5 minute read 5 Oct 2023
Surgeon and Female Doctor Walk Through Hospital Hallway

How predictive data models can vitalise Ireland’s health system planning

By Mary Coghlan

EY Ireland Partner, Data, Analytics & AI

Lover of learning and new experiences. Medical doctor, actuary, analytics hybrid. Mom to amazing Darragh. All about the journey and the people you meet on the road. I’m probably out running now.

Edel Smith
5 minute read 5 Oct 2023

A dynamic, iterative approach to demand and capacity modelling has the power to deliver transformative change in Ireland’s healthcare service.

In brief

  • The mismatch between capacity and demand in the health system is manifest through an overburdened and overcrowded system.
  • Traditional health service planning processes have not historically been data driven and have instead been based on a collection of subjective experience.
  • Tailored demand and capacity models based on health and population data have the potential to greatly enhance healthcare service efficiency and, in turn, critically improve patient outcomes.

Ireland’s population has grown by over 10% in the last 10 years and to compound this, we have one of the fastest ageing populations in Europe. With people living longer, often with multiple chronic diseases, and the health system already suffering from creaking waiting lists, overcrowded emergency departments and staff shortages in key areas, new thinking is required to address these old problems. The pace of change with regard to both the demographic as well as rapidly evolving modernised care pathways guarantee that the challenges of the past with regard to service delivery will increase exponentially in the future if we don’t find a new way.

Amongst the key difficulties faced by those charged with running our health service is the enormous and increasing complexity of the system. The number of separate and interconnected moving parts to be dealt with is vast whilst demand, by its nature, is uncertain and can change rapidly.

Health service planning, whether it is at national, local, clinical service, or clinician level therefore requires a deep understanding and interrogation of many variables, including how they interact with each other and how they will evolve in the short, medium, and long term across a range of plausible scenarios.

Looking at long-term strategic goals

Traditional budgeting and planning processes have tended to be reactive and short term. They have relied on subjective factors and opinions. Of course, these opinions are based on critical experience of the system. However, hard experience has shown that this in isolation is an unreliable means of forecasting system needs. It inevitably incorporates unintended bias and is frequently not aligned with long-term strategic objectives.

Additionally, the service planning process has tended to be a secondary function of health leadership and suffered the pressures of being squeezed into timeframes and constraints that are externally dictated. This can be at the expense of due consideration of and investment in long-term strategic priorities such as preventative medicine and other wellbeing initiatives which have the potential to deliver significant population health benefits and cost savings in the longer term.

The planning processes and environment are therefore vulnerable to planning decisions that have not been sufficiently data driven and evidence based. These decisions can involve very significant expenditure and more importantly have the potential to affect the health outcomes of large cohorts of the most vulnerable in our population. Additionally, the nature of the process can lead to significant challenges with respect to both implementation and impact measurement.

The ability to evaluate implementation success and impact compared with strategic objectives should be a core part of the service planning process and cycle. However, a further consequence of sub-optimal planning processes can be an undermined capacity to measure the success or failure of implementation in the first instance and impact in the second.

Bridging demand and capacity gaps

The application of data and analytics to health planning functions to deliver robust modelling tools and methodologies are core components of a data-driven service planning function. They should be integral to planning and fully aligned with health strategy and policymakers, the lived reality of service provision and, most importantly, the healthcare needs of the population.

These leading-edge tools can help address the fundamental issue of the all too frequent mismatch between demand and capacity in key areas of the healthcare system.

By analysing demographic shifts, epidemiological data, clinical data and other population and societal trends, demand modelling assists in predicting more accurately healthcare service requirements from a clinical and operational perspective.

In parallel, capacity modelling evaluates workforce availability, the physical capacity of facilities and the availability of specialist equipment to align resources with anticipated demand. These models can identify potential bottlenecks and inefficiencies within the system and can incorporate agreed interventions to resolve problems before they arise.

It is important to understand that there is no off-the-shelf solution for a highly complex undertaking like health service demand and capacity planning. The number of variables to be taken into consideration is constantly changing due to factors such as medical advances, changing population behaviours, human resource issues, and much else besides.

Additionally, there is no “one-time-fits-all” approach – modelling health system needs is an ongoing, live and iterative process. The rapid evolution of factors that can impact the system means that heath planning models function best where there is an ongoing ability to ingest new information to inform outputs. This approach ensures that the modelling stays current, relevant and, most importantly, delivers actionable outputs.

The unique model developed to replicate any given system and the demands placed on it must therefore be constantly updated to reflect both internal system changes and those affecting the external environment in which it operates.

Ultimately, demand and capacity models are only as good as those who fine-tune them with historical and emerging data as well as clinical and operational factors experienced on the ground.

The application of the best data and analytics, which are iteratively updated and improved, combined with the integration of clinical insights and operational expertise are an invaluable asset in enhancing healthcare delivery.

Collaboration and engagement with relevant stakeholders as models are developed and deployed are crucial to developing robust, adaptable, and sustainable models.

Amongst the key benefits of system specific capacity and demand models is the ability to plan ahead for different scenarios and design improvement initiatives in a confident and structured manner. Proposed new interventions and services to meet specific challenges and arising demands can be tested prior to implementation to assess potential impact and effectiveness. They are especially valuable in identifying any unintended consequences that may arise from proposed plans.

They enable health leaders and decision makers to compare the projected impact of proposed changes to service delivery – both in terms of different options available as well as relative to current system configuration. The modelling permits the impact of interventions to be benchmarked against key metrics including:

Advanced health analytics/ modelling, traditionally know as demand and capacity modelling, has the potential to become a real driver of change in the healthcare system, bringing the combined power of data and clinical and operational knowledge to the fore. This, in turn, can support service delivery to improve patient experience and quality outcomes, leading to a positive societal impact for all.

By harnessing clinical and operational insights and translating them into data-driven strategies, Ireland’s healthcare ecosystem can navigate complexities, enhance patient care quality, and achieve sustainable growth amidst evolving healthcare dynamics.


Ireland’s growing and ageing population will put increased pressure on an already strained health system in the coming years. While increased funding will be required, its application and investment needs to be informed by new ways of thinking and planning health services. The use of advanced data analytics to create accurate and dynamic capacity and demand models has the potential to enhance patient experience and outcomes. It can improve overall population health while delivering significant efficiency gains for the health service.

About this article

By Mary Coghlan

EY Ireland Partner, Data, Analytics & AI

Lover of learning and new experiences. Medical doctor, actuary, analytics hybrid. Mom to amazing Darragh. All about the journey and the people you meet on the road. I’m probably out running now.

Edel Smith