AI used to create & # 039; digital twin & # 039; hearts that allow surgeons to test their technique

The twin digital heart (in the picture) developed by Siemens Healthineers is an example of how medical device manufacturers are using artificial intelligence (AI) to help doctors make more accurate diagnoses as medicine enters an age more and more personalized

Armed with a mouse and a computer screen instead of a scalpel and an operating room, cardiologist Benjamin Meder carefully places the electrodes of a pacemaker in a digital heartbeat.

Using this "digital twin" that mimics the electrical and physical properties of the cells in the heart of patient 7497, Meder runs simulations to see if the pacemaker can keep the patient with congestive heart failure alive, before he has inserted a knife.

The twin digital heart developed by Siemens Healthineers is an example of how medical device manufacturers are using artificial intelligence (AI) to help doctors make more precise diagnoses as medicine enters an increasingly personalized age.

Scroll down to watch the video

The twin digital heart (in the picture) developed by Siemens Healthineers is an example of how medical device manufacturers are using artificial intelligence (AI) to help doctors make more accurate diagnoses as medicine enters an age more and more personalized

The twin digital heart (in the picture) developed by Siemens Healthineers is an example of how medical device manufacturers are using artificial intelligence (AI) to help doctors make more accurate diagnoses as medicine enters an age more and more personalized

WHAT IS A & # 39; TWIN DIGITAL & # 39 ;?

Siemens Healthineers has created a vast database with more than 250 million annotated images, reports and operational data on which you can train your new algorithms.

In the example of the digital twin, the AI ​​system was trained to interweave data about the electrical and physical properties and structure of a heart in a 3D image.

Both virtual models and 3D printed hearts will be used to help surgeons develop treatment plans.

The challenge for Siemens Healthineers and its rivals such as Philips and GE Healthcare is to keep the technology giants from Google to Alibaba in the hope of using large amounts of data to get a share of health care spending.

For Siemens Healthineers and its traditional rivals, making the transition from being primarily hardware companies to pioneers of medical software is considered crucial in a field increasingly filled with new entrants.

Google has developed a lot of Artificial Intelligence tools, which include algorithms that can analyze medical images to diagnose eye diseases or examine digital records to predict the probability of death.

Alibaba, meanwhile, hopes to use its data and cloud systems to address the shortage of medical specialists in China. He is working on AI-assisted diagnostic tools to help analyze images such as CT scans and MRIs.

Siemens Healthineers, which broke away from German parent Siemens in March, has outperformed the market in recent quarters with sales of medical imaging equipment thanks to a series of new products.

But analysts say that the German firm, the Dutch Philips and GE Healthcare, a subsidiary of General Electric, will be pressured to show that they can save money to health systems since the expense is more linked to the results of patients and patients. hospitals rely on massive purchases to push for discounts

Siemens Healthineers has a long history in the industry.

He made the first X-ray machines manufactured industrially in 1896 and is now the world's largest manufacturer of medical imaging equipment.

An electrode of a pacemaker with a three-dimensional impression of a human heart is represented. To create a digital twin, an AI system is trained to weave a heart in a 3D image

An electrode of a pacemaker with a three-dimensional impression of a human heart is represented. To create a digital twin, an AI system is trained to weave a heart in a 3D image

An electrode of a pacemaker with a three-dimensional impression of a human heart is represented. To create a digital twin, an AI system is trained to weave a heart in a 3D image

Now, the ambition of the CEO, Bernd Montag, is to transform it into the "GPS of medical care", a company that uses its data to sell smart services, and allows smaller technology companies to develop applications that feed on their database.

As it adapts, Siemens Healthineers has invested heavily in IT. It employs some 2,900 software engineers and has more than 600 patents and patent applications in machine learning.

THE RISE OF AI IN HEALTH CARE

With health care budgets under increasing pressure, AI tools such as the digital cardiac twin could save tens of thousands of dollars by predicting results and avoiding unnecessary surgery.

The shortage of doctors in countries like China is also stimulating the demand for new artificial intelligence tools to analyze medical images and the race is underway to market products that could shake health systems around the world.

While AI has been used in medical technology for decades, the availability of large amounts of data, lower computing costs and more sophisticated algorithms means that the income from AI tools will skyrocket to $ 6.7 billion in 2021 from $ 811. million in 2015, according to a study by research firm Frost & Sullivan.

The size of the global medical imaging software market is also expected to jump to $ 4.3 billion in 2025 from $ 2.4 billion in 2016, said data portal Statista.

Experts are calling for the emergence of AI in medical technology & # 39; an evolution that is accelerating towards more than one revolution & # 39;

You are not alone. Philips says that about 60 percent of its research and development staff and spending is focused on software and data science.

The company said it employs thousands of software engineers, without being specific.

