2017
DOI: 10.1609/aaai.v31i1.10721
|View full text |Cite
|
Sign up to set email alerts
|

ICU Mortality Prediction: A Classification Algorithm for Imbalanced Datasets

Abstract: Determining mortality risk is important for critical decisions in Intensive Care Units (ICU). The need for machine learning models that provide accurate patient-specific prediction of mortality is well recognized. We present a new algorithm for ICU mortality prediction that is designed to address the problem of imbalance, which occurs, in the context of binary classification, when one of the two classes is significantly under--represented in the data. We take a fundamentally new approach in exploiting the clas… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
14
0
3

Year Published

2019
2019
2022
2022

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 39 publications
(17 citation statements)
references
References 14 publications
0
14
0
3
Order By: Relevance
“…Medical models often focus on risk of adverse event estimation, which intrinsically carries data imbalance. Re-sampling has been widely applied Chawla et al (2002); Bhattacharya et al (2017). Cost-sensitive training is also applied, for example on Intensive Care Unit (ICU) data Rahman and Davis (2013).…”
Section: Related Workmentioning
confidence: 99%
“…Medical models often focus on risk of adverse event estimation, which intrinsically carries data imbalance. Re-sampling has been widely applied Chawla et al (2002); Bhattacharya et al (2017). Cost-sensitive training is also applied, for example on Intensive Care Unit (ICU) data Rahman and Davis (2013).…”
Section: Related Workmentioning
confidence: 99%
“…# 4 - [Bhattacharya and et al 2017] propôs um novo algoritmo para predição de mortalidade em UTIs para resolver o problema de desequilíbrio entre classes. O método é baseado na transformação das variáveis preditoras para reduzir a correlação existente entre elas.…”
Section: Trabalhos Relacionados Explorando Aprendizado De Máquina Par...unclassified
“…Conforme apresentado na Seção 3.2, o banco de dados utilizado no desenvolvimento desse modelo possui uma incidência de mortalidade de 13,57%, de forma que há uma distribuição desigual entre as classes. A modelagem preditiva com classes desequilibradas representa um desafio para o Aprendizado de Máquina, pois a maioria dos métodos usados para classificação foram projetados com base na suposição de um número igual de exemplos para cada classe [Bhattacharya and et al 2017].…”
Section: Balanceamento Das Classesunclassified
See 1 more Smart Citation
“…AI approaches have been utilized extensively in the past to analyze EHR data, concentrating mostly on predicting and presenting problems (for example, patient result expectation and time-series demonstration). There have been a few recent attempts at using deep learning alongside factual investigation [3][4][5] and AI techniques [5][6][7][8]. Compared to conventional AI, deep learning has greater performance in picture arrangement [9], discourse acknowledgement [10], normal language handling VIEWPOINTS PAPERS 2022 • Vol.…”
mentioning
confidence: 99%