Can AI be a final solution for clinical Trials?

The 21st century has witnessed various global pandemics, like COVID19, Ebola, Zika and Lassa, and Artificial Intelligence, Machine Learning and Deep Learning algorithms are now recognized as classical tools to identify early signs of infectious diseases. They have become essential principles of infectious diseases research (and indeed all areas of modern research) and management and applications of AI and ML in healthcare are expected to grow nearly $8 billion this year, (up from $667.1 million in 2016). At the height of the COVID19 pandemic, AI and ML algorithms were used to connect universes of healthcare data dots in instants, making meaning out of mountains of medical records, disease registries, and scientific papers, informing sharper trial hypotheses, innovative drug discovery, and even new health device concepts.

AI and machine learning can reduce the time to get health-beneficial and even life-saving treatments in the hands of medical doctors and their patients in weeks instead of years, by eliminating big challenges such as poor study design, and patient recruitment. AI algorithms can be applied in all phases of drug development, from the identification and validation of drug targets, the design of new molecules, the repurposing of old drugs, improved efficiency of clinical trial conduct, to pharmacovigilance. Deep learning has already exhibited remarkable success in pharmacovigilance by identifying potential new drug candidates and improving prediction of their properties and the possible safety risks. AI can improve the efficiency of search for correlation between indications and biomarkers and help in selecting lead compounds which could have a higher chance of success during clinical development. ML and NLP have been used to automatically detect adverse events and drug–drug interactions. Cognitive services (a combination of ML and NLP algorithms) have been identified and developed to solve specific tasks in the PV process of Individual Case Safety Reports, which would require human intelligence. Such AI techniques can reduce the cognitive burden of PV professionals such as myself, improve efficiencies of various PV processes, but unfortunately, we do not know enough about them or use them enough in clinical trials management in Africa.

Leveraging vast healthcare data sets, we can use AI, ML and natural language processing (NLP) tools to assess and select optimal primary and secondary endpoints in study design, to ensure the most relevant protocols are defined; and help optimize study design by informing ideal country and site strategies, enrollment models, patient recruitment and study start-up plans. This optimization can increase the chance of clinical trial success and facilitate realistic and accurate planning. AI can help even us interpret patient sample data to find the best-fit candidates for successful trials. This can help clinical trials move faster with better, more informative and accurate results, participants can stay more engaged and satisfied with the trial process, and huge investments in research become groundbreaking healthcare treatments and solutions at incredible speed. The possibility of AI to transform crucial steps of clinical trial conduct-study design, planning, and execution is thoroughly fascinating.

Algorithms can be used for linking big and diverse datasets such as electronic medical records (EMRs), published medical literature, and clinical trial databases to improve recruitment by matching patient characteristics to selection criteria. Patient populations can be mapped, and proactively targeted and accurately predicted to deliver the most patients – before a single site is opened – and the best avenues to recruit participants easily identified. This means sponsors can open fewer sites, accelerate recruiting, reduce the risk of under-enrollment and prevent clinical trial failure.

According to Optum’s Survey on Artificial Intelligence (AI) in healthcare, 83% of healthcare organizations already have an AI strategy in place, and most others (15%) plan to create one; and in response to the pandemic, 56% of healthcare organizations are accelerating their AI deployment timelines. This is the time to improve our understanding and competence in integrating AI and ML programs into safety and monitoring plans. COVID-19 clinical trials as well as public health experts are using a dynamic database of information to explore treatment and management possibilities, and this serves as a great case study in how the industry can leverage this information.

AI is not a quick fix cure which can improve efficiencies of clinical trials in infectious diseases or other therapeutic areas overnight, and man and machine are still on the learning curve, but the experts at Gartner say data and analytics combined with artificial intelligence technologies will be paramount in the effort to predict, prepare and respond in a proactive and accelerated manner to a global crisis and its aftermath. We would like to be at the fore of that in Africa.