Current position:Home >>News >>Trade news

Six new developments in the medical industry.

Date:2017-12-26 14:49:10

The latest development of artificial intelligence in the medical industry is mainly focused on new drug development and disease diagnosis.

  new drug research and development

  1. Sanofi Pasteur used AI to develop a flu vaccine.

  Sanofi Pasteur is a world-renowned research and development company.Recently, it teamed up with BERG, a biomedical company, to use artificial intelligence to develop a flu vaccine.

Every year, 10 to 20 percent of the U.S. population is infected with the flu, and the centers for disease control and prevention (CDC) believes that the best way to control influenza is to vaccinate.However, different people have different reactions to the flu vaccine, and some people get better immunity from it, and the effect is very general.Artificial intelligence is expected to find the underlying cause.

BERG's platform USES its developed artificial skills to conduct data-driven analysis of high-throughput molecules and clinical information.It can extract executable insights from scattered, massive data, and this approach has been validated.Using this artificial intelligence platform, sanofi Pasteur will look for potential biomarkers that can assess the effects of seasonal flu vaccines.If all goes well, these markers can predict the extent and durability of the immune response caused by flu vaccines, which will help future vaccine development and benefit patients.

  2. Two big computer networks help GSK to develop new drugs.

  each other - was the second of new drugs, network fault will get further in the first network, and through ascension of new drug molecules, and makes the second drawn from the network.

After training to each other, the two networks from the 7200 chemical elements in the public databases to find a lot of potential anti-cancer drugs, including 60 money that has been registered by other company, this system is verified from the side can really find molecules with antitumor activity.In just a month, the researchers claim, their technology will be able to find the 100 most promising candidates from millions of molecules.This will greatly reduce the discovery process and hopefully reduce the cost of trial and error.

In August, glaxosmithkline (GSK) had reached a deal to find new drugs.Perhaps the first new drug designed by AI has entered the field of artificial intelligence.

  Disease diagnosis

3. In less than 1 second, artificial intelligence can diagnose colorectal cancer with 86% accuracy.

Diagnosing cancer correctly and timely has always been a problem.Recently, a group of scientists from Japan used artificial intelligence to make a diagnosis of colorectal cancer in less than a second, with an accuracy rate of 86 percent.What's amazing is that it can even make a diagnosis before a benign tumor worsens.

In this study, the scientists gave artificial intelligence a deep insight into the polyps in the colorectal.They amplified polyps by 500 times, allowing artificial intelligence to carefully see the changes in these tissues.They then provided 30, 000 pre-cancerous and cancerous cell photos, using machine learning to train artificial intelligence.In the end, the system could be diagnosed in just one second, with a whopping 86 percent accuracy.This is the first time that artificial intelligence has been used to diagnose colorectal cancer.

4. Diagnosis of breast cancer, the accuracy of artificial intelligence is up to 97%.

Breast cancer kills 40, 000 women a year in the United States.This unfortunate result was not associated with a timely diagnosis of breast cancer.According to statistics, if breast cancer can be found early, they may even be cured.

On the other hand, mammography, as a routine screening method for breast cancer, has a high false positive rate.Some patients have suspicious tissue in the mammogram, and they also opt for surgery to remove it.However, the analysis of these tissues after surgery often finds that they are benign.In other words, these women were treated unnecessarily.So, is there any technology that can be used to ensure that breast cancer is diagnosed and that it can reduce the false positive rate?

Artificial intelligence can do that.The system, developed by researchers at harvard medical school and Massachusetts general hospital, can be diagnosed from a range of data points.In addition to biopsy results and pathology reports, the ai will also analyze family history and race information.In this way, the diagnostic accuracy is greatly improved.

In 335 high-risk pathologies, the diagnostic accuracy of the artificial intelligence was 97%.Because of its accuracy, the researchers said, the chance of patients receiving unnecessary surgery dropped by 30%!For patients, this is a huge boon.

5. Progress markers of Parkinson's disease detected by artificial intelligence.

GNS Healthcare, based in Cambridge, mass., announced that it had used artificial intelligence to find a marker for progress in Parkinson's disease, published in The Lancet Neurology.

It is worth noting that this is a typical case of using "computer" to solve the problem of "human brain".Using the machine learning technology, GNS from 312 Parkinson's disease patients and 312 control group volunteers collected in genetics and clinical data, and the genetic variation in the progress of the disease.The system found a gene called LINGO2.Along with another genetic variant, they can be used to predict the progress of a patient's decline in motor ability.In addition, researchers have identified a number of demographic factors related to disease progression.

6. Alzheimer's disease was predicted several years ago.

University of Bari in Italy (University of Bari, the researchers used magnetic resonance imaging (MRI) scan of the 67 volunteers of the brain, some of them suffer from alzheimer's disease, some patients with mild cognitive impairment, and some normal healthy people.Using algorithms, they were able to accurately identify patients with alzheimer's disease, with 86 percent accuracy.In addition, they were able to distinguish healthy people from mild cognitive impairment.

Mild cognitive impairment is generally considered a precursor to alzheimer's disease.In the study, scientists also found that people with mild cognitive impairment in the experiment eventually developed alzheimer's disease.In other words, using the algorithms they developed, we could see the brain with cognitive impairment in the years leading up to alzheimer's disease, predicting the onset of alzheimer's disease.

There is no doubt that the age of artificial intelligence has arrived.Researchers who understand the use of artificial intelligence have a significant advantage over those who do not understand the use of artificial intelligence.


Category: Trade news