Thursday 22 May 2025 | 13:15-14:30

Format: Presentation

Stream: Science

Content filters: Recommended for those working at system level in QI

PART ONE: Listening at scale with SenseMaker®: using patient and carers’ experiences to drive improvement and innovation

This session draws upon two case studies, in the UK and the Netherlands, where the hybrid qualitative-quantitative SenseMaker® tool has been used to collect and make sense of relatively large numbers of patient and carers’ narratives in order to support collaborative learning and identify improvement and intervention opportunities.

The session demonstrates how the tool can be used at all levels, from patient, to clinician to policy maker, to generate actionable insights from tacit, experiential knowledge. This type of knowledge is more easily transferable and actionable than codified knowledge, thus facilitating action for change based on collaborative intelligence.

Delegates will also experience for themselves how the anthro-complexity tools (triads and dyads) that are integrated into the SenseMaker® platform, can also be used separately to facilitate sense-making and actionable intelligence in collaborative spaces.

By the end of this session, participants will be able to:

• Have a basic understanding of complex adaptive systems and the key challenges for innovation and improvement in such systems


• Understand how and why gathering large numbers of micro-narratives with signification data provided by the patients and nurses themselves can help us to make sense of such systems and find the next best step forward


• Have a good grasp of two real-world examples, and some hands-on experience with the basic principles underlying the method

Rosanna Hunt Midlands and Lancashire CSU; England

PART TWO: Beyond run & control charts: advanced uses of data and artificial intelligence (AI) to support quality improvement

We perhaps assume that data for quality improvement focuses on run charts and control charts, to help learn from variation. But how are health systems adopting more advanced analytics and data science to support quality improvement work?

This session will bring examples from healthcare organisations who have been utilising big data and artificial intelligence (AI).

Examples will include using natural language processing, and large-language models, to interpret millions of rows of qualitative data and build predictive algorithms to provide actionable intelligence for clinical and managerial teams.

We will share innovative work to automate aspects of key clinical processes and work to build early warning systems, based on statistical process control charts. Other examples will illustrate the development of predictive algorithms from big data, in order to help tackle clinical improvement opportunities as we try to move care further upstream and support operational efficiencies.

By the end of this session, participants will be able to:

• To learn from the latest advances in the field of data and analytics to support quality improvement


• To understand how data science can transform and accelerate quality improvement work, through natural language processing and predictive analytics


• To take away some practical ideas to start exploring the potential of AI in supporting quality improvement, and to do this within a framework that supports this to be undertaken safely and equitably

Erik Mayer Imperial College Healthcare NHS Trust; England

PART THREE: From data to improvement: social mechanisms as a key to quality dashboard adoption

Previous research on dashboards has focussed on technical and design requirements needed for adoption. However, successful dashboard adoption for quality improvement extends design and technical requirements, encompassing also social mechanisms such as human interaction and embedding into daily routines and mundane practices. This session will give insight into the complex process of dashboard adoption from a social perspective, based on an embedded case study performed in a regional teaching hospital in the Netherlands. Multiple social mechanisms will be explained, which together stimulate a learning environment in which quality and safety of care can be discussed and improved using data. Knowledge of these social mechanisms is important for quality improvement initiatives, since it calls for action from individuals and teams to collectively create an environment for learning to enhance the quality and safety of care.

By the end of this session, participants will be able to:

• Understand that social mechanisms play an important role in successful adoption of dashboards for quality improvement


• Recognise different social mechanisms, within the team of end-users, that influence the successful adoption of dashboards in practice


• Understand that social mechanisms stimulate a learning environment in which data can be used to discuss and improve quality and safety of care

Tamara Broughton Tilburg University / Meander Medical Centre; Netherlands

PART FOUR: Right care, right time, right patient – an innovative approach

Join us for an insightful session on delivering the right care, at the right time, for the right patient through innovative approaches like machine learning. With a proven track record in this field, we will share our journey thus far and future plans with practical examples that demonstrate the impact of these technologies on patient outcomes. Learn about the dos and don’ts we’ve discovered along the way, ensuring you can navigate this transformative field effectively. This session is essential for all professionals working in healthcare or related fields seeking to enhance their practice with cutting-edge solutions, improve patient care, and stay ahead in an ever-evolving industry. This will be an opportunity to gain insights and practical tips for integrating machine learning among other things into your healthcare strategy.

By the end of this session, participants will be able to:

• Understand how machine learning can be leveraged to deliver personalised patient care at the right time


• Identify practical examples and best practices for integrating innovative technologies into their healthcare practice


• Apply the dos and don’ts learned from our journey to effectively navigate and implement machine learning solutions in their own organisations

Sheena Bhagirath Amsterdam UMC; Netherlands