Abstract
Background: Near-infrared spectroscopy (NIRS) has recognized potential but limited application for non-invasive diagnostic evaluation. Data analysis methodology that reproducibly distinguishes between the presence or absence of physiologic abnormality could broaden clinical application of this optical technique.Methods: Sample data sets from simultaneous NIRS bladder monitoring and invasive urodynamic pressure-flow studies (UDS) are used to illustrate how a diagnostic algorithm is constructed using classification and regression tree (CART) analysis. Misclassification errors of CART and linear discriminant analysis (LDA) are computed and examples of other urological NIRS data likely amenable to CART analysis presented.Results: CART generated a clinically relevant classification algorithm (error 4%) using 46 data sets of changes in chromophore concentration composed of the whole time series without specifying features. LDA did not (error 16%). Using CART NIRS data provided comparable discriminant ability to the UDS diagnostic nomogram for the presence or absence of obstructive pathology (88% specificity, 84% precision). Pilot data examples from children with and without voiding dysfunction and women with mild or severe pelvic floor muscle dysfunction also show potentially diagnostic differences in chromophore concentration.Conclusions: CART analysis can likely be applied in other NIRS monitoring applications intended to classify patients into those with and without pathology.
Highlights
Recent detailed reviews summarize the evolution of near-infrared spectroscopy (NIRS) and describe the basic principles, instrumentation, advantages and limitations of this optical technique in the context of multiple research and clinical applications [1,2,7,11,25,34,35]
Similar diagnostic accuracy was obtained just using changes in [ΔO2Hb] and [ΔHHb] and an algorithm generated by mathematical modeling and Classification and Regression Tree (CART) analysis [31]. As we believe this method of analysis could be applicable in other research and clinical applications using Near-infrared spectroscopy (NIRS) monitoring, this paper describes the principles and process required to apply classification and regression tree (CART) analysis to NIRS data and develop a diagnostic algorithm
Forty six data sets (30 obstructed and 16 unobstructed) [31] were used to correlate the diagnostic classifications derived from urodynamic pressure-flow studies (UDS) data with NIRS parameters
Summary
Recent detailed reviews summarize the evolution of near-infrared spectroscopy (NIRS) and describe the basic principles, instrumentation, advantages and limitations of this optical technique in the context of multiple research and clinical applications [1,2,7,11,25,34,35]. In many monitoring applications it is the pattern and magnitude of change in O2Hb and HHb that are of principal interest [7,23,25,34]. Even though this data provides changes in chromophore concentration from baseline, rather than quantified values [7,15,34] the well-recognized patterns of change occurring in response to known physiologic events such as hypoxia, ischemia and changes in blood volume can be of considerable clinical value [3,7,11,15,25]. Data analysis methodology that reproducibly distinguishes between the presence or absence of physiologic abnormality could broaden clinical application of this optical technique
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
