Roche has received a European CE mark for integrating its Accu-Chek SmartGuide continuous glucose monitoring (CGM) system with its mySugr app.
The Swiss company unveiled the major regulatory milestone, along with new real-world evidence on its Accu-Chek SmartGuide CGM system at the 2025 European Association for the Study of Diabetes (EASD) Annual Meeting, taking place in Vienna from 15 – 19 September 2025.
This marks a significant step in Roche’s digital health strategy, combining predictive artificial intelligence (AI) capabilities with diabetes management platforms. The integration, formally branded as mySugr Glucose Insights, represents the first CE-marked solution that allows patients to view and interpret predictive glucose data directly within mySugr.
Roche executives and patient advocates underscored the announcement at a dedicated EASD media event, where they discussed both the clinical relevance of predictive CGM and the broader implications of blending technology with lived patient experience.
Why Predictive Insights Matter
Continuous glucose monitoring has become a standard of care for many people with diabetes. Yet, as multiple studies highlight, a large proportion of patients still fail to meet glycemic targets even with access to CGM. The key challenge, experts argue, lies not in generating more data but in delivering meaningful, actionable insights.
Accu-Chek SmartGuide addresses this with predictive algorithms that forecast glucose levels up to two hours ahead and, uniquely, offer overnight predictions extending up to seven hours. According to Roche, the system is the first CE-marked CGM solution with these AI-enabled predictive features.
Dr. Jackie Elliott, Clinical Lead for Diabetes at Sheffield Teaching Hospitals, emphasized at the media session that predictability is critical: “Living with diabetes is a constant balancing act. What people need are solutions that don’t just deliver data but help them make sense of it with confidence and ease. Predictive tools that give personalized insights and trustworthy alarms offer people more control and peace of mind.”
Real-world data presented at Roche’s symposium during EASD highlighted the clinical value of the predictive approach. Use of the SmartGuide’s “Night Low Predict” function reduced the likelihood of level 1 nocturnal hypoglycemia by 20% and severe (level 2) hypoglycemia by 31%, without increasing nighttime hyperglycemia.
The mySugr Integration: Simplifying the Daily 180 Decisions
One of the most striking messages from Roche’s media event was the burden of daily decision-making faced by people living with diabetes. Jochen Berchtold, Lifecycle Leader for Continuous Monitoring at Roche, noted that patients must make, on average, 180 diabetes-related decisions every day, from insulin dosing and meal planning to exercise adjustments.
“Patients live with diabetes 24/7. Our goal is to help them stop worrying about every choice by offering insights that are proactive rather than reactive,” Berchtold said.
The integration with mySugr seeks to centralize this support. Users will be able to log meals, track insulin, and visualize CGM predictions all within one application. For many, this replaces the fragmented experience of juggling multiple apps and devices.
Rodrigo Diaz de Vivar, Roche’s Lifecycle Leader for Patient Insights, framed the CE mark approval as an evolution: “By combining predictive glucose data with the existing strengths of mySugr—meal tracking, bolus calculation, device integration—we can deliver a single, comprehensive tool. This helps people take preventative action without feeling overwhelmed by data.”
A Balance Between Sophistication and Simplicity
One recurring theme of the session was the diversity of patient needs. Some are tech-savvy and eager to interpret complex data. Others, particularly older patients, may find an overload of numbers confusing or even anxiety-inducing.
Palani Kumaresan, Roche’s Global Head of Diagnostic Solutions, acknowledged this challenge: “At the end of the day, it’s about insights presented simply. For someone in their 70s, daily insulin dosing and glucose values can already be overwhelming. Our job is to reduce complexity, not add to it.”
The mySugr integration, Kumaresan argued, addresses this by offering layered functionality: users can choose how deeply they engage with data, whether at the level of simple predictive alerts or detailed pattern analysis.
Beyond user experience, Roche emphasized the system’s technical accuracy. Clinical evaluations reported a mean absolute relative difference (MARD) of 9.2% and 99.8% of glucose readings falling within clinically safe ranges (zones A and B on the Parkes Error Grid).
These technical benchmarks, combined with the real-world evidence on reduced hypoglycemia risk, position Accu-Chek SmartGuide as a strong competitor in the growing CGM landscape.
Expanding Access
Since its initial rollout last year, SmartGuide has been launched in 13 countries. With CE mark approval for the mySugr integration, Roche plans to expand availability to more than 30 countries across Europe, Latin America, and Asia-Pacific by the end of 2025.
Berchtold highlighted the momentum: “The feedback from both patients and healthcare professionals has been overwhelmingly positive, especially on the predictive features and ease of use. We’re excited to accelerate rollout and bring these benefits to more people worldwide”.
While diabetes technology was the immediate focus, Roche used its EASD platform to outline a longer-term vision. Berchtold noted that diabetes often coexists with other chronic conditions such as cardiovascular and kidney disease, and Roche aims to build “holistic solutions” addressing these interconnected conditions.
This reflects a broader trend in digital health: moving beyond isolated tools to integrated platforms that support whole-patient management.
As the discussion closed, panelists reflected on the broader potential of artificial intelligence in diabetes and beyond. Dr. Elliott suggested AI could help clinicians identify at-risk subgroups across large populations, tailoring interventions more effectively. Kumaresan pointed to Roche’s internal AI capabilities, which span from drug discovery to diagnostics, underscoring that AI-enabled prediction is not limited to glucose management.
