Projects

Abby Dewhurst - Dorset Intelligence and Insight Service (NHS Dorset)

Claire Davies - BCP Council

Krzysztof Cepa - Dorset Intelligence and Insight Service (NHS Dorset)

The current Referral to Treatment waiting list is at its highest level in NHS history. Identifying methods for reducing the waiting list and waiting times would benefit patient care. 

The aim of the project was to look at what changes in capacity, the number of appointments, could be made to reduce the waiting list and waiting times for Rheumatology services in Dorset. This was done using Discrete Event Simulation (DES), which is a technique that models flow through a pathway and can show what happens if changes are made. 

During the project the team built a DES model to look at the Rheumatology pathway. They then built an app using Steamlit so that stakeholders can model the impact of capacity changes on the size of the waiting lists and the average waiting time for patients.

They will be presenting the final model and app to stakeholders and getting feedback, adapting if required; then putting it on GitHub to be shared.

Watch the project presentation

Alex Owens - NHS Arden and Greater East Midlands CSU
Phoebe Woodhead - Wessex AHSN
Sian Heath - Nottingham University Hospitals NHS Trust

This project hopes to empower NHS service providers with a tool that grants a deeper understanding of the population they serve and allows them to direct future service expansion to provide access to underserved groups.

It will provide a nuanced demographic breakdown of the patient population, including age, ethnicity, and deprivation, offering crucial insights into the diversity of healthcare needs within the service area – with potential additions to allow providers to add new demographic information to better understand catchment by the conditions they look to treat.

Undertaking this project, gave us a deeper understanding of health modelling methodologies and their practical applications. The team learned to combine geospatial analysis, demographic data, and travel distance calculations to create a dynamic tool for use by NHS service providers.

They will continue developing this tool, adding data sources that collaborating service providers hold, but are unable to publish alongside the open-source code, to better identify underserved groups with specific ailments to be treated. This will allow them to give more precise information to let their new service allocation tool pick more appropriate potential locations for new sites.

Watch the project presentation

Becky Crofts - Royal Devon University Healthcare (RDUH) NHS Foundation Trust
Kayleigh Haydock - Royal Devon University Healthcare (RDUH) NHS Foundation Trust

The team’s project was to create a computer model of part of the acute medical pathway in their hospital trust. As part of this process patients come in with non-surgical emergencies, like an abnormal heart beat, and they’re triaged to decide the best route of care for them. In some cases that will be an admission to hospital, but increasingly this may involve alternatives that combine just a few hours in hospital with close follow up and perhaps even forms of remote monitoring, like monitoring their heart through a mobile app.

The aim of this project was to model part of the acute medical pathway in this hospital trust, simulate how the system currently works, and investigate whether there is optimal allocation of staff and resources. The benefit of this model is it allows for changing parameters such as adding extra staffing to see what impact that has on the pathway. Testing these changes in the real-world costs time and money, while computer simulation allows you to trial these changes with minimal cost and no risk.

The model isn’t validated yet, but when it is it’ll be handed over to users (e.g. clinicians and managers) to support them in making decisions about staffing or resourcing. They’ll be able to test those changes mentioned above without risk before proceeding to a real-world test of change.

GitHub repository
Watch the project presentation

Benjamin Mouncer - NHS & Norfolk County Council

The aim of this project was to determine on an ICB, LTLA and UTLA the overall level of disparity in accessing planned appointments in hospital. The team did this for each high deprivation LSOA calculating the true rate of planned hospital admissions.

They learnt that estimating equity in planned admissions may be possible but not with a minimal set of public data and simple machine learning models.

They put these findings into practice by building in a way to quantify the confidence interval of a machine learning model is essential to effectively use them in real world environments. They also found combining multiple years of data can work with low quality datasets. Of the datasets used the age distribution of an area was the most consistently predictive feature encountered.

One avenue for progression with this project is the creation of synthetic data to have each person within an area as a row of data. Model complexity must increase to create viable models if they even exist. Other feature sets could be explored such as the emergency admissions, type of planned admissions and other variable synthesised from the HES APC dataset.

