A Novel Technique for Non-Invasive Measurement of Human Blood Component Levels From Fingertip Video Using DNN Based Models

Abstract

Blood components such as hemoglobin, glucose, creatinine measuring are essential for monitoring one's health condition. The current blood component measurement approaches still depend on invasive techniques that are painful, and uncomfortable for the patients. To facilitate measurement at home, we proposed a novel non-invasive technique to measure blood hemoglobin, glucose, and creatinine level based on PPG signal using Deep Neural Networks (DNN). Fingertip videos from 93 subjects have been collected using a smartphone. The PPG signal is generated from each video, and 46 characteristic features are then extracted from the PPG signal, its derivatives (1 st and 2 nd ) and from Fourier analysis. Additionally, age and gender are also included to feature because of the significant effects on hemoglobin, glucose, and creatinine. A correlation-based feature selection (CFS) using genetic algorithms (GA) has been used to select the optimal features to avoid redundancy and over-fitting. Finally, DNN based models have been developed to estimate the blood Hemoglobin (Hb), Glucose (Gl), and Creatinine (Cr) levels from the selected features. The approach provides the best-estimated accuracy of R 2 = 0.922 for Hb, R 2 = 0.902 for Gl, and R 2 = 0.969 for Cr. Experimental aftermaths show that the proposed method is a suitable technique to be used clinically to measure human blood component levels without taking blood samples. This paper also reveals that smartphone-based PPG signal has a great potential to measure the different blood components.

Development of sensor system and data analytic framework for non-invasive blood glucose prediction

“…A source and detector at 850 nm for Hb, 950 nm for blood glucose, and 1150 nm for Cr were employed. A Deep Neural Network (DNN) is applied, which achieved an accuracy of 90.2% for blood glucose, 92.2% for hemoglobin, and 96.9% for creatinine 30 . The process of detecting blood glucose is a major limitation as it is non-portable, and deploying the application on different mobile phones can lead to errors in readings owing to different camera resolutions.…”

“… The proposed methodologies have a high MAE/MARD/prediction error, which makes the device non-replicable using invasive or minimally invasive methods. The devices have been tested on normal patients 25 , 28 , 30 , 33 , non-diabetic patients with chronic health disorders 24 , 29 , and a few diabetic patients 26 , 27 , 31 , 32 . The cost of the developed prototypes in the existing literature is estimated from a minimum of $100 to $300, which is not suitable for continuous monitoring of blood glucose, is non-portable, and is non-reliable with a higher error in predictions.…”

A Novel Technique for Continuous Blood Pressure Estimation from Optimal Feature Set of PPG Signal Using Deep Learning Approach

“…Recent advances in sensor technology have made it possible to monitor physiological parameters unobtrusively anywhere, anytime [7,8,9]. In this regard, photoplethysmogram (PPG) signal is crucial for the assessment of vital health-related factors without a reference signal and clinical condition [10].…”

“…In this regard, photoplethysmogram (PPG) signal is crucial for the assessment of vital health-related factors without a reference signal and clinical condition [10]. PPG is a simple, low cost optical technique having the ability to detect the variations in blood volume in the microvascular bed of tissue with each cardiac cycle [9]. A typical two-pulse PPG signal with its characteristic points is depicted in Fig.…”

Corrections to “A Novel Technique for Non-Invasive Measurement of Human Blood Component Levels From Fingertip Video Using DNN Based Models”

“…

In the above article [1], the details of the data collection source and data collection protocol were not included.

…”