AI techniques, machine learning and deep learning have received increased attention during the COVID-19 pandemic. Applications include: disease outbreak detection, contact tracing, forecasting on outbreak, detecting COVID-19 in medical images, drug and vaccine development.
The increasing adoption of electronic health records (EHRs) lead to the development of several standards for data interoperability, thus leading to the creation of large datasets which can make clinical predictive modelling research possible. Developing a reliable and reusable predictive model, requires a common data model into which diverse EHR data sets are transformed and stored. OMOP CDM and the OHDSI ecosystem is community driven and aims at enabling research into characterization, population-level effect estimation and patient-level prediction questions about the disease . ML algorithms on OMOP data are being used to help predict clinical outcomes such as mortality, risk for intubation and risk for requiring intensive care in patients with COVID-19. In this project we aim at using OMOP CDM and OHDSI tools to harmonise Covid-19 data in Malawi and Kenya.
Apart from clinical research, AI has other applications. AI algorithms using natural language processing and information retrieval techniques are used to detect information about possible outbreaks in social media. Agencies such as Ministries of Health lack end-to-end visibility or understanding of their data (which may reside in many disparate structured or unstructured sources) as well as face challenges with data accessibility, integrity and quality. AI can be used for data archeology in the discovery and cataloguing of valuable data. AI can be used to automate meta-data production and to augment sets of documents.