<p>The healthcare industry requires advanced data analytics methods for predicting the exact condition of the data since the volume of the data is drastically growing continuously. Predicting the accurate condition of the data in a healthcare environment requires a well-developed data analytics approach since the volume of healthcare data is growing rapidly. Unsupervised ML models, like a clustering approach, help to group similar data. While performing the clustering algorithm individually faces so many problems with various data types and also get troubles with several tasks like adaptability, prediction and scalability. Thus, this paper introduced the combinations of multiple clustering approach to address these existing challenges. Hence, this paper proposed an advanced hybrid ML model that combines the work of K-means and the Gaussian Mixture Model (GMM) to enhance the overall accuracy while clustering the data. To improve the data quality and assure the reliable model input is based on some standard pre-processing steps like normalization, imputation and dimensionality reduction. Moreover, the hybrid ML-based algorithm combines the intrinsic denoising capability at the clustering process, this assists to reduce the outlier and noise without any need of manual cleaning process. The challenges in healthcare data are addressed by the proposed method through performing the non-linear patterns and high-dimensional datasets. The real-time health care dataset is used for validating the hybrid ML algorithm in Python framework and the results indicates the data analytics is enhanced by model improvement and efficiency.</p>