قالب وردپرس درنا توس
Home / LifeStyle / How does AI change the way doctors treat patients?

How does AI change the way doctors treat patients?

Advances in artificial intelligence (AI) are much faster than anyone could have guessed. This emerging technology is now being used by businesses and is even entering consumer goods. One industry fully committed to AI is the healthcare industry, and doctors and other hospital staff are using advanced machine learning algorithms to solve problems in new ways.

TechRadar Pro spoke with HeartFlow's Founder and Chief Technology Officer Charles A. Taylor about how the company is using deep learning to create 3-D models of the patient's heart to make physicians safer and more effective Method to diagnose cardiovascular disease.

Can you explain the technology behind HeartFlow and its use in the healthcare industry?

HeartFlow pioneered technology to help clinicians diagnose coronary heart disease (CHD). HeartFlow analysis uses data from a standard cardiac CTA scan and first uses deep learning to create a personalized 3D digital model of the patient's coronary arteries. HeartFlow then applies computational fluid dynamics and advanced algorithms to the model to evaluate the effects of blockages on blood flow. This analysis can help clinicians diagnose CHD, develop the optimal treatment for each patient, and reduce the need for additional testing.

The potential of HeartFlow technology to influence the world is enormous, with CHD the most common cause of death worldwide. It is responsible for more than 66,000 deaths in the UK each year, and it is estimated that more than 2.7 million Britons are currently living with the disease.

The practicality of the technology has been demonstrated in recent studies. For example, the research of the ADVANCE registry examined more than 5,000 patients in Europe, Japan and North America. The HeartFlow analysis allowed physicians to change their recommended treatment plan in two-thirds of patients. This meant that some patients receiving stenting or a bypass could be treated with medications instead. Other medicated treatments were considered invasive to optimize blood flow to the heart.

How does your product receive the information from a standard CT scan to create a personalized 3D digital model of a patient's arteries?

The HeartFlow analysis process begins with a cardiac CT scan of the patient's heart. The hospital uploads image data to HeartFlow's secure cloud-based system, where machine learning and trained human analysts create a personalized 3D digital model of the patient's coronary arteries.

Next, powerful algorithms solve millions of complex equations to simulate the blood flow inside the model. The effects of blockages on blood flow in the arteries can then be assessed.

Full analysis is safely returned to the hospital and doctors. Cardiologists can interact with the model ̵

1; by selecting, enlarging and reducing certain areas of the coronary arteries for examination, and rotating the image to obtain a level of examination that is normally possible only through an invasive procedure.

Ultimately, physicians have a non-invasive ability to consider fractional flow reserve (FFRct) values ​​along arteries leading to the heart. The fractional flow reserve values ​​describe the ratio of pressures before and after blockage in an artery to help physicians determine the effects of blockage on blood flow. A positive FFRct value ( < 0.80) indicates that blockage is obstructing blood flow to the heart muscle. The HeartFlow analysis was previously validated against invasive FFR and showed excellent correlation.

How many hospitals have used your technology and how has it influenced the way they look after patients?

To date, HeartFlow technology is available in more than 30 hospitals in NHS England. Further extensions are planned. The technology is being accelerated by the NHS Innovation and Technology Payment Program (ITP) and Rapid Uptake product through the Accelerated Access Collaborative of the National Institute of Health & Care (NICE). These programs aim to invest in state-of-the-art, market-ready medical advances, diagnostics and digital platforms that improve the quality and efficiency of patient care.

For patients, the benefits of the technology are clear – most can be diagnosed without an invasive diagnostic angiogram – something that carries some risk and may help some people to reluctant to study CHD symptoms feel.

In addition to the clear medical benefits that HeartFlow offers, it also aims to save the cost of the NHS. NICE estimates that HeartFlow could save the healthcare service by more than nine million pounds each year. Savings are largely due to the ability of the technology to reduce the need for costly additional testing or invasive procedures that may require close monitoring or overnight recording.

How does HeartFlow use algorithms to determine if a blockage will significantly affect blood flow?

The core of the HeartFlow analysis is based on deep learning, computational fluid dynamics, and cloud computing. HeartFlow uses deep-learning technology that is applied to image data from a cardiac CTA scan to create a personalized 3D model of the patient's coronary arteries. We then apply computational fluid dynamics to the model to calculate blood flow and evaluate the effects of blockages on coronary blood flow. This information helps physicians diagnose CHD and determine optimal treatment. The Deep Learning and Computational Fluid Dynamics algorithms all run in the cloud, which is necessary to provide a comprehensive HeartFlow analysis for a large number of patients.

HeartFlow also uses web and mobile applications to communicate with the Internet Hospital IT infrastructure. An important safeguard is that only coronary CT image data will be sent to HeartFlow in the United States for analysis via the cloud, and patient identification information will remain in the country of origin. Once the analysis is complete, the 3D model is retrieved from the patient identification information and then sent back to the web interface for physicians to review their analysis.

(Photo: © Credit: Devrimb / iStockPhoto)

Would you say that the healthcare industry is taking AI faster than other industries? If not, what are the barriers to AI adoption in healthcare?

It's hard to say for sure, as there are certainly some compelling applications already. Naturally, politicians and health professionals are careful about technology and patient care because people's lives can be at stake. Thorough testing is always required before implementing new working methods, as was the case with the HeartFlow analysis.

However, the benefits of new technologies can be significant – such as improving patient care, health outcomes, and saving money from the NHS. It comes as no surprise that Prime Minister Theresa May has promised millions in the healthcare industry how AI can support the NHS. In addition, Health Secretary Matt Hancock has made expanding the technology capability of hospitals a top priority. Last year, he released a white paper titled future of healthcare advocating the role of technology for modernizing the NHS and improving efficiency.

What advice would you give CTOs who would like to integrate AI into their operations?

People can defend themselves against change. This applies to employees of all industries, and this resistance is often experienced when new technologies are introduced somewhere without sufficient stakeholder engagement.

However, the integration of AI will, in most cases, greatly facilitate the lives of healthcare professionals and staff, and serve as tools to achieve better outcomes. Too often this is understood only at the top of the organization and in the C suite. As CTOs, we should try to work with Human Resources and Internal Communications to ensure that all employees understand the organization's technology strategy, how it can help them do their jobs better, and, most importantly, what opportunities arise.

(Photo: © image credits: Rawpixel / Pixabay)

What is the potential of AI in health care and could it possibly replace a consultant in the future?

The potential for AI in health care is enormous as AI becomes more integrated into the healthcare system. AI is changing the way physicians offer their patients affordable, high-quality diagnostic and treatment services. For example, the technology can detect patterns and anomalies in diagnostic data from medical scans at a speed and volume that people simply can not replicate.

AI's processing power offers far more applications than simple diagnostics. It can be used to help healthcare professionals identify the severity of what's wrong with the patient and give insight into why certain symptoms occur. This additional information helps physicians decide on the most effective treatment.

AI has virtually unlimited potential, but the bright future it offers can not be achieved unless the necessary infrastructure is in place to support its development.

The implementation of AI technology is designed to enhance, not replace, the performance and efficiency of trained healthcare professionals. Using HeartFlow analysis, AI technology can quickly generate an accurate 3D model of the patient's arteries using a CT scan, but it still requires a physician to interpret the meaning of the disease in the model and with other patient data to integrate. and then decide on the best treatment.

The AI ​​and its analysis are invaluable, helping physicians make the most of their time and make better diagnoses. However, human intervention is always the focus of patient care.

Charles A. Taylor, Founder and Chief Technology Officer of HeartFlow

Source link