Here you can find details of a range of HSMA projects that are currently being worked on.
Click on the preview for each project to read the full details. For many completed projects, you can watch a short talk from the HSMAs who undertook the project on their plans, successes and challenges.
Projects In Progress
Using Machine Learning and Explainable AI to predict and understand mental health appointment DNAs to reduce inequalities
This project uses machine learning to explore correlations whether there is a correlation between missed mental health appointments and factors like deprivation, age, ethnicity, and travel distance. Reducing non-attendance can significantly impact waiting lists.
Discrete Event Simulation modelling of Non-elective flow
Poor patient flow in Emergency Departments leads to long admission waits and poorer patient outcomes. Strategies include increasing beds and reducing discharge delays. This project uses Discrete Event Simulation to explore bed numbers, length of stay, and Same Day Emergency Care impacts on ED waits, aiming to optimise patient flow.
Geographic and Boosted Tree Modelling of Healthcare worker vaccination uptake
There is a decreasing uptake of COVID and flu vaccinations among healthcare workers. Identifying patterns by staff uptake, gender, ethnicity, deprivation, and other factors can help. Using geographic and boosted tree modelling, along with regression analysis, can capture these patterns and provide useful data for stakeholders to address the issue.
DESmond: Discrete Event Simulation and Artificially Intelligent Forecasting: Modelling the 62 Day Prostate Cancer Pathway
We're missing the 62-day prostate cancer treatment target due to resource allocation issues. The project aims to develop a Discrete Event Simulation model to predict demand and identify bottlenecks using live data. This model will help reallocate resources proactively, ensuring targets are met. The outcome includes an interactive web app and dashboard for key metrics.
Discrete Event Simulation to model othopaedic theatre capacity optimisation
The project aims to use Discrete Event Simulation to optimize theatre capacity for elective and major trauma orthopaedic procedures at UHCW. Increasing emergency referrals are impacting elective lists and finances. The model will explore adding theatre slots and increasing capacity to improve patient flow and reduce waiting lists.
Improving ambulance care via fast feedback from Quality Care Indicators
The project aims to improve ACQI data quality and provide rapid feedback using a tool to analyse free text fields, capture sentiment, categorize incidents, and assess treatment appropriateness. This tool could be shared with other Ambulance Trusts and serve as a backup for to manually review data. It will also predict rule changes and their impact on scores.
Discrete Event Simulation modelling of childrens ADHD diagnosis and treatment
The project uses Discrete Event Simulation to model the children's ADHD diagnostic and treatment pathway, aiming to reduce waiting times and lists. It proposes a new pathway with preliminary diagnostic testing to ensure accurate ADHD assessments. The model will evaluate the impact of these changes and may extend to include 1:1 and group session appointments.
Modelling eye injection pathways
The project aims to develop a flexible simulation model to optimise anti-VEGF treatment strategies in ophthalmology. It will use dual modelling frameworks, a modular design, and an interactive dashboard. The model will analyse clinical effectiveness, costs, and resource requirements, adapting to new treatments. The objective is to provide a tool to improve patient outcomes and optimize resource use and costs.
Modelling the impact of 111 and GP access on Emergency Departments
This project will use Discrete Event Simulation to model patients’ navigation of GP vs 111 services and assess the knock-on effect for Emergency Departments.
Using machine learning models to predict future frailty
The project uses machine learning to estimate future frailty in the Wakefield District and identify key predictive features. It aims to plan resource allocation based on evidence, using two years of linked data. The project will also explore predicting other long-term conditions and produce reports and a user interface for stakeholders.
Understanding drivers of increased length of stay
NCL has seen a rise in long Length of Stay (LoS) over the past 5 years, causing system strain. This project aims to develop a causal model to identify factors affecting LoS and estimate the impact of interventions. Key aims include building qualitative and quantitative models of LoS and modelling changes in response to interventions.
Forecasting modelling for A&E attendance
The project aims to forecast A&E attendances 6 weeks in advance, considering seasonal patterns. This helps manage limited resources, plan staffing levels, and assess the need for escalation during abnormal events. Using Time Series Forecasting and a Repeatable Analytical Pipeline, the project addresses the unpredictability of A&E demand influenced by various factors.
Using classification modelling technques to investigate changes in Healthcare Resources Group (HRG) coding over time
The project will use classification modelling and explainable AI to identify changes in complexity and comorbidity categorisation over time, ensuring accurate cost pressure insights.
