Creation
Draft
Initial
Detailed
Accepted
Adoption
Idea Description
Supplementary Information
Innovation 'Elevator Pitch':
PredictX Machine Learning system has been successfully deployed to solve a similarly difficult problem of identifiying School Ready Children. This model is ideal for solving the problem of early identification of MUS.
Overview of Innovation:
The Complex Symptoms Service (CSS) will focus on the problem of MUS following on from the success of the BMUSS Phase 1 pilot. A system that automatically segments and identifies patients with high probability of MUS at an early stage will significantly increase the savings realised of the CSS as well as improve the well-being of patients. The complexity of MUS makes it difficult to identify manually especially at early stage.

Machine Learning (ML) has advanced to a stage that the challenging task of identifying Medically Unexplained Symptoms (MUS) automatically is now possible.

Our ML model can infer & predict results even with large variety of causal factors and disparate source data and where a single data point in isolation is a poor indicator. In the case of some long term conditions such as diabetes, a single source such as blood sugar levels can be a confirmatory indicator. MUS suffers from the fact that one episode whether via GP assessment or hospital admission does not indicate MUS on its own. Instead, it takes multiple events and episodes examined together in a holistic model that indicates the probability of MUS.

If a system could identify MUS with minimal historical data, early intervention avoids much more serious and costly problems later on. ML models such as the one PredictX developed for Essex County Council (see attachments) is ideal for working on a large range of data sets and inferring relationships not obvious to human observers.

An accurate MUS identification system must be able to meet several requirements.
  1. Robustness of the model. The model must adapt to differences in local data availability and preserve the accuracy by using proxy data if core data is missing.
  2. Leverage a wide range of data sources including social care and health
  3. Capability to read, understand, and classify free text information in any format including PDF as the source data management is often a challenge.
The PredictX Risk model deals with all of the issues. ML models are utilised not just for the forecasting models but also to facilitate understanding of free text utilising advances in Natural Language Processing (NLP).

The model has further advantage of having real-world analogues & explanability. There could be a direct relationship from the features to the phenotypes greatly aiding the health professionals responsible for the interventions.

The model has effectively been deployed in a similar context at Essex CC.https://youtu.be/3J2S82vjb8U
Stage of Development:
Market ready and adopted - Fully proven, commercially deployable, market ready and already adopted in some areas (in a different region or sector)
Similar Content3
Innovation 'Elevator Pitch':
Early identification lies at the heart of the Mental Illness Prevention strategy. PredictX’s proven machine learning model for identification of not school ready children forms the basis for wider application.
 
Overview of Innovation:
The “Get It Right, First Time” program is an ambitious effort to transform the mental health treatment to focus more on early diagnosis and intervention. The benefits of early intervention are clear and well documented. PredictX (PX) believe that we can the application of Machine Learning (ML) based systems improves the identification of at-risk individuals, especially children.

At Essex CC, we developed and deployed a working ML system to identify children and households where the children had a higher probability of not being school ready. As the report states, “ the most productive and cost-effective element of any prevention of mental ill-health strategy will be during a child’s early years.”  The PX school readiness model has proven to be effective in the early identification of not school ready children - beyond previous methods. The system not only identifies at-risk children for early intervention but also indicates the most impactful intervention for a locality.

The PX model not only applies to school readiness but is a flexible framework that adapts to new use cases and available data to solve other similar challenging issues. The model uses data from housing, education, social care, police, health, benefits, and population can use this data for applications beyond school readiness. For instance, early work suggests that the model will be effective predicting domestic abuse - another causal precursor of childhood mental health issues. Because such a wide range of data is accessed, the model is resilient to sparse or missing data from any particular data source.

We believe that the school readiness model is one branch among several that leads to a much more holistic and accurate identification of individuals, families, and locations at risk of mental health issues. Moreover, the model can be tuned to further identify those who would be positively impacted by intervention thus aiding the most effective resource allocation of the intervention team.

The model has the further advantage of having real-world analogues and explainability.  This means that the model will aid the experts by identifying the key causal factors most prevalent in a particular locality, thereby systematically aiding the work with Schools and Education to identify the most critical vulnerabilities and risk markers for mental illness and aiding building the most impactful preventative resilience and wellbeing practices.

Please see:https://youtu.be/3J2S82vjb8U
 
Stage of Development:
Close to market - Prototype near completion and final form may require additional validation/evaluation and all CE marking and regulatory requirements are in place
WMAHSN priorities and themes addressed: 
Mental Health: recovery, crisis and prevention / Advanced diagnostics, genomics and precision medicine / Wellness and prevention of illness / Digital health / Innovation and adoption / Person centred care
Benefit to NHS:
The Five Year Forward View for Mental Health (2016) states that “the future health of millions of children, the sustainability of the NHS, and the economic prosperity of Britain all now depend on a radical upgrade in prevention and public health.” Further it warns that the circumstances since the Wanless review published 12 years ago has become worse. “Mental health problems account for a quarter of all ill health in the UK. Despite important new developments in mental health research it receives less than 5.5 per cent of all health research funding. Latest figures suggest that £115 million is spent on mental health research each year compared with £970 million on physical health research.”  The paper also clearly articulates the importance of Innovation to tackle current and future challenges. In particular , “We see a pivotal role for digital technology in driving major changes to mental health services over the next five years”. Better prevention tools based on AI and Machine Learning is inline with this thinking.

Twelve years ago Derek Wanless’ health review warned that unless the country took prevention seriously we would be faced with a sharply rising burden of avoidable illness. That warning has not been heeded -and the NHS is on the hook for the consequences.”

One of the few silver linings to commencing this work today rather than a decade ago is that the AI technologies to deliver advanced risk identification capability is fully proven now whereas twelve years ago, the technology was nascent if it existed at all.  Therefore the ability to execute the goal of the “Get it Right, First Time” agenda is now feasible with excellent ROI.
 
Initial Review Rating
4.40 (2 ratings)
Benefit to WM population:
According to Mental Health In The West Midlands Combined Authority, a report commissioned by the  West Midlands Mental Health Commission,  Nearly a quarter of adults living in the WMCA are experiencing a mental health problem at any one time. The report also documents that the cost of mental health problems in the WMCA is estimated at around £12.6 billion in 2014–15, equivalent to a cost of about £3,100 per head of population.

Clearly these challenges and the significant benefits for addressing these challenges are key drivers behind the initiatives already in place in the region.

Identification of at risk individuals, especially children must go hand in hand with the infrastructure to intervene for maximum impact. The work by the West Midlands Academic Health Science Network (WMAHSN) supported by Forward Thinking Birmingham to construct the Proof of Concept program that incorporates partners across health and social care, education and policing, as well as community resources suggests that the program will have the resources and focus to execute the intervention strategies.

The effectiveness of the ML model depends on the access to data. Part of the success of the Essex School Readiness project is the buy-in of the different service areas to share their data to achieve the overall aims of enabling a prevention-based service culture.  West Midlands is ahead with forward thinking localities already sharing data across social care and health. This is a promising position from which extension of data sharing to include education, environment and other key information can develop.

From a PredictX perspective, there is already good working relationships with many of the local authorities in the region including integrated social care data - one of the key elements of the ML model.

This work has been performed in collaboration with the Midlands and Lancashire CSU. The close and strategic working relationship established over many years between PredictX and the Midlands and Lancashire CSU will help to ensure that projects are executed per agreed scope and delivered on time and on budget.
 
Current and planned activity: 
PredictX works with the NHS at several levels currently. We work directly with Provider Trusts such as UCLH supplying them with advanced analytic solutions. We also work with CCGs and STPs focusing on advanced analytics that need to integrate social care and health information. We also work with Local Authorities and regions such as the School Readiness system with Essex CC.

We also have a strategic partnership with the West Midlands CSU working to serve their CCG members as well as investing in research and development efforts to apply Artificial Intelligence and Machine Learning techniques to address challenges the sector faces. This partnership has recently been codified with the launch of the Midlands and Lancashire Innovation Partnership - a partnership of the CSU, private sector and academia working together to deliver advanced, AI-enabled solutions.
 
What is the intellectual property status of your innovation?:
IPR is 100% the property of PredictX with no conflicts. We are happy to co-create new IPR with the sector and share the innovation
Return on Investment (£ Value): 
Very high
Return on Investment (Timescale): 
1 year
Ease of scalability: 
2
Read more
Hide details
Innovation 'Elevator Pitch':
UK developed patient focused Population Health solution pulls cross sector data (i.e. GP, Acute, Mental health, etc) and performs analytics and intelligent cohort finding that can identify patients with reported unexplained symptoms.  
Overview of Innovation:
ArtemusICS supports a health system to analyse population data and identify specific gaps, health inequalities and unwarranted variations in its population’s health. ArtemusiCS secure web accessed hosted system provides a wide range of tools, dashboards, selection and filtration options to identify and create patient cohorts. ArtemusICS can then further identify costs, utilisation and gaps in care.

