Explainable machine learning model for predicting the occurrence of postoperative malnutrition in children with congenital heart disease

Shi, Hui; Yang, Dong; Tang, Kaichen; Hu, Chunmei; Li, Lijuan; Zhang, Linfang; Gong, Ting; Cui, Yanqin

doi:10.1016/j.clnu.2021.11.006

Cited by 41 publications

(20 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Descriptive results show that the xgbTree algorithm has better predictive capabilities than common linear mixed algorithms. Research by Shi et al [8] use machine learning models to predict the occurrence of postoperative malnutrition in children. Using five predictive algorithms to predict the occurrence of postoperative malnutrition in children, the XGBoost model achieved largest AUC in all outcomes.…”

Section: Coefficient Of Determinationmentioning

confidence: 99%

“…Malnutrition is a serious problem in the global community resulting in chronic disease and death [7]. Malnutrition affects decreased muscle function, immune disorders, and brain dysfunction and can cause disorders of nerve development [8]. The World Health Organization (WHO) estimates the prevalence of stunted toddlers worldwide at 22% or as many as 149.2 million by 2020.…”

Section: Introductionmentioning

confidence: 99%

“…Descriptive results show that the xgbTree algorithm has better predictive capabilities than common linear mixed algorithms. Research by Shi et al [8] use machine learning models to predict the occurrence of postoperative malnutrition in children. Their study used the machine learning model used five machine learning algorithms to build predictive models and performance models from machine learning measured with the area under the curve (AUC).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Prediction of linear model on stunting prevalence with machine learning approach

Mambang

Marleny²,

Zulfadhilah³

2023

Bulletin EEI

View full text Add to dashboard Cite

An increase in the number of residents should be anticipated including in the health sector, especially the problem of stunting. Stunting in children disrupts height and lack of absorption of nutrients. Information and data drive change in many areas such as health, entertainment, economics, business, and other strategic areas. The stages carried out in this study are initiating, developing linear models, and making prediction results on linear machine learning models. The results of testing with the scikit-learn linear model with a minimum variable of 19 get the best test results, namely the polynomial regression with pipeline model with mean absolute percentage error (MAPE) 0.02, root mean square error (RMSE) 3.32, and coefficient of determination (R2) 1,00. Testing with the scikit-learn linear model with a maximum variable of 48 gets the best test results, namely the polynomial regression with pipeline model with MAPE 0.00, RMSE 3.79 and R2 1.00. Testing with the scikit-learn linear model with an average variable of 32 gets the best test results, namely the polynomial regression model with MAPE 0.01, RMSE 3.32, and R2 1.00. The results of testing with the scikit-learn linear model with the minimum, maximum, and average variables get the best test results, namely the polynomial regression with pipeline model.

show abstract

Section: Coefficient Of Determinationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Descriptive results show that the xgbTree algorithm has better predictive capabilities than common linear mixed algorithms. Research by Shi et al [8] use machine learning models to predict the occurrence of postoperative malnutrition in children. Their study used the machine learning model used five machine learning algorithms to build predictive models and performance models from machine learning measured with the area under the curve (AUC).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of linear model on stunting prevalence with machine learning approach

Mambang

Marleny²,

Zulfadhilah³

2023

Bulletin EEI

View full text Add to dashboard Cite

show abstract

“…Machine Leaning Approach (Minn 2022) in this method by using several libraries contained in python programming such as Pandas, Numpy, Matplotlib and also Seaborn. With Machine Learning, data can be developed with many models aimed at predicting data on many fields (Shi et al 2022). Studying data with a computer is one of the goals of Machine Learning which is one of the branches of Artificial Intelligence.…”

Section: Machine Learningmentioning

confidence: 99%

Explanatory Data Analysis to Evaluate Keyword Searches for Educational Videos on YouTube with a Machine Learning Approach

Mambang

Hidayat

Wahyudi³

et al. 2022

SinkrOn

View full text Add to dashboard Cite

One of the most important parts of data science is the process of explanatory data analysis. This study aims to analyze learning videos on YouTube using search keywords such as learning biology, chemistry, physics, computers, mathematics, management, accounting, citizenship, history, and culture. The method used is the explanatory data analysis technique with a Machine Learning approach. The dataset used in this study uses learning video search keywords found on the YouTube digital platform. After doing a thorough analysis of all existing variables, we found that in the context of searching for learning video keywords on YouTube, the viewing variable has a heatmap correlation of 0.97 on the likes variable, 0.97 on the subscribers variable, -0.15 on the duration variable and 0.95 on the comment variable. The duration variable negatively correlates with all variables based on the analysis using a correlation heatmap using the seaborn library. Our analysis found that the number of learning videos with the search keyword Mathematics had the highest number of views among other variables. Further research can use existing variables or also add variables and add search keywords on YouTube. The data analysis approach can also be done using SPSS, R and also a Machine Learning approach with different libraries.

show abstract

“…The use of artificial intelligence methods holds further promise in improving early identification of children at high risk. A recent study using machine learning could establish accurate early prediction of malnutrition 1 year after surgery in children with congenital heart disease, which could aid in determining individual treatment and nutritional follow-up strategies for individual sick children [9].…”

mentioning

confidence: 99%

Editorial: Disease-associated malnutrition in paediatric patients must be diagnosed and treated

Koletzko

Shamir

2022

Current Opinion in Clinical Nutrition &Amp; Metabolic Care

View full text Add to dashboard Cite

show abstract

Explainable machine learning model for predicting the occurrence of postoperative malnutrition in children with congenital heart disease

Cited by 41 publications

References 26 publications

Prediction of linear model on stunting prevalence with machine learning approach

Prediction of linear model on stunting prevalence with machine learning approach

Explanatory Data Analysis to Evaluate Keyword Searches for Educational Videos on YouTube with a Machine Learning Approach

Editorial: Disease-associated malnutrition in paediatric patients must be diagnosed and treated

Contact Info

Product

Resources

About