How Teva is Making Innovative Use of AI and Advanced Analytics in the Pharma and Health Sector

Artificial Intelligence and advanced analytics technologies have huge potential to improve the world of health. We talk to Teva employees who are using the technologies.

Artificial intelligence (AI) and advanced analytics technologies have the potential to improve almost all aspects of human life.

The AI technologies, which mimic human intelligence and enable machines to autonomously or semi-autonomously analyse large amounts of data, are becoming more common in healthcare and the pharmaceutical industry.

These technologies, for example, are already being used in some countries to [1] improve the speed and accuracy of diagnosis and screening for diseases; to assist with clinical care; strengthen health research and medicines development, and support diverse public health interventions, such as disease surveillance, outbreak response, and health systems management.

The global market for AI in healthcare may be worth (US dollars) $61.59 billion by 2027, up from $3.39 billion in 2019, according to forecasts [2].

Teva is using AI and advanced analytics to improve the drug development process and help provide medicines for patients with various conditions such as schizophrenia, depression, Parkinson’s and Chronic Obstructive Pulmonary Disease (COPD).

The technologies are being used to utilize feedback from digital devices to help diagnose and treat diseases. They are also being used in chemistry manufacturing and control (CMC) procedures to ensure quality and consistency during manufacturing, and in drug discovery, the process through which potential new medicines are identified.

But what are the potential medical benefits of these projects? How do the technologies work? And what are the challenges of developing them?


Mobility – how well we walk – is an important indicator of health. A slow walking speed is associated with a greater risk of disease, cognitive decline, risk of falls and even earlier death [3]. As the population ages, the number of people experiencing mobility issues is expected to rise. However, accurately assessing people’s mobility in the real world can be tricky.

Teva is involved in a project called MOBILISE-D, which aims to develop a comprehensive system to analyse people’s gait based on digital technologies, including sensors worn on the body. It focuses on conditions which often affect mobility − chronic obstructive pulmonary disease (COPD), Parkinson’s disease, multiple sclerosis, hip fracture recovery, and congestive heart failure.

The project is part of the Innovative Medicines Initiative – a public private partnership between the European Union and the European pharmaceutical industry to improve health by speeding up the development of innovative medicines.

“The goal is to connect digital mobility tech with clinical outcomes,” says Michal Melamed, Data Scientist, Advanced Analytics and AI at Teva. “Our hope is to gain regulatory approval of the wearable technology and data it gathers, which may be used in clinical trials to aid in the understanding of and treatment needed to tackle the progression of Parkinson's disease."

For this ongoing project Teva developed its own solutions and has worked with a team of clinicians and biomechanical engineers at the Tel Aviv Medical Center. During the project, people with Parkinson’s wear sensors on their lower back, ankles and wrists. The sensors' data is analysed to depict their walking speed, regularity and symmetry, among other factors.

“We are using AI and analytics to try to predict and assess the motor stage of the patients' disease, which affects the body’s movement,” says Michal. “And to identify the walking factors most associated with Parkinson's disease motor stages.”

Analysis of our AI models outcomes show that the walking factors' discriminative power vary according to the disease progression: in the early, mild and advanced phases, the important walking factors are measured from the wrists, lower back, and ankles, respectively. This supports the clinical impression of Parkinson's disease progression. “One benefit of this wearable tech is that you monitor the progression of Parkinson’s disease at the patients' home,” Michal adds.

Teva is also using AI to help improve treatment for cluster headaches.

Currently, much of the research into headaches, including migraines and the medicines developed for them, relies on patients keeping a record of their symptoms. Delays to the recording of migraines in the diary and inaccurate patient recall mean that this data is not always accurate.

Like any project that is trying to innovate, there are challenges, including figuring out discrepancies in the data on the frequency and timing of migraines recorded by the patients and when the events actually happened. Getting good quality data is a major challenge, and the key for any project success.

The Teva research uses patient data, says Michael Reich, Director of Advanced Analytics and Artificial Intelligence at Teva. “The purpose of the technology is to find patterns or identify symptoms that are related to the patients’ clinical situation.”

Research into biologic medicines

Biologic medicines’ research involves designing antibodies to help treat a disease. Its success depends, in part, on being able to manufacture medicines at scale while meeting high standards of quality.

In a new manufacturing process being developed, a modified cell, capable of producing the antibody developed by Teva, is placed in a bioreactor so it can grow and produce the required medicine. Teva’s scientists then develop a good “feeding strategy” that will keep the cell “happy” over many days, by giving it the right amount of nutrients, such as vitamins and minerals. At Teva, finding this formula became a task that AI could possibly help with.

The project aims to “predict the cell behaviour based on the feeding strategy, so that the best strategy can be selected”, says Felipe Mello, Data Scientist, Advanced Analytics and AI at Teva.

To analyse its data, Teva is using a neural network model − which is a type of algorithm inspired by how the human brain works. Potential benefits of the project include producing new medicines faster and at a lower cost.

Other Teva projects use AI and analytics to discover new connections between genes and diseases.

“We are using AI to understand what can cause human diseases,” Felipe explains. “One way to do this is by representing our knowledge about biology like a social network, where diseases, genes and other entities are connected to each other. The job of AI is to recommend new connections that might help us understand which biological entities are responsible for a disease and how we could possibly treat it.”

AI-based neural network technologies that analyse these biological networks and connection “have a lot of power”, he says.

Another possible application, for example, is to spot if two medicines could exacerbate some effect when taken together.

These innovative projects are not short of challenges. In some cases there can be a vast amount of data – millions to even billions of data points, and “separating noise from good-quality is one of them”, says Felipe. “AI is only as good as the data it works on”.

Advanced analytics and Artificial Intelligence have huge potential for the future of health care. At Teva, we continue to explore the possibilities that may help to improve the lives of patients worldwide.

NPS-ALL-NP-00562 APRIL 2022


[1] World Health Organization, ‘WHO issues first global report on Artificial Intelligence (AI) in health and six guiding principles for its design and use’, 28 June 2021.

[2] Reports and Data, ‘Artificial Intelligence (AI) in Healthcare Market Size Worth $61.59 Billion By 2027’. January 19 2021.

[3] Innovative Medicines Initiative, ‘Connecting digital mobility assessment to clinical outcomes for regulatory and clinical endorsement’,

Read more

Share this article: