11th EAI International Conference on Pervasive Computing Technologies for Healthcare

Research Article

A Decision Support System for Home BP Measurements

  • @INPROCEEDINGS{10.1145/3154862.3154891,
        author={Akshay Jain and Mihail Popescu and James Keller and Jeffery Belden and Richelle Koopman and Sonal Patil and Shannon Canfield and Linsey Steege and Victoria Shaffer and Pete Wegier and Kathrene Valentine and Andrew Hathaway},
        title={A Decision Support System for Home BP Measurements},
        proceedings={11th EAI International Conference on Pervasive Computing Technologies for Healthcare},
        publisher={ACM},
        proceedings_a={PERVASIVEHEALTH},
        year={2018},
        month={1},
        keywords={home bp dss linguistic summaries fuzzy rules},
        doi={10.1145/3154862.3154891}
    }
    
  • Akshay Jain
    Mihail Popescu
    James Keller
    Jeffery Belden
    Richelle Koopman
    Sonal Patil
    Shannon Canfield
    Linsey Steege
    Victoria Shaffer
    Pete Wegier
    Kathrene Valentine
    Andrew Hathaway
    Year: 2018
    A Decision Support System for Home BP Measurements
    PERVASIVEHEALTH
    ACM
    DOI: 10.1145/3154862.3154891
Akshay Jain1,*, Mihail Popescu1, James Keller1, Jeffery Belden1, Richelle Koopman1, Sonal Patil1, Shannon Canfield1, Linsey Steege2, Victoria Shaffer1, Pete Wegier1, Kathrene Valentine1, Andrew Hathaway1
  • 1: University of Missouri
  • 2: University of Wisconsin
*Contact email: aj4g2@mail.missouri.edu

Abstract

Wearable and non-wearable sensors are pervasive. However, the health implications of the data they provide is not always clear for the user. In this paper we present a Decision Support System (DSS) that assists a user of a Home Blood Pressure (HBP) monitor to decide timely consultation with a doctor. While HBP is more reliable than office readings, it is more variable due to factors such as food, exercise or error in recording measurements. Our DSS is based on fuzzy rules composed of linguistic summaries of the data. The rules are designed from the current US clinical guidelines and are tuned using an evolutionary algorithm. On a dataset of 40 patients monitored over 3 months, we obtained an interrater agreement of 0.97 between the physicians and DSS trained with their data, while the average agreement between these same physicians was 0.95.