Forecasting acute bed occupancy, and simulating short term demand and capacity for acute beds
The project aims to develop a tool for time series forecasting of bed occupancy using historical data, incorporating seasonality and growth. A web-based app will simulate acute bed models, including variables like closed beds and additional capacity. Using machine learning and discrete event simulation, the tool will aid decision-making and provide reliable daily forecasts.
Modelling Musculoskeletal Physiotherapy services across Exeter, Mid and East Devon
The project explores demand and access to Musculoskeletal Physiotherapy services in Exeter, Mid, and East Devon. It uses Geographic Modelling to show variations in demand and access times, using DES to optimize resource placement. A Streamlit App will be developed for ongoing service development and review.
Forecasting the supply of medical doctors
The project aims to forecast the regional demand for medical doctors, considering factors like trainees and population. It will plot a graph showing the current supply versus demand. Additionally, it will simulate outcomes under different scenarios, such as changes in trainee numbers or population health, to better understand and address the gap.
Optimising the location of Breast Cancer diagnostic services across Devon
Over 6000 patients are referred annually for fast-track breast symptom diagnosis at RD&E and NDDH. Increasing referrals and limited infrastructure necessitate building or extending diagnostic units. The project aims to determine optimal locations for additional services to minimize patient travel time and reduce costs, using data science to map demand and calculate travel distances and benefits.
Referral to treatment waiting times for Neurosurgical patients
The project models the neurosurgical patient pathway to predict waiting list changes and treatment wait times. It aims to add user interaction to explore how capacity adjustments affect waiting times and track patients waiting over 52 weeks each month.
Predicting the risk of injurious falls in older people with atrial fibrillation
Atrial fibrillation (AF) increases stroke risk, and anticoagulation reduces this risk but can cause bleeding. Despite guidelines, many clinicians avoid prescribing anticoagulants to those at risk of falls. This project explores using machine learning to predict injurious falls in older AF patients and aims to develop a tool to personalize anticoagulant treatment based on falls risk.
Clinical coding automation using Natural Language Processing
The project aims to use Natural Language Processing (NLP) to automate the prediction of ICD-10 or OPCS-4 codes from doctor/patient notes, currently done manually. Initially focusing on 3-character ICD-10 chapters, it will eventually predict full 4-character codes. Collaborating with a provider, the project will streamline coding and improve accuracy.
Modelling 111 option 2 call centre
The project aims to improve two struggling 111 call centres for mental health patients in Norfolk and Suffolk. It will develop a DES model to compare staffing approaches and determine the resources needed for safe service. Additionally, a tool will be created to ensure safe rosters by inputting current rosters and forecasting call levels.
Predicting the future demand for Renal replacement therapy
Kidney disease is projected to be the fifth leading cause of premature deaths globally by 2040. Rising demand for dialysis and transplants exceeds capacity in England. The project aims to develop a model using forecasting techniques to predict future demand and address it by increasing home dialysis or introducing a new dialysis centre.
Intelligent Pathway Management
The project uses data science to quantify the impact of deviations from the "Best Case Scenario" in patient pathways. It involves process mining, an unsupervised learning model to determine relationships between deviations and patient risk, validation, to create Streamlit app reporting suite. The suite presents statistics and risk stratification, with simulations to identify risk profile changes as pathways change.
Predicting Gestational Diabetes and other maternity-related conditions using machine learning
The project aims to use machine learning to predict gestational diabetes and other maternity-related conditions early in pregnancy, enabling timely interventions and personalised care. It will develop a predictive model, an interactive web app for clinicians to input patient data and receive predictions, and reports on the model's accuracy and effectiveness.
Developing a streamlit app for creating Theographs of patient journeys
The project aims to create an open-source application for generating interactive theograph visuals to understand patient/client journeys. It will be a generic tool requiring minimal data fields, usable in various healthcare or social care settings.
Modelling delays in breast, head and neck cancer pathways
The project uses DES to model post-diagnosis pathways for breast and head and neck cancer. It aims to identify delays and treatment variations across England, focusing on two key steps - time from neoadjuvant SACT to surgery or radiotherapy, and time from surgery to first adjuvant treatment.
Modelling secondary care psychological therapy flow
The project aims to improve patient flow for severe mental health treatment by assessing and projecting service user pathways under various conditions. It will provide statistical reasoning for future changes to enhance patient experience. Outputs include time in system, queue lengths, resource utilisation rates, and probabilities of exceeding thresholds for queue length, queue time, and resource utilisation.
