Potentials and Challenges of Pervasive Sensing in the Intensive Care Unit

Pulse oximetry in pediatric care: Balancing advantages and limitations

BACKGROUND

Pulse oximetry has become a cornerstone technology in healthcare, providing non-invasive monitoring of oxygen saturation levels and pulse rate. Despite its widespread use, the technology has inherent limitations and challenges that must be addressed to ensure accurate and reliable patient care.

AIM

To comprehensively evaluate the advantages, limitations, and challenges of pulse oximetry in clinical practice, as well as to propose recommendations for optimizing its use.

METHODS

A systematic literature review was conducted to identify studies related to pulse oximetry and its applications in various clinical settings. Relevant articles were selected based on predefined inclusion and exclusion criteria, and data were synthesized to provide a comprehensive overview of the topic.

RESULTS

Pulse oximetry offers numerous advantages, including non-invasiveness, real-time feedback, portability, and cost-effectiveness. However, several limitations and challenges were identified, including motion artifacts, poor peripheral perfusion, ambient light interference, and patient-specific factors such as skin pigmentation and hemoglobin variants. Recommendations for optimizing pulse oximetry use include technological advancements, education and training initiatives, quality assurance protocols, and interdisciplinary collaboration.

CONCLUSION

Pulse oximetry is crucial in modern healthcare, offering invaluable insights into patients’ oxygenation status. Despite its limitations, pulse oximetry remains an indispensable tool for monitoring patients in diverse clinical settings. By implementing the recommendations outlined in this review, healthcare providers can enhance the effectiveness, accessibility, and safety of pulse oximetry monitoring, ultimately improving patient outcomes and quality of care.

Building an automated, machine learning-enabled platform for predicting post-operative complications

Objective. In 2019, the University of Florida College of Medicine launched theMySurgeryRiskalgorithm to predict eight major post-operative complications using automatically extracted data from the electronic health record.Approach. This project was developed in parallel with our Intelligent Critical Care Center and represents a culmination of efforts to build an efficient and accurate model for data processing and predictive analytics.Main Results and Significance. This paper discusses how our model was constructed and improved upon. We highlight the consolidation of the database, processing of fixed and time-series physiologic measurements, development and training of predictive models, and expansion of those models into different aspects of patient assessment and treatment. We end by discussing future directions of the model.