The Chi-squared Automatic Interaction Detection model accurately predicted mortality among women with heart disease with an overall accuracy of 93.25% and an area under the curve of 0.825.
Observational (n=2,028)
Yes
Does the Chi-squared Automatic Interaction Detection model accurately predict mortality in women with heart disease?
The Chi-squared Automatic Interaction Detection model accurately predicts cardiovascular mortality among women using electronic health record data.
Effect estimate: AUC 0.825
BACKGROUND: Many current studies have claimed that the actual risk of heart disease among women is equal to that in men. Using a large machine learning algorithm (MLA) data set to predict mortality in women, data mining techniques have been used to identify significant aspects of variables that help in identifying the primary causes of mortality within this target category of the population. OBJECTIVE: This study aims to predict mortality caused by heart disease among women, using an artificial intelligence technique-based MLA. METHODS: A retrospective design was used to retrieve big data from the electronic health records of 2028 women with heart disease. Data were collected for Jordanian women who were admitted to public health hospitals from 2015 to the end of 2021. We checked the extracted data for noise, consistency issues, and missing values. After categorizing, organizing, and cleaning the extracted data, the redundant data were eliminated. RESULTS: Out of 9 artificial intelligence models, the Chi-squared Automatic Interaction Detection model had the highest accuracy (93.25%) and area under the curve (0.825) among the build models. The participants were 62.6 (SD 15.4) years old on average. Angina pectoris was the most frequent diagnosis in the women's extracted files (n=1,264,000, 62.3%), followed by congestive heart failure (n=764,000, 37.7%). Age, systolic blood pressure readings with a cutoff value of >187 mm Hg, medical diagnosis (women diagnosed with congestive heart failure were at a higher risk of death n=31, 16.58%), pulse pressure with a cutoff value of 98 mm Hg, and oxygen saturation (measured using pulse oximetry) with a cutoff value of 93% were the main predictors for death among women. CONCLUSIONS: To predict the outcomes in this study, we used big data that were extracted from the clinical variables from the electronic health records. The Chi-squared Automatic Interaction Detection model-an MLA-confirmed the precise identification of the key predictors of cardiovascular mortality among women and can be used as a practical tool for clinical prediction.
Hani et al. (Thu,) conducted a observational in Heart disease (n=2,028). Chi-squared Automatic Interaction Detection (CHAID) model vs. Other machine learning models was evaluated on Prediction of mortality (overall accuracy) (AUC 0.825). The Chi-squared Automatic Interaction Detection model accurately predicted mortality among women with heart disease with an overall accuracy of 93.25% and an area under the curve of 0.825.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: