Artificial Intelligence – A boon to Pharmaceuticals and Healthcare

Artificial Intelligence in Pharmaceuticals and Healthcare

Over the last few years, Artificial Intelligence and Machine learning have become widely discussed topics in the area of pharmaceuticals, healthcare and life sciences. A lot of pharmaceuticals companies and healthcare organizations express significant interests in possible new opportunities associated with Artificial intelligence and related technologies.

The use of Artificial Intelligence in pharmaceuticals and healthcare can save time and simultaneously earn profits. It provides a better understanding of the relationship between different formulations and process parameters. A considerable gap still exists when it comes to understanding new technologies including Artificial Intelligence by pharmaceuticals and healthcare professionals.

What is Artificial Intelligence in Healthcare and Pharmaceutical Industry?

Artificial Intelligence in Healthcare and Pharma sector is the use of algorithms and software, to reduce human efforts by utilizing complex medical data that leads to more accurate and precise end result. If a machine is able solve problems, complete a task, or exhibit other cognitive functions that humans can, then we refer to it as having artificial intelligence.

Need of Artificial Intelligence in Healthcare and Pharmaceutical

Dr. Charles Wright, Prescouter project architect of healthcare and life science industry reported that there are three common challenges faced by a pharmaceutical industry. Firstly, Timeliness of about 15 years, costs in excess of $ 1bn and minuscule rate of success. Artificial Intelligence has the potential to revolutionize the time scale and scope of Drug discovery and development.

The decrease in drug development is because every 90% of the drugs developed fail to make it to the pre-registration. This is due to poor efficacy and poor absorption, distribution, metabolism or excretion (ADME). Artificial Intelligence is used by alleviating this decline through the use of innovative technique such as in silico (on a computer) drug design. This technique allows the mapping of drug structures and targets, allowing the development of more successful drugs without costly scientific developments.

How does Artificial Intelligence work in Pharmaceuticals and Healthcare sector?

Artificial Intelligence technology in healthcare gains information, processes it and gives a well-defined output to the end-user. Artificial Intelligence does this through machine learning algorithms. These algorithms build a mathematical model of sample data, in order to make predictions or decisions without being explicitly programmed to perform the task. It recognizes patterns in behavior and create its own logic. In order to reduce the margin of error, AI algorithms need to be tested repeatedly. AI algorithms deviate from humans in two ways:

(1) The algorithm can’t adjust itself and only understand what is has been told explicitly.

(2) Algorithms can predict extremely precise, but not the cause.

To name a few types of Algorithms used in AI

Neural networks, genetic algorithms and fuzzylogic are rapidly growing technologies that could be applied to the formulation and processing of pharmaceuticals products.

Artificial Neural Networks (ANNs):This technology models the pattern recognition capabilities of the neural networks of the brain. Similar to a single neuron in the brain, artificial neuron unit receives inputs from many external sources, processes them, and makes decisions. ANN is composed of various processing units (PE) and artificial neurons.

Genetic Algorithm:Genetic algorithm is a probing technique used to find concurrent solutions for optimization and search problems. In drugs designing, a molecule is defined as input to GA and a binary string is used to code the molecule. A large number of solutions are generated by using genetic operator. The best population is selected and further used to generate the new population until a desired solution is reached.

Fuzzy logic:Fuzzy set is different from traditional set theory i.e. fuzzy set has un sharp boundaries. Contrary to the traditional set theory that has either value 0 or 1, values of fuzzy set lies between 0 ≥ μ ≥ 1. Where, μ is the membership function. Most important characteristic of fuzzy logic is fuzzy inference. Fuzzy inference systems based on fuzzy set theory are considered suitable for dealing with many real world problems. For example, the formulator might be seeking a tablet disintegration time of 200s. Any value less than 200s has a desirability of 1 ( i.e. 100%). But a tablet which disintegrates in 210s is not entirely undesirable and instead might be assigned a desirability value of 0.9 (90%).

What are the practical applications of AI in Healthcare Industry?

AI programs are developed and applied to practices such as faster and better diagnosis, clinical trial process optimization, drug development, patient monitoring and care, Dosing, Recognize Depression, precision medicine health risk assessment based on symptoms, recruitment for clinical trials, manufacturing process optimization, business intelligence etc.

In drug development and manufacturing processes, AIs are specially employed in development of ‘controlled release drugs’ and ‘Immediate release drugs’.

Broad categories of Artificial Intelligence

AI is divided broadly into three stages: artificial narrow intelligence (ANI), artificial general intelligence, and artificial super intelligence.

ANI systems can attend to a task in real time, they take in information from a specific data set. As a result, these systems don’t perform outside of the single task that they are designed to perform. ANI could analyze data sets, draw conclusions, find new correlations, and support physicians’ job.