Collecting data from Acute, GP, Community, Mental, Social and Ambulance, ArtemusICS provides commissioners and providers with a tool to identify cohorts of patients, and understand the integrated care needs of a population right down to an individual. It contains analytical tools to allow for LTC risk, EOL risk, Frailty, Social isolation, etc to be collated and presented in one picture. It also allows for evaluation of interventions (i.e outcomes) and identification of RoI.

It has a unique attributes based architecture, where all data items are linked to one or more “attributes”, based on their coding (i.e. Snomed, Read, ICD10, etc). Inherently future proof and expandable, it allows us to utilise Machine Learning and AI techniques to drill through large data sets to find correlations and trends in specified data types, such as the symptoms presented in the MUS cohorts.

ArtemusICS operates on three distinct levels:
  • Overview Dashboards: provide whole-population analytics with facilities to filter down to key patient cohorts. A range of Dashboards provides commissioners and clinicians pertinent population count, event counts, service and usage counts and costs; with the facility to then drill through to cohort and patient specific views.
  • Cohort Manager enables the user to review sub-lists of patients, caseload management groups or individual patients against a range of detailed views including conditions, events, measures, timelines and management lists. Venn diagrams offering cohort comparisons to enable care planners and clinicians to pin-point a specific cohort with a specific set of attributes for intervention and care management.
  • Patient view provides a range of views specific to patient conditions, medications, diagnosis, events and measures, supporting the clinical user to improve diagnosis and plan care.
In addition, our remote monitoring technology can also collect surveys such as PHQ,GAD7, HADs etc
Stage of Development:
Market ready and adopted - Fully proven, commercially deployable, market ready and already adopted in some areas (in a different region or sector)
WMAHSN priorities and themes addressed: 
Mental Health: recovery, crisis and prevention / Long term conditions: a whole system, person-centred approach / Advanced diagnostics, genomics and precision medicine / Wellness and prevention of illness / Wealth creation / Clinical trials and evidence / Digital health / Innovation and adoption / Patient and medicines safety / Person centred care
Benefit to NHS:
ArtemusICS currently identifies all patients with a mental health condition, including those with unexplained medical symptoms; this achieved by the use of Read, SNOMED and ICD10 codes.   Through the development of artificial intelligence and the use of inferential statistics, we would be able to provide rich case finding and provide greater insight in the nature of the specific problem associated with the patients.
Repeat admissions, vague multiple comorbidities and results of screening are all available in the ArtemusICS database and could inform the AI development. Using the ArtemusICS impactability management module, commissioners will be able to assess adherence to care pathways and also monitor the impact of the given interventions.
As patients with medically unexplained symptoms are often seen in multiple care and social settings, ArtemusICS would create and provide a clear picture of all the cross sector activities associated with the patients in order to develop bespoke interventions.
This affords both primary (and potentially) secondary care clinicians the opportunity to introduce patients to a specific MUS care pathway that will deal with the specific requirements of MUS in a timely manner that will prevent the condition becoming chronic.  Effective stratification of patients could aid in a reduction in need for acute secondary care outpatients, reducing unnecessary healthcare costs and freeing up resources.
Initial Review Rating
4.20 (1 ratings)
Benefit to WM population:
As for the health system above
Current and planned activity: 
Docobo are continuously adding additional functionality to its solutions, usually to meet the requests from our NHS customers or our own staff
The uniqueness of ArtemusICS is that Docobo fully owns and controls all of the product. It is not a 3rd party product that we sell, like many others, so we can easily add functionality and are not at the mercy of the overseas priorities of a 3rd party product
What is the intellectual property status of your innovation?:
Fully owned by Docobo
Return on Investment (£ Value): 
high
Return on Investment (Timescale): 
0-6 mon
Ease of scalability: 
3
Read more
Hide details
Innovation 'Elevator Pitch':
This is a risk stratification model that aims to predict and prevent crisis by segmenting the mental health patient population by risk and likelihood of an acute mental health crisis.
 
Overview of Innovation:
Currently, the response to mental health crisis is mostly reactive. To address the increasing pressures faced by the urgent care services by patients presenting with mental health crisis, prevention and early intervention must be prioritised. This will not only alleviate pressure of several emergency care services but will also improve patients’ prospect by ensuring  timely interventions that avoid patients’ mental health deteriorating further.