Pharmacy Clinical prioritisation tool
The project aims to enhance the Clinical Prioritisation Tool in the pharmacy department using machine learning and a feedback loop system. This will streamline the identification of high-risk patients and improve scoring accuracy based on feedback from pharmacists and pharmacy technicians, addressing workforce challenges and ensuring better patient interaction.
Modelling of theatre recovery flow requirements
Staffing levels in NHS recovery are unclear, with minimal literature on requirements. Factors like operation type, patient variables, and anaesthetic risk affect recovery time, causing queues. Current systems log patient flow but lack integration. The project aims to predict recovery stay, determine staffing needs, and identify key factors, improving workload planning for recovery staff.
Machine learning to identify possible outpatient DNAs
This project will train a machine learning model to predict outpatient DNAs (did not attend) and prioritise support, such as extra reminders and calls. It may also use discrete event simulation to show the impact on clinic utilisation and waiting times if DNA rates are reduced.
Exploring factors that impact Opiate Cessation using explainable machine learning
Many patients on opiates for acute pain continue long-term, causing adverse effects and dependence. Efforts are underway to reduce long-term opiate use. This project aims to develop a machine learning model to predict successful opiate cessation and explore factors influencing cessation success.
Using Agent Based Simulation to understand criminal adoption of new technologies
This project tests agent-based modelling, using consumer behaviour theory, criminology, and domain knowledge. The project aims to create a general methodology for digital behaviour models, applicable to specific cases, and develop methods to present findings static and interactively.
Identifying unpaid carers in Norfolk
Unpaid carers face mental health risks, loneliness, and isolation. The project will identify carer locations using geographic modelling and predict high-need areas with regression models, focusing on older populations and unpaid carers.
111 Downstream forecasting
This project aims to develop a model predicting the place, time, and volume of downstream activity from 111 calls, deployed as a secure API. It integrates with an existing UEC webapp, using weekly patient-level 111 call data and near-live feeds.
Forecasting blood donation session capacity
Blood donation sessions face issues with cancellations, non-attendance, and medical rejections, leading to missed donations. This project aims to develop a Machine Learning tool to predict actual attendance and assess additional capacity. It will also build a web app for users to review current session capacity and manage bookings effectively.
Developing a web app to recommend appropriate technology enabled care
Technology Enabled Care (TEC) supports independence and health and social care. This project aims to develop a web app providing comprehensive, user-friendly guidance on TEC equipment. It will serve as a one-stop platform for health professionals, carers, and individuals, enhancing personal safety, independence, and reducing the burden on health and social care systems.
Forecasting demand in RDUH breast care services and the impact of urban development
Between 2011 and 2021, the population served by Royal Devon & Exeter Hospital grew by 13%, doubling the national average, leading to long waiting lists. This project aims to develop a forecasting tool for breast services to predict referrals and service demand, inform workforce planning, and justify infrastructure expansion. It will also predict geographical demand changes for optimal service locations.
Mapping health inequalities, depreviation, ethnicities and crime across the UK
The aim of the project is to use ONS data around ethnicities of population, health index England, Deprivation data from QOF, and overlay the same with crime statistics at a…
Evaluating the use of machine learning calssifiers for the identification of the determinants of stage at diagnosis of prostate cancers using registry data
This project uses various Machine Learning methods to classify prostate cancer diagnosis stages using registry fields. The focus is on methods comparison in prostate cancer diagnosis, driven by a recent increase in diagnoses.
Applying Natural Language Processing to automate the extraction and classificiation of congenital anomaly diagnoses from free text and genetic data
This project aims to use Natural Language Processing to automate and standardise extraction and classification of Congenital anomaly diagnoses under ICD10 code Q87.8 which are manually classified from free text, risking errors and inefficiency. To validate diagnoses with genetic data by defining a data linkage method.
Modelling the benefit of MECC (Making Every Contact Count) Training using agent based simulation
Making Every Contact Count (MECC) is an e-learning program for health and social care staff to promote healthy lifestyles. This project uses Agent Based Simulation to model MECC's impact on behaviors like smoking, drinking, and exercise.
• Surrey and Sussex Healthcare NHS Trust
• Somerset NHS Foundation Trust
Identifying which patients are most at risk for an outcome across integrated neighbourhood teams
Population health management uses segmentation to categorise people by health status and needs. However, generic segments may not identify high-risk groups effectively. This project aims to create a tool to identify at-risk patient groups across different geographies, focusing on outcomes like emergency admissions, vaccination rates, and screening uptake.
