Electronic classification of barcoded particles for multiplexed detection using supervised machine learning analysis

Time‐domain signal averaging to improve microparticles detection and enumeration accuracy in a microfluidic impedance cytometer

“…This is notable primarily for bringing the 1 and 3 µm particle solutions above the discernible 20 dB SNR threshold after SMA and likewise lowering the device's limit of detection (LOD). The changes in SNR after SMA for different particle sizes also had a linear trajectory (gray, R 2 = 0.970), which is the combination of logarithmic changes in SNR for a typical linear increase in bipolar amplitude and the cubic increase in PS volume per linear diameter changes, as PS volume scales with displaced media in the channel detection regime and likewise a direct change in recorded impedance (Sui et al, 2020). This is supported by the cubic increase in bipolar amplitude relative to particle size shown in Figure 5a.…”

“…Another limitation is that SMA cannot distinguish competitive analyte species with similar pulse frequencies or exaggerate their amplitude differences, treating all objects which are counted with equal scrutiny. To better differentiate two or more materials, other phenotypic properties must be exploited (e.g., measure more electrically sensitive particles, probe particles at different input frequencies, or use functionalized particles for receptor attachment and identification) (Ashley et al, 2021; Prakash et al, 2020; Sui et al, 2020). Finally, the maximum SNR achieved would reach a climax and begin to decline from increasing number of data points used in the SMA algorithm.…”

Point‐of‐critical‐care diagnostics for sepsis enabled by multiplexed micro and nanosensing technologies

“…Further, by employing electrically sensitive nanoparticles or “barcoded” species as target agents, the ceiling for multiplexing is only limited by nanoparticle material or physical properties. Indeed, particles with different electrical properties have shown high selectivity for different types of biomarkers with the availability of an extensive library of particles far greater than other modalities (Sui et al, 2020; Xie et al, 2017). Additionally, investigative research in novel polymer particles fabricated from stop‐flow lithography can produce barcoded particles and with only five barcoded regions the multiplexing potential may reach 120 unique biomarkers (Prakash et al, 2020).…”

“…This can improve sepsis diagnosis from many perspectives, including processing a patient's medical history from electronic medical records (EMR) to predict a patient's likelihood of developing sepsis (Taneja et al, 2017). Similarly, many studies have already incorporated machine learning with sensors for measuring sepsis biomarkers and will continue to grow based on its automated iterative model building from substantial data sets and allows for an increase in multiplexing potential without a relative increase in processing (Ahuja et al, 2019; Ellett et al, 2018; Green et al, 2019; Hassan et al, 2017; Sui et al, 2020). Future POCC strategies may implement machine learning from multiple perspectives—predicting sepsis development from patient EMR data and analyzing multiple biomarkers after symptom onset—to identify sepsis earlier and treat more specifically.…”

Antibody-functionalized aluminum oxide-coated particles targeting neutrophil receptors in a multifrequency microfluidic impedance cytometer

“…Each MOJP then has a specific amplitude shift at different output frequencies, which can be used to electrically identify the particles. 46 Based on the thickness of antibody-functionalized Janus particles (i.e., aluminum oxide-semi coated particles with CD11b and CD66b targeting surface-functionalized antibodies), characteristic impedance shifts across a multifrequency voltage will occur. This translates to receptor identification when conjugated to neutrophils with one emission and detection source.…”