Researchers from SMART CAMP and MIT have developed an innovative method that utilizes machine learning and UV light to detect microbial contamination in cell cultures.

This novel approach employs UV absorbance spectroscopy combined with machine learning, allowing for rapid, label-free, and non-invasive contamination detection in under thirty minutes.

The method offers a significant improvement over traditional sterility tests, which can take up to fourteen days, thereby accelerating sterility testing during cell therapy product (CTP) manufacturing.

Timely contamination detection is crucial for critically ill patients awaiting CTPs, as any delays can be life-threatening.

Current sterility testing methods are labor-intensive and require skilled manpower, highlighting the need for more efficient solutions.

Unlike traditional methods, this new approach eliminates the need for cell staining and extraction, simplifying the workflow and reducing costs associated with CTP manufacturing.

The technique allows for continuous monitoring of cell cultures, enabling early detection of contamination and timely corrective actions, which optimizes resource allocation and manufacturing timelines.

By streamlining the sterility testing process, this method aims to enhance the efficiency of CTP manufacturing, which is critical for timely treatment.

Beyond its application in cell therapy, the technology may also benefit the food and beverage industry for microbial quality control testing.

Future research will explore the method's effectiveness against a broader range of microbial contaminants and its application across different cell types.

This research is supported by Singapore's National Research Foundation under the CREATE program.