fbpx
Features Hub

How Big Data can improve population health management

Fri 10 Sep 2021

Big Data health

Managing population health has always been a difficult undertaking, but since the emergence of COVID early last year, this task has become even more complex. From an ageing population to increasing expectations from patients, healthcare providers across the globe are facing a range of challenges.

In a bid to enhance patient outcomes, reduce costs and improve efficiency, many health systems are expanding their use of Big Data solutions. While other sectors such as insurance, banking and manufacturing have taken the lead in implementing cutting-edge Big Data analytics, the success of these technologies in healthcare is driving adoption in the industry.

Big Data tools like machine learning, predictive analytics and AI can be used to mine patient data to find patterns that a single doctor would not be able to see. According to a 2019 report, the global big data in the healthcare market is forecast to total more than $34 billion by 2022, growing at a rate of over 22% per year until 2022.

Powerful use cases

Medical imaging firm Carestream has shown how big data analytics have the ability to transform how doctors interpret all types of medical images. By using advanced algorithms to analyse countless thousands of images, a range of patterns can be identified that help support staff in providing an accurate diagnosis to their patients. As algorithms are able to learn as they read and analyse more images, they will constantly keep up to date with how conditions present themselves.

The preventative element of Big Data solutions used in healthcare is showing a great deal of promise. The phrase ‘prevention is better than cure’ is hardy new. But utilising Big Data solutions can be a robust tool for clinicians to find indications of future health issues and communicate these signs to patients who will have the capacity to make an informed choice on how to address these risks.

With the World Health Organization (WHO) finding that 700,000 people die due to suicide each year globally, offering the right level of support to at-risk members of the public is vital to reduce the number of deaths from this cause. Predicting which community members are more likely to attempt suicide is a difficult decision for a doctor or clinician to make. But a study found that when electronic health records are combined with results from standardised depression questionnaires, new models are able to more accurate than ever before predict suicide risk.

“We demonstrated that we can use electronic health record data in combination with other tools to accurately identify people at high risk for suicide attempt or suicide death,” said one of the study authors, Gregory E. Simon, a Kaiser Permanente psychiatrist in Washington and a senior investigator at Kaiser Permanente Washington Health Research Institute.

Linking together questionnaire answers with information about previous mental health diagnosis and psychiatric medications dispensed, can provide unrivalled insight into risky behaviours and inform treatment. For example, if an at-risk patient misses scheduled appointments, medical staff can reach out and potentially avert a mental health crisis.

Ethical considerations

As more and more hospital networks upgrade their IT systems and implement Big Data tools to interrogate patient data, the concerns around patient privacy are likely to grow. Protecting patient data and privacy are of the up-most importance to healthcare providers, as without clearly defined rules guiding how data is processed, patient trust will decline.

In a healthcare ecosystem with many different operators, all with their own unique policies on data security, close collaboration will be required to establish guidelines to enable the secure sharing of data for Big Data purposes. While the advantages of Big Data in public health are clear, they will not replace the expertise of medical staff, but rather augment their treatment plans.

Doctors can draw on their vast experiences of treating patients and use this background to inform their understanding of the insights drawn from Big Data. As researchers are able to undertake more analysis of COVID and how it impacts different populations, Big Data can also play a key role in this work.

For example, the medical journal, The Lancet, found that, after adjusting for other factors, not only are South Asian, Black, and mixed ethnic groups all more likely to test positive for COVID than White people in England, they were also more likely to die from this illness.

Understanding the disproportionate impact COVID has had on these communities is not a one-step process, with a range of experts across statistics, medicine and social science needing to work out the race gaps in COVID deaths. Deploying Big Data tools may be able to allow researchers to identify patterns in the data about those who died from COVID and create more effective treatment plans based on these discoveries.

Balancing individual rights with the ‘common good’ is a problematic endeavour, with issues expected to arise during the finding of this middle ground. If public health experts are able to effectively communicate the benefits that all communities can achieve from the widespread usage of Big Data, then unlocking valuable insights from patient data may be able to revolutionise treatment.

Tags:

Big Data Covid-19 public health world health organization
Send us a correction Send us a news tip