PARIS: A China-developed Artificial Intelligence (AI) program that runs test results, health records, and even handwritten notes that diagnose teething problems just like doctors did, researchers said Monday (February 12).
The flu and asthma with life-threatening pneumonia and meningitis matched or outperformed the primary pediatricians, she reports in Nature Medicine.
Dozens of studies in recent months have described in detail how AI is revolutionizing the detection of diseases. These include cancer, genetic disorders, and Alzheimer's.
AI-based technology learns and improves in a similar way to humans, but has nearly unlimited data processing and storage capabilities.
"I think she will do the most" From the work of a doctor, "senior author Kang Zhang, a researcher at the University of California, San Diego, told AFP.
" But AI never will replacing a doctor, "he says, comparing the relationship with an autonomous car that remains under the supervision of a human driver.
" It will simply allow doctors in less time and lower
The new technology, Zhang notes, is the first to allow AI to absorb unstructured data and "natural language" to mimic the process by which a doctor finds out what happens to a patient
"It can mimic and integrate a human pediatrician to interpret and integrate all types of medical data – patient complaints, 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 with individual patients with a tremendous inventory of acquired knowledge, theTechnologyConnects the Early Static Methods and sometimes also doctors for meat and blood-leaking
IN NICK OF TIM E
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 pediatric patients visit a large referral center in Guangzhou, China.
The AI program diagnosed respiratory infections and sinusitis – a common sinus infection – with an accuracy of 95 percent.
Surprisingly, Kang also said in less common diseases: acute asthma (97 percent), bacterial meningitis and varicella (93%) and mononucleosis (90%).
Such technologies may come in a short time.
"The spectrum of diseases, diagnostic tests and treatment options has increased exponentially in recent years. The decision to make doctors more complicated," Nature noted in a press release.
Experts not involved in the research said the study was further evidence of AI's growing role in medicine.
"The work has the potential to imp health care by helping the clinician to make faster and more accurate diagnoses," said Duc Pham, a professor of engineering at the University of Birmingham.
"The results show that the system was on average better than young doctors."
"But it will not replace clinicians," he added.
Machine learning, which outlines general rules from certain training examples, "can not guarantee 100% correct results, no matter how many training examples they use." ] AI-based diagnostic tools abound, especially for the interpretation of machine-generated images such as MRI and CAT scans.
A detection method for cervical cancer that was introduced in the United States last month, 91 percent accuracy, compared to 69 percent for physicians and 71 percent for conventional laboratory tests.
Similarly, an AI-based mobile app experienced dermatologists potentially outperformed cancerous skin lesions of benign lesions, according to a study in Annals of Oncology.