Digital service to manage high-risk chronic obstructive pulmonary disease (COPD) patients
A digital healthcare service was created to change the management of chronic obstructive pulmonary disease patients to a proactive and preventative care model.
It uses Artificial Intelligence (AI) to analyse output from patients’ daily monitoring and wearable devices to predict deterioration. This enables targeted intervention by care teams for those patients at most risk.
In the UK, 1.2 million people are affected by COPD.
COPD exacerbations are the second most common cause of emergency hospital admissions, accounting for 1 in 8 UK hospital admissions.
A 40% increase in COPD prevalence is projected and an annual cost to the NHS of £2.5 billion by 2030 is predicted.
A large part of these costs relate to hospital management of COPD exacerbations.
There is a policy to transform the reactive, high-cost approach to caring for COPD patients to one that's more proactive.
This service delivers on this policy. It focuses on prevention, anticipation and co-management.
Personalised risk scores are shown within a clinical dashboard. These help to predict deterioration and death and means COPD patients can be managed proactively.
Solution and impact
The COPD service is developed on the Lenus Health platform, which connects patient-generated data with clinical data from Electronic Patient Records (EPRs).
The platform provides the following capabilities:
- data capture
The COPD service consists of the clinician dashboard, a patient-facing app and asynchronous messaging service.
The service is deployed to Microsoft Azure. Clinical data is mapped to SNOMED CT coding standard whilst Fast Healthcare Interoperability Resources (FHIR) APIs enable the secure exchange of patient-generated healthcare data. This includes Patient Reported Outcomes (PROs).
- Provided devices will automatically gather patient health data and securely share it with the care team.
- Patients are prompted to answer set PROs questions every day.
- Patients can message the care team if support is required.
- A clinical dashboard for health professionals gathers and displays health data for all onboarded patients.
Clinicians can use Lenus to:
- send messages to patients or the designated care team
- create and share self-management plans and rescue pack medication with patients
- Wearable and collects granular Fitbit heart rate, steps and sleep data via API
- Collects home non-invasive ventilation (NIV) data such as Airview NIV use and daily therapy data via API.
- Options for any patient input, passive integration of any sensor or connected therapy via Lenus and APIs.
The patient can use the app to:
- provide PROs and is prompted to by a daily reminder notification
- log symptoms in a diary
- complete daily COPD assessment tests
- report Medical Research Council and exacerbation occurrences each week
- complete COPD EQ5D health status questionnaire each month
The service is used to support remote management of high-risk COPD patients in the home and in community settings.
Key learning points
- Patients are happy to use the service if they understand the data is used to deliver better care.
- Patients and family learn about variability and what’s normal.
- Data-supported reviews and access to clinicians offer reassurance to the patient.
- Clinicians appreciate an additional way to optimise patient care.
- Patients do not view it as a burden.
- Patients are open to AI insights from their data going to the clinical team.
- The impact on clinical team resources was manageable.
A clinical trial of the COPD Service was initiated in NHS Greater Glasgow and Clyde in 2018 and was concluded in autumn 2021.
Initial analyses are encouraging, showing sustained patient engagement (4 interactions per week) and associated positive impact on patient outcomes. This includes the reduction of 1 hospital admission and 9 days in hospital per patient per year. This adds up to a saving of £8,500 per patient per year.
The data from the trial is being combined with historical data for machine learning analyses. It will train, validate and put into use prediction models for:
- 12 month mortality
- 3 month readmission
- 72 hour exacerbation risk
Find out more
Chris Carlin, NHS Greater Glasgow and Clyde
Paul McGinness, Storm ID and Lenus Health
These case studies summarise user and patient experiences with digital solutions along the relevant care pathway. Unless expressly stated otherwise, the apps and digital tools referenced are not supplied, distributed or endorsed by NHS England or the Department of Health and Social Care and such parties are not liable for any injury, loss or damage arising from their use.
All playbook case studies have either passed, or are currently undergoing the Digital Technology Assessment Criteria (DTAC) assessment.
Please note the full legal disclaimer: NHS England playbook disclaimer