The Rapid, Assessment, Interface and Discharge Plus project, in partnership with Telefonica Alpha, aims to achieve this by developing and validating a risk stratification model and algorithm to predict mental health crises. The risk stratification model will use four years of pseudonymised clinical and sociodemographic data to capture potentially robust predictors from a wide range of sources to provide an overall indication of a patient’s risk of experiencing a mental health crisis.

By applying the model onto the Trust’s mental health population, we can stratify the patients into different risk groups and subsequently target the highest risk segment of the population for preventative early intervention with improved accuracy. This information will be provided to clinicians who will determine the necessary measures required to prevent the progression from high-risk status to actual mental health crisis. This will act as a ‘clinical support tool’ for clinicians in making their decision and does not replace the clinicians decision on how to manage patients.

The project will look at how the risk stratification model can be implemented into practice, working with Community Mental Health Teams (CMHTs) to pilot the model. The model will be refined, tested and validated by a team of data analysts, clinicians and to embed it into systems for routine clinical care. Using this tool can help improve patient care by avoiding unnecessary admission, presentation at A&E, or potentially prevent an escalation in the worsening of a patient’s mental health state.
 
Stage of Development:
Trial stage - Trial stage to prove that the idea actually works as intended
WMAHSN priorities and themes addressed: 
Mental Health: recovery, crisis and prevention / Long term conditions: a whole system, person-centred approach / Wellness and prevention of illness / Digital health / Innovation and adoption
Benefit to NHS:
In a pressurised financial environment, faced continually with greater challenges to meet quality objectives, this innovative product can simultaneously improve patient outcome by reducing intensity and/or preventing mental health crisis as well as reduce costs by stopping the over saturation of emergency services.
 
The use of technology systems and data is at the centre of the NHS Five Year Forward View. It highlights how the use of data and technology will transform outcomes for patients and citizens. The insights derived from the risk stratification model will help the NHS explore how the information/ data they hold could be used in clinical settings to benefit patients. It will highlight patterns in the data that can be used to develop proactive preventative measures to support mental health patients.  The ability to stratify risk and predict those who might be at risk of mental health supports frontline mental health clinicians to de-escalate situations before crises arise. This leads to improved patient outcomes by avoiding the further deteriorating on mental health and potential saving where the intervention has prevented an entry to the crisis care system.
 
The reduction in demand for emergency and inpatient mental health services will relieve the pressure from the crisis care pathways resulting in enhanced patient experiences, improved staff support and morale, and greater efficiency and effectiveness within urgent care mental health services to respond to current and future patient needs.
 
Initial Review Rating
1.00 (1 ratings)
Benefit to WM population:
Mental health crisis is a significant and increasing problem across Birmingham and Solihull. The number of crises in the region has increased by an average of 7% year on year for the past 5 years and is projected to increase further in the future, according to the Midlands and Lancashire CSU. Therefore, this places increased level of pressure on urgent care services and it is important to be able to introduce proactive measures to stop at risk patients from going into crisis.

The redesign of the crisis care pathway is a key NHS England target for CCGs and a central theme within the STPs. Within the Birmingham and Solihull STP, one of the key mental health objectives is to ‘Manage – preventing mental health crises and managing them better when they do’. Identification of at risk patients and supporting them by intervening sooner fall in line with the STP objective and while this tool doesn’t directly prevent the onset of crisis, it helps refine predictions and manage at risk patients proactively. The use of data-informed decision making leads to better clinical outcomes for West Midlands patients and can potentially release both capacity and resources across the emergency and urgent care system
Current and planned activity: 
The risk stratification model was developed collaboratively between BSMHFT and Telefonica Alpha as part of the Rapid, Assessment, Interface and Discharge Plus NHS Test Bed. The pilot work testing is being supported by The Health Foundation.
 
The tool is planned to be tested in real time by Community Mental Health Teams (CMHTs) in Birmingham and Solihull from September 2018. The CMHTs were identified to be in the most suitable position to be able to utilise a predictive model for crisis presentation into their working practice. The patients at risk will be flagged in real time and this will be reviewed by the CMHTs and an effective intervention put in place to avert the crisis. A robust evaluation is being conducted by the CSU looking at the effectiveness of the tool in supporting clinician’s decision making.
Return on Investment (£ Value): 
N/A
Return on Investment (Timescale): 
N/A
Ease of scalability: 
3
Read more
Hide details
0
0
Votes
-99999

Created by

Share and Follow