AGI refers to machines that can exhibit human intelligence. It can successfully perform any intellectual task that a human being can. AGI include machines and operating systems that are conscious, sentient, and driven by emotion and self-awareness.

ASI is defined by Oxford philosopher Nick Bostrom as any intellect that greatly exceeds the cognitive performance of humans in virtually all domains of interest.

Presently, AGI and ASI are only imaginary and ANI is just emerging, there are rising concerns raised by renowned scientists including Stephen Hawking over Artificial General and Super Intelligence. No doubt, that ANI is a boon to mankind but there is always a fear that further advances might lead to inventions that can be detrimental to the entire world.

Regulations of AI in pharmaceuticals

Currently no regulations exist specifically for the use of AI in healthcare. Use of AI may nonetheless introduce several new types of risks to patients and healthcare providers, such as algorithmic bias and other machine morality issues.

Case Studies

There are many pharmaceutical companies employing AI technologies in different area of their projects and gaining far better results than before.

Glaxosmithkline partnered with startups including Exscientia and Insilico Medicine.The partnership with Excscientia, in July 2017, is to discover novel and selective small molecules for up to 10 disease-related targets across undisclosed therapeutic areas. The partnership with Insilico, in August 2017, is to identify novel biological targets and pathways. GSK is also part of the Accelerating Therapeutics for Opportunities in Medicine (ATOM) Consortium. ATOM aims to leverage artificial intelligence to go from drug target to patient-ready therapy in less than a year. GSK gave ATOM, chemical and in vitro biological data of more than 2 million compounds it has screened. (For more information on how GSK became such a leader, check out this article “6 Steps to AI Leadership in Pharma: An Interview with John Baldoni of GSK.”). In January 2019, the Alliance for Artificial Intelligence in Healthcare announced GSK as a founding member.

Merck struck an early partnership with Numerate, which they announced in March 2012. The collaboration focuses on generating novel small molecule drug leads for an unnamed cardiovascular disease target. In December 2018, Merck announced partnership with Cyclica to use its AI-augmented proteome screening platform. It aimed to elucidate mechanisms of action, evaluate safety profiles, and explore additional applications for investigational small molecules. Merck also has a confidential projectwith Atomwise

Detecting skin cancer: A recent study, published in the Annals of Oncology, showed an AI was able to diagnose cancer more accurately than 58 skin experts. This AI was trained using images of skin cancer and the corresponding diagnoses were made. Human doctors got 87% of the diagnosis correct, while their machine counterpart achieved a 95% detection rate.:

The AI technology reduces the number of false positives. Symptoms are assessed accurately, that is fewer people would undergo unnecessary treatment. It could also help reduce the overall delays for patients who require urgent medical actions.

The list of pharmaceutical start-ups and MNCs, healthcare sectors, using AI technology is quite vast. This shows that the advent of AI is showing its impact over pharmaceuticals and healthcare. In near future, AI can be expected to be an integral part of pharmaceuticals and healthcare units.

Conclusion

A better approach towards drug development and various research oriented healthcare sectors can be achieved with the advent of AI. AI technologies can be applied to acquire knowledge of productive molecules and methods to develop a better end product/drug. Huge Investments made on primitive techniques giving lower success rate can be avoided by taking AI into consideration.

It is clear that ANI that are build to perform specific task pose no major threat to the user in particular and to the entire globe as whole. As a part of modernization, innovations and inventions cannot be stopped. Therefore, further advancements in the area of artificial intelligence must be made having clear picture of pros and cons of the technology and that which can be controlled by humans at any point of time.

Future Scope

Induction of AI in healthcare and pharmaceuticals has already taken a central stage. In future it has the potential to radically transform healthcare and pharmaceutical industries. The technological advancement in mobile computing, artificial neural networks, robotics, storage of huge data in internet, cloud-based machine learning and information processing algorithms etc. Has propelled the use of AI in modern healthcare and Pharma sector. Because of AI, the modern healthcare can now become data-driven or data-oriented and personalized.

References:

1. https://www.pharmaceutical-technology.com/comment/can-artificial-intelligence-help-pharma/
2. https://www.biopharmatrend.com/folder/biopharma-insights/?page=1
3. https://www.altexsoft.com/blog/datascience/10-ways-machine-learning-and-ai-revolutionizes-medicine-and-pharma/
4. https://www.outsourcing-pharma.com/Article/2018/10/11/The-opportunities-for-AI-to-revolutionize-the-pharmaceutical-industry-are-clear-Report
5. https://www.google.co.in/amp/s/blog.benchsci.com/pharma-companies-using-artificial-intelligence-in-drug-discovery%3fhs_amp=true
6. http://www.pharmahealthsciences.net/pdfs/volume6-issue22018
7. https://www.tandfonline.com/doi/full/10.1080/23808993.2017.1380516
8. https://medium.com/@tjajal/distinguishing-between-narrow-ai-general-ai-and-super-ai-a4bc44172e22