Learning from our past for a healthier future

What’s happening today
The COVID-19 crisis caught the world largely unprepared.
The medical research community is working urgently to understand the coronavirus’s cellular mechanisms and search for effective therapies and vaccines while racing against the virus’s spread.
Though it’s nothing any of us wants to think about today, scientists estimate there could be over a million viruses in nature with potential to progress in a similar manner as SARS-CoV-21, the novel coronavirus that causes COVID-19. Therefore, epidemiologists assume the current viral threat won’t be our last.
The prediction
While it takes roughly 10 years and upwards of $10–$100 million on average to discover one new material with specific properties, it can take up to $2.6 billion and more than 10 years for a new drug to reach market2. A third of this overall cost and time is attributed to the drug discovery phase in which researchers need to synthesize thousands of molecules to develop a single pre-clinical lead candidate3.
One way to more quickly generate treatments for emerging viruses like COVID-19 is identifying potential therapies from drugs already on the market, which have been tested and proven safe for humans — jumpstarting subsequent research to help enable more rapid clinical trials and regulatory review.

Solutions for the future
A combination of AI, analytics and data can potentially help with the rapid analysis of real-world medical evidence to suggest new candidates for drug repurposing and speed clinical trials.
The process can scale the systematic reuse of digitized medical data, including its aggregation, analyses and interpretation. The goal will be to help the medical community identify new patterns amid the medical records of millions of de-identified patients and generate insights about the epidemiology of infectious diseases and potential treatments for them.
In the context of COVID-19, researchers used these technologies with real-world evidence to suggest the use of two existing drugs, one approved for specific immunological and endocrine disorders, seen to be effective in reducing mortality of hospitalized COVID-19 patients, and the second one in use for treating prostate cancer, found to protect against complications of COVID-19 after performing a widespread retrospective study in Spain4.

Developments at IBM Research
While many of these repurposing studies start as anecdotal observations or informed scientific hypotheses, real-world evidence can be systematically mined and brought to scale with the accelerated discovery cycle—allowing researchers to move beyond current correlation studies. In the future, these tools may reach widespread adoption across industries, effectively becoming one of the means of rapidly responding to global, life-threatening viruses.
Over the next five years, medical researchers can identify new opportunities for drug repurposing at a greater scale and prioritize them for clinical trials based on available evidence, helping to reduce time spent in the drug discovery process.

- Live Science, Why Scientists Are Rushing to Hunt Down 1.7 Million Unknown Viruses, February 23, 2018; https://www.livescience.com/61848-scientists-hunt-unknown-viruses.html
- PhRMA, https://www.phrma.org/en/Advocacy/Research-Development/Clinical-Trials
- DiMasi, J.A.; Grabowski, H.G.; Hansen, R.W., 2016. Innovation in the pharmaceutical industry: New estimates of R&D costs Journal of Health Economics. 2016. 47:20-33
- Pagano, F., Ragazzi, E. and Prayer-Galetti, T., 2020. Androgen-deprivation therapies (ADTs) for prostate cancer and risk of infection by SARS-CoV-2: a population-based study