An article regarding applications of AI technology in clinical diagnoses of diseases children suffering from reported that the AI system implemented has surpassed doctors in diagnostic accuracy.

The article, published in the medical journal Nature Medicine on Feb. 12, was co-authored by Guangzhou Women and Children’s Medical Center and YITU Healthcare, a startup that pioneers in AI healthcare innovation.

The research team used natural language processing (NLP) to achieve high accuracy rates on par with doctors when reading electronic health records and generating patient diagnoses.

For comparison purposes, the research team collected cases of 12,000 children patients and found that the AI system performed better than less experienced doctors and almost as well as experienced ones in the diagnostic accuracy rate.

The article also said that the system could assist doctors to diagnose some acute and potentially life-threatening diseases. The AI system has achieved high accuracy in assessing many dangerous conditions including bacterial meningitis (93%), varicella (93%), and influenza (94%).

101.6 million data points have been gathered for the research involving over 1.36 million outpatient visits from January 2016 to July 2017 in Guangzhou Women and Children’s Medical Center to train and validate the model. The primary diagnoses included 55 diagnosis codes encompassing common diseases in pediatrics all of which represent a wide range of pathologies.

Since the system was put into clinical use at Guangzhou Women and Children’s Medical Center on Jan. 1, 2019, it has helped doctors diagnose 30,276 patients with an accuracy rate of 87.4 percent.