Watch the project presentation

Dominic Allen - Guy’s and St Thomas’ NHS Foundation Trust

The aim of the project was to create a Discrete Event Simulation in SimPy to model elective surgery pathways, which could be used to model changes to a pathway and their impact on waiting times. This was accomplished and realised as an interactive webapp using Streamlit.

The project is FOSS and is available for anyone to use in the future to model their own surgical pathways or other waiting lists. Future HSMA participants, and anyone else who is interested, will be able to modify this model into a format useful to their organisation.

This will provide possible opportunities for the optimisation of surgical pathways, and also provide a ready-made format for future HSMA participants to create interactive SimPy-based webapps without having to “reinvent the wheel.”

Streamlit app
Watch the project presentation

Eleanor Jeram – Public Health Dorset
Lee Robertson – Public Health Dorset
Wilson Otitonaiye – Public Health Dorset

The project was based on the Dorset ICS (Integrated Care Systems) Health Inequalities programme aim to improve access, enhance the experience of services for everyone. Through this and the ICP (Integrated Care Partnership) integrated care strategy supporting early intervention and prevention approaches, reducing the variation in how well people are supported with long-term conditions. This in turn reduces excess mortality.

The aim of the project was to understand and build on the definition of excess mortality and how the baseline is measured. Identifying periods of unexpected mortality (increases and decreases) to understand factors which may be driving changes.

The team learnt that the discrepancies of measuring expected mortality through five year rolling averages removes the impact of seasonality on mortality resulting in hidden trends; with seasonality patterns varying across different underlying causes. The output of the project will allow for differing definitions of expected mortality, providing a base line and forecast moving forward. In addition, different cohorts of the population are considered in line with the Public Health objectives and priorities.

The team are hoping to further develop their StreamLit app to make sharing and access available to the wider team – building questions and bringing in wider subject matter expertise. 

“HSMA was an invaluable opportunity, I was impressed by how much the three members of the team learnt and the development of advanced analytics and forecasting. The hands-on approach in the course has resulted in instant results in our understanding of excess mortality” Natasha Morris, Public Health Intelligence Team Leader

Watch the project presentation

Hamzah Shami – NHS England

In A&E a patient can be given one or more diagnostic procedures. These can be as simple as the various blood test or more complicated procedures like an MRI test. The aim of this project was to look at the relationship between the different investigations. Hamzah pulled data from the NHS ECDS and created a series of graphs based by A&E provider.

The aim of the project become to create a web tool that can provide insight in how diagnostic procedure are used in A&E departments across the country. Hamzah learnt a lot about graph analysis and the connection between clinical theory and analytical process. 

Hamzah is now working on creating a web tool that allows users to explore the graphic visualisation as well as some analytics that accompany the graphs. 

GitHub repository

Hannah Perkins - University Hospitals Plymouth NHS Trust

Hospitals across the country are struggling to provide patients with the care they need in a timely manner. Increasing waiting times in A&E departments, long waits for ambulances and growing waiting lists are all examples of these issues. A possible cause of these issues is the difficulty in discharging patients from acute hospital beds efficiently, due to lack of onward care capacity. Timely discharges are crucial to patient care, to get the right care in the right place at the right time.

A previous PenCHORD project, IPACS, looked at understanding the capacity required in social and community care to facilitate timely flow out of acute hospitals. This project was based on IPACS, and extended the scope to include elective inpatient waiting lists and patients in the emergency department. 

The aim of the project was to model flow of patients into and out of an acute hospital site, with particular focus on how delays to complex discharges affect patients waiting to come into the hospital. The results from this project will help to articulate how the issues in discharging patients from an acute hospital bed affect emergency care performance (time spent in A&E and ambulance handover time) as well as waiting lists for elective inpatient care. A discrete event simulation was created to model patient flow through an acute facility and into community/social care.

Watch the project presentation 

Jane Kirkpatrick - NHS England
Mathew Ojo - NHS England
Lyndsey Allen - NHS North of England Commissioning Support Unit
Luke Asante - NHS North of England Commissioning Support Unit
Evelyn Koon - NHS England

Within the organisation (NHS England) forecasting for clock starts is currently done using scenario-based modelling in Excel. This limits how much data can be used to make forecasts, and the techniques that can be deployed. There was a desire to explore other forecasting methods to see if they could obtain more accurate forecasts, and also to valid the forecasts that are being made using the existing model. Understanding demand is important to manage wait lists, which is a high priority for the NHS, hence the interest in modelling clock starts.

