Detecting Postpartum Depression Stages in New Mothers: A Comparative Study of Novel LSTM-CNN vs. Random Forest

A Novel long-short term memory with convolutional neural networks (LSTM-CNN) is used to predictpostpartum depression and compared it with Random Forest (RF) Algorithm. Materials and Methods: For thisresearch two groups were taken: The Novel Long-Short Term Memory with Convolutional Neural Networks(LSTM-CNN) and for comparison the Random Forest (RF) Algorithm was considered. After carefulconsideration each with a sample size of 20 to help in this research. Results: The outcomes of the study areshown in the following table (LSTM-CNN). The mean accuracy of the LSTM -CNN is 77.75% and theRandom Forest (RF) Algorithm model is 72.12%, respectively. The significance of the Independent samplet-test is evident with a p-value of 0.04 (p < 0.05), underscoring the statistical significance of the comparisonbetween the LSTM-CNN model and the Random Forest algorithm in the study. Conclusion: The LSTM-CNNtechnique outperformed the Random Forest (RF) Algorithm and other machine learning algorithms in termsof accuracy, and deep learning algorithms have generally showed promise in the prediction of Postpartumdepression.