Pharmaceuticals

AI in the pharmaceutical industry

Healthcare is becoming increasingly complex with the arrival of new treatments, changing roles for healthcare professionals, new laws and regulations, and new payment models. Artificial intelligence (AI) is also being used more often. The resulting applications can often perform a specific healthcare task effectively. In many cases, they can already do it better than a doctor. AI applications can, for example, detect infections at an early stage or improve the accuracy of diagnoses. The coronavirus crisis has accelerated this development considerably. Technology companies, researchers and governments are focusing heavily on developing AI applications to create, for example, a medicine or vaccine against the coronavirus. The need and interest in using AI applications are there, but unfamiliarity and a lack of knowledge often make it difficult to get these data science projects started. Using a few examples, this article discusses how AI can help stimulate innovation and generate value.

Drug discovery and development

Bringing a new pharmaceutical product to market is a lengthy process with many obstacles. Tests regularly fail to meet their objectives, which can cause delays and increase the cost of an already expensive process. In situations such as the current coronavirus crisis, where a virus spreads rapidly, it is important to obtain accurate results quickly to accelerate drug development.

Various AI applications are therefore used in drug development. They draw on data from viruses that, for example, have similar structures. These data provide insight into how certain medicines affect the treatment of patients with a similar virus. For example, Google’s sister company ‘DeepMind’ has used AI to identify patterns relating to the coronavirus and speed up vaccine development. DeepMind uses an AlphaFold system to predict the structures of various proteins linked to SARS-CoV-2 that have been studied to different degrees. These predictions have not been experimentally verified, but they may help scientists understand how the coronavirus works. This could be useful in developing an effective vaccine. Gaining insight into these little-understood proteins would normally take months. By applying AI algorithms, however, researchers can make predictions much sooner based on the structures of similar proteins.

Selecting patients for clinical trials

Bringing a new medicine to market takes between 10 and 15 years on average. Around half of that time, and the associated costs, go towards clinical trials. This often makes clinical trials the most expensive stage of drug development. Researchers therefore want to be sure they select the right patients for a given study. Despite substantial investment, clinical trials still have a low success rate. Failures are mainly due to imprecise selection methods and ineffective patient monitoring. AI can help improve these processes and increase clinical trial success rates. For example, some AI applications can reduce heterogeneity within a population, leaving patients who are more likely to respond to treatment. Remote patient monitoring helps researchers track the behaviour of patients in clinical trials and identify possible adverse reactions to medicines. This makes it possible to predict which patients may drop out. AI is also used to select a niche patient population to reduce costs.

Source: ERT, Transforming Clinical Trials through the Power of AI

Improving diagnostic accuracy

When a new pandemic strikes, diagnosing people is difficult. Large-scale testing is complicated and often expensive. Many people with COVID-19 symptoms worry that they have contracted the virus, even when those symptoms could indicate a milder illness. AI can play an important role in diagnosing diseases. A hospital in Florida was among the first to attract attention for using AI to diagnose COVID-19. When patients arrive at the hospital, they receive an automatic facial scan that uses machine learning to detect whether they have a fever.

A recent study found that 12 million adult patients in the United States receive an incorrect diagnosis each year and that diagnostic errors account for 10% of deaths. By harnessing big data and analytics, healthcare providers can improve diagnostic accuracy and reduce mortality. Many data analytics companies now offer solutions that use innovative data science techniques and machine learning algorithms to improve diagnostic accuracy. These predictive techniques analyse historical data such as patient records, symptoms, habits, diseases and genome structure to produce an accurate prediction.

Source: Deloitte Analysis

Improving medication prescriptions

Pharmacists need insight into how often incorrect prescriptions occur. AI can help reduce the risks associated with prescribed medicines. When a patient is prescribed a medicine, AI applications can identify patterns in historical data. This allows doctors to be alerted when a prescription deviates from standard treatment procedures. It helps healthcare providers improve health outcomes and prevent complications associated with incorrect prescriptions. Clustering and scoring models can also be used to determine which treatment or medicine is recommended for patients based on historical outcomes and the success rates of treatment programmes.

Predicting medicine stock levels in pharmacies

According to the Koninklijke Nederlandse Maatschappij ter bevordering der Pharmacie (KNMP), medicine shortages are becoming increasingly common. In 2018, 769 medicines were in short supply. In 2019, that number had almost doubled to 1,492. Shortages can be caused by problems in production or distribution, or by other economic factors. Demand for specific medicines can also rise during certain seasons or periods. This demand cannot always be estimated accurately, resulting in supply shortages. How can we help pharmacies prepare better for certain uplift/downlift events? And how can we ensure that stock levels better meet demand at such times?

KNMP Farmanco provides information on medicine shortages nationwide and historical data from pharmacies. This data offers a starting point for finding patterns and relationships that can help predict demand for medicines. The historical data contains a great deal of useful information. Take the hay fever season, which peaks in May and June. During this period, people are most likely to experience hay fever symptoms and are therefore more likely to visit a pharmacy for hay fever medication. Machine learning algorithms can quickly identify a trend. This also applies to conditions that are not seasonal: they can help predict which medicine will be dispensed most frequently at a given time. Pharmacies can then be given access to these results. This can be implemented in their existing systems, allowing them to plan medicine purchases more accurately.

Natural Language Processing for text data

A computer programme’s ability to understand human language is called Natural Language Processing (NLP). One of the best-known products that uses NLP is ‘Siri‘, Apple’s virtual assistant. Siri uses NLP techniques to turn speech into commands (speech recognition) for navigating a phone.

But where does NLP fit into healthcare? The sector collects vast amounts of data, for example through electronic health records, reviews and other sources. Since healthcare began adopting advanced technologies, the volume of data collected has grown enormously. But how can we put this data to good use?

This is where NLP comes in. Pharmacies and health insurers hold a great deal of data. By carrying out topic and sentiment analysis on, for example reviews from patients about pharmacies or customers about health insurers, we can find out what they experience positively or negatively. These insights can help pharmacies and health insurers improve their services, leading to greater customer satisfaction. We also live in the age of social media: a single negative post about a medicine that does not work well can be enough to expose a pharmaceutical company to lawsuits. NLP and other AI algorithms are now used to quickly identify patterns and relationships in sources such as social media, local news reports and measurement data. By ‘scraping’ the internet for early warning signs, the pharmaceutical industry can make better decisions about its safety information and avoid potential backlash and associated risks’s.

Which solutions are relevant to you?

The healthcare sector is currently focused on the fight against coronavirus. This crisis has accelerated the use of AI, wearables and innovative healthcare apps. The examples in this article illustrate just some of the possibilities. If this article has sparked your interest, we would be glad to talk, exchange ideas and explore which AI solutions could be relevant and make an impact for you! We are creating the future for you and with you!