首页|Randers Regional Hospital Researchers Provide New Study Findings on Artificial I ntelligence [Continued versus discontinued oxytocin stimulati on in the active phase of labour (CONDISOX): individual management based on arti ficial intelligence - a …]
Randers Regional Hospital Researchers Provide New Study Findings on Artificial I ntelligence [Continued versus discontinued oxytocin stimulati on in the active phase of labour (CONDISOX): individual management based on arti ficial intelligence - a …]
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Research findings on artificial intell igence are discussed in a new report. Accordingto news reporting out of the Ran ders Regional Hospital by NewsRx editors, research stated, “Currentguidelines r egarding oxytocin stimulation are not tailored to individuals as they are based on randomisedcontrolled trials. The objective of the study was to develop an ar tificial intelligence (AI) model for individualprediction of the risk of caesar ean delivery (CD) in women with a cervical dilatation of 6 cm after oxytocinsti mulation for induced labour.”The news correspondents obtained a quote from the research from Randers Regional Hospital: “Themodel included not only variables known when labour induction wa s initiated but also variables describingthe course of the labour induction. Se condary analysis of data from the CONDISOX randomised controlledtrial of discon tinued vs. continued oxytocin infusion in the active phase of induced labour. Ex tremegradient boosting (XGBoost) software was used to build the prediction mode l. To explain the impact ofthe predictors, we calculated Shapley additive expla nation (SHAP) values and present a summary SHAPplot. A force plot was used to e xplain specifics about an individual’s predictors that result in a changeof the individual’s risk output value from the population-based risk. Among 1060 inclu ded women, 160(15.1%) were delivered by CD. The XGBoost model foun d women who delivered vaginally were more likelyto be parous, taller, to have a lower estimated birth weight, and to be stimulated with a lower amountof oxyto cin. In 108 women (10% of 1060) the model favoured either continua tion or discontinuation ofoxytocin. For the remaining 90% of the women, the model found that continuation or discontinuation ofoxytocin stimulat ion affected the risk difference of CD by less than 5% points.”
Randers Regional HospitalArtificial In telligenceEmerging TechnologiesMachine LearningRisk and Prevention
NETL
NSTL
