Neural network pattern recognition analysis of graft flow characteristics improves intra-operative anastomotic error detection in minimally invasive CABG

Cerrito, Patricia B.; Koenig, Steven C.; VanHimbergen, Daniel J.; Jaber, Saad F.; Ewert, Dan; Spence, Paul A.

doi:10.1016/s1010-7940(99)00139-6

Cited by 15 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The models are not "aware" of evidence indicating that increases in a variable in one factor (e.g., nitrite production in Table I) would tend to increase host resistance, whereas decreases in others (e.g., NK cell activity in Table I) would tend to decrease host resistance. Nonregression-based multivariate methods such as neural network analysis may ultimately prove to be more effective (62). To date, the use of such methods in evaluating the immune system has been limited to developing theoretical models that will predict the behavior of particular immune parameters (e.g., Ab responses) (63).…”

Section: Discussionmentioning

confidence: 99%

Quantifying the Relationship Between Multiple Immunological Parameters and Host Resistance: Probing the Limits of Reductionism

Keil¹,

Luebke

Pruett

2001

The Journal of Immunology

View full text Add to dashboard Cite

Although reductionist experimental designs are excellent for identifying cells, molecules, or functions involved in resistance to particular microbes or cancer cells, they do not provide an integrated, quantitative view of immune function. In the present study, mice were treated with either dexamethasone (DEX) or cyclosporin A (CyA), and immune function and host resistance were evaluated. Multivariate statistical methods were used to describe the relative importance of a broad range of immunological parameters for host resistance in mice treated with various dosages of DEX. Multiple regression and logistic regression analysis indicated that changes in 24 immunological parameters explained a substantial portion of the changes in resistance to B16F10 tumor cells or streptococcus group B. However, at least 40% of the change in host resistance remained unexplained. DEX at all dosages substantially suppressed numerous relevant immunological parameters, but significantly decreased resistance to Listeria monocytogenes only at the highest dosage. In contrast, CyA substantially decreased resistance to L. monocytogenes at dosages that caused relatively minor suppression of just a few immunological parameters (unfortunately, CyA data and host resistance data for L. monocytogenes were not suitable for multivariate analysis). These results illustrate that mathematical models can be used to explain changes in host resistance on the basis of changes in immune parameters, and that moderate changes in relevant immunological parameters may not produce the types of changes in host resistance expected on the basis of results from reductionist experimental designs.

show abstract

Section: Discussionmentioning

confidence: 99%

Quantifying the Relationship Between Multiple Immunological Parameters and Host Resistance: Probing the Limits of Reductionism

Keil¹,

Luebke

Pruett

2001

The Journal of Immunology

View full text Add to dashboard Cite

show abstract

“…Pattern recognition of flow probe tracings using neural network systems can detect anastomotic errors (46). Spectral analysis of graft flow waveforms may be more accurate (44).…”

Section: Intraoperative Analysis Of Graft Flowmentioning

confidence: 99%

Off-pump vs On-pump Surgery: A Review

Svennevig

2000

Scandinavian Cardiovascular Journal

View full text Add to dashboard Cite

“…However, a less-than-critical anastomotic error might not affect the graft flow significantly. Based on a complex mathematical analysis of the flow curve, it is suggested that a stenosis causing a 50% or greater narrowing of anastomoses can affect graft flow substantially and enable detection by TTFM [25]. In addition, it has been found that the transit time blood flow in a sequential graft is substantially higher than that in a single graft [11,17], which could further mask the effect of a less-than-critical defective anastomosis on the total graft flow.…”

Section: Discussionmentioning

confidence: 99%

The application of intraoperative transit time flow measurement to accurately assess anastomotic quality in sequential vein grafting

Fan

Gao

et al. 2013

Interact CardioVasc Thorac Surg

View full text Add to dashboard Cite

show abstract

Neural network pattern recognition analysis of graft flow characteristics improves intra-operative anastomotic error detection in minimally invasive CABG

Abstract: Pattern recognition of transit-time flow probe tracings using neural network systems can detect anastomotic errors significantly better than the surgeon's visual assessment, thereby improving the clinical outcome of minimally invasive CABG.

Cited by 15 publications

References 9 publications

Quantifying the Relationship Between Multiple Immunological Parameters and Host Resistance: Probing the Limits of Reductionism

Quantifying the Relationship Between Multiple Immunological Parameters and Host Resistance: Probing the Limits of Reductionism

Off-pump vs On-pump Surgery: A Review

The application of intraoperative transit time flow measurement to accurately assess anastomotic quality in sequential vein grafting

Contact Info

Product

Resources

About