Prevention of delayed diagnosis in congenital heart disease

Delayed diagnosis of critical congenital heart defects predicting risk factors and survival rate in newborns in Beijing: a retrospective study

OBJECTIVE

To assess the prevalence and survival rate of newborns with a delayed diagnosis of critical congenital heart defects (CCHD) in Beijing.

METHODS

This retrospective study analysed data from births between 2010 and 2017 from the Birth Defects Monitoring Network in Beijing. Newborns with CCHD were analysed according to seven categories. Statistical analyses were used to calculate the mortality rate within the first week (days 0-6) after live birth. Multivariate logistic regression analysis of survival was performed to analyse the potential risk factors for newborn mortality.

RESULTS

A total of 1 773 935 perinatal newborns were screened in Beijing and 1851 newborns were diagnosed with CCHD, showing a prevalence of 10.43 per 10 000. Among the total 1851 CCHD patients, the majority (1692 of 1851; 91.41%) were identified through prenatal diagnosis, 104 of 1851 (5.62%) were diagnosed before obstetric discharge/transfer and 55 of 1851 (2.97%) were identified through delayed diagnosis. The prevalence of CCHD in newborns was 1.96 per 10 000 births. Multivariate logistic regression analysis of survival demonstrated that gestational age at delivery was the only risk factor for death within the first week after birth.

CONCLUSIONS

Within the first week after birth, gestational age was the only risk factor for death in newborns with CCHD.

Automatic Evaluation of Heart Condition According to the Sounds Emitted and Implementing Six Classification Methods

The main cause of death in Mexico and the world is heart disease, and it will continue to lead the death rate in the next decade according to data from the World Health Organization (WHO) and the National Institute of Statistics and Geography (INEGI). Therefore, the objective of this work is to implement, compare and evaluate machine learning algorithms that are capable of classifying normal and abnormal heart sounds. Three different sounds were analyzed in this study; normal heart sounds, heart murmur sounds and extra systolic sounds, which were labeled as healthy sounds (normal sounds) and unhealthy sounds (murmur and extra systolic sounds). From these sounds, fifty-two features were calculated to create a numerical dataset; thirty-six statistical features, eight Linear Predictive Coding (LPC) coefficients and eight Cepstral Frequency-Mel Coefficients (MFCC). From this dataset two more were created; one normalized and one standardized. These datasets were analyzed with six classifiers: k-Nearest Neighbors, Naive Bayes, Decision Trees, Logistic Regression, Support Vector Machine and Artificial Neural Networks, all of them were evaluated with six metrics: accuracy, specificity, sensitivity, ROC curve, precision and F1-score, respectively. The performances of all the models were statistically significant, but the models that performed best for this problem were logistic regression for the standardized data set, with a specificity of 0.7500 and a ROC curve of 0.8405, logistic regression for the normalized data set, with a specificity of 0.7083 and a ROC curve of 0.8407, and Support Vector Machine with a lineal kernel for the non-normalized data; with a specificity of 0.6842 and a ROC curve of 0.7703. Both of these metrics are of utmost importance in evaluating the performance of computer-assisted diagnostic systems.