Aire-DM, the world’s first Artificial Intelligence (AI) tool to predict type 2 diabetes risk 13 years early
In a ground breaking medical advancement, the National Health Services (NHS) in England is set to trial on innovative AI tool designed to predict the risk of developing type 2 diabetes. This pioneering technology, hailed as a potential game-changer in preventive health care, is set to begin trials in 2025.
This article is divided into three parts – A. Type 2 Diabetes; B. Artificial Intelligence (AI); and C. World-First Trial of AI Tool for Type 2 Diabetes:
- TYPE 2 DIABETES:
More than 500 million people worldwide have type 2 diabetes, and finding new ways to spot people at risk before they develop the condition is a major global health priority. Estimates suggest 1 billion people will have type2 diabetes by 2050.
In 2021, diabetes was the direct cause of 1.6 million deaths and 47 percent of all deaths due to diabetes occurred before the age of 70 years. Another 530 000 kidney disease deaths were caused by diabetes, and high blood glucose causes around 11 percent of cardiovascular deaths.
The World Health Organization estimated that 90 percent of people around the world who have diabetes have type 2. An estimated 6.28 percent of the world’s population is impacted by type 2 diabetes which is translated to a prevalence rate of 6,059 cases per 100,000 people.
Type 2 diabetes is also known as type 2 diabetes mellitus.
Diabetes is a chronic disease that occurs either when the pancreas does not produce enough insulin or when the body cannot effectively use the insulin it produces. Insulin is a hormone that regulates blood glucose. Hyperglycaemia, also called raised blood glucose or raised blood sugar, is a common effect of uncontrolled diabetes and over time leads to serious damage to many of the body’s systems, especially the nerves and blood vessels.
Here’re some key facts as per World Health Organization:
- The number of people living with diabetes rose from 200 million in 1990 to 830 million in 2022. Prevalence has been rising more rapidly in low- and middle-income countries than in high-income countries;
- More than half of people living with diabetes did not take medication for their diabetes in 2022;
- Diabetes treatment coverage was lowest in low- and middle-income countries;
- Diabetes causes blindness, kidney failure, heart attacks, stroke and lower limb amputation;
- In 2021, diabetes and kidney disease due to diabetes caused over 2 million deaths. In addition, around 11 percent of cardiovascular deaths were caused by high blood glucose;
- A healthy diet, regular physical activity, maintaining a normal body weight and avoiding tobacco use are ways to prevent or delay the onset of type 2 diabetes; and
- Diabetes can be treated and its consequences avoided or delayed with diet, physical activity, medication and regular screening and treatment for complications.
According to Diabetes Canada released figures in 2022, the continued rising trend of diabetes rates in Canada with no signs of leveling or decreasing. Diabetes continues to affect more Canadians than ever before and reasserts the need for further investment into diabetes research to help turn the tide.
Laura Syron, President and CEO of Diabetes Canada said:
- The new diabetes figures show a steady, continued increase in diabetes in our country with 11.7 million Canadians living with diabetes or prediabetes; and
- These figures reaffirm our dedication to funding leading-edge research to advance medical innovations and find a cure to end diabetes.
It is also costing the healthcare system $30 billion per year to treat people with diabetes. The high prevalence of diabetes and its overwhelming impact in Canadian communities and health-care system mean that we must further diabetes research.
B. ARTIFICIAL INTELLIGENCE (AI):
Here is good news – Artificial Intelligence (AI) is playing an increasingly significant role in the management and treatment of type 2 diabetes.
AI, the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings. The term is frequently applied to the project of developing systems endowed with the intellectual processes characteristic of humans, such as the ability to reason, discover meaning, generalize, or learn from past experience.
The use of AI in healthcare, including diabetes care, can help improve outcomes, enhance decision-making, and optimize treatment plans. Here are some key areas where AI is making an impact in the field of type 2 diabetes:
- Predicting and Diagnosing Type 2 Diabetes: AI is being used to analyze large datasets of medical records, genetic information, and lifestyle factors to predict the risk of developing type 2 diabetes. Machine learning models can identify patterns and risk factors that may not be immediately obvious to healthcare professionals. This can help with:
- Early Prediction: Identifying individuals at high risk of developing diabetes before symptoms appear; and
- Risk Stratification: Classifying patients into different risk categories, enabling tailored prevention strategies.
- Personalized Treatment Plans: AI can assist in developing personalized treatment plans by analyzing a patient’s medical history, lifestyle, and genetic factors. Machine learning algorithms can:
- Recommend Optimal Treatments: AI models can suggest medications, dietary changes, exercise regimens, and lifestyle modifications based on individual needs; and
- Monitor Progress: AI-powered systems can track glucose levels, lifestyle factors, and other data to help adjust treatment plans in real time.
- Continuous Monitoring and Remote Care: AI is integrated into wearable devices (such as continuous glucose monitors and smart insulin pens) that track glucose levels and other important health metrics throughout the day. These devices can use AI algorithms to:
- Predict Blood Sugar Fluctuations: AI models analyze data from continuous glucose monitors to predict future blood glucose levels and provide real-time alerts to patients and healthcare providers; and
- Provide Insights into Behavior: AI can identify trends in blood sugar related to specific foods, activities, or stress, helping patients adjust their behavior for better control of their condition.
- Medication Management: AI can aid in managing the complex medication regimens often required for type2 diabetes. For example:
- Insulin Dosing: AI-driven apps can calculate insulin doses based on factors like glucose readings, food intake, and exercise, helping people with diabetes make more informed decisions;
- Medication Adherence: AI tools can remind patients to take their medications as prescribed and alert them when they miss doses, improving adherence and outcomes.
- Data Analysis and Research: AI has the power to analyze vast amounts of health data much more quickly than humans. This ability is driving breakthroughs in diabetes research by:
- Discovering New Treatment Options: AI algorithms can sift through scientific literature and clinical trial data to identify promising new drugs or therapeutic approaches; and
- Understanding Diabetes Mechanisms: By analyzing genetic and molecular data, AI can help researchers understand the underlying causes of type 2 diabetes and develop more effective interventions.
- Health Coaching and Behavior Modification: AI-powered virtual health coaches can assist individuals in managing their diabetes by providing:
- Dietary Recommendations: Based on an individual’s glucose levels, activity, and preferences, AI can suggest meal plans and snacks that help keep blood sugar levels in check;
- Exercise Guidance: AI can recommend exercise routines tailored to an individual’s condition and fitness level, helping patients incorporate physical activity into their daily lives; and
- Mental Health Support: Managing a chronic condition like type 2 diabetes can be mentally challenging. AI tools can provide emotional support and behavioral strategies to improve adherence to treatment.
- AI in Diabetes Retinopathy Screening: Diabetic retinopathy, a complication of diabetes that affects the eyes, can be detected early with AI-powered image analysis. AI models can:
- Analyze Retinal Images: Using deep learning techniques, AI can detect signs of retinopathy in retinal scans with high accuracy; and
- Support Early Intervention: By identifying early signs of retinopathy, AI helps doctors intervene earlier and prevent vision loss.
- Improving Access to Care: AI has the potential to increase access to healthcare for individuals with type 2 diabetes, especially in underserved or remote areas:
- Telemedicine: AI can assist in virtual consultations, allowing patients to receive care without needing to visit a healthcare facility; and
- Automated Decision Support: AI-powered tools can provide guidance to healthcare providers, helping them make more informed decisions in real time.
- Challenges and Considerations: While AI offers many benefits, there are also challenges:
- Data Privacy: The use of AI in healthcare requires access to personal medical data, which raises concerns about data security and patient privacy;
- Bias and Fairness: AI models must be trained on diverse datasets to avoid biases that could lead to unequal care for different populations; and
- Regulation and Approval: AI-based medical devices and systems need to meet regulatory standards, which can be time-consuming and complex.
In summary, AI has the potential to revolutionize the way we manage and treat type2 diabetes, offering more personalized, efficient, and proactive care. However, its integration into healthcare must be carefully managed to address challenges related to data privacy, fairness, and regulation.
C. NATIONAL HEALTH SERVICES (NHS) WORLD-FIRST TRIAL OF AI TOOL:
AI tools are being increasingly tested in clinical trials to improve the management and treatment of Type 2 diabetes. These trials focus on using AI for various aspects of diabetes care, from diagnosis and monitoring to personalized treatment. Below are examples of what these AI trials typically aim to achieve and the type of tools involved:
Two London hospitals to test tool that predicts who may develop type 2 diabetes up to 13 years early. The NHS in England is starting a world-first trial of an AI tool that can find people at risk of type 2 diabetes over 10 years before they get the condition.
Imperial College and Chelsea and Westminster hospital NHS foundation trusts have started training the AI system – called Aire-DM – that checks patients’ ECG heart traces for subtle early warning signs that are tricky for doctors to otherwise detect.
Aire-DM, uses cutting edge AI algorithms to analyze electrocardiogram (ECG) reading taken during routine heart scan. By identifying subtle changes in the heart’s electrical signals – imperceptible to the human-eye-the AI system can provide early warnings of a person’s likelihood of developing type 2 diabetes.
Early work suggests the system can spot risk about 70 percent of the time.
Giving the AI extra details about other background risk factors, such as the patient’s age, sex and whether they already have high blood pressure and or are overweight, can improve the predictive power, says lead researcher Dr. Fu Siong Ng.
He told BBC News: “It is already quite good just with the ECG data, but it is even better when you add in those.”
An ECG (electrocardiogram) records and can reveal problems with the electrical activity of the heart, including the rate and rhythm.
Dr. Ng says the ECG changes that the system detects are too varied and subtle for even highly skilled doctors to interpret with the naked eye. He said:
“It’s not as simple as saying it’s this or that bit of the ECG. It’s looking at a combination of subtle things.”
As part of the trial up to 1,000 patients at both hospitals will have ECG scans read by the AI system to see if it helps detect and predict disease.
It’s not something that will be offered to routinely yet, although the experts hope it could be rolled out more widely on the NHS. That could take five years or more, says Dr. Ng.
The British Heart Foundation, which is funding the work, says detecting people at risk of diabetes could ultimately save lives.