The aim of the project was to explore different ways of forecasting demand, evaluate their performance and offer suggestions as to how forecasting could be done in the future.

The team carried out exploratory data analysis to understand differences between different data types and the differences in the patterns of demand for different subgroupings. They built a codebase that loaded the required data and ran model functions for Naïve, ARIMA, Prophet and a combination of Linear Regression and Random Forrest. They evaluated the performance of these models to each other, and the modelling technique currently used. They also made some progress on rebuilding the current excel model in Python. 

They found that while the more performant models that we used performed well (produced low error metrics), they generally didn’t perform as well as the model currently used within the organisation. This suggested that a helpful next step of the project might be to complete the work of translating the excel model into python and doing further work to understand if they can get more data to better understand the drivers of demand beyond just time series. 

Watch the project presentation

Lauren Szarvas
Holly Dale
Tom Haddock

Since the amount of data being collected and stored has increased significantly, datasets are often reviewed manually, particularly when free text fields are present. This project focussed specifically on the detection of drug-related content, following the announcement of the Governments 10-year drugs plan in December 2021. If successful, this could then be adapted and applied to further crime types at a later date.

The aim was to create a model that would be able to make predictions on future datasets by classifying each piece of text into drug/non-drug related content, to prevent manual coding of the data. To achieve this, the team used a machine learning technique known as Natural Language Processing, to train various models on the structure of text and any patterns in language.

The team created a model pipeline to automate this process end-to-end. Initial findings suggesting these techniques could be rather successful, however, it has only been possible to test this on dummy data at present. If this were to be implemented as a permanent solution, this could potentially be made available to the wider policing community through the development of a Streamlit app, which could greatly assist in reducing the amount of data and time taken to review each dataset manually.

Watch the project presentation

Sarah Houston – UCL Partners
Deborah Newton – Reading Borough Council

Community diagnostic centres (CDCs) have been launched across England to tackle the diagnostic backlog and address healthcare inequalities. CDCs and commissioners struggle to identify their baseline of healthcare inequalities and monitor their impact going forwards. This leads to resourcing constraints on teams in the short term and risks minimising the CDC’s impact on healthcare inequalities in the long term. As these are emerging services, the quality of data collected by them to understand their impact is unclear. This impact can be estimated through a health equity audit, however this is usually and long and manual process.

The aim of the project was to create an open source and shareable tool to: 

• Perform a health equity audit to identify where the service may be having an impact on healthcare inequalities

• Identify where data may be incomplete or poor quality, and automatically suggest evidence-based strategies to improve the data

This has been achieved through development of Python code to process data and a Streamlit app to present data. This project involved developing a toolkit to explore inequalities for multiple sites. Through trialling this toolkit with dummy data for different sites we have developed metrics would be most suitable to identify different regions.

The team would like to further develop the tool to make it more widely applicable and include more robust analysis of inequalities. They are planning to engage with local and national stakeholders of CDCs to demonstrate the tool and gather feedback. They are also planning to implement changes suggested by the Patient and Public Involvement Group (PenPEG).

The tool itself, at a minimum, will support a local CDC to understand their local impact on healthcare inequalities and address areas of concern where relevant. It’s an example to demonstrate the power of open-source techniques and data in healthcare inequalities. If adopted by multiple regions, it would allow different regions to generate similar outputs which would allow for easier comparison and sharing of learning. The code developed could also be easily adapted and reused for other healthcare services beyond CDCs.

GitHub repository

Watch the project presentation

Glenn Ubly – NHS England Specialised Commissioning – South East Region
Atonia Drummond - NHS England and Improvement
Janine James - NHS England and Improvement
Victor Yu - The Strategy Unit

The aim of the project was to employ geographical and statistical analysis of past and present travel times to understand the impact the flow of activity into London has on travel times for patients, whether referral pathways could be changed to minimise patient travel, and the extent to which additional sites would have a beneficial impact.

