Artificial intelligence, especially in combination with machine learning, is fundamentally transforming modern medicine in medical diagnostics. The strength of AI lies in its ability to process large amounts of data and thus provide medical information significantly faster.
Scientific innovation has always been a key concern for the pharmaceutical industry, and the integration of artificial intelligence into pharmaceutical research is rapidly expanding the possibilities. At every stage of drug development, AI accelerates the identification of therapeutic targets, the development of new molecules, and the optimization of clinical trials. Through greater accuracy, shorter work processes, and lower costs, AI is transforming the way new drugs are discovered, tested, and delivered.
Treatment plans, lab results, MRI scans—clinics, practices, and research institutions generate enormous volumes of data every day. Big Data refers to these complex datasets and the technologies used to store and analyze them. Its defining characteristics are the three Vs: Volume, Velocity, and Variety — large, rapidly growing, and diverse data (Springer, 2021).
We all want to live healthy and long lives. This is a good reason to support medical research, as it is a decisive factor in the prevention, early detection and successful treatment of diseases. Health data plays a central role in this, as patient data helps to gain insights that in turn enable advances in treatment. In this way, we all help to extend our own lifespan and that of our fellow human beings.
What is secondary data and why is it so valuable?
In the age of digital transformation, data has become one of the most valuable resources in healthcare. The collection of new data through clinical trials and observational studies is commonplace in science, but the reuse of existing healthcare data to answer new scientific questions is now receiving increasing attention. For good reason: secondary medical research offers enormous potential to understand, evaluate and improve patient care.
Unlocking the potential of shared knowledge for global health advancement
Open data in health research refers to datasets that are freely available for use, reuse, and redistribution by anyone - typically with minimal restrictions. Examples include epidemiological statistics, genomic sequences, clinical trial results, and anonymized patient-generated health data. The goal: foster transparency, accelerate scientific discovery more economically, and ensure that health research is a global, collaborative effort.
Understanding the value of structured health data in research
Health research data is any data used to produce knowledge that enhances health outcomes, policies, and medical understanding. It includes clinical, administrative, genomic, and lifestyle data, collected from sources like electronic health records (EHRs), wearable devices, patient registries, and insurance claims.
Standardized health data leads to new insights
From Fragmented Insights to Global Action – how Data is Shaping the Future of Vaccines.
Vaccines have saved millions of lives, and behind every dose lies a mountain of research data. From clinical trials and real-world studies to market surveillance, data plays a central role in vaccine development, efficacy, and availability.
Enabling Transparent, Reproducible, and Ethical Health Data Use
Imagine having to reinvent the wheel for every scientific question-this is still the reality in much of health research today. In today's health research, data is the foundation of progress. Yet, many valuable datasets remain difficult to locate, poorly documented, or incompatible with other sources. This is where the FAIR principles, introduced in 2016 in Scientific Data by Wilkinson et al., come into play. They outline four key guidelines to optimize research data management:
OHDSI WebAPI is an application, with several RESTful services, that you can use to access 1 or more databases for querying OMOP Common Data Model (CDM) data. WebAPI is developed by Observational Health Data Sciences and Informatics (OHDSI), an interdisciplinary collaborative program making analytics on large-scale health data possible.
WebAPI is a vast topic. It has many features that correspond to observational patient data, which aren’t in the scope of this blog. The focus of this article is to dissect WebAPI to show how it communicates with different CDM databases. We also explain the addition of the SAP HANA database to the list of existing ones.