TY - JOUR
T1 - Dynamic laser speckle imaging meets machine learning to enable rapid antibacterial susceptibility testing (DYRAST)
AU - Liu, Zhiwen
AU - Ebrahimi, Aida
AU - Zhou, Keren
AU - Zhou, Chen
AU - Sapre, Anjali
AU - Pavlock, Jared Henry
AU - Weaver, Ashley
AU - Muralidharan, Ritvik
AU - Noble, Josh
AU - Chung, Taejung
AU - Kovac, Jasna
N1 - Publisher Copyright:
© 2020 American Chemical Society
PY - 2020/10/23
Y1 - 2020/10/23
N2 - Rapid antibacterial susceptibility testing (RAST) methods are of significant importance in healthcare, as they can assist caregivers in timely administration of the correct treatments. Various RAST techniques have been reported for tracking bacterial phenotypes, including size, shape, motion, and redox state. However, they still require bulky and expensive instruments which hinder their application in resource-limited environmentsand/or utilize labeling reagents which can interfere with antibiotics and add to the total cost. Furthermore, the existing RAST methods do not address the potential gradual adaptation of bacteria to antibiotics, which can lead to a false diagnosis. In this work, we present a RAST approach by leveraging machine learning to analyze time-resolved dynamic laser speckle imaging (DLSI) results. DLSI captures the change in bacterial motion in response to antibiotic treatments. Our method accurately predicts the minimum inhibitory concentration (MIC) of ampicillin and gentamicin for a model strain of Escherichia coli (E. coli K-12) in 60 min, compared to 6 h using the currently FDA-approved phenotype-based RAST technique. In addition to ampicillin (a β-lactam) and gentamicin (an aminoglycoside), we studied the effect of ceftriaxone (a third-generation cephalosporin) on E. coli K-12. The machine learning algorithm was trained and validated using the overnight results of a gold standard antibacterial susceptibility testing method enabling prediction of MIC with a similarly high accuracy yet substantially faster.
AB - Rapid antibacterial susceptibility testing (RAST) methods are of significant importance in healthcare, as they can assist caregivers in timely administration of the correct treatments. Various RAST techniques have been reported for tracking bacterial phenotypes, including size, shape, motion, and redox state. However, they still require bulky and expensive instruments which hinder their application in resource-limited environmentsand/or utilize labeling reagents which can interfere with antibiotics and add to the total cost. Furthermore, the existing RAST methods do not address the potential gradual adaptation of bacteria to antibiotics, which can lead to a false diagnosis. In this work, we present a RAST approach by leveraging machine learning to analyze time-resolved dynamic laser speckle imaging (DLSI) results. DLSI captures the change in bacterial motion in response to antibiotic treatments. Our method accurately predicts the minimum inhibitory concentration (MIC) of ampicillin and gentamicin for a model strain of Escherichia coli (E. coli K-12) in 60 min, compared to 6 h using the currently FDA-approved phenotype-based RAST technique. In addition to ampicillin (a β-lactam) and gentamicin (an aminoglycoside), we studied the effect of ceftriaxone (a third-generation cephalosporin) on E. coli K-12. The machine learning algorithm was trained and validated using the overnight results of a gold standard antibacterial susceptibility testing method enabling prediction of MIC with a similarly high accuracy yet substantially faster.
UR - http://www.scopus.com/inward/record.url?scp=85094220319&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85094220319&partnerID=8YFLogxK
U2 - 10.1021/acssensors.0c01238
DO - 10.1021/acssensors.0c01238
M3 - Article
C2 - 32942846
AN - SCOPUS:85094220319
SN - 2379-3694
VL - 5
SP - 3140
EP - 3149
JO - ACS Sensors
JF - ACS Sensors
IS - 10
ER -