Multi-input stochastic prediction of insulin sensitivity for tight glycaemic control using insulin sensitivity and blood glucose data

Simple item page
dc.contributor.authorDavidson S
dc.contributor.authorPretty C
dc.contributor.authorUyttendaele V
dc.contributor.authorKnopp J
dc.contributor.authorDesaive T
dc.contributor.authorChase, Geoff
dc.date.accessioned2019-10-17T00:19:04Z
dc.date.available2019-10-17T00:19:04Z
dc.date.issued2019en
dc.date.updated2019-08-27T09:35:43Z
dc.description.abstractBackground: Glycaemic control in the intensive care unit is dependent on effective prediction of patient insulin sensitivity (SI). The stochastic targeted (STAR) controller uses a 2D stochastic model for prediction, with current SI as an input and future SI as an output. Methods: This paper develops an extension of the STAR 2D stochastic model into 3D by adding blood glucose (G) as an input. The performance of the 2D and 3D stochastic models is compared over a retrospective cohort of 65,269 data points across 1,525 patients. Results: Under five-fold cross-validation, the 3D model was found to better match the expected potion of data points within, above and below various credible intervals, suggesting it provided a better representation of the underlying probability field. The 3D model was also found to provide an 18.1% narrower 90% credible interval on average, and a narrower 90% credible interval in 96.4% of cases, suggesting it provided more accurate predictions of future SI. Additionally, the 3D stochastic model was found to avoid the undesirable tendency of the 2D model to overestimate SI for patients with high G, and underestimate SI for patients with low G. Conclusions: Overall, the 3D stochastic model is shown to provide clear potential benefits over the 2D model for minimal clinical cost or effort, though further exploration into whether these improvements in SI prediction translate into improved clinical outcomes is required.en
dc.identifier.citationDavidson S, Pretty C, Uyttendaele V, Knopp J, Desaive T, Chase JG (2019). Multi-input stochastic prediction of insulin sensitivity for tight glycaemic control using insulin sensitivity and blood glucose data. Computer Methods and Programs in Biomedicine. 105043-105043.en
dc.identifier.doihttps://doi.org/10.1016/j.cmpb.2019.105043
dc.identifier.issn0169-2607
dc.identifier.urihttp://hdl.handle.net/10092/17465
dc.languageEnglish
dc.language.isoen
dc.publisherElsevier BVen
dc.rightsCreative Commons Attribution Non-Commercial No Derivatives Licenseen
dc.subjectGlycaemic Controlen
dc.subjectStochastic Modelen
dc.subjectGaussian Kernelen
dc.subjectInsulin Sensitivityen
dc.subjectStochastic Targeteden
dc.subject.anzsrcFields of Research::49 - Mathematical sciences::4905 - Statistics::490510 - Stochastic analysis and modellingen
dc.subject.anzsrcFields of Research::32 - Biomedical and clinical sciences::3202 - Clinical sciences::320208 - Endocrinologyen
dc.subject.anzsrcField of Research::09 - Engineering::0903 - Biomedical Engineeringen
dc.titleMulti-input stochastic prediction of insulin sensitivity for tight glycaemic control using insulin sensitivity and blood glucose dataen
dc.typeJournal Articleen
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
3D Stochastic Model - Paper (CMPB).pdf
Size:
710.12 KB
Format:
Adobe Portable Document Format
Download
Collections
Engineering: Journal Articles