Four ways machine learning is set to revolutionize breast surgery

Machine learning has grown to become quite the buzzword in clinical research. Across recent years, we’ve seen an almost exponential increase in the number of successful machine learning trials conducted, with the technology now hailed as a torchbearer for healthcare’s artificial intelligence revolution. Yet, this begs an obvious question for doctors and healthcare professionals alike—what actually is “machine learning”? 

Machine learning refers to the concept of using large amounts of data to build elaborate algorithms that aim to mimic the way the human brain thinks. Whilst the ground-breaking technology has had an undeniable impact across many aspects of surgery, its implementation in breast surgery is one crucially yet to be established.

Below, we distil down four ways we see machine learning revolutionizing the day-to-day operations that a breast surgeon undertakes. 

1. Planning before surgery

Imaging plays a phenomenal role in planning for any major breast operation—whether it be from pinpointing the location of a breast tumour to helping a surgeon navigate complex breast anatomy. Radiologists now have access to swarms of imaging data to aid the former, thanks in part due to modern imaging techniques. Nonetheless, it can be time-consuming to process this information before a surgery is planned.

New machine learning technology aims to bring greater efficiency and accuracy to this process. Initial trials suggest that machine learning performs to the same level if not better than a radiologist in detecting cancer, and also shows a higher sensitivity (i.e. a better ability to detect cancer in an individual that actually has cancer). Not only will this provide surgeons with prerequisite knowledge to make smarter treatment decisions but will lead to reduced workloads, a reduced burden on resources, and reduced chance of error.

2. Making long-term predictions

Clinicians always want to ensure what they do is backed up by strong evidence—one of the reasons why so much time is spent applying traditional statistical ideas to monitor and predict what might happen to patients after their breast surgery operations.

Whilst a relatively new phenomenon, machine learning looks promising as a gamechanger within this field. New trials suggest it predicts five-year mortality after breast cancer operations more accurately than statistical models and have even gone on to suggest it can predict a patient’s chance of developing a complication like lymphoedema (a long-term swelling in the tissues of the body after an operation).

All of this has been down to the creation of a specific type of machine learning dubbed an “artificial neural network”—a type of machine learning modelled after a human brain cell called a neurone.

 3. Holistic care

With the growing recognition of how important it is that we apply a holistic attitude to treating anyone, machine learning holds an important key. Pain following breast operations can be a debilitating experience and is often something we don’t investigate as much as we ought to. Research has suggested machine learning can allow us to predict neuropathic pain, a type of pain that results from nerve damage, more quickly after an operation. This could allow surgeons and doctors to provide more optimised support to patients in the recovery period.

4. Beyond predicting and planning

The potential applications of machine learning to breast surgery are vast and boundless, and some ideas have applied machine learning concepts in exciting and innovative ways. With advances in medical research, come a wealth of new treatments. Conceptual studies suggest that machine learning can be integrated in decision-making support systems for breast surgeons, including examples such as the “DESIREE Project”, that aim to simplify the process of choosing specific therapeutic options.

Alternatively, machine learning has predicted that the more times a breast surgeon has carried out a specific operation before improves the long-term success of their patients after surgery. It is now theorised that machine learning can be used to study the technique of more experienced surgeons and use this information in the training of inexperienced surgeons.

So, where does this leave us? As exciting as this technology sounds, it is still limited by its relative infancy and hence shrouded in challenges.

It comes with no surprise that machine learning is complicated. Before any of this technology can move forward, we need to ensure breast surgeons are equipped and trained with extensive knowledge on how to utilise it. Stakeholder collaboration will form a major part of designing a practical machine learning platform ready for clinical use. In addition, machine learning is inherently driven by data and hence it is our shared responsibility to ensure any data fed into it is as reliable and representative of our target population as possible. 

Nonetheless, it’s certainly an exciting time to be a breast surgeon and we can’t wait to watch machine learning’s trajectory in overhauling patient care in the not-so-distant future.

_{Featured image by Irwan iwe, via Unsplash.com, public domain.}