Artificial Intelligence in Microbiology? The Potential Advantages in The Lab

Artificial intelligence has been getting a lot of attention in recent years. As our technology advances, we’re making great strides in the capabilities and sophistication of AI. While some people may worry about dystopian sci-fi scenarios, much of the AI that we use today can actually end up helping humanity.

For example, artificial intelligence in microbiology is now being used to produce faster results for labs. Automation in labs has plenty of uses, but it comes down to a few main algorithms that are helping to identify and count colonies and increase the speed with which labs can accurately assess growth cultures.

Chromogenic Media

Chromogenic Media is commonly used as a detection method for HAI infections, such as MRSA, VRE, or ESBL in screening programs around the world. Human detectors can easily miss positive results in cultures. The reasons for this can vary, but include fatigue, heavy workloads, and the repetitive nature of the task. Visually inspecting large amounts of cultures is a task that lends itself to human error. In two separate studies, imaging analysis software identified 100% of colonies that were positive for MRSA and VRE. They also correctly identified  positive cultures that had been labeled negative by technicians.

Colony Counting

Urine specimens used for urinary tract infection testing are one of the largest volume samples in many clinical laboratories. The rules for interpreting these samples are complex and are subject to several variables. Lab automation software that can differentiate between negative and non-negative urine cultures can save huge amounts of time in the lab and reduce the turnaround time for samples. That in turn could potentially change the way that doctors prescribe antibiotics to their patients with UTIs and a trend towards antimicrobial stewardship in prescriptions would end up benefitting us all.

Phenotypic Colony Recognition

The algorithms and AI are even sophisticated enough to recognize and interpret colonies in a mixed culture. They can then flag the sample and pass it on to the lab workers for additional investigation. This works by counting colonies accurately and then querying a phenotypical database. User-defined results are then applied to the specimen based on its source, location, or the individual patient’s demographic information.

Adopters of full laboratory automation say that the benefits are both real and impressive. They include decreased turnaround times, reduced labor costs, and increased antimicrobial stewardship. Although it’s stressed that these advances will never replace human expertise or skill, more and more labs are recognizing the benefits of AI software to both their labs and the patients that they serve.

AI may be the wave of the future, but there are some things it simply can’t replace. At Lifecycle, we’ve been working to support lab facilities for decades. By supplying them with the products and services they need to operate safely and efficiently, we’ve become a leader in our industry. If you’d like to learn more about the difference that a quality partner can make for your lab, then call us today.