Testing Optical Character Recognition of Home Blood Pressure Measurements, a Randomized Trial

A J Strom; E Khader; P M Polgreen; S L Francis; A M Segre; T Herman; L M Antes; A R Karanikolas; L A Polgreen

doi:10.1093/ajh/hpaf227

Back

Testing Optical Character Recognition of Home Blood Pressure Measurements, a Randomized Trial

Journal article

Open access

Peer reviewed

Testing Optical Character Recognition of Home Blood Pressure Measurements, a Randomized Trial

A J Strom, E Khader, P M Polgreen, S L Francis, A M Segre, T Herman, L M Antes, A R Karanikolas and L A Polgreen

American journal of hypertension, Vol.39(6), pp.744-749

06/01/2026

DOI: 10.1093/ajh/hpaf227

PMCID: PMC13101530

PMID: 41258999

Appears in UI Libraries Support Open Access

Files and links (1)

url

https://doi.org/10.1093/ajh/hpaf227View

Published (Version of record) Open Access

Abstract

Diagnosing hypertension typically requires repeated blood pressure (BP) readings taken over multiple days, but obtaining accurate BP measurements from patients at home is known to be challenging, at least in part due to failure to accurately report those measurements. Here, we evaluate two low-cost electronic reporting strategies, text messaging and a novel image-based alternative, for acceptability and accuracy. We developed and tested a two-stage optical character recognition (OCR) model to "read" a BP monitor display from patient-provided cellphone photographs. We then conducted a crossover trial to test the accuracy and acceptability of image-based BP reporting with having patients report BP measurements by text messaging. We compared the response rates and values obtained from photo uploads to those from text messages. The majority of the 50 respondents submitted most of the requested data. We received an average of 12/14 texted BP responses and 11.3/14 photo responses from participants. Only 4 participants sent neither text nor photo responses. In addition, our OCR model achieved 98.3% accuracy when "reading" BP values from images of sufficient quality (17.9% were rejected for quality issues), and the average BP reported by subjects did not differ between our text and image-based methods. We were able to successfully "read" BP values from photos of BP monitors sent by participants. Both text messaging and photo uploads of monitor displays appear to be accurate and acceptable approaches for collecting home BP readings.

texting

optical character recognition

Blood pressure

home measurement

UIOWA OA Agreement

Details

Title: Subtitle: Testing Optical Character Recognition of Home Blood Pressure Measurements, a Randomized Trial
Creators: A J Strom - University of Iowa
E Khader - University of Iowa
P M Polgreen - University of Iowa
S L Francis - University of Iowa
A M Segre - University of Iowa
T Herman - University of Iowa
L M Antes - University of Iowa
A R Karanikolas - University of Iowa
L A Polgreen - University of Iowa, Pharmacy Practice and Science
Resource Type: Journal article
Publication Details: American journal of hypertension, Vol.39(6), pp.744-749
DOI: 10.1093/ajh/hpaf227
PMID: 41258999
PMCID: PMC13101530
NLM abbreviation: Am J Hypertens
ISSN: 0895-7061
eISSN: 1941-7225
Publisher: Oxford University Press
Grant note: National Center for Advancing Translational Sciences: UM1TR004403
This project was funded in part by a grant from the National Center for Advancing Translational Sciences, no. UM1TR004403 (to P.M.P., S.L.F., and L.A.P.).
Language: English
Electronic publication date: 11/19/2025
Date published: 06/01/2026
Academic Unit: Infectious Diseases; Epidemiology; Nursing; Pharmacy Practice and Science; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Computer Science; Nephrology; Internal Medicine
Record Identifier: 9985033763302771

Metrics

9 Record Views