The technical nature of data and analytics can make it seem disconnected from the human experience. But that couldn't be farther from the truth.
Data and analytics have real-world impacts on our everyday lives—and sometimes, even on our health.
For example, the use of data and analytics can help organizations like the NHS optimize their systems and processes, which can free up health professionals’ time, and ultimately give NHS workers more time with their patients.
From Electronic Health Records (EHRs) and wearable devices to staffing schedules, here are a few ways that data can be used operationally to help streamline health services like the NHS.
A big hurdle faced within healthcare is not being able to control the flow of patients, which makes it difficult to predict the number of resources needed at any given time.
Despite on-call systems designed to overcome this issue, hospitals are often caught on the back foot with more patients than staff or beds to offer. This is where data can help.
Hospitals are brimming with data points, from a patient’s condition on arrival at the hospital to individual medical records and broader demographic information.
Using this plethora of information, predictive analytics can generate valuable forecasts, predictions, and recommendations that can give healthcare professionals a chance to work proactively rather than reactively and ensure hospital resources are effectively allocated.
For example, predictive tools were used across the healthcare industry throughout the pandemic. The NHS COVID-19 Data Store provided invaluable data to aid decision-making at a national, regional, and local level.
By using a single integrated data, analysis, and modelling platform (Foundry) NHS analysts were able to develop tools to support local systems in responding to the pandemic including short-term forecasts, supply management capability (for critical equipment such as oxygen and PPE), and an early warning system to support regional and local teams to anticipate pressures and make the best use of resources.
The capacity challenge
Managing capacity is another predicament in healthcare.
There is no way to regulate how many beds will be needed at any one time, and there is a constant balancing act between ensuring that only those who need hospital care are in the hospital, so that there is enough space and staff to go around.
Analytic techniques can be used to better manage the demand for hospital beds and other healthcare resources.
For example, non-urgent A&E visits continue to be a cost constraint on the NHS. In August of 2021, 2,038,661 members of the public attended A&E. Of this number, only 1 in 5 (19 per cent) were admitted as an emergency, suggesting that the other 81 per cent attended for otherwise avoidable reasons.
Using historical and real-time data, AI and machine learning techniques can be used to predict which members are at risk for generally avoidable A&E visits and then establish intervention strategies.
This allows staff to connect patients with the right care and services in advance, which helps prevent unnecessary A&E visits.
To keep patients out of the hospital when possible, doctors are exploring the use of wearable devices that collect patients’ health data continuously and link it to a tracking and alerting system.
For instance, if a patient’s blood pressure increases alarmingly, the system will send a live alert to the doctor who will then take action to reach the patient and administer treatment.
By using these sources of data to inform and shape processes and strategies, hospitals will have the best chance of cutting costs, reducing waste, and improving staffing ratios, as well as patient outcomes.