Initial analysis was undertaken on a sample of cardiac procedures within the hospital spell level data. The analysis identified a particular gap in the accessibility of cardiac surgery for patients in the Kent & Medway area, where there would be a significant benefit for the local population in the provision of a new cardiac surgery site or sites. The methods used gave a quantified and visual view of the impact of the options, and indicated the optimal configurations with 1 or 2 additional sites.

The team created a Streamlit application which allows a user to select from a list of possible new sites, and see the impact on travel times for Kent & Medway patients using maps, charts and a number of key travel time metrics.

The South East Cardiac Network have reviewed the findings, and this work will form part of the evidence base for service planning in the region. More generally, there has been interest in applying the methods and tools to other services.

Shilpa Patel - University College Hospital Trust

The primary aim of the project was to improve Urgent Treatment Care (UTC) performance by developing a model which would help the Emergency Department (ED) team with the allocation of staff and rooms to match patient flow. The team wanted to understand what further staff and resources would be required for any variations in patient attendance. The ED team wanted to understand how changes in the patient pathway would reduce bottlenecks, for example, what would be the impact of front-loading diagnostics. 

Initially, a discrete event simulation model was developed to show how patients currently flow through UTC. After an initial model had been developed, it was used to test the proposed alternative pathways for diagnostics. It was also used to model different numbers of staff and rooms. The model made it easy to understand the impact of changes to the existing provision and what would be most cost-effective. 

The ED department was redesigned based on the model findings, which identified a need for additional rooms leading to reconfiguration of the space. It started a review of staffing rotas to see how they could be better aligned to findings from the analysis and future staffing rotas are designed to align with what the model identified was needed to meet the 95% target.

Alice Waterhouse - NHS England and Improvement

The aim of the project was to examine in more detail the question of whether booked appointment times might reduce waiting times in Urgent Treatment Centres (UTC). This was done by considering a “generic” UTC – a kind of average over services of this type which were submitting high quality data to the Emergency Care Dataset.

Data on the paths patients took through these services, how frequently patients arrived and the number of staff present were taken from this data and used to build a Discrete Event Simulation model. The modelled average time taken for initial assessment of the patient, treatment, and any investigations or tests was chosen to give the best fit to actual waiting times. The distribution of patient arrival times was then modified to simulate the introduction of additional booked appointments, leading to a more even spread of patient arrivals throughout the day. 

The model showed a decrease in overall waiting times when higher percentages of patients booked a timeslot in advance. This will be used to better inform policy on the number of booked appointments needed to make a significant impact to waiting times. Further analysis is expected to shed light on the impact of different ways of prioritising patients according to both clinical need and whether they have booked in advance. 

This is a great test case for the use of Discrete Event Simulation to inform policy and strategy at a national level. It demonstrates the impact that such modelling can have and creates opportunity for similar work in the future, ensuring that decision making is supported by high quality analytical insight. 

Andy McCann - NHS Midlands and Lancashire Commissioning Support Unit 

The aim of the project was to use available Primary and Secondary Care patient history and demographic information to better predict the chance of admission for respiratory conditions and subsequent length of stay, in order to better target interventions. 

Due to time and data constraints, the modelling is currently at an early stage, but has demonstrated some interesting preliminary findings and put the structure in place for further development.

A Logistic Regression confirmed some expected factors but also revealed some surprises. An initial neural network with very little optimisation matches the Logistic Regression performance, with the potential to beat it when other features are included.

The model needs to take other features, particularly more patient history, into account to improve performance and be extended to predict length of stay as well as admission. 

Angel Masih - Gloucestershire Hospitals Foundation Trust
James Page - University Hospitals of Morecambe Bay NHS Trust
Mahya Kaveh - Dartford and Gravesham NHS Trust

The project aim was to develop a Discrete Event Simulation (DES) model based on Colorectal Cancer pathway at Gloucester Royal Hospital to identify the key delays within the pathway and identifying feasible solutions.

The team met with cancer service leads to discuss the scope of the project and discussed the patient pathway in detail. Three years of anonymised patient records were used to create the model. Delays for the pathway were split into patient & provider delays to focus only on provider delays.

They used SimPy to create a DES model using the current colorectal patient pathway. They ran the simulation for 100 runs to get the average waiting time for each stage of the pathway to identify the stages that took the longest amount of time. The DES model showed us the key delay, which is diagnostic delays caused during investigative stages.

