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.

Notes on Information Propagation in Noisy Multichannel Data Models: Insights into Sensor Selection and Fusion in Multimodal Biomedical Applications

Multimodality and multichannel monitoring have become increasingly popular and accessible in engineering, Internet of Things, wearable devices, and biomedical applications. In these contexts, given the diverse and complex nature of data modalities, the relevance of sensor fusion and sensor selection is heightened. In this note, we study the problem of channel/modality selection and fusion from an information theoretical perspective, focusing on linear and nonlinear signal mixtures corrupted by additive Gaussian noise. We revisit and extend well-known properties of linear noisy data models in estimation and information theory, providing practical insights that assist in the decision-making process between channel (modality) selection and fusion. Using the notion of multichannel signal-to-noise ratio, we derive conditions under which, selection or fusion of multimodal/multichannel data can be beneficial or redundant. This contributes to a better understanding of how to optimize sensor fusion and selection from a theoretical standpoint, aiming to enhance multimodal/multichannel system design, especially for biomedical multichannel/multimodal applications.

Beyond Convergence: Identifiability of Machine Learning and Deep Learning Models

Machine learning (ML) and deep learning models are extensively used for parameter optimization and regression problems. However, not all inverse problems in ML are ``identifiable,'' indicating that model parameters may not be uniquely determined from the available data and the data model's input-output relationship. In this study, we investigate the notion of model parameter identifiability through a case study focused on parameter estimation from motion sensor data. Utilizing a bipedal-spring mass human walk dynamics model, we generate synthetic data representing diverse gait patterns and conditions. Employing a deep neural network, we attempt to estimate subject-wise parameters, including mass, stiffness, and equilibrium leg length. The results show that while certain parameters can be identified from the observation data, others remain unidentifiable, highlighting that unidentifiability is an intrinsic limitation of the experimental setup, necessitating a change in data collection and experimental scenarios. Beyond this specific case study, the concept of identifiability has broader implications in ML and deep learning. Addressing unidentifiability requires proven identifiable models (with theoretical support), multimodal data fusion techniques, and advancements in model-based machine learning. Understanding and resolving unidentifiability challenges will lead to more reliable and accurate applications across diverse domains, transcending mere model convergence and enhancing the reliability of machine learning models.

A Synthetic Electrocardiogram (ECG) Image Generation Toolbox to Facilitate Deep Learning-Based Scanned ECG Digitization

The electrocardiogram (ECG) is an accurate and widely available tool for diagnosing cardiovascular diseases. ECGs have been recorded in printed formats for decades and their digitization holds great potential for training machine learning (ML) models in algorithmic ECG diagnosis. Physical ECG archives are at risk of deterioration and scanning printed ECGs alone is insufficient, as ML models require ECG time-series data. Therefore, the digitization and conversion of paper ECG archives into time-series data is of utmost importance. Deep learning models for image processing show promise in this regard. However, the scarcity of ECG archives with reference time-series is a challenge. Data augmentation techniques utilizing \textit{digital twins} present a potential solution. We introduce a novel method for generating synthetic ECG images on standard paper-like ECG backgrounds with realistic artifacts. Distortions including handwritten text artifacts, wrinkles, creases and perspective transforms are applied to the generated images, without personally identifiable information. As a use case, we generated an ECG image dataset of 21,801 records from the 12-lead PhysioNet PTB-XL ECG time-series dataset. A deep ECG image digitization model was built and trained on the synthetic dataset, and was employed to convert the synthetic images to time-series data for evaluation. The signal-to-noise ratio (SNR) was calculated to assess the image digitization quality vs the ground truth ECG time-series. The results show an average signal recovery SNR of 27$\pm$2.8\,dB, demonstrating the significance of the proposed synthetic ECG image dataset for training deep learning models. The codebase is available as an open-access toolbox for ECG research.

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.

Electrode Selection for Noninvasive Fetal Electrocardiogram Extraction using Mutual Information Criteria

Blind source separation (BSS) techniques have revealed to be promising approaches for, among other, biomedical signal processing applications. Specifically, for the noninvasive extraction of fetal cardiac signals from maternal abdominal recordings, where conventional filtering schemes have failed to extract the complete fetal ECG components. From previous studies, it is now believed that a carefully selected array of electrodes well-placed over the abdomen of a pregnant woman contains the required `information' for BSS, to extract the complete fetal components. Based on this idea, in previous works array recording systems and sensor selection strategies based on the Mutual Information (MI) criterion have been developed. In this paper the previous works have been extended, by considering the 3-dimensional aspects of the cardiac electrical activity. The proposed method has been tested on simulated and real maternal abdominal recordings. The results show that the new sensor selection strategy together with the MI criterion, can be effectively used to select the channels containing the most `information' concerning the fetal ECG components from an array of 72 recordings. The method is hence believed to be useful for the selection of the most informative channels in online applications, considering the different fetal positions and movements.