Drivers of Deficit in Healthcare:

This management methodology is a systematic analysis and modelling exercise providing two key outputs:

• 1. The size of the THHT financial deficit to create a single, shared understanding of the current position. 
• 2. An analysis of the deficit to support an understanding of the position, outlining any elements which are structural (outside the control of the NWL System1).

This understanding of both the above outputs will provide a diagnosis to support the               generation of relevant and appropriate solutions and a yardstick to test the sufficiency of these plans. 

The final report is linked to the THHT Medium Term Financial Plan document, which will build on the diagnosis outlined in this report and describe the plan to deliver financial sustainability. This will include current savings and investment plans.

Cancer Services Intelligence Modelling

• This project, originally developed with the East of England Cancer Alliances, provides an up to date understanding of various performance criteria around cancer waiting times, patients treated, diagnostic imaging, survival etc. by Cancer Alliance, ICB and Trust.

Cancer Services Quality of Life Modelling and Service Improvement

• This project is currently sponsored by Suffolk and North East Essex ICB, with data and data support provided by NHS England as part of the National Quality of Life in Cancer Survey. Our objective is to model the data in such a way as to provide our large and multidisciplinary team of stakeholders (QOLI Working Group) with a dynamic reference Power BI application capable of answering their intelligence needs. The Working Group, for their part use this intelligence to engage with patients, improve services and provide better outcomes for patients whilst improving value for money.

Medicines Optimisation

• Medicines Optimisation is a critical aspect of healthcare management, especially in the United Kingdom. It involves understanding and distinguishing between three key categories of drugs: Branded, Generic, and Biosimilar. These distinctions are crucial for healthcare professionals and patients as they impact treatment decisions based on safety, quality, effectiveness, and cost.

Health Location Targeting and Segmentation

• This model employs targeting and segmentation methods, commonly used in the pharmaceutical industry, to identify undiagnosed patients with early-stage health conditions. It calculates risk factors based on disease registers, local conditions, and demographics to determine the likelihood of certain diseases, such as Hypertension, Cancer, Diabetes and Dementia. It helps in the early identification of patients who would benefit from new treatments or an early diagnosis allowing the patient the opportunity to review their lifestyle choices.

Patient Voice Modelling and Service Improvement 

• Is it just noise or are we really listening - To develop a full understanding of the meaning of patient feedback as provided in the form of recorded comments, suggestions, and complaints from systems and methods such as Open Questioning, Patient Advice and Liaison Service (PALS) and iWantGreatCare. Rather than NHS colleagues attempting to read, understand and report on hundreds if not thousands of such comments, we are using Artificial Intelligence (AI) methods along with Microsoft Power BI to automate the process.

Emergency Care Modelling and Service Improvement

• Incorporating activity and cost data our Emergency Care models provide a comprehensive understanding of history and the current position plus forecasts and predictions into the future using Power BI. It can also include modelling options regarding Minor Injuries, the incorporation of growth assumptions, Staff and Bed requirements based on activity trends and defined scenarios detailed by Specialty.

Inpatient Modelling and Service Improvement

• Similar in principle to our Emergency Care model, our Inpatient model Incorporates activity and cost data for between 3 to 5 years of history, designed to provide a comprehensive understanding of history and the current position plus forecasts and predictions into the future. It also provides for a scenario development and analysis providing cause and effect forecast predictions and analyses based on different assumptions using Power BI Statistics, Artificial Intelligence and Machine Learning capabilities. It also includes modelling options regarding growth assumptions, Staff, Specialist and Bed requirements etc. based on activity trends and defined scenarios detailed by Specialty.