A simple device and associated analytical methods are reported. We provide objective and accurate determination of saliva alcohol concentrations using smartphone-based colorimetric imaging. The device utilizes any smartphone with a miniature attachment that positions the sample and provides constant illumination for sample imaging. Analyses of histograms based on channel imaging of red–green–blue (RGB) and hue–saturation–value (HSV) color space provide unambiguous determination of blood alcohol concentration from color changes on sample pads. A smartphone-based sample analysis by colorimetry was developed and tested with blind samples that matched with the training sets. This technology can be adapted to any smartphone and used to conduct color change assays.

We report a smartphone-based colorimetric analysis of saliva–alcohol concentrations, utilizing optimal color space and machine-learning algorithms. Commercial saliva–alcohol kits are used as a model experiment, utilizing a custom-built optical attachment for the smartphone to obtain consistent imaging of the alcohol strips. The color of the strips varies with the alcohol concentration, and the smartphone camera captures the color produced on the test strip. To make a suitable library for each alcohol concentration, statistical methods were tested to maximize between-scatter and minimize within-scatter for each concentration. Results of three different classification methods (LDA, SVM, and ANN) and four-color spaces (RGB, HSV, YUV, and Lab) were evaluated with various machine-learning data sets and five different smartphone models. Cross-validation results were used to assess the statistical performance, such as positive (PPV) and negative (NPV) predictive values. An Android app developed and provided average classification rates of 100% and 80% for the standard and enhanced concentrations, respectively.

We report a smartphone-based device and associated imaging-processing algorithm to maximize the sensitivity of standard smartphone cameras, that can detect the presence of single-digit pW of radiant flux intensity. The proposed hardware and software, called bioluminescent-based analyte quantitation bysmartphone (BAQS), provides an opportunity for onsite analysis and quantitation of luminescent signals from biological and non-biological sensing elements which emit photons in response to an analyte. A simple cradle that houses the smartphone, sample tube, and collection lens supports the measuring platform, while noise reduction by ensemble averaging simultaneously lowers the background and enhances the signal from emitted photons. Five different types of smartphones, both Android and iOS devices, were tested, and the top two candidates were used to evaluate luminescence from the bioluminescent reporterPseudomonas fluorescensM3A. The best results were achieved by OnePlus One (android), which was able to detect luminescence from ~10⁶ CFU/mL of the bio-reporter, which corresponds to ~10⁷photons/s with 180 seconds of integration time.