize the portions of text associated with their laboratory tests, history of illness and the child’s complaint.

When tests were done on previously unidentified cases, the artificial intelligence (AI) was able to diagnose chicken pox, roseola, influenza, hand-foot-mouth illness and glandular fever, which is also referred to as mononucleosis, with an accuracy rate of between 90 and 97%.

READ MORE: Hot AI Healthcare Startup Babylon Unveils a Chatbot that Beats GP at Medical Exams

“When you’re busy you can see 80 patients a day. And you can only grasp so much information. That’s where we potentially as human physicians might make mistakes. AI doesn’t have to sleep, it has a large memory and doesn’t lose energy,” he says.

The team compared the accuracy of the model to that of 20 human doctors (pediatricians) with different years of experience.

The model did a better job than the junior pediatricians, even though their senior colleagues outperformed the AI.

The artificial intelligence-based model could be leveraged in triaging patients in emergency departments. “Given sufficient data, AI should be able to tell if this is an urgent situation and needs a referral or if it’s a cold,” says Zhang.

According to Chris Russell from the London-based Alan Turing Institute, the model will not allow people to bypass physicians completely when seeking treatment, as such medical records ought to be developed by trained experts, and their knowledge is vital for the diagnosis.

“Someone needs to be there discussing your symptoms and putting them into the machine. I don’t see how this technology could be used to take doctors out of the loop. It could be used to help them, but it’s a very long way from replacing medical professionals,” he says.

“If it’s deployed as an interface directly with the person where they type in their symptoms, I can see how people would be very uncomfortable with this. When you go see a doctor, you want to feel like there’s someone there who cares about you,” Russell says.

“But you don’t want to go to the emergency room and wait 5 hours because you have some pain in the abdomen that’s not appendicitis but just related to gastroenteritis or the food you ate. All those diseases have tell-tale signs, and just as we physicians ask a series of questions to drive a diagnosis, AI can do the same,” says Zhang.

What’s more, Zhang and his team are currently training the artificial intelligence (AI) to diagnose adulthood illnesses.

Subscribe to our newsletter

Signup today for free and be the first to get notified on the latest news and insights on artificial intelligence

KC Cheung
KC Cheung has over 18 years experience in the technology industry including media, payments, and software and has a keen interest in artificial intelligence, machine learning, deep learning, neural networks and its applications in business. Over the years he has worked with some of the leading technology companies, building and growing dynamic teams in a fast moving international environment.
- Advertisment -


AI Model Development isn’t the End; it’s the Beginning

AI model development isn’t the end; it’s the beginning. Like children, successful models need continuous nurturing and monitoring throughout their lifecycle. Parenting is exhilarating and, if...