Machine Learning Approach to Study Social Determinants of Chronic Illness in India: A Comparative Analysis.

BACKGROUND: Several studies on noncommunicable diseases (NCDs) have been carried out worldwide, the basis of most of which is the identification of risk factors-modifiable (or behavioral) and metabolic. Majority of the NCDs are due to sociodemographic factors, lifestyle, and behavior, which can be prevented to a great extent. Thus, it is a health challenge and a necessity to identify such factors of NCDs. OBJECTIVES: The objective is to make a thorough systematic and comparative analysis of diverse machine learning (ML) classifiers and identify the best-performing model to study social determinants of NCDs. MATERIALS AND METHODS: We used data from the Longitudinal Ageing Study in India, and predicted the prevalence of NCDs based on a set of sociodemographic, lifestyle, and behavioral risk factors by conducting a comparative analysis among 25 different algorithms. RESULTS: Evaluating the performance metrics, the random forest model was found to be the most-suited method with 87.9% accuracy and hence chosen as the final model for the analysis. The model's performance was optimized by a hyper-parameter tuning process using grid-search with a 5-fold cross-validation strategy and results suggested that it was able to make accurate predictions on new instances. CONCLUSION: The epidemic of chronic illness cannot be completely addressed without comprehending the social determinants. With advancements in medical and health-care industry, ML has been applied to analyze diseases based on clinical parameters. This work is an attempt by the authors to explore and encourage the use of ML in the field of social epidemiology.

Stain color translation of multi-domain OSCC histopathology images using attention gated cGAN.

Oral Squamous Cell Carcinoma (OSCC) is the most prevalent type of oral cancer across the globe. Histopathology examination is the gold standard for OSCC examination, where stained histopathology slides help in studying and analyzing the cell structures under a microscope to determine the stages and grading of OSCC. One of the staining methods popularly known as H&E staining is used to produce differential coloration, highlight key tissue features, and improve contrast, which makes cell analysis easier. However, the stained H&E histopathology images exhibit inter and intra-variation due to staining techniques, incubation times, and staining reagents. These variations negatively impact computer-aided diagnosis (CAD) and Machine learning algorithm's accuracy and development. A pre-processing procedure called stain normalization must be employed to reduce stain variance's negative impacts. Numerous state-of-the-art stain normalization methods are introduced. However, a robust multi-domain stain normalization approach is still required because, in a real-world situation, the OSCC histopathology images will include more than two color variations involving several domains. In this paper, a multi-domain stain translation method is proposed. The proposed method is an attention gated generator based on a Conditional Generative Adversarial Network (cGAN) with a novel objective function to enforce color distribution and the perpetual resemblance between the source and target domains. Instead of using WSI scanner images like previous techniques, the proposed method is experimented on OSCC histopathology images obtained by several conventional microscopes coupled with cameras. The proposed method receives the L* channel from the L*a*b* color space in inference mode and generates the G(a*b*) channel, which are color-adapted. The proposed technique uses mappings learned during training phases to translate the source domain to the target domain; mapping are learned using the whole color distribution of the target domain instead of one reference image. The suggested technique outperforms the four state-of-the-art methods in multi-domain OSCC histopathological translation, the claim is supported by results obtained after assessment in both quantitative and qualitative ways.