Using Data Science techniques to address delays in the pathway for Neurodiversity Diagnoses in Children and Young People in Devon
In Devon, around 6,000 children have waited over 52 weeks for a neurodiversity diagnosis, crucial for their education and independence. This project aims to reduce the waiting list and streamline the process using DES modelling, NLP, machine learning, and geographic modelling to identify inequalities and optimise resource allocation.
Predictive modelling for smoking cessation success
Smoking cessation remains challenging despite public health efforts. This project aims to develop a predictive model to identify individuals likely to quit smoking based on demographics and behaviours. It will uncover key predictors and effective pathways using machine learning algorithms like logistic regression, decision trees, random forests, and neural networks, evaluating each for accuracy and interpretability.
Population segmentation of GP-registered population in Dorset
This project aims to develop a machine learning-based population segmentation model for the GP-registered Dorset population, using multiple characteristics including healthcare utilisation. The goal is to identify segments based on care needs to inform service design, enhancing patient understanding and improving resource allocation.
Forecasting NHS planning and performance metrics
This project aims to create a robust forecasting approach for NHS Planning metrics, improving system planning and operational management, and ensuring consistent adoption across the system to aid decision-making.
Proactive Patient Attendance Prediction: Enhancing Healthcare Efficiency through Attendance Forecasting
At Barts Health NHS Trust, 12% of outpatient appointments are missed monthly, wasting over 10,000 hours of clinical resources. Missed appointments can lead to extended waiting lists and patient deterioration. This project aims to develop a machine learning model to forecast non-attendance, a patient contact capture tool, and integrate the model into enterprise reports.
RALPulator : Predicting Robotic-assisted laparoscopic prostatectomy (RALP) operative times from patient letters
This project is an app that reads in patient letters ahead of surgery, using Natural Language Processing techniques to extract key information from the text, and then feeds all of that into a Machine Learning model which then predicts how long the Robotic-assisted laparoscopic prostatectomy (RALP) surgery is going to take.
Identifying potential concurrent treatment areas and services that would better support patients with multiple, complex referral to treatment (RTT) pathways.
The aim of this project is to use machine learning approaches to support analysis of patients with multiple concurrent RTT pathways, focusing particularly on healthcare…
Using machine learning to identify factors that increase number of appointments per pathway
The new EPP data set offers the most comprehensive view of elective pathway activity. Currently, the reasons for varying appointment numbers are unclear, but one theory is that longer waits lead to sicker patients and more appointments. This project plans to use Machine Learning to investigate this further.
Discrete Event Simulation model to support the flow of patients through Community Diagnostic Centres
Community Diagnostic Centres (CDCs) aim to improve patient flow and reduce diagnostic test waits. This project will create a DES model to identify bottlenecks and model scenarios to optimise investments.
Agent Based Simulation modelling influences on access to hospice care
Not everyone eligible for hospice care is offered or accepts it, healthcare professionals' reluctance to refer early and patients' or carers' lack of awareness or willingness to discuss options. This project uses Agent Based Simulation to explore motivations for accessing hospice care, aiming to improve early access and outcomes for patients and carers.
Geographical mapping in specialist palliative and end of life care
This project aims to use geographic mapping with national health and census data to assess if we are caring for a fair represent the population. It will map some characteristics to include cancer/non-cancer status and protected characteristics like gender, sexual orientation, religion, and ethnicity. This understanding can support funding for specific areas and target referrals from underrepresented groups.
Analysis and prediction of seasonality in pathologies requiring ITU admission
This project aims to model patterns in intensive care admissions, such as seasonal variations, using existing data. If patterns are found, Machine Learning will predict patient numbers and time periods. The project will also identify patients needing more physiotherapy, informing staffing, leave, and training.
DES model of a North West Renal Dialysis Unit to evaluate the impact of the growing need for in-centre Chronic Kidney Disease dialysis provision
Rising dialysis demand for Chronic Kidney Disease patients is straining regional centres. The North West Kidney Network aims to demonstrate this pressure and explore adjusting staffed capacity and training ratios. The project will create a DES model of a renal unit to evaluate impact, justify investment, and optimise resources.
DES Modelling of The Hyperacute / Acute Stroke Pathway - Patient and Economic Outcomes
Stroke prevalence in the UK is forecasted to increase by 40-60% from 2021 to 2030, straining hospitals and society. This project aims to develop a discrete simulation model to optimise the Hyperacute/Acute stroke pathway, improving patient outcomes, reducing costs, and enhancing economic benefits. It will analyse variables like staffing and operating hours
Redrawing North West Ambulance dispatch Boundaries
North West Ambulance Service (NWAS) has three dispatch suites in Manchester, Preston, and Liverpool, with dispatch areas mainly based on postcodes. Changes in the landscape and increased emergency demand have led to unequal resource distribution, causing delays. This project aims to generate evidence to redraw boundaries to ensure equitable resource allocation across the three areas.
