Blog

Recently, I was fortunate to chair a panel discussion where the potentials of Artificial Intelligence (AI) and Machine Learning (ML) were fiercely discussed. AI/ML seems to be talked about everywhere at the moment, heralded as a solution for many challenges in pharma and healthcare (and indeed many other industries). But, does AI/ML really warrant this level of excitement and hype?

AI/ML leaders in advanced statistics, NLP, deep learning, neural networks come together

One thing that is often overlooked in these discussions is that AI/ML is a broad group of diverse disciplines, not a singular item. AI/ML includes advanced statistics, Natural Language Processing (NLP), deep learning, neural networks, and many other mathematical and computer science specialities. The event I attended was a Linguamatics-hosted dinner. The panel of five experts covered a broad span of expertise across different AI/ML disciplines, and ranged from academia to small and large pharma:


How to Choose the Right Natural Language Processing Solution

These days there is a lot of talk about AI in respect to Artificial intelligence, but AI has another abbreviation, Augmented Intelligence. Artificial Intelligence implies a level of machine automated processing with no human intervention whereas Augmented Intelligence is the use of technology to enhance human performance. One AI technology that has been proven to support both interpretations is Natural Language Processing, or NLP for short. This is not a new technology, in fact, Linguamatics has been successfully completing projects using NLP since 2001.

For Payers and Health plans investigating new technologies there are many areas where NLP can support improved efficiency and business insights: HEDIS medical record review for hybrid measures, Medicare risk adjustment, clinical review/medical necessity and risk stratification to name just a few. The first four areas are about using NLP to improve efficiency of often manual processes by extracting key insights from medical records and summarizing the findings; the last example is a more automated analysis of large-scale populations to identify high risk members based on Social Determinants of Health and disease severity information.

The growth of interest in NLP and AI has led to more and more businesses claiming to have AI solutions that can help healthcare organizations to make the most of their unstructured data. The question is: how do you decide which NLP offering actually works, and which NLP solution is right for you?


Until recently I kept hearing claims such as, “Vaping is so much better for you than smoking…” My response is “It’s just a matter of time before the data will let us know”. Turns out the data is starting to speak, and it doesn’t have a positive outlook on the matter. Vaping is really in its infancy, and research even more so. We are still discovering which additives are in which types of vaping cartridges. Let’s compare vaping to tobacco: the Cancer Council in Australia reports that tobacco has been grown in the Americas for nearly 8,000 years, and the first significant medical reports weren’t out until the 1950s and 1960s. Relatively speaking we are early to this arena. Fast forward to the present where we know cigarettes have over 4,000 chemicals, 70 of which are known carcinogens.


It Takes a Village to Raise Modern Medicine

Learning from the past

“It takes a village to raise a child” is a popular old African proverb, that in my opinion has a lot of merit. Now that single parents are part of the mainstream, as well as divorced families, and other non-traditional parenting units and methods are adopted; it’s still very important for the nurturing and development to come from many different influences- especially those that are closest. I also believe this old proverb can be applied to not just childrearing, but in other areas, such as how we work together and adopt new methods to make healthcare better.


It is well known that the drug discovery and development process is lengthy, expensive and prone to failure. Starting from the selection of a novel target in discovery, through the multiple steps to regulatory approval, the overall probability of success is less than 1%.

One factor is that the majority of diseases are multifaceted, hence the challenge is identifying the most appropriate patient populations who will respond to specific interventions. A stratified approach has proven beneficial in a number of cancers and genetic diseases, and pharmaceutical companies have a strong interest in understanding how to find the sub-populations of patients to ensure the most appropriate therapies are tested in clinical trials, and applied in broader clinical use.

The ultimate aim of a stratified approach to medicine is to enable healthcare professionals to provide the “right treatment, for the right person, at the right dose, at the right time”; and there are many research initiatives (governmental, private, public) on-going to develop the appropriate knowledge and models.