Researchers have developed a way to use smartphone images of a person’s eyelids to assess blood haemoglobin levels. The ability to perform one of the most common clinical lab tests without a blood draw could help reduce the need for in-person clinic visits, make it easier to monitor patients who are in critical condition, and improve care in low- and middle-income countries where access to testing laboratories is limited.
“Our new mobile health approach paves the way for bedside or remote testing of blood haemoglobin levels for detecting anaemia, acute kidney injury and haemorrhages, or for assessing blood disorders such as sickle cell anaemia.” said research team leader Young Kim from Purdue University. “The COVID-19 pandemic has greatly increased awareness of the need for expanded mobile health and telemedicine services.”
Kim and colleagues from the University of Indianapolis, Vanderbilt University School of Medicine in the US and Moi University School of Medicine in Kenya were involved in the research.
The researchers used software to transform the built-in camera of a smartphone into a hyperspectral imager that reliably measures haemoglobin levels (a measure of the oxygen-carrying capacity of blood) without the need for any hardware modifications or accessories. A pilot clinical test with volunteers at the Moi University Teaching and Referral Hospital showed that prediction errors for the smartphone technique were within 5 to 10 percent of those measured with clinical laboratory blood.
Kim’s lab focuses on developing healthcare technologies that are first designed and tested in the resource-limited settings of low- and middle-income countries. These innovations are then applied to important health challenges in developed countries such as the US.
“This new technology could be very useful for detecting anaemia, which is characterized by low levels of blood haemoglobin,” said Kim. “This is a major public health problem in developing countries, but can also be caused by cancer and cancer treatments.”
Spectroscopic analysis is commonly used to measure blood haemoglobin content because it has a distinct light absorption spectrum, or fingerprint, in the visible wavelength range. However, this type of analysis typically requires bulky and costly optical components.
The researchers created a mobile health version of this analysis by using an approach known as spectral super-resolution spectroscopy. This technique uses software to virtually convert photos acquired with low-resolution systems such as a smartphone camera into high-resolution digital spectral signals.
The researchers selected the inner eyelid as a sensing site because microvasculature is easily visible there; it is easy to access and has relatively uniform redness. The inner eyelid is also not affected by skin colour, which eliminates the need for any personal calibrations.
To perform a blood haemoglobin measurement with the new technique, the patient pulls down the inner eyelid to expose the small blood vessels underneath. A healthcare professional or trained person then uses the smartphone app developed by the researchers to take pictures of the eyelids. A spectral super-resolution algorithm is applied to extract the detailed spectral information from the camera’s images and then another computational algorithm quantifies the blood haemoglobin content by detecting its unique spectral features.
The mobile app includes several features designed to stabilize smartphone image quality and synchronise the smartphone flashlight to obtain consistent images. It also provides eyelid-shaped guidelines on the screen to ensure that users maintain a consistent distance between the smartphone camera and the patient’s eyelid. Although the spectral information is currently extracted using an algorithm on a separate computer, the researchers expect that the algorithm could be incorporated into the mobile app.
The researchers tested the new technique with 153 volunteers who were referred for conventional blood tests at the Moi University Teaching and Referral Hospital. They used data from a randomly selected group of 138 patients to train the algorithm, then tested the mobile health app with the remaining 15 volunteers. The results showed that the mobile health test could provide measurements comparable to traditional blood tests over a wide range of blood haemoglobin values.
In a separate clinical study, the mobile app is being used to assess oncology patients at the Indiana University Simon Cancer Centre. The researchers are also working with the University of Rwanda to conduct further studies and are planning to partner with the Shrimad Rajchandra Hospital in India to use the mobile health tool to assess nutritional status, anaemia, and sickle cell disease in their patients.
“Our work shows that data-driven and data-centric light-based research can provide new ways to minimise hardware complexity and facilitate mobile health,” says Kim. “Combining the built-in sensors available in today’s smartphones with data-centric approaches can quicken the tempo of innovation and research