International – Could AI Become the New Quality Control Manager in Medical Device Manufacturing?

By applying predictive analytics, medical device companies can make a shift to a proactive mode to avoid potential problems before they happen, according to an expert in business strategy and software engineering.

Quality is of utmost concern to manufacturers everywhere, but perhaps nowhere does it hold greater importance than in the plant where medical devices are being made and defects can have life or death consequences.

Think for a second about the implications of faulty X-ray or ultrasound machines, surgical devices, or pacemakers. Until now, the way the quality of these devices has been controlled is through manual inspections performed by quality analytics (QA) teams. They often randomly inspect products coming off the assembly line, and if a product seems to contain a defect, it is eliminated. But what happens if the defects were not noticed until the product has been in use for a while, possibly even implanted into a patient?

Now consider if you could predict which devices might be defective and get to the root cause of the problem. Then you could have a chance to reduce defects and prevent them from happening.

By applying predictive analytics, companies can make a shift to a proactive mode to avoid potential problems before they happen, and look at the variables and data to know with a high degree of probability which products will sail and which will fail. It also frees up manufacturers from spending 90% of their time focusing on quality assurance and addressing problems so they can spend more time on strategic approaches and innovation. It’s certainly a win-win situation for everyone, companies and consumers alike.

AI, more specifically machine learning is already being used among leading medical device manufacturers to help ensure that products are defect-free before they leave the plant. For example, a medical device manufacturer in Puerto Rico is using machine learning software to conduct predictive analytics using a combination of historical and current data to identify discrepancies, variances, and the smallest weakness that could cause a specific product to fail well before the product leaves the factory floor…