Kenya’s healthcare landscape is a paradox because it has plenty of data, but its potential remains underutilised. This is caused by data inconsistencies, incomplete data, poor quality data, and inadequate interoperability, amongst others.
As such, the data lies idly in the various information centres with no tangible insights derived that can help improve system processes and patient care.
In this data-fueled age, the Kenyan healthcare landscape should invest heavily in big data analytics. Big data analytics entails the use of various techniques, such as machine learning and artificial intelligence, to unearth hidden data patterns and trends by cross-examining and processing various contexts, thus getting appropriate results.
Whereas fields such as insurance, telecommunication, and marketing have put considerable investments in big data analytics to refine and produce the latest market trends and personalised product developments, the Kenyan healthcare landscape lags a little behind.
Kenya is a low-income country with an increasing population, which is significantly within the poverty margins and under a high burden of disease that puts an economic strain on its health systems.
The Social Health Authority (SHA) unveiled in 2024 marked a great leap towards the attainment of universal health coverage. SHA facilitates healthcare services from enlisted providers by pooling contributions and distributing healthcare services equitably to all Kenyans.
This authority houses a wealth of data, including claims data, utilisation records, enrollment records, health costs incurred, and insurance performance metrics. But data alone does not point to performance improvement in terms of service delivery.
Despite it being compulsory, the coverage of this insurance scheme is low. Some of the challenges noted are cumbersome claim settlements, inadequate consumer knowledge, negative perception, operational inefficiencies, long wait times for service delivery and claim reimbursements, amongst others. Fraud in this health financing sector remains a challenge.
Through data analytics, trends can be established based on historical transactions and, in particular, heavy loss-making contracts to assess indicators of fraud.
Trends and analytics will enable interrogation of the quality and cost of business from specific indicators. Targeted interventions through big data analytics can greatly improve this national health financing model.
The appropriate data analytics technique will enhance customer experience, real-time fraud detection techniques, enhanced claims processing, and improve operational tasks execution. Besides, the process will contribute to improved data-driven policy decision-making and financial sustainability.
The analysis of SHA data will allow for a strategic and informed rethink of product packaging to more relevant, affordable, and need-centric insurance coverage, even depending on contribution.
Another compelling case for big data analytics in Kenya's health sector lies in the fight against antimicrobial resistance. Antimicrobial resistance is a silent pandemic ravaging Kenya's public health system.
Through concerted efforts by the government to ensure genomic sequencing, real-time laboratory data reporting, and unified electronic health records, Kenya can generate critical data sets necessary to track patterns. The application of big data analytics to the generated data can unravel resistance hotspots, transmission techniques, and identify the culprit genes driving the resistance.
Dr Munga is a pharmacist
