Machine learning of blood haemoglobin and haematocrit levels via smartphone conjunctiva photography in Kenyan pregnant women: a clinical study protocol.

Journal: BMJ open
PMID: 40345683

Abstract

INTRODUCTION: Anaemia during pregnancy is a widespread health burden globally, especially in low- and middle-income countries, posing a serious risk to both maternal and neonatal health. The primary challenge is that anaemia is frequently undetected or is detected too late, worsening pregnancy complications. The gold standard for diagnosing anaemia is a clinical laboratory blood haemoglobin (Hgb) or haematocrit (Hct) test involving a venous blood draw. However, this approach presents several challenges in resource-limited settings regarding accessibility and feasibility. Although non-invasive blood Hgb testing technologies are gaining attention, they remain limited in availability, affordability and practicality. This study aims to develop and validate a mobile health (mHealth) machine learning model to reliably predict blood Hgb and Hct levels in Black African pregnant women using smartphone photos of the conjunctiva.

Authors

  • Haripriya Sakthivel
    Weldon School of Biomedical Engineering, Purdue University, West Lafayette, Indiana, USA.
  • Sang Mok Park
    Weldon School of Biomedical Engineering, Purdue University, West Lafayette, Indiana, USA.
  • Semin Kwon
    Weldon School of Biomedical Engineering, Purdue University, West Lafayette, Indiana, USA.
  • Eunice Kaguiri
    Academic Model Providing Access to Healthcare, Eldoret, Kenya.
  • Elizabeth Nyaranga
    Academic Model Providing Access to Healthcare, Eldoret, Kenya.
  • Jung Woo Leem
    Weldon School of Biomedical Engineering, Purdue University, West Lafayette, Indiana, USA.
  • Shaun G Hong
    Weldon School of Biomedical Engineering, Purdue University, West Lafayette, Indiana, USA.
  • Peter J Lane
    Vanderbilt Institute for Global Health, Vanderbilt University Medical Center, Nashville, Tennessee, USA.
  • Edwin O Were
    Academic Model Providing Access to Healthcare, Eldoret, Kenya eowere@mu.ac.ke martin.c.were@vumc.org youngkim@purdue.edu.
  • Martin C Were
    Vanderbilt Institute for Global Health, Vanderbilt University Medical Center, Nashville, Tennessee, USA eowere@mu.ac.ke martin.c.were@vumc.org youngkim@purdue.edu.
  • Young L Kim
    Weldon School of Biomedical Engineering, Purdue University, West Lafayette, Indiana, USA eowere@mu.ac.ke martin.c.were@vumc.org youngkim@purdue.edu.

Keywords

External Resources

Popular Topics
Recent Journals