Combining RWE Data Science for Better Clinical Outcomes for Immunological Diseases

By Hemanth Kanakamedala, Senior Director, The Janssen Pharmaceutical Companies of Johnson & Johnson

As we continue to push ourselves to better understand immune-mediated inflammatory diseases (IMID) and develop new solutions for unmet patient treatment needs – especially for patients with rare diseases or those with prevalent diseases but difficult to treat like psoriatic arthritis (PsA), rheumatoid arthritis (RA) and inflammatory bowel disease (IBD), which includes Crohn’s disease (CD) and ulcerative colitis (UC) – the teams Janssen Immunology and R&D Data Science are using real-world data (RWD) to impact the drug development lifecycle.

We apply machine learning and artificial intelligence (AI) to real-world data (RWD) – including administrative claims, electronic health records, laboratory data, disease registries – to generate evidence on diagnosis, prognosis and etiology. This is essential to provide relevant context for the appropriate use of new and existing therapies. Such real-world evidence (RWE) gives us a better understanding of patients’ medical needs, their journeys, gaps in current treatment options, and insight into new areas of research. Some specific areas of impact are highlighted below.

RWD proves invaluable for the identification and development of biomarkers

RWD, powered by data science, helps us better understand the diseases we tackle and the patients who are affected by them. At Janssen, we use RWD to create detailed phenotypic profiles, which provide a comprehensive analysis of patients’ clinical characteristics and their immunological diseases. This is not only an assessment of what is documented in patients’ medical records, but also their labs and/or imaging. This information helps us develop more accurate disease classification systems using AI and NLP, bringing us closer to the path to precision medicine.1 This helps us identify new disease biomarkers, find and clinically advance promising compounds that can target them.

Using Data Science and RWD to Design Smarter, More Efficient, and More Representative Clinical Trials

Knowledge of the natural history of a disease is essential for drug development. We use RWD to inform the design of our intervention studies, including inclusion/exclusion criteria, diagnostic criteria, adequate follow-up, assumptions to power the study, and other design elements.

RWD is particularly critical for drug development in ultra-rare immunological diseases such as hemolytic disease of the fetus and newborn (HDFN), a condition that occurs when maternal red blood cells or blood group antibodies cross the placenta. during pregnancy and cause the destruction of fetal red blood cells. . Randomized controlled trials are often impractical and unethical in these populations. Consequently, patient populations like these have historically been underserved by traditional clinical development programs. We enroll these patients in single-arm studies with actual external control arms using rigorous methods to control for confounders.

Recruiting patients who reflect the same characteristics as those in the real world for our studies is fundamental to the success of the treatment of immunological diseases. Diversity, equity and inclusion built into study inclusion/exclusion criteria and active patient recruitment are critically important to meeting the needs of all patients and enabling us to improve access to innovative therapies. Without the inclusion of all subpopulations of patients with immunological disease, it is difficult for researchers to gain a comprehensive understanding of disease progression and treatment response in important subgroups. of patients.

This is especially important in underrepresented and understudied populations. We continually question whether our clinical trial sites are in the right places and whether we are making our clinical trials accessible to all patient populations with immunological diseases. With that in mind, Janssen is applying AI and machine learning to RWD to help identify where pockets of patients with rare or hard-to-diagnose diseases are and help inform placement of study sites – with the aim to allow patient communities who may not have participated in a clinical trial in the past to enroll in a study.

We know that diseases and drugs can impact people differently based on their race and ethnicity, so aligning clinical trial recruitment with patient demographics is critical. Simple yet impactful decisions, like ensuring clinical trial sites are located in accessible locations within historically underserved communities, make a big difference in our ability to reach a representative population to ensure we learn everything. on how our new therapies address unmet medical needs. need across all races, ethnicities and genders.

Integration of real digital terminals in the tests

Understanding how improvement would be perceived and measured in a real clinical setting is key to advancing outcomes in patients with conditions such as CD and other IMIDs. Important RWDs such as endoscopy videos and histology slides – using computer vision algorithms to measure disease severity – are integrated into our CD clinical trials and bridge the gap between the results of standard clinical trials and measures evaluated in a real clinical setting.

An RWE approach allows for the collection of more comprehensive data so that we can contextualize the results of randomized controlled trials (RCTs) to questions about diagnosis, prognosis, and disease etiology. The answers to these questions are also critical to articulating the value of changing a health outcome.

Comparative effectiveness research after product launch

Tokenized RWE also helps us generate evidence about healthcare resource utilization and other actual outcomes during and after the conclusion of our trials. After launch, we monitor the effectiveness and safety of our products through RWD analysis. To mitigate the limitations of traditional case-control designs, we emulate pragmatic RCTs of our approved treatments2. This type of generation of comparative evidence is essential to inform the real effectiveness of our therapies.

RWE is increasingly playing a vital role throughout the product life cycle in our immunoassays. To learn more about our work, visit our Immunology and R&D Data Science sites.

References

  1. Weng, C. et al. Deep phenotyping: embracing complexity and temporality – Towards scalability, portability and interoperability. J Biomed Inform. 2020;105:103433. https://doi.org/10.1016/j.jbi.2020.103433
  2. Miguel A. Hernan, James M. Robins. Use Big Data to emulate a target trial when a randomized trial is not availableAmerican Journal of Epidemiology, Volume 183, Issue 8, April 15, 2016, Pages 758-764https://doi.org/10.1093/aje/kwv254

About the Author:

Hemanth Kanakamedala is Senior Director, Immunology at Janssen R&D Data Sciences. His expertise lies in drawing causal inferences using non-randomized observational data. His work focuses on externally controlled interventional trials, mimicking randomized experiments using observational data and integrating patient-centered digital health metrics into trials. Prior to joining Janssen, Kanakamedala spent 10 years supporting the design and execution of Phase 1-3 randomized controlled trials and non-interventional studies. He holds a degree in mathematics and statistics from the University of Massachusetts, Amherst.

Comments are closed.