Sepsis mortality prediction with the Quotient Basis Kernel

Ripoll, Vicent J. Ribas; Vellido, Alfredo; Romero, Enrique; Ruiz‐Rodríguez, Juan Carlos

doi:10.1016/j.artmed.2014.03.004

Cited by 32 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [ 67 ], data were first embedded in a suitable feature space; then algorithms based on linear algebra, geometry and statistics for inference were used. Even from this informal definition, it becomes apparent that all the methods used so far could be kernelized provided the appropriate mappings, spaces, measures and topologies were used.…”

Section: Resultsmentioning

confidence: 99%

“…Given the simplicity of the models (only multinomial and multivariate Gaussian distributions are considered, all of which can be efficiently modelled algebraically using the Regular Exponential Family), we proposed to use a generative approach and exploit the inner data structure to build a set of efficient closed-form kernels best suited for these two distributions. More specifically, the performance of the Quotient Basis Kernel (QBK) [ 67 ], the simplified Fisher kernel against other state-of-the art methods such as, support vector machines with a Gaussian, Polynomial and linear kernels, generative kernels based on the Jensen-Shannon metric (Centred, Inverse and Exponential kernels) [ 90 ] and RVM [ 63 ] were all assessed as sepsis mortality predictors.…”

Section: Resultsmentioning

confidence: 99%

“…Relevance Vector Machines (RVM), which are SVM variants with embedded feature relevance determination, were used in [ 63 ], DTs were used in [ 64 ], while BN models were used in [ 65 , 66 ]. Finally, kernel methods were used in [ 67 ].…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning in critical care: state-of-the-art and a sepsis case study

Vellido

Ribas²,

Carles

et al. 2018

BioMed Eng OnLine

Self Cite

View full text Add to dashboard Cite

BackgroundLike other scientific fields, such as cosmology, high-energy physics, or even the life sciences, medicine and healthcare face the challenge of an extremely quick transformation into data-driven sciences. This challenge entails the daunting task of extracting usable knowledge from these data using algorithmic methods. In the medical context this may for instance realized through the design of medical decision support systems for diagnosis, prognosis and patient management. The intensive care unit (ICU), and by extension the whole area of critical care, is becoming one of the most data-driven clinical environments.ResultsThe increasing availability of complex and heterogeneous data at the point of patient attention in critical care environments makes the development of fresh approaches to data analysis almost compulsory. Computational Intelligence (CI) and Machine Learning (ML) methods can provide such approaches and have already shown their usefulness in addressing problems in this context. The current study has a dual goal: it is first a review of the state-of-the-art on the use and application of such methods in the field of critical care. Such review is presented from the viewpoint of the different subfields of critical care, but also from the viewpoint of the different available ML and CI techniques. The second goal is presenting a collection of results that illustrate the breath of possibilities opened by ML and CI methods using a single problem, the investigation of septic shock at the ICU.ConclusionWe have presented a structured state-of-the-art that illustrates the broad-ranging ways in which ML and CI methods can make a difference in problems affecting the manifold areas of critical care. The potential of ML and CI has been illustrated in detail through an example concerning the sepsis pathology. The new definitions of sepsis and the relevance of using the systemic inflammatory response syndrome (SIRS) in its diagnosis have been considered. Conditional independence models have been used to address this problem, showing that SIRS depends on both organ dysfunction measured through the Sequential Organ Failure (SOFA) score and the ICU outcome, thus concluding that SIRS should still be considered in the study of the pathophysiology of Sepsis. Current assessment of the risk of dead at the ICU lacks specificity. ML and CI techniques are shown to improve the assessment using both indicators already in place and other clinical variables that are routinely measured. Kernel methods in particular are shown to provide the best performance balance while being amenable to representation through graphical models, which increases their interpretability and, with it, their likelihood to be accepted in medical practice.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning in critical care: state-of-the-art and a sepsis case study

Vellido

Ribas²,

Carles

et al. 2018

BioMed Eng OnLine

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ho, Lee, and Ghosh (2012) used the MIMIC-II database to construct three different septic shock predictive models with accuracy rate close to 80%. Another significant model is the Quotient Basis Kernel (QBK), which showed a sensitivity of 79.34%, and a specificity of 83.24% (Ribas Ripoll, Vellido, Romero, & Ruiz-Rodríguez, 2014). Henry et al (2015) used supervised learning methodologies and the MIMIC-II database to construct the targeted real-time early warning score (TREWScore).…”

Section: Relevance and Significancementioning

confidence: 99%

“…Ribas Ripoll et al (2014) presented a sepsis mortality prediction method using linear algebra, geometry, and statistical inference. They built a kernel for multinomial distributions and named it the Quotient Basis Kernel (QBK), which used the Simplified Acute Physiology Score (SAPS) for ICU patients and the Sequential Organ Failure Assessment (SOFA) to deliver a mortality prediction from sepsis with high accuracy (Ribas Ripoll et al, 2014). Ho et al (2014) added a third imputation method to deal with missing data.…”

Section: Septic Shock Predictionmentioning

confidence: 99%