Experts say that the success of AI in medical technology will depend on access to reliable data, not only to create diagnostic models, but also to predict how effective treatments will be for a specific patient in the days and years to come.

"Imagine that in the future, we have a patient with all the functions of their organs, all their cellular functions, and we can simulate this complexity," said Meder, a cardiologist at the Heidelberg University Hospital in Germany who is testing Siemens digital devices. Healthineers heart software

"We would be able to predict weeks or months in advance which patients will become ill, how a particular patient will react to a given therapy, which patients will benefit the most, which could revolutionize medicine."

To this end, Siemens Healthineers has created a vast database of more than 250 million annotated images, reports and operational data on which its new algorithms can be trained.

In the example of the digital twin, the AI ​​system was trained to interweave data about the electrical and physical properties and structure of a heart in a 3D image.

A monitor shows a 3D image of a human heart. Using this "digital twin" that mimics the electrical and physical properties of the cells in the heart of patient 7497, doctors perform simulations to see if the pacemaker can keep the patient alive with congestive heart failure without surgery

A monitor shows a 3D image of a human heart. Using this "digital twin" that mimics the electrical and physical properties of the cells in the heart of patient 7497, doctors perform simulations to see if the pacemaker can keep the patient alive with congestive heart failure without surgery

A monitor shows a 3D image of a human heart. Using this "digital twin" that mimics the electrical and physical properties of the cells in the heart of patient 7497, doctors perform simulations to see if the pacemaker can keep the patient alive with congestive heart failure without surgery

One of the main challenges was to hide the complexity and create an interface that is easy to use, said Tommaso Mansi, senior director of R & D at Siemens Healthineers, who developed the software.

Experts say that the success of artificial intelligence in medical technology will depend on access to reliable data, not only to create models for diagnosis but also to predict how effective treatments will be for a specific patient in the days and years to come.

Experts say that the success of artificial intelligence in medical technology will depend on access to reliable data, not only to create models for diagnosis but also to predict how effective treatments will be for a specific patient in the days and years to come.

Experts say that the success of artificial intelligence in medical technology will depend on access to reliable data, not only to create models for diagnosis but also to predict how effective treatments will be for a specific patient in the days and years to come.

To test the technology, the Meder team created 100 digital cardiac twins from patients treated for heart failure in a six-year trial.

The computer makes predictions based on the digital twin and then compared with the actual results.

His team hopes to finish evaluating the predictions by the end of 2018.

If the results are promising, the system will be tested in a larger multi-center test as the next step to obtain software approved by regulators for commercial use.

Siemens Healthineers declined to say when the technology could be used by the clinics or give details on how you can monetize your digital heart or the models of other organs you are developing, such as the lungs and liver.

Both GE and Philips are also working on versions of twin digital hearts, while non-traditional players have also been active.

Both GE and Philips are also working on versions of twin digital hearts, while non-traditional players have also been active.

Both GE and Philips are also working on versions of twin digital hearts, while non-traditional players have also been active.

WHO'S MAKING TWINS OF THE DIGITAL HEART?

Both GE and Philips are also working on versions of twin digital hearts, while non-traditional players have also been active.

Philips sells AI-enabled heart models that can, for example, convert 2D ultrasound images into data that help doctors diagnose problems or automatically analyze scans to help surgeons plan operations.

His vision, like Siemens Healthineers, is to add more complexity to their existing cardiac models by combining explorations, ECGs and medical records to create a model that can predict how a heart will respond to therapy in real life.

For now, such software is still in the early stages of development and companies will have to work with regulators to determine how predictive models can be approved before doctors are willing to rely on a machine-generated diagnosis.

Access to high-quality data with enough variation will be crucial, as will the ability to interpret that data and turn it into something medical professionals can use, experts say.

In particular, models should be trained in exceptional cases as they get closer to perfection, said Vivek Bhatt, technology director of the clinical care solutions division of GE Healthcare.

"It will be extremely critical to have a continuous process to get more data, get the right kind of data and get data with those unique cases," he said.

Established Medtech players say that their long-term relationships with hospitals and research institutes and vast networks of installed machines will give them an advantage over new technology entrants.

Siemens Healthineers, GE Healthcare and Philips say their databases are powered by a mix of publicly available data, clinical trial data or collaborations with hospitals, as well as some customer data. All data are anonymous and are only used with the consent of patients, they say.

Still, some activists and academics worry that patient data will be used primarily by companies as a commercial tool.

Boris Bogdan, managing director of Accenture's scientific practice in Switzerland, believes that the ownership of the data is a gray area that could provoke a violent reaction from the patient if the companies begin to make a fortune.

"When Facebook started, nobody really cared who had the information," he said.

"Now that people understand that Facebook makes a lot of money with their data, questions like data privacy, data usage and data monetization are becoming more visible."

.