Learning from Two Decades of Blood Pressure Data: Demography-Specific Patterns Across 75 Million Patient Encounters

Hypertension remains a global health concern with a rising prevalence, necessitating effective monitoring and understanding of blood pressure (BP) dynamics. This study delves into the wealth of information derived from BP measurement, a crucial approach in informing our understanding of hypertensive trends. Numerous studies have reported on the relationship between BP variation and various factors. In this research, we leveraged an extensive dataset comprising 75 million records spanning two decades, offering a unique opportunity to explore and analyze BP variations across demographic features such as age, race, and gender. Our findings revealed that gender-based BP variation was not statistically significant, challenging conventional assumptions. Interestingly, systolic blood pressure (SBP) consistently increased with age, while diastolic blood pressure (DBP) displayed a distinctive peak in the forties age group. Moreover, our analysis uncovered intriguing similarities in the distribution of BP among some of the racial groups. This comprehensive investigation contributes to the ongoing discourse on hypertension and underscores the importance of considering diverse demographic factors in understanding BP variations. Our results provide valuable insights that may inform personalized healthcare approaches tailored to specific demographic profiles.

Leveraging Large Language Models for Analyzing Blood Pressure Variations Across Biological Sex from Scientific Literature

Hypertension, defined as blood pressure (BP) that is above normal, holds paramount significance in the realm of public health, as it serves as a critical precursor to various cardiovascular diseases (CVDs) and significantly contributes to elevated mortality rates worldwide. However, many existing BP measurement technologies and standards might be biased because they do not consider clinical outcomes, comorbidities, or demographic factors, making them inconclusive for diagnostic purposes. There is limited data-driven research focused on studying the variance in BP measurements across these variables. In this work, we employed GPT-35-turbo, a large language model (LLM), to automatically extract the mean and standard deviation values of BP for both males and females from a dataset comprising 25 million abstracts sourced from PubMed. 993 article abstracts met our predefined inclusion criteria (i.e., presence of references to blood pressure, units of blood pressure such as mmHg, and mention of biological sex). Based on the automatically-extracted information from these articles, we conducted an analysis of the variations of BP values across biological sex. Our results showed the viability of utilizing LLMs to study the BP variations across different demographic factors.

A Survey on Blood Pressure Measurement Technologies: Addressing Potential Sources of Bias

Blood pressure is a vital sign that offers important insights into overall health, particularly cardiovascular well-being. It plays a critical role in medical settings and homes for disease prevention, diagnosis, treatment, and management. Physicians heavily rely on blood pressure values for making crucial decisions. Most commercial devices utilize cuffs for blood pressure measurement, and automatic devices have gained popularity due to the high prevalence of hypertension. Self-measurement and home monitoring of blood pressure are also recommended. However, concerns arise regarding the accuracy of blood pressure measurement technologies and the alignment of reported values with actual values. People often adjust their medication based on these reported values, making accuracy vital. This study focuses on the concept of ``bias'' to highlight potential discrepancies between reported and actual blood pressure values. Previous research has identified biases originating from three categories: (1) blood pressure measurement devices, (2) subject-specific factors, and (3) measurement sessions. Specifically, this study examines biases associated with cuff-based blood pressure technologies due to their widespread use in medical applications and the growing trend of home monitoring. Identifying and addressing the primary sources of biases is crucial to prevent their propagation and mitigate potential consequences. Additionally, the study explores the future prospects of blood pressure monitoring using machine learning methods.