Purpose: In this research, we studied the intricate interplay between demographic indicators and survival rates across various diseases, aiming to address the gap in comprehensive analyses across multiple conditions.
Methodology: Drawing from a dataset encompassing 9105 critically ill patients from five medical centers in the United States [1], admitted between1989-1991 and 1992-1994, our analysis spans eight disease categories. Leveraging techniques such as Cox-proportional hazard models and machine learning algorithms, we explore the influence of socio-economic status, gender, race, and education on survival outcomes.
Findings: Our findings underscore significant demographic disparities in disease survivability, with ethnicity, gender, and education level showing varying impacts across different medical conditions. Notably, Asians exhibit lower hazards for certain diseases but higher hazards for others, while females demonstrate better survival probabilities compared to males. Moreover, individuals with higher education levels tend to have slightly increased hazards for certain conditions.
Unique Contribution to Theory, Practice, and Policy: The call for comparative analyses across multiple diseases using comprehensive datasets marks a pivotal shift in research strategy. It aims to highlight the interplays and shared risk factors across diseases, contributing significantly to the advancement of theoretical frameworks, the refinement of healthcare practices, and the shaping of informed public health policies. This approach seeks to bridge a critical gap in the literature, offering a foundation for interventions designed to enhance disease management and improve population health outcomes comprehensively.