New AI tool makes it possible to predict weight loss after bariatric surgery

First-time patients in need of bariatric surgery will now be able to predict their weight loss ahead of undergoing a gastric bypass or sleeve gastrectomy operation.

A new AI driven web-tool developed by University of Lille and supported by the European Union SOPHIA project now allows patients and their doctors to accurately predict weight loss over five years following different types of bariatric surgery.

“Usually, weight loss after bariatric surgery vary widely and predicting weight loss was difficult,” said Professor Carel le Roux, from the UCD School of Medicine, co-ordinator of the SOPHIA consortium. “Using artificial intelligence, we’ve developed a new pre-surgery prediction tool – created with data from eight counties in Europe, America, and Asia.”

Publishing their findings in The Lancet Digital Health, SOPHIA researchers used data from 9,861 patients as part of the project – with 385 relevant measures taken to decide on the seven most valuable variables for accurately predicting weight loss post-bariatric surgery. This include height, weight, type of operation, age, diabetes status, diabetes duration, and smoking status.

The prediction tool is the most accurate approach to predicting weight loss post-surgery created so far, and is likely to only improve over the next two years given the on-going European Union project SOPHIA’s investment.

“The tool will substantially reduce uncertainty for patients as they can now make a much more informed decision about which surgical option to select. This is why we developed and validated this easy-to-use tool to predict an individual’s 5 year-weight loss after the most common bariatric operations,” said lead author Professor Francois Pattou, Lille University, France. “Patients and clinicians are now able to make more informed decisions about which surgical option to select.”

Obesity affects 150 million people in Europe and 650 million worldwide, and increases the risk of health complications like heart disease, diabetes and cancer.

The aim of SOPHIA is to improve the ability to predict how patients will respond best to different obesity treatments and to help minimise complications.

The five-year project has received funding from the Innovative Medicines Initiative 2 Joint Undertaking (JU) under grant agreement No 875534. The JU receives support from the European Union’s Horizon 2020 research and innovation programme and EFPIA and T1D Exchange, JDRF, and Obesity Action Coalition.

The 28th of April 2022 we had the pleasure to host our 2nd yearly SOPHIA General Aseembly meeting at Favrholm Campus in Denmark. The video will show a recap of a fantastic day.


The theme of this year’s World Obesity Day was ‘everybody needs to act’. On the day itself we saw clear and compelling accounts from advocacy groups, scientific contributions from leading medics and researchers, and policy recommendations from think-tanks and NGOs. The message was clear – to develop an effective understanding of, and response to, obesity as a chronic disease, everybody needs to act.

IMI SOPHIA is pleased to announce an agreement with Maccabi Research and Innovation Center (KSM), Pfizer, and the Lausanne University Hospital to initiate activities for the public-private research consortium ‘SOPHIA (Stratification of Obesity Phenotypes to Optimize Future Obesity Therapy), a €16-million EU-supported international research consortium that aims to improve obesity treatment and change the narrative around obesity.

KSM, Pfizer, and the Lausanne University Hospital will join SOPHIA’s 29 other partners from civil society, academia, and industry with the aim to better understand obesity as a chronic disease and optimise future treatment.

“Did you also experience FOMO on that Microsoft Teams meeting?” FOMO stands for Fear of Missing Out and is defined in the dictionary as: “the worried feeling that you may miss exciting events that other people are going to”. In the current environment where digital fatigue has become another symptom of COVID-19, you might think that the opening question is more of an oxymoron, an alluring figure of speech in order to capture your attention as a reader.

dedicated four years of a mathematics PhD to studying the distant (1.5×10^8m away to be precise) mass we refer to as ‘The Sun’, desperately trying to make or simulate complicated measurements that my peers wouldn’t instantly disbelieve. Nevertheless, I felt an urge to study a subject somewhat closer to my home. Maybe one that might have an impact on my own environment, where I live and thrive, my family, or even the local shopkeeper’s. Basically anything where I didn’t have to show patience for the next ten billion years to see an effect.

Diabetes is a chronic disease of carbohydrate, fat and protein metabolism that results from the inadequate action of insulin. It affects an estimated 463 million people worldwide and is predicted to rise to approximately 578 million people by 20301. Dangerous acute complications of diabetes include diabetic ketoacidosis and severe hypoglycemia (low blood glucose), which can lead to a trip to the emergency room or worse.  In the long-term, chronic hyperglycemia (high blood glucose) can lead to a number of micro- and macro- vascular complications, including nephropathy, retinopathy, coronary artery disease, stroke and peripheral neuropathy.

The main topic of interest within SOPHIA’s WP3 is to assess the risk factors involved in obesity.  However, obesity itself is a well-known risk factor of other diseases. For example, obesity has been considered a long-term risk factor for chronic diseases such as cardiovascular disease and diabetes; on the other hand, obesity is considered a risk factor for acute diseases as well.