The Data Analytics Blog

Our news and views relating to Data Analytics, Big Data, Machine Learning, and the world of Credit.

All Posts

How Machine Learning Is Transforming Medicine

October 7, 2019 at 7:39 AM

At Principa, we are passionate about new ideas and product development.  20% of our revenue is ploughed back into innovation.  One of our key areas of focus is machine learning where we have built machine learning solutions in both collections and the customer acquisition space.  While our focus is primarily on credit risk and customer engagement, we are always interested in how machine learning has gained traction in other industries.

In this blog, we explore the application of machine learning and, in particular, deep learning in the medical field.

What is Deep Learning?

Deep learning is a type of machine learning that utilises artificial neural networks to learn patterns and then apply them in a range of activities.  In some cases, the process outperforms human ability. Deep learning has been particularly effective in the spheres of image recognition, board games, lip reading and self-driving to mention a few.

Drug Discovery

capsule shows 3d molecule as medical conceptBringing a new drug to market can cost pharmaceutical companies between $350million to $5billion.  There is an extensive process at play and a high failure rate at different stages.  Machine learning and its subset, deep learning, can play a role in assisting the process.    

Some of the key areas are listed below:

  1. Early-stage discovery – machine learning and deep learning are now used for initial screening of compounds for the prediction of success in compound activity and interaction.
  2. Enhanced manufacturing – ML can be used to help reduce the costs of reproducing a drug.
  3. Personalised medicine – ML and its subset DL can use drug and patient data to predict responses to treatment.
  4. Medical trial cohort selection – using unsupervised DL to help select medical cohorts with specific genetic traits could reduce the size and cost of trials.

A concern with this approach is that DL may offer solutions that lack “explainability” which is outlined by some to be of strong importance. Although it should be noted that many medical treatments today lack explainability (for example many drugs used in anaesthesiology).

Human Genome Mapping

Cost per genomeWhilst the human genome was first “mapped” in the 1990s at a cost of $2.7billion, the price of mapping a genome has been falling making it increasingly likely that many of us will have our genome mapped out in the future. The mapping of the 3 billion base pairs in a human genome results in 100GB of information.  While parts of the genome are well understood, much of it is not.  Concept of biochemistry with dna molecule on blue backgroundAssessing correlations and deterministic relationships between genotypes and phenotypes and, in particular, combinations of genes and mutations to predict susceptibility to conditions, or reaction to medical treatments is where deep learning is starting to have and will continue to play a significant role.

Companies such as Insight Genomics are utilising deep learning in oncology to help map treatments to tumours with genetic profiles.

Medical Image Analysis

In imaging, deep learning has been applied extensively from saving whales and classifying plankton to self-driving cars and describing photos.  In medicine where visual diagnostics play an important role, so medical imaging is important too.  Here are some examples.

Deep learning has been used to diagnose skin cancers simply from images.  In a study published in September 2019, deep neural networks performed as well as trained dermatologists after the former was trained on a database of just over 4000 images.  This is quite encouraging, as in certain countries, dermatologists are rare, and this provides an opportunity to improve healthcare.  Companies such as Skin Vision provides an app where users can submit their skin pictures to be automatically screened for melanoma.  

xray held by hands isolated over a white background

Just as dermatologists are in short supply, so too are radiologists who spend their careers analysing a variety of imagery.  A paper published in November 2018 showed how Berkley data scientists were able to produce deep learning machines that performed as well as radiologists in Alzheimer diagnoses using PET scans.  Another study in 2018 from Stanford showed convolutional networks outperforming radiologists in pneumonia diagnoses from chest X-rays.

All of this is very encouraging, and as with many AI advances, we don’t see a replacement of skills, but rather an augmented approach where the algorithms will assist the experts in the diagnosis process. 

Epidemic outbreaks

HeatmapMachine learning is currently being used to predict epidemics around the world. An example of this is malaria outbreaks utilising data on temperature, humidity, rainfall and region in India.

More recently, the rise of the opioid epidemic has also provided an opportunity for machine learning.  In the US over 2 million are addicted to opioids, and it is estimated that 33,000 died of opioid abuse in 2015.   Machine learning is being used to predict where high rates of addiction are likely and where patient relapse is likely (utilising a phone app).


As with many other industries, the medical industry has ample areas of opportunity for the application of machine learning, including deep learning.  We look forward to following the progress here.  We hope to benefit from the learnings in health-care and apply it to other areas such as customer engagement and credit

Subscribe to our blog

Thomas Maydon
Thomas Maydon
Thomas Maydon is the Head of Credit Solutions at Principa. With over 17 years of experience in the Southern African, West African and Middle Eastern retail credit markets, Tom has primarily been involved in consulting, analytics, credit bureau and predictive modelling services. He has experience in all aspects of the credit life cycle (in multiple industries) including intelligent prospecting, originations, strategy simulation, affordability analysis, behavioural modelling, pricing analysis, collections processes, and provisions (including Basel II) and profitability calculations.

Latest Posts

The Pros and Cons of a Multi-Bureau Strategy in Credit

Although not a new concept, very few lending organisations have deployed a true multi-bureau strategy (MBS). It is however talked about fairly regularly, but often dismissed as “too hard” or “not important enough”. So why should you consider a multi-bureau strategy? What are the key considerations? How do you go about deploying a MBS? This blog hopes to address all these questions.

PART 1: How to Cure the Post Pandemic “Collections” Symptoms

It has been a year and a half since the first case of the coronavirus (COVID-19) was reported from Wuhan, China. As we move into the third wave of the virus, there is an apparent dilution in both collection and recovery yields in the financial services sector, primarily because relief schemes and packages come to an end.

Predicting Customer Behaviour

Propensity modelling attempts to predict the likelihood that visitors, leads and customers will perform certain actions. It’s a statistical approach that accounts for all the independent and confounding variables that affects said behaviour. The propensity score, then, is the actual probability that the visitor, lead, or customer will perform a certain action.