There is a substantial worldwide effect, both in terms of disease and death, that is caused by pediatric pneumonia, which is a disorder that affects children under the age of five. Even while Streptococcus pneumoniae is the most prevalent agent responsible for this sickness, it may also be brought on by other bacteria, viruses, or fungi. An efficient approach utilizing deep-learning methods to forecast pediatric pneumonia reliably using chest X-ray images has been developed. The current study presents an updated version of the DenseNet-121 deep-learning model developed for identifying scans of pediatric pneumonia. The batch normalization, maximum pooling, and dropout layers introduced into the standard model were done so to improve its accuracy. The activations of the preceding layers are scaled and normalized using batch normalization, leading to a mean value of zero and a variance of one. This helps to decrease internal variability during training, which in turn speeds up the training process, promotes model stability, and improves the model’s overall capacity to generalize. Max pooling is a beneficial technique for cutting down on the number of model parameters, making the model more computationally effective. Meanwhile, dropout is a preventative measure against overfitting by decreasing the co-dependence of neurons. As a result, the network acquires more durable and adaptive features. Classifying instances of pediatric pneumonia with the help of the proposed model resulted in an exceptional accuracy rate of 97.03%.

Chronic Kidney Disease (CKD) is a sickness in that the kidney's operation and shape worsens for at least three months. It is one of the non-communicable diseases that remain undetected in the early stages and become life-threatening in the advanced stages. The major risk factors of CKD are hypertension, diabetic nephropathy, age, glomerulonephritis, etc. The kidney function is approximated on the basis of the glomerular filtration rate. Hence, detection of CKD in the early stages is vital to reduce the growth of the disease. This research introduces Nephro Predict, machine learning research concerning building binary models for classification with the aim of determining the occurrence of CKD. Emphasizing hypertension and diabetic nephropathy as two of the key risk factors, we derived hypertension status using diastolic blood pressure thresholds based on European Society of Hypertension (ESH) guidelines using the CKD-KPI equation. These medically grounded features were computed to reflect real-world diagnostic standards. From the original 26 attributes in the UCI CKD dataset, and attributes created by feature engineering, six were selected for model training. Preprocessing included missing value imputation and encoding, followed by stratified K-fold cross-validation and hyperparameter modification. Various ensembling models are trained and evaluated for CKD data set. The decision tree model provides the best precision of 94.2%. Future work involves incorporating deep learning models to improve prediction performance.