The findings from the analysis will be presented to cancer leads to support reducing the waiting times for colorectal patients. The DES model helped to evidence key bottlenecks of the patient pathway and will help to discuss the prospect of how increased resource can help improve patient outcomes.  

Anupma Wadhera
Linda Wystemp 

Andrea Casajuana Massanet - Counter Terrorism Policing 

Helen Browne - Devon and Cornwall Police 

Alessia Rose - Devon County Council

The aim of this project was to use various crime data variables and spatial analysis to turn them into useful insights for inclusion in assessed intelligence reporting.

The team chose to focus on violent crime offence data as they wanted to create our model using free and open source software. 

They used QGIS and various Python libraries to explore the data. For the purpose of their model they obtained detailed geographic offence data uploaded by police forces in England and Wales.

The model was able to take a crime indicator (e.g. violent and sexual offences) for a region in the UK, prepare the data, apply and compare map classification schemes and run various analysis techniques to identify spatial autocorrelation, LISA , identify hotspots, coldspots and outliers. The statistical output provided a level of confidence in the findings that they can incorporate into intelligence confidence reporting levels.

The model will be shared with Commodity Threat Leads with the intention of using it internally to identify spatial trends in datasets that are restricted. Applying spatial analysis to these datasets will help identify regional variation and help quantify visual observations that will provide statistical certainty to any observed visual findings. The model will be proposed and applied to more restricted crime data in order to be used to draw out useful visualisations and insights to feed into intelligence reporting. 

Charlene Black – South Central and West Commissioning Support Unit
Adonis Sithole - South Central and West Commissioning Support Unit
Edward Chick - South Central and West Commissioning Support Unit
Mayoor Dhokia - Surrey and Borders Partnership NHS Trust

The aim of the project was to create an easy to use model for predicting demand and capacity for Covid vaccinations. 

During the project the team came up against many barriers, the biggest of which was getting access to the data. The other issue they had with getting the data was the limits imposed on the amount of data you could download in one go, meaning that it was a lengthy process.

They modelled potential update scenarios and have started to work on this and have making great progress. They will use the previous vaccination data, along with the Winter 2022 vaccination data to strengthen the tool, so that following vaccination seasons it can be used more widely. They will look at other vaccinations it could be applied to, such as flu. 

This will give users an easy to use tool to keep track of vaccinations and pick up problem areas quickly. It will save time and money on current methods and enable more people to use and understand the vaccination position 

Helen Young - Nottingham University Hospitals NHS Trust
Thomas Knight - Sandwell and Birmingham NHS Trust

Nottingham University Hosptials has two major Acute Medicine Assessment areas (WB3 and AMRA), where patients can be reviewed before being sent to the most appropriate specialty base ward bed for their needs.

WB3 and AMRA run at very high occupancy levels, and patients frequently wait in the Emergency Department (ED) for a WB3/AMRA bed for more than 6 hours – this is a known cause of delay-related harm. Stakeholders feel that a major constraint is patients waiting in WB3/AMRA who are ready to be moved to a ward bed. 

The team wanted to investigate what the impact would be if patients were able to leave WB3/AMRA more quickly. What would this do to the backlog of queues in ED, and how would it affect waiting times there?

A Discrete Event Simulation (DES) was made of the entire Acute Medicine assessment pathway. They then simulated several alternative scenarios in which patients leave WB3/AMRA more quickly after their period of assessment is completed – and were able to see the impact of this in the key metrics.

If all patients left WB3/AMRA within four hours of their request for a ward bed, patients would never have to wait in ED for a WB3/AMRA bed for more than 6 hours. Even if all patients left WB3/AMRA within 16 hours of their request, this would still reduce the number of patients waiting more than 6 hours by 90% - substantially reducing the risk of delay-related harm

We can now start to quantify the number of additional ward beds that would need to be freed up to support this improved flow, and bring these findings to discussions on how/where additional bed days could be released. 

Iain Waring – Birmingham & Solihull Mental Health NHS Foundation Trust 

The aim of the project was to see if the occurrence of violent incidents on hospital wards could be reduced, if incidents could be pre-empted and interventions could be taken to try to prevent them from happening.

