Improving Septic Shock Prediction with AdaBoost and Cox Regression Model

Darwiche, Aiman; EL-Geneidy, Ayman; Mukherjee, Sumitra

doi:10.1109/iccece51280.2021.9342457

Cited by 3 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised learning was used in 55 (75%) studies, commonly for the purpose of early identification of septic shock with the aim of enabling timely intervention and reducing disease progression. In particular, 8 studies [15][16][17][18][19][20][21][22] evaluated septic shock prediction systems using the MIMIC dataset, version III. Despite this apparent similarity, however, direct comparison of these systems' predictive performance is not 8 meaningful due to other sources of heterogeneity: their time between prediction and septic shock onset ranged from 15 minutes to 48 hours, between 25 and 4786 episodes of septic shock were identified during dataset processing, reflecting large differences in inclusion criteria and hence the meaning of the 'septic shock' labels, and the studies used different measures of model performance.…”

Section: Supervised Learning For Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Data-driven decision support for individualised cardiovascular resuscitation in sepsis: a scoping review and primer for clinicians

Catling,

Nagendran,

Festor

et al. 2023

Preprint

View full text Add to dashboard Cite

BackgroundWe conducted a scoping review of machine learning systems that inform individualised cardiovascular resuscitation of adults in hospital with sepsis. Our study reviews the resuscitation tasks that the systems aim to assist with, system robustness and potential to improve patient care, and progress towards deployment in clinical practice. We assume no expertise in machine learning from the reader and introduce technical concepts where relevant.MethodsThis study followed thePreferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviewsguidance. MEDLINE, EMBASE, Scopus, ClinicalTrials.gov, arXiv, bioRxiv and medRxiv were systematically searched up to September 2021. We present a narrative synthesis of the included studies, which also aims to equip clinicians with an understanding of the foundational machine learning concepts necessary to interpret them.Results73 studies were included with 80% published after 2018. Supervised learning systems were often used to predict septic shock onset. Reinforcement learning systems were increasingly popular in the last five years, and were used to guide specific dosing of fluids and vasopressors. A minority of studies proposed systems containing biological models augmented with machine learning. Sepsis and septic shock were heterogeneously defined and 63% of studies derived their systems using a single dataset. Most studies performed only retrospective internal validation, with no further steps taken towards translating their proposed systems into clinical practice.ConclusionsMachine learning systems can theoretically match, or even exceed, human performance when predicting patient outcomes and choosing the most suitable cardiovascular treatment strategy in sepsis. However, with some notable exceptions, the vast majority of systems to date exist only as proof of concept, with significant barriers to translation.

show abstract

Section: Supervised Learning For Predictionmentioning

confidence: 99%

“…Several studies compared the performance of multiple algorithms on a single task [38,39], or combined them in "ensemble" models as a means of increasing overall performance and generalisability [15,22,40].…”

Section: Supervised Learning For Predictionmentioning

confidence: 99%

Data-driven decision support for individualised cardiovascular resuscitation in sepsis: a scoping review and primer for clinicians

Catling,

Nagendran,

Festor

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…It adopts single-factor analysis and multiple stepwise logistic regression analysis to find risk factors [4]. And, the semi-parametric COX regression models (i.e., proportional hazards regression) is also used in some works [5][6][7]. Moreover, the logistic regression in [13] is also a widely used model for lung infection prediction.…”

Section: Introductionmentioning

confidence: 99%