Please enable JavaScript.
Coggle requires JavaScript to display documents.
Paper fall prediction of the elderly and cardiogneic shock, Prediction…
Paper fall prediction of the elderly and cardiogneic shock
Cardiogenic shock
304 patients
ratio 60% training:20% testing:20% validation
K-fold cross validation
11 eigenvalues
Random Forest
Logistics Regression
XGBoost
SVM
KNN
Extreme Random Tree
SGD
Light GBM
ADABoost
Fall prediction elderly
15 eigenvalues
XGBoost model
LightGBM model
ExtremeRandomTree
Random Forest
Gradient Boosting
5 important parameters
MNA
hearing impairment
height
ADL
diastolic blood pressure
1101 patients
female
86,1 year
fall?
349 faller
lower ADL, IADL, MNA, Brade
higher VAS, CHS
752 non-faller
dataset Jan 2015-Dec 2019
data
medication information
blood tests
general physiological measurements
comprehensive geriatric assessment
medical history
Web page presentation
login
input patient's personal information
name
gender
ID number
birthday
phone number
address
emergency contact
automated generate patient's medical record
Prediction Model of the Cardiogenic Shock and the Falling Risk in Death Risk Mitigation
Introduction
The cutting-edge technology
medical domain using AI/machine learning
the mortality rate in emergency department
The Cardiogenic shock
Elderly fall
Machine Learning approach
Tree
Non-tree
Feature importance
paper structure
Research question
Abstract
Methodolgy
Primer
Literature study
Secondary
Dataset Hospital
Result and Discussion
Comparison Evaluation IndexCI of XGBoost and ADAboost
Result Model in Elderly Fall (ADABoost)
Result Model in Cardiogenic Shorck (XGBoost)
Discussion
Conclusion and Future Works
Deep Learning
Machine Learning Classifier
ADABoost (Adaptive Boosting)