The trust has a wealth of electronic information about service users, staff, incidents, and what happens on inpatient units. The plan was to combine this information into a dataset and use machine learning techniques to predict which of our wards were most likely to suffer from an incident the following day. A dashboard would highlight these wards to senior nursing staff, who could experiment with actions to reduce incidents.

Discussions with key staff helped to identify which features from our systems would be the most helpful in predicting incidents.  A large dataset was constructed, and machine learning methods were used in an attempt to predict where incidents might happen. Unfortunately, the dataset did not prove to be informative enough to generate a working model – the predictions made were inaccurate and there was no way to apply them to the work environment.

Irma Tanovic - Oxford Health NHS Foundation Trust 

The aim of the project was to understand the current pathway to assessment of Autism and ADHD in children, identifying any bottlenecks. We wanted to know what change needed to take place in order to keep on top of ongoing demand levels and see patients within an acceptable time - what do we need to do to maintain a steady state and avoid a backlog from developing?

In addition to maintaining a steady state, we wanted to understand how to eliminate the backlog that has developed as a result of the ongoing demand not being met. 

The main bottlenecks were identified and the issue is not at the beginning of the pathway (getting the completed questionnaires back from parents/schools) like it has been suggested at the start of the project, but further down the pathway due to clinical staffing capacity. Furthermore, the developed model shows that recruiting just one extra clinician would result in having a steady state with the backlog not growing. The model also shows possible staffing requirements to remove existing backlog in 1-5 years in addition to keeping a steady state.

The findings and the model demo have been presented to the stakeholders including service managers, clinical and operational leads, service heads and the Trust board, and discussions on plans for how the model is used to support any improvement work in the service is already taking place.

Katie Brown - Dorset HealthCare
Hannah Carroll - Dorset HealthCare

Andrew Poole - NHS Dorset
Matthew Chapman - Dorset HealthCare 

The aim of the project was to use Discrete Event Simulation (DES) to model the current wait list for High Intensity Cognitive Behavioural Therapy (HI-CBT). The team wanted to see if changing the allocation of therapist resources by running an evening face-to-face clinic, instead of an evening group, would improve overall wait times for therapy.

Patients were created as entities within the model, and average % preferences for IESO (online therapy), group therapy, virtual or face-to-face 1-1 appointments were assigned. Along with whether the patient was a priority, preferred evening or face-to-face appointments, and average number of appointments offered. They used current and historic data of people waiting or seen for therapy, attendance rates, and meeting with the data lead and service managers within Steps 2 Wellbeing, in order to gain an accurate picture of the waiting and treatment pathway for patients. 

The model does confirm that the longest wait times appear to be for people waiting for face-to-face or evening 1-1 appointments. The model shows improvements in waiting times when an evening group is changed to a 1-1 face-to-face evening clinic. 

The team is making changes to the model based on stakeholder feedback and will present to senior management within the service.

Lisa Sabir - Sheffield Children’s Hospital 

The project aimed to use forecasting and machine learning methods to predict the length of stay and arrivals to the Emergency Department (ED) at different times of day, days of the week and months of the year. Understanding this would allow the team to examine trends and predict future demand so they better plan workforce. 

They have designed a web-based app where they can input the Sheffield Children’s hospital data and use it to explore trends in attendances and length of stay. This allows them to see patterns and suggest improvements, such as when it would be better for extra staffing. The web-page produces a “Forecast” demonstrating the attendances by hour/day/month/year as well as length of stay via interactive buttons. It is then able to give an estimate for a selected time to predict future demand. 

They have completed the forecasting methods for this project and are now developing the machine learning model. The team hope to gain permission for this to be used on a wider scale so individual trusts can input their own data. 

Martina Fonseca – NHS England and Improvement  
Xiaochen Ge - NHS England and Improvement

The aim of the project is to find out what role Patient Initiated Follow-up (PIFU) can play in the redeployment of capacity to address the backlog. This will be done by mapping outpatient pathways for rheumatology sub-pathway using discrete event simulation (DES).

The team did what-if modelling of resource use based on the proportion of patients on a PIFU pathway, the rate of PIFU patient-initiated requests and the use of advice & guidance. They used this to understand how released resource is redeployed, and how the upstream referral-to-treatment (RTT) waiting list behaves (size and waiting time to first outpatient).

