MedTech: How AI is changing the way medications are developed

With the coronavirus spreading throughout the world, startups are turning to artificial intelligence and machine learning to help scientists develop a vaccine in order to halt and reverse its spread. How can AI help in medicine generally and how can the technology be used to develop medication and vaccines to stem future epidemics?

AI as a true “all-round talent” for medicine

AI has the potential to be applied in various ways in medicine: It can structure healthcare data, identify and summarize a patient’s historical medical records. AI is also used to identify clinical similarity between patients, helping to understand which care path works better for a given group of patients. Moreover, AI can filter unstructured medical literature, such as Medline, and help discover new insights, according to IBM Watson Health. These insights could help prevent disease outbreaks. For example, the startup BlueDot was days ahead of the official alerts from the World Health Organisation for warning about the coronavirus. The company’s AI algorithms used different sources of information beyond official statistics about the number of cases reported and can therefore predict and track infectious diseases. BlueDot uses a cloud-based Geographical Information System (GIS) platform integrating more than 100 diverse datasets, including near real-time disease surveillance. Due to that, they can access the data of people and their movements across the planet through air travel, so they can get insights about whether a disease is going to spread. And if so how it might spread. Their AI algorithms thereby analyse these online data to detect these threats faster and filter out all that background noise. AI can not only help to track and predict outbreaks, but also help to develop medications for those who already got infected.

AI to speed up the drug development process & save millions

Developing medications and vaccines can take years of work and hundreds of millions in investments. Using AI and machine learning can cut cost and help in all four stages of drug development.

Source: Data Revenue

There are four main stages in drug development. In the first step, scientists have to understand the origin of a disease and to identify good targets which are usually proteins for treating the disease. Here’s where AI comes in: Machine learning algorithms can analyse a huge amount of data and even learn how to automatically identify good targets. In the second step, machine learning can predict properties of molecules or design molecules and materials with the desired properties. In the third stage, suitable candidates for clinical trials have to be found. Choosing unsuitable candidates will prolong the time. Machine learning can speed up clinic trials by identifying automatically the right candidates. It can also predict which trials won’t produce expected results, allowing researchers to react faster, find a new clinical trial and save thereby time. In stage four, people suffering from diseases have to be found as well as suitable Biomarkers. A biomarker is a measurable indicator — molecules that are typically found in human blood — which can identify whether or not a patient has a disease. Finding these biomarkers requires screening tens of thousands of potential molecule candidates. AI can speed up these manual work by classifying molecules into suitable and unsuitable candidates. This saves a lot of time, brings the medication faster to the market, and potentially saves more lives. “The average time to bring a molecule from discovery through to launch is 10–12 years”, says a report by Deloitte.

A Swiss Use Case

There are different AI startups that are specialised in one or more of these stages. For example, the Swiss startup Scailyte, which was founded in 2017, is specialised in discovering biomarkers. The spin-off from ETH developed an AI-based software for the analysis of complex single-cell data which can be used for research, drug discovery, and diagnostics.

The future of healthcare is about detecting and understanding valuable information hidden in complex data patterns. With our AI-based software for single-cell data interpretation, we will accelerate biomedical discovery and enable the next generation of precision diagnostics.” said Peter Nestorov, CEO of Scailyte AG, to EU-Startups.

Would you take medication created by AI?

The Lucerne-based AI startup is one of many startups contributing to a faster and cheaper drug development. An increasing number of startups across the globe are targeting diseases with unmet medical needs using the power of AI. AI solutions have the potential to accelerate scientific research using quick and accurate testing by using algorithms to identify new potential drugs faster and cheaper. Of course, AI can not replace doctors and scientists, but it can help them discover drugs and medications much faster. Especially in difficult times such as the coronavirus outbreak, we need to react fast when it comes to developing drugs and vaccines.

THE RELEVANCE HOUSE is a full-service marketing consulting agency for firms in the blockchain and emerging technology sector. We don’t operate like a regular agency. Think of us more as an outsourced marketing department. We become part of the team. We focus on helping technology start-ups and projects to build and communicate a relevant brand and story. Why? Because only relevance has impact.

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
The Relevance House

The Relevance House

56 Followers

We’re a full-service marketing agency for the blockchain and emerging technology sectors. Building, designing and delivering relevant brands and stories.