Illuminate-τ: a portable platform combining autofluorescence lifetime characteristics and machine learning for rapid detection of <100 CFU/ml bioburden in water

Bioburden detection in water is an important challenge in the contexts of both consumer and industrial water. Water-borne infections due to bacteria and fungi are becoming key public health concerns. Further, in biologics manufacturing sector, it is of key importance to use water with zero bioburden in all critical manufacturing processes. However, current methods of detecting and classifying bioburden in water samples is a tedious process involving time-consuming microbiological steps where it takes about 5-7 days to infer trace levels of pathogen contamination. It is possible to hasten the detection process using cytometry-based platforms that offer high levels of sensitivity and specificity in pathogen detection and enumeration of various pathogens. However, these solutions may not be able to determine the bacterial species and viability in a label-free set up. Here, we present Illuminate-τ, a portable label-free detection platform for rapid bioburden assessment in water samples in under 10 minutes, thereby demonstrating a >1000x improvement in detection time. This works on the principle of inferring the presence of pathogen cells in water through their native autofluorescence lifetime characteristics. The Illuminate-τ device is integrated with pulsed nanosecond UV light sources and drivers, high-speed single photon avalanche detectors, and sophisticated timing circuits controlled by an embedded electronics subsystem. In addition, the device also has an edge inferencing SVM-based machine learning algorithm that takes in autofluorescence lifetime characteristics and detects <100 CFU/ml of bioburden such as Pseudomonas, E.coli, Salmonella, Candida species etc. with an accuracy exceeding 99%. Further, we show that we the platform is also able to differentiate Pseudomonas from other bacteria and fungi with a 100% accuracy under similar conditions of concentration. In summary, we demonstrate that Illuminate-τ a device based on autofluorescence lifetime coupled with machine-learning-based detection strategies can achieve high bioburden detection sensitivity.