The focus was on rheumatology as a case study since it had well documented pathways and good clinical evidence base on PIFU, with PIFU actively endorsed by NHSE and GIRFT. It is mainly an outpatient specialty with many chronic patients on long-term follow-up, meaning that the effect of PIFU is in theory amplified. 

Other opportunities include discussing a spin-off model that includes effect of other digital musculoskeletal peri-treatment interventions or creating a proof-of-concept generalised DES that can be used for other PIFU specialties (PIFU is being advocated across most elective specialties). 

On the PIFU rheumatology model itself, the team aim to continue refining the model based on internal stakeholder feedback. A secondary aim is to create an end-user toy tool that could help demonstrate some of the what-if scenarios to operational managers, in collaboration with NHSE Digital Care Model colleagues.  

Matt Eves - Derbyshire Community Health Services NHS Foundation Trust

Anya Gopfert - Torbay Council
Sally Brown - West Sussex County Council 

There are three current significant health agendas to which this project broadly relates. These are 1) The inequalities agenda, 2) The digital and transformation agenda, and 3) The Net Zero agenda.

The aim of this project was to explore feasibility of considering the impact of a new clinic location on inequalities and carbon emissions, and any co-benefits or trade-offs between the two. Ultimately, the aim was to enable decision making to incorporate these two significant areas.

The team have achieved:

1. The automation of a Health Equity Assessment to compare the profile of patients in a service to the population at large

2. The running of a number of variations to a logistic regression model to identify features predictive of someone not attending their appointment

3. Quantifying an estimate for the patient travel carbon emissions associated with the current service design. 

They are intending to continue working together as a team to finish the project’s initial scope (e.g. inc. possible new clinic sites and model impact on unmet need / emissions) – potentially supported by code from another project, emphasising the benefit of open source.

They have been successful in securing a funding from the Greener NHS Healthier Futures Action Fund joint bid. 

Stephen Ashmead – Royal Devon University Healthcare NHS Foundation Trust
Karim Kamara - Royal Devon University Healthcare NHS Foundation Trust
Jahangir Alam - NHS North East London CSU

The project aim was to develop a predictive model to identify patients at high risk of admission and to provide explanatory feedback as to why the patients were at risk. There were three elements of the project:

• Using structured data to generate a predictive model

• Use unstructured data from patient notes to generate a predictive model

• To combine the two models to create an enhanced model

Three models were developed using structured data – logistic regression, random forest and neural network. Logistic regression performed best.

For the unstructured data, attempts to use more advanced Natural Language Processing techniques (such as neural networks and transformers) were unsuccessful due to limited computing power. However, a more basic model using a Term Frequency-Inverse Document Frequency matrix with a random forest showed some improvement on accuracy.

Electronic health record data can accurately be used to predict whether a patient is at risk of non-elective admission. Administrative events are often better indicators than clinical measures, however EHR data is prone to several limitations and biases which can lead to counter-intuitive correlations. For analysis of unstructured data, greater computing power than I have access to is required to analyse the large quantities of patient notes, even when focusing on relatively short time frames.

It will make a difference to patient care by allowing patients at risk of non-elective admission to receive preventative care, leading to better health outcomes for the individual patients and freeing up inpatient resources for other patients.

Mike Hill – Analyst, Avon and Somerset Constabulary

This project used AI-based Natural Language Processing methods to develop a dashboard that predicts the sentiment (positive or negative) of every tweet to every police force in the country, and automatically identifies the topics that people are talking about positively or negatively. The project has transformed the way in which Avon and Somerset Constabulary’s social media team can respond to concerns identified by members of the public. The HSMA who led this project is now mentoring a project in the fourth round of the programme, to help spread the skills and knowledge he acquired during the programme.

Claire Rudler – NHS Devon CCG
Matt Smith – Information Analyst, NHS Devon CCG
Imca Hensels-Pelling – Information Analyst, Royal Devon and Exeter NHS Foundation Trust
Zoe Ficken – Senior Information Analyst, Royal Devon and Exeter NHS Foundation Trust

This project used Discrete Event Simulation to model the hip surgery patient pathway in Exeter to understand the potential impact of various strategies to reduce the backlog for hip surgery. The work represented a collaboration between the CCG and the acute provider and fed into their long-term planning to support decision-making.

