Document Type
Article
Language
eng
Publication Date
12-5-2018
Publisher
American Medical Informatics Association
Source Publication
AMIA Annual Symposium Proceedings
Abstract
Blood hemoglobin level (Hgb) measurement has a vital role in the diagnosis, evaluation, and management of numerous diseases. We describe the use of smartphone video imaging and an artificial neural network (ANN) system to estimate Hgb levels non-invasively. We recorded 10 second-300 frame fingertip videos using a smartphone in 75 adults. Red, green, and blue pixel intensities were estimated for each of 100 area blocks in each frame and the patterns across the 300 frames were described. ANN was then used to develop a model using the extracted video features to predict hemoglobin levels. In our study sample, with patients 20-56 years of age, and gold standard hemoglobin levels of 7.6 to 13.5 g/dL., we observed a 0.93 rank order of correlation between model and gold standard hemoglobin levels. Moreover, we identified specific regions of interest in the video images which reduced the required feature space.
Recommended Citation
Hasan, Md Kamrul; Haque, Md. Munirul; Adib, Riddhiman; Tumpa, Jannatul F.; Begum, Azima; Love, Rechard M.; Kim, Young; and Ahamed, Sheikh Iqbal, "SmartHeLP: Smartphone-based Hemoglobin Level Prediction Using an Artificial Neural Network" (2018). Computer Science Faculty Research and Publications. 5.
https://epublications.marquette.edu/comp_fac/5
Comments
Published version. AMIA Annual Symposium Proceedings. Vol. 2018 (12/5/2018) : 534-544. DOI. © 2018 American Medical Informatics Association.
Md. Munirul Haque and Young L. Kim were affiliated with Purdue University at the time of publication.