Using Machine Learning to identify factors that predict cardiac mortality
This project will use machine learning and explainable AI techniques to try to identify the factors that predict cardiac mortality.
Building a Machine Learning tool to predict Did Not Attend (DNA) events
This project is developing a machine learning-based tool that looks at the likelihood outpatient Did Not Attend (DNA) incidences across different services/demographics.
Modelling Same Day Emergency Care (SDEC) Pathways
This project uses Discrete Event Simulation to model alternative pathways, like Same Day Emergency Care (SDEC), for patients to avoid ED attendance. It aims to understand pathway availability for SWAST, impact analysis, and implementation of new SDEC pathways. Initially piloted in Devon, it includes clinical variables and pathway criteria, with plans to expand to other areas SWAST covers.
Optimising Same Day Emergency Care (SDEC) Resourcing
This project will model Same Day Emergency Care (SDEC) and Emergency Department (ED) pathways at University Hospitals Bristol and Weston NHS Foundation Trust.
Analysis and forecasting of referrals into hospital
This project will use Python and forecasting approaches to analyse growth in referrals into the hospital.
Developing a primary care load management tool
A GP practice with 35,000 patients has peak call wait times of 60 minutes. Adding more staff improved this, but staff are idle during lulls. This project will model the telephone system and call handlers' workload to optimise resourcing and efficiency. A web app will be developed to test different scenarios.
Modelling the Talking Therapies clinical pathway using a Discrete Event Simulation
The NHS Talking Therapies programme, supports NICE guidelines for treating anxiety and depression. The aim is to develop a Discrete Event Simulation to model patient flow through the new clinical pathway. This project will identify potential waiting list build-ups due to increased referrals into Talking Therapies.
Data Visualisation to enhance the efficiency and equity of Community Rehabilitation Services
An Excel dashboard shows team and individual clinician demand, waits, and activity but lacks demographic, waiting list, or engagement data. Inconsistent data use hinders quality improvement. By integrating and visually presenting data to clinicians, service users, and managers, the project aims to highlight service impact, reduce health inequalities, and improve efficiency.
Automating injury coding using language models
Traumatic injuries are common in emergency care and a leading cause of death and disability in working-age individuals. Patients undergo clinical assessments, blood tests, and CT imaging upon arrival. Major trauma centres (MTCs) are funded based on injury severity, requiring accurate coding. The HSMA project aims to train a language model to generate injury codes from free-text radiology reports.
Evaluating the Impact of Community Diagnostic Centres on Health Inequalities and Patient Access to Diagnostic Services
Community Diagnostic Centres (CDCs) aim to expand diagnostic capacity and improve access, but their equitable distribution is unclear. This project will assess CDCs' impact on patient access and health inequalities by analysing socio-demographic, geographic, and utilisation data.
Geographic modelling of resource utlitisation at Devon Air Ambulance
A geographical modelling project on the utilisation of resources at Devon Air Ambulance. Modelling current demand and conducting what if scenarios to optimise service…
Automating and scaling waiting list equity analysis at a trust level
This project uses a streamlit app to automates/scales waiting list equity analysis at a trust level and (optionally) service level.
SIMPACT: Simulation of Medical Patient Admission and Care Throughput
Project details coming soon.
eFIT: Extra funding allocation - inequality tool
The project addresses the lack of national guidance for allocating extra primary care funding by ICBs. It proposes using an equation based on deprivation scores and local needs. A Streamlit web-app tool will help ICBs allocate funds more equitably, considering various indicators and demographics, ensuring a fair distribution and reducing inequalities.
Modelling resourcing scenarios to meet increases in demand on a Devon eye clinic
The project aims to develop a DES model for an eye clinic at Royal Devon University Healthcare NHS Foundation Trust. It will use "what if?" analysis to explore the impact of increasing staff and room resources, and AI support in the POD clinic, on meeting a 10% annual demand increase, reducing waiting times, and improving service efficiency.
Using Machine Learning to predict whether a patient might develop a SSI (Surgical Site Infection)
This project is to develop a simple classification model to predict whether a patient will develop a SSI (Surgical Site Infection).