Jenna Thomas – Strategic Analyst, Devon and Cornwall Police
Charly Bartlett – Analyst, Devon and Cornwall Police
Neil Mitchell – Business Intelligence Developer, Devon and Cornwall Police

This project used Network Analysis methods to identify the social relationships between groups of people who could be causing significant issues within their communities, and enable the police to consider pro-active interventions to target those who may be at risk of future offending because of their social links with offenders. The team developed a proof of concept initially that demonstrated they could use this type of analysis to identify “at risk” individuals in a matter of hours compared to over many months using traditional manual methods. The methods were then applied to identify a highly connected network of youths causing issues in a community within a Devon city.

Fiona Bohan, Performance and Analysis Manager at Devon and Cornwall Police, had this to say about the work :

“The need for Social Network Analysis is clear. Criminal and exploitative networks are a huge and costly issue for police, their partner agencies, and the community. SNA, using minimal resource, can identify children at current and future risk of exploitation, as well as those key players within the network who pose the greatest risk. By targeting and removing these key players, and concentrating limited early intervention resources on protecting those at risk in the future, there are potential significant savings both in terms of child harm and partnership spend. This proof of concept has highlighted the significant benefits of embedding this approach in force and, in my view, will play an important part in policing in the future.”

Adam Scull – Transformation Intelligence Manager, NHS England and NHS Improvement

This project used a combination of Discrete Event Simulation and Geographic Modelling approaches to determine where Level 2 Pediatric Critical Care Units should be located in South West England to bring care closer to home. The project demonstrated the clear need for units outside of Bristol to better serve the population in the South West, and was able to identify proposed locations for such sites. The HSMA who led this project is now mentoring a project in the fourth round of the programme, to help spread the skills and knowledge he acquired during the programme.

Dr Adam Kwiatkowski – GP and Clinical Director, Torridge Primary Care Network

In winter 2020, vaccinations had recently been approved for use in the UK to protect people against the COVID-19 virus. Consequently, a mass vaccination programme was required to vaccinate most of the population of the country, which led to local GP surgeries having to pivot to deliver vaccinations for their communities at a scale and pace never seen before. 

This project was led by a HSMA who had never undertaken any coding work before but using his training from the HSMA programme he rapidly developed a Discrete Event Simulation model of the proposed pathway and resourcing for a vaccination service in North Devon. The model was able to predict not only the rate at which patients could be vaccinated with proposed resourcing, but also the potential risks of social distancing breaches in the waiting room and overflowing in the carpark. The model identified potential issues with the proposed plans, and was used to refine the plans to enable a safe but efficient delivery of the vaccinations in North Devon. 

The HSMA also worked with the South West Academic Health Science Network (AHSN) to develop a generic version of the model that could be used for any future vaccination services, and has made the model available Free and Open Source for anyone to use anywhere in the world:

Dr Kwiatkowski said:
“I enjoyed designing it. It predicts queue lengths, car park capacity and times for every step of the vaccination process in the clinic to avoid overcrowded waiting rooms. In the winter of 2020/1 the country was back in lock down and there seemed no end in sight regarding COVID. The vaccines seemed like a ray of hope and setting up the clinics was instrumental in turning the tide. Being able to use the knowledge gained from the HSMA course to help design the process was fantastic. The clinic has now delivered over 100,000 vaccines.”

Dr Adam Kwiatkowski – GP and Clinical Director, Torridge Primary Care Network
Prof Mona Nasser – Associate Professor of Evidence Based Dentistry, Peninsula Dental School
Imca Hensels-Pelling – Information Analyst, Royal Devon and Exeter NHS Foundation Trust

This exploratory project explored the use of Natural Language Processing methods to automate the extraction of key information from free-text patient notes in order to ascertain whether clues in notes could be used to predict an imminent admission to hospital. The team found certain important aspects that seemed to offer indications of an imminent admission, such as increased frequency and verbosity of patient notes, and the use of certain words. The team is now continuing to use these preliminary insights to develop a machine learning algorithm to try to predict an imminent admission for patients in Devon.