by Michael Firgens
Biopharmaceutical companies are facing significant challenges in improving their drug development processes due to increased R&D costs and reduced efficiency. The use of artificial intelligence (AI) technologies is a key technology that can revolutionize drug development as well as all other areas of our healthcare system.
Generally, AI is defined as a technique that enables computers to mimic intelligent human behavior. Machine learning and deep learning are two common methods employed. Machine learning is a data analysis method that automates analytical model building using algorithms that iteratively learn from data. Deep learning is part of machine learning using more sophisticated, layered algorithms. It processes data and creates patterns for decision-making purposes.
Basically, AI has potential uses in all healthcare areas and can be employed throughout the lifecycle of drugs from drug discovery and development up to its use in clinical practice (Mak 2018). Figure 1 summarizes the outcomes and strategies of the drug development process and the potential applications of AI at each development stage.
Based on its current technology status (Bulgaru 2019), AI has successfully been used in many of the following areas and examples:
Discovery and development of new drugs
AI-augmented and cloud-based platforms and big data technologies support scientists to design, screen and customize drugs and to analyze large sets of genomic and clinical data. As a result, drug developers can gain deeper insights into pharmacological profiles of molecules and can generate predictive models for pharmacokinetic properties.
Identify cures for complex and rare diseases
Using its data processing power, AI can provide new insights into complex or rare diseases and help to identify potential treatments. AI can also facilitate to analyze diagnostic data faster and to identify rare diseases earlier, more efficiently and more reliably. AI technologies are also used to monitor and manage diseases with currently no available cure thereby providing additional patient safety.
Drug adherence and dosage
In combination with mobile technologies, AI can help monitoring the adherence to the study treatments during clinical trials and can identify patients who are not compliant.
Better analytics of clinical data
AI generally assists in analyzing huge sets of patient data. AI can make sense of patient data for example to detect side effects early or to assess the efficacy of a drug in a patient population.
Finding suitable patients for clinical trials
AI can extract information from patient records to identify clinical trial subjects that match the inclusion and exclusion criteria of a clinical study.
We are THE experts for the development of novel biopharmaceuticals and for the use of innovative technologies to support drug development. We consider AI as an important innovation that will change the way new medicines are developed. We are thus committed to follow and utilize this disruptive technology and to develop suitable regulatory pathways in using it in the future. If you are interested to learn more how to make use of AI during drug development, please contact us.
Kit-Kay Mak, Mallikarjuna Rao Pichika (2018), Artificial intelligence in drug development: present status and future prospects, Drug Discovery Today
Iolanda Bulgaru (2019), Pharma Industry in the Age of Artificial Intelligence: The Future is Bright, Healthcare Weekly, https://healthcareweekly.com/artificial-intelligence-in-pharmacology/