Data is increasingly powering healthcare, from electronic health care records providing real-world data to information captured from wearables, or remote patient monitoring solutions
The rapid advancement of analytical technology, such as machine learning and big-data analytics, means this explosion in healthcare data can be used to significantly enhance how we research, manage and treat health conditions, allowing us to offer a more personalised approach to medical diagnosis and treatment. However, for the vast amounts of data that exists to be put to good use, we need to be able to access, analyse and interpret it effectively. So, the question is – how do we make effective use of data and analytics to power a new, insight-driven era of healthcare?
Ensure data is integrated, not in siloes
Put simply, the inability to see accurate and complete patient records, limits the level of care professionals can deliver. Records are often spread across many fragmented sources of data, part paper and part digital, with multiple gatekeepers who all have their own data for the patient.
Integrating and taking a holistic approach to these data sets is crucial to improving patient outcomes, as it gives a rounded and more insightful view of the patient’s health, rather than a partial view of a single point in time in the patient pathway.
Therefore, before applying AI or other analytical technologies to data, it first needs to be linked and aggregated – and this must be done in an ethical, and clinically relevant manner, preserving patient privacy while ensure clinical accuracy.
To do so effectively, we must build interdisciplinary teams that understand the relevance and importance of effective data wrangling, understand data-dictionaries and standards, clinical expertise, and privacy experts. Technology has helped inform every step of this process, enabling the
standardisation and analysis of data sets sat across disparate databases to impact patient care.
Implement AI for advanced analytics
The sheer quantity and complexity of health data available to us means it is now impossible to analyse for trends and insights without the assistance of tools such as AI.
What’s more, the ability to collect data and analyse through advanced tools now allows us to question our classical, and perhaps outdated approaches to understanding biology and disease manifestations. For example, Inflammatory Bowel Disease (IBD) or heart failure, which are currently classified as a disease, are, in-fact, syndromes made up of multiple pathologies. By classifying them as one disease and treating all patients with those symptoms with one treatment, we are mismanging and not providing the best care possible for these patients who are suffering.
If instead we consider them to be a spectrum of disorders, and use advanced analytical tools applied to patient outcomes captured in Electronic Patient Records (EPR), we can model the patient outcomes. For example, the response to a treatment, rather than just looking at the symptoms and understanding which biomarkers classify a patient into which patient trajectory. This allows us to provide targeted care for our patients, but also focus future drug discovery and development on
the patients who are not responding to current lines of therapy.
Work to overcome bias or discrimination
Once data is integrated and AI tools are in place, there is another challenge to overcome for data analysis to be effective – overcoming bias. As AI continues to advance and the boundaries in which it operates expands, we will naturally begin to face challenges around bias. It’s an issue because fundamentally AI systems partly require training from humans, so it can be difficult to entirely eliminate any bias that will exist in the data sets we are using to train the algorithms.
That being said, we must make a concerted effort to ensure the data sets used to train AI algorithms adequately cover global diversity. Inherently, this has challenges as most data sets available for research are biased, and as a sector, it is essential we take active steps to reverse this bias and include diversity across the board from training data sets in algorithms to patient populations studied in drug discovery, acknowledging that this has been a challenge for the industry historically.
Be ambitious about what the future of data in healthcare looks like
Alongside all of these steps, we must be ambitious about what we expect to achieve, keeping in mind the ideal or best practice and striving to reach it – regardless of where in the journey we may be.
For me, the goal is using data insights to create life-sciences outcomes which are truly patient centric. To achieve this, we must have access to large scale, fully anonymised, sharable banks of patient holistic records, linked to their EPRs and outcomes. A drug discovery or Healthcare program
could start with medical record data to define the target product profile and samples from patients could be used to run drug discovery and development as an iterative process, moving away from a
linear system from Targets ID to clinical trials. It is akin to how agile ways of working transformed the technology sector. Iterating this whole process, would allow us to fail faster and reduce the cost of innovation.
When we think about analysing and using data more effectively in the healthcare sector, the overarching aim must be to offer better patient experiences and bring drugs to market faster. Instead of the lengthy and costly drug creation process, data can allow us to accelerate this, and take
away the need for patients to be given unnecessary drugs or placebos, for example. By making sure data is integrated, applying AI and analytics tools, working to remove bias and striving to make the most effective use of data, we have the potential to usher in a new era of healthcare.
About the Author
Alan Payne is CIO at Sensyne Health. Sensyne Health plc is a healthcare technology company that creates value from accelerating the discovery and development of new medicines and improving patient care through the analysis of real-world evidence from large databases of anonymised patient data in collaboration with NHS Trusts.
Featured image: ©DarioLoPresti