AI system spots childhood disease like a doctor
AN ARTIFICIAL intelligence (AI) programme developed in China that combs through test results, health records and even handwritten notes diagnosed childhood diseases as accurately as doctors, researchers said on Monday.
From the flu and asthma to life-threatening pneumonia and meningitis, the system consistently matched or outperformed primary care paediatricians, they reported in Nature Medicine.
Dozens of studies in recent months have detailed how AI is revolutionising the detection of diseases including cancers, genetic disorders and Alzheimer’s.
AI-based technology learns and improves in a way similar to humans, but has virtually unlimited capacity for data processing and storage.
“I believe that it will be able to perform most of the jobs a doctor does,” said senior author Kang Zhang, a researcher at the University of California.
“But AI will never replace a doctor,” he added, comparing the relationship to an autonomous car that remains under the supervision of a human driver.
“It will simply allow doctors to do a better job in less time and at lower costs.”
The new technology, said Zhang, is the first in which AI absorbs unstructured data and “natural language” to imitate the process by which a physician figures out what’s wrong with a patient.
“It can mimic a human pae- diatrician to interpret and integrate all types of medical data – patient complaints, medical history, blood and imaging tests – to make a diagnosis,” he said.
The system can be easily transferred to other languages and settings, he added.
By comparing hundreds of bits of information about a single patient with a vast store of acquired knowledge, the technology unearths links that previous statistical methods – and sometimes flesh-andblood doctors – overlook.
In the nick of time
To train the proof-of-concept system, Zhang and a team of 70 scientists injected more than 100 million data points from 1.3 million pedi- atrics patient visits at a major referral centre in Guangzhou, China.
The AI programme diagnosed respiratory infections and sinusitis – a common sinus infection – with 95 per cent accuracy.
More surprising, Kang said, it did as well with less common diseases: acute asthma (97 per cent), bacterial meningitis and varicella (93 per cent), and mononucleosis (90 per cent).
Such technologies may be coming in just the nick of time.
“The range of diseases, diagnostic testing and opt ions for treatment has increased exponentia lly in recent years, rendering t he decision-making process for physicians more complicated,” Nature noted in a press release.
Experts not involved in the research said the study is further proof of AI’s expanding role in medicine.
“The work has the potential to improve healthcare by assisting the clinician in making rapid and accurate diagnoses,” said Duc Pham, a professor of engineering at the University of Birmingham.
“The results show that, on average, the system performed better than junior doctors.”
“But it will not replace clinicians,” he added.
Machine learning – which forms general rules from specific training examples – “cannot guarantee 100 per cent correct results, no matter how many training examples they use.”
AI-based tools for diagnosis abound, especially for interpreting machine-generated images such as MRI and CAT scans.
A method unveiled last month in the US to detect lesions that can lead to cervical cancer found pre-cancerous cells with 91 per cent accuracy, compared to 69 per cent for physical exams performed by doctors and 71 per cent for conventional lab tests.
Likewise, a cellphone app based on AI technology outperformed experienced dermatologists in distinguishing potentially cancerous skin lesions from benign ones, according to a study in the Annals of Oncology.