We know that Physiotherapy is a medical science that’s come a long way.

We know that it’s mostly still, humans treating humans helping fix strained, sore, recovering joints and muscles.

But did you know that Machine Learning and Computer Vision can help take the load off physiotherapists and healthcare professionals with the help of Artificial Intelligence?

Before we get into details, let’s quickly understand what AI is. AI, or Artificial Intelligence really is.

Artificial intelligence is a field of mathematical engineering which has the potential to enhance healthcare through new care delivery strategies, informed decision making and facilitation of patient engagement. 

Machine learning (ML) is a form of narrow artificial intelligence within the AI realm, which can be used to automate decision making and help make better predictions based upon pre-recorded patient data. There are various kinds of supervised, and unsupervised musculoskeletal learnings that are used to treat patients like diagnostic imaging, patient measurement data, and clinical decision support that make a physiotherapists job a lot easier, and streamline the patient’s treatment as well.

What are these ‘SUPERVISED’ and UNSUPERVISED’ Machine Learnings you might wonder? Let’s talk a bit about that too.

We human beings are absolutely great at recognising patterns. This ability is key to developing clinical reasoning skills as a physiotherapist.

But when we start to consider larger data sets of multiple patients, such as at the population level, it can get quite tricky.

Advances in technology & cheaper storage solutions for electronic information and a greater understanding of the power of data science now allow pattern recognition at a level far beyond human ability.     

Machine learning exists in a spectrum that stretches from ‘supervised’ to ‘unsupervised’.


Here the computers can access labelled examples that physiotherapists have garnered from patients and their experience. We know that physios use knowledge of similar patients to work cases and solve problems of future patients with similar symptoms or ailments. One popular kind of supervised learning is called ‘deep learning’. This uses neural networks and an algorithm to mimic the activity of the human brain when processing information. It’s been used as an effective tool to direct patients with severe back pain to the right form of management pathway.


In this form of ML, no previous records or labelled examples are fed into the computer. The computer uses it’s algorithm and data analysis to correctly find previously unidentified patterns. This can help in predictive medicine, evaluating a patient’s health records and finding the likelihood of future diseases.

The potential for such classification and prediction in physiotherapy is huge and can reduce clinical variation in care, allowing professionals to ‘get it right first time’. Cost is subsequently reduced and quality of care enhanced.

Besides that BIG DATA also has a fairly important role to play in the onset of a new era of technology in musculoskeletal medicine. 

‘Big data’ in healthcare refers to large data sets that can be analysed to identify patterns related to patient behaviour and outcomes.

Such data is growing and is likely to exceed the manpower required to manage it efficiently. 

In healthcare, this data application takes multiple forms including: 

  • Patient details stored in electronic care records.
  • Information contained in medical imaging.
  • Information shared in health apps on individuals’ smartphones.
  • Streams of data generated from wearable or implanted sensors. 

To summarise, AI as a whole, including Machine learning and Computer Vision has a multitude of benefits for healthcare. It can enhance its performance, make medical knowledge more accessible and optimise application of resources and manpower.