Machine Learning Methods in Real-World Studies of Cardiovascular Disease

Zhou, Jiawei; You, Dongfang; Bai, Jianling; Chen, Xin; Wu, Yaqian; Wang, Zhongtian; Tang, Yingdan; Zhao, Yang; Feng, Guoshuang

doi:10.15212/cvia.2023.0011

Cited by 6 publications

(1 citation statement)

References 92 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Supervised learning algorithms use the labeled data to train the model, and are used to predict the probability or classification. Some of the widely used supervised algorithms include random forests, support vector machines, and neural networks [ 3 , 4 ]. Mannil et al developed a ML model based on the cardiac computed tomography imaging data to predict myocardial infarction, quantified the image data using texture analysis, and used the KNN algorithm to achieve a good performance (sensitivity 69.0%, specificity 85.0%, false positive rate 15.0%, AUC value 0.78) [ 5 ].…”

Section: Introductionmentioning

confidence: 99%

Comparative analysis of supervised learning algorithms for prediction of cardiovascular diseases

Dou,

Liu,

Meng

et al. 2024

THC

View full text Add to dashboard Cite

BACKGROUND: With the advent of artificial intelligence technology, machine learning algorithms have been widely used in the area of disease prediction. OBJECTIVE: Cardiovascular disease (CVD) seriously jeopardizes human health worldwide, thereby needing the establishment of an effective CVD prediction model that can be of great significance for controlling the risk of the disease and safeguarding the physical and mental health of the population. METHODS: Considering the UCI heart disease dataset as an example, initially, a single machine learning prediction model was constructed. Subsequently, six methods such as Pearson, chi-squared, RFE and LightGBM were comprehensively used for the feature screening. On the basis of the base classifiers, Soft Voting fusion and Stacking fusion was carried out to build a prediction model for cardiovascular diseases, in order to realize an early warning and disease intervention for high-risk populations. To address the data imbalance problem, the SMOTE method was adopted to process the data set, and the prediction effect of the model was analyzed using multi-dimensional and multi-indicators. RESULTS: In the single classifier model, the MLP algorithm performed optimally on the preprocessed heart disease dataset. After feature selection, five features eliminated. The ENSEM_SV algorithm that combines the base classifiers to determine the prediction results by soft voting on the results of the classifiers achieved the optimal value on five metrics such as Accuracy, Jaccard_Score, Hamm_Loss, AUC, etc., and the AUC value reached 0.951. The RF, ET, GBDT, and LGB algorithms were employed in the first stage sub-model composed of base classifiers. The AB algorithm was selected as the second stage model, and the ensemble algorithm ENSEM_ST, obtained by Stacking fusion of the two stages exhibited the best performance on 7 indicators such as Accuracy, Sensitivity, F1_Score, Mathew_Corrcoef, etc., and the AUC reached 0.952. Furthermore, a comparison of the algorithms’ classification effects based on different training set occupancy was carried out. The results indicated that the prediction performance of both the fusion models was better than the single models, and the overall effect of ENSEM_ST fusion was stronger than the ENSEM_SV fusion. CONCLUSIONS: The fusion model established in this study improved the overall classification accuracy and stability of the model to a significant extent. It has a good application value in the predictive analysis of CVD diagnosis, and can provide a valuable reference in the disease diagnosis and intervention strategies.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparative analysis of supervised learning algorithms for prediction of cardiovascular diseases

Dou,

Liu,

Meng

et al. 2024

THC

View full text Add to dashboard Cite

show abstract

Association between serum calcium and in-hospital mortality in critically ill atrial fibrillation patients from the MIMIC IV database

Zheng,

Zhang,

Wang

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Thongprayoon et al. found in a study of 12,599 non-dialysis adult hospitalized patients that serum calcium (SC) disturbances affected more than half of the patients and were associated with increased in-hospital mortality. Similar impacts of SC disturbances on in-hospital mortality have been observed in patients with acute myocardial infarction and the general hospitalized population. Atrial fibrillation (AF), the most common arrhythmia in the intensive care unit (ICU), affects around 6% of critically ill patients. However, the significance of the relationship between SC levels and in-hospital mortality in these patients remains unclear. This study aimed to explore the correlation between SC levels and in-hospital mortality in ICU patients diagnosed with AF. Data from the MIMIC-IV database included 11,621 AF patients (average age 75.59 ± 11.74 years; 42.56% male), with an in-hospital mortality rate of 8.90%. A nonlinear relationship between SC levels and in-hospital mortality was observed. Effect sizes on either side of the inflection point were 0.79 (HR: 0.79, 95% CI 0.67–0.94, P = 0.006) and 1.12 (HR: 1.12, 95% CI 1.01–1.25, P = 0.029). Sensitivity analyses confirmed these results. SC levels around 8.56 mg/dL were associated with the lowest risk of in-hospital mortality, with risks increasing as SC levels deviated from this point. SC levels below this inflection point were linked to more pronounced clinical impacts. This finding has significant clinical implications for clinicians. Therefore, in the treatment of ICU patients with AF, clinicians should closely monitor SC levels, with a focus on maintaining them around 8.56 mg/dL.

show abstract

Advancements in Heart Disease Prediction: A Comprehensive Survey of Logistic Regression and Feature Engineering Techniques Enhanced by Random Forest Algorithm

Srivastava,

Sharma,

Negi

et al. 2024

2024 International Conference on Emerging Innovations and Advanced Computing (INNOCOMP)

View full text Add to dashboard Cite

Machine Learning Methods in Real-World Studies of Cardiovascular Disease

Cited by 6 publications

References 92 publications

Comparative analysis of supervised learning algorithms for prediction of cardiovascular diseases

Comparative analysis of supervised learning algorithms for prediction of cardiovascular diseases

Association between serum calcium and in-hospital mortality in critically ill atrial fibrillation patients from the MIMIC IV database

Advancements in Heart Disease Prediction: A Comprehensive Survey of Logistic Regression and Feature Engineering Techniques Enhanced by Random Forest Algorithm

Contact Info

Product

Resources

About