We put patients more in the driver’s seat themselves.

“What does that mean for me?”

“When you talk with a patient about the best treatment for cardiovascular disease — and especially about preventing it — the medical advice is often quite far-reaching,” says Visseren. “Especially because the patient may not have any symptoms at all yet. You want to keep it that way, so you advise a lifestyle change and may prescribe cholesterol- or blood-pressure-lowering medication, or anticoagulants. As a doctor, you can refer to large scientific studies and to the average effects for the average patient, but when someone in the consulting room asks, ‘What does that mean for me?’ you are left without an answer.”

Predicting individual effects

“Everyone is different, but the way we practice medicine is still somewhat one size fits all.” That observation led Visseren to ask whether it would be possible to estimate the effect of treatments on individual people. “Together with Jannick Dorresteijn (internist and vascular medicine specialist at UMC Utrecht, ed.) and colleagues from Harvard, we then developed a methodology to predict the effect of individual interventions and express it in terms of how many healthy life years, free from cardiovascular disease, someone gains. We can do this for people who are healthy, people who have already had a cardiovascular problem, and people with diabetes.”

This way of working — not only thinking in terms of risk, but in terms of solutions — has found a place in the new European guideline published last August. “You get a completely different conversation in the consulting room when you can express health gains in years. Everyone understands that and can use it, together with their doctor, to assess whether the gain is sufficient to start a treatment, for example. It says much more than stating that a ten-year cardiovascular disease risk drops from, for instance, 18 to 16 percent if someone starts taking medication. Patients also look at the result on the screen. It is highly motivating to see graphs about your future health and the effects of lifestyle changes. In this way, patients take more control themselves. This approach also means that you treat people when it has an effect, and do not treat them when medication has little or no effect. It is cost-effective, as all studies show. And it helps people live healthily for as long as possible. I invest in my financial old age by building up a pension. You also want to invest in a healthy old age.”

Lifetime prediction

Without going too deeply into the underlying methodology, Visseren explains how U-Prevent came about: “We brought together clinical, epidemiological and statistical knowledge. And above all, a great deal of data, from which we derive predictions that we then validate in independent cohorts. For personalized estimates of risk and treatment effects, we use the best of two worlds: the world of prediction — we can make lifetime predictions — and the world of trials, in which the effects of medicines are studied very precisely. The gold-standard trial — placebo-controlled, double-blind and randomized — produces an average effect. You can link this average relative trial effect to an absolute individual risk of cardiovascular disease. The result is the amount of absolute health gain achieved. Lifetime prediction must be based on robust data.” Visseren himself does not really believe in Big Data in the sense that more data is always better, he says: “A lot of rubbish is still rubbish. If you bring together a lot of low-quality data, you still have low-quality data. What I mainly want is good data, and preferably a lot of it. The art is to bring together such high quality data. You need good baseline measurements and good follow-up of participants, because you can only estimate the value of a particular variable once you know how patients fare. You only know after five or ten years whether a particular risk factor or biomarker truly increases the risk of cardiovascular disease. It would be fantastic if, in the Netherlands, as in Scandinavia, we had many more national registries, so that the Netherlands becomes one large cohort. That can be done anonymously, with privacy safeguards, and if you do not want to participate you can indicate that, but in essence everyone takes part. That would deliver a great deal for the Netherlands as a whole.”

“What I mainly want is good data, and preferably a lot of it. The art is to bring together such high quality data.”

Trust in the ‘black box’

In addition to collaborating with universities and data centers worldwide, Visseren and his U-Prevent colleagues have also entered into a partnership with ORTEC. Why? “As scientists, we identify a problem, try to contribute to the solution, validate it and publish it. In the case of U-Prevent, we created a website where we placed the algorithms to make them available to the rest of the world. But we soon realized that we needed a partner who knows how to handle data safely and reliably. ORTEC also brought explainable AI to our attention. For many people, prediction is still something of a ‘black box’: how can you trust an outcome if you do not know what is happening? CE certification is fine, but you also have to help people understand it. And if we want to apply U-Prevent successfully in practice, it has to improve. The algorithms are based on relatively simple patient data such as age, sex, cholesterol and blood pressure. If you can load those automatically from the electronic health record, it saves a lot of time and input errors: then a doctor does not have to spend time on that during a ten-minute consultation. That is where we want to go. The link with the EHR is already technically possible; it is a matter of making good agreements.”

However, there is still a fair amount of hesitation, including among hospitals. “That is indeed the biggest hurdle we have to overcome. A copy of the data is briefly used outside ‘the hospital’ to perform calculations, the results are shown, and then the data disappears from the cloud. This can be done securely, but for many hospital administrators it is still unfamiliar territory. You have to look for cloud solutions if you want to make this scalable and keep costs under control. Healthcare providers put a great deal of information into the EHR, but we then do little to use all that information to make the best decisions for that one patient. That requires calculations. There are so many variables to take into account that you can no longer do it in your head. The final decision about treatment must be made by the healthcare professional together with the patient, and that conversation must be informed by smart, individualized information. That is how you make the decision-making process more personal.” Ideally, Visseren would like U-Prevent to become a self-learning system that will be used as a foundation in many places in the Netherlands, but also worldwide, with the algorithm fine-tuned on the basis of locally available data. “To make even better predictions, you have to adapt the prediction rule to the situation on a continent, in a country, in a region. For example, particulate matter in exhaust fumes may mean that the condition of patients differs between urban and rural areas. Even within the city of Utrecht, differences may exist — simply because of referral patterns — between patients at Diakonessenhuis and UMC, even though we are only a few kilometers apart.” In any case, Visseren believes U-Prevent should be widely implemented in the coming years: “This is the way to go. Everyone thinks this is a good idea, and U-Prevent has been included in the 2021 European guideline for cardiovascular prevention. Good for patients, good for healthcare providers and good for health insurers.”

About Frank Visseren

Frank Visseren is an internist, epidemiologist and professor of vascular medicine at University Medical Center Utrecht. As head of the vascular medicine department, he is responsible for patient care, research and education. Visseren focuses in particular on research into patients who are at increased risk of cardiovascular disease and/or insulin resistance. Together with national and international partners, he translates the results of large clinical studies to individual patients. Visseren is also Principal Investigator of the SMART (Second Manifestations of ARTerial disease) cohort, which includes more than 14,000 patients with vascular disease, diabetes or other serious risk factors. Visseren has authored or co-authored more than 400 publications and is associate editor of two scientific journals.

About U-Prevent

U-Prevent is an innovative application developed by UMC Utrecht and ORTEC (Logiqcare) in the field of cardiovascular risk management. U-Prevent calculates the ten-year and lifetime risk of cardiovascular disease for individual patients and estimates individual treatment effects. In this way, U-Prevent supports the conversation between healthcare provider and patient in reaching the best decision, and helps healthcare provider and patient work together to prevent cardiovascular disease. ORTEC owns U-Prevent and the platform underlying U-Prevent for risk prediction models, including in other medical domains. The ORTEC version of U-Prevent has been completely redeveloped to meet the requirements and regulations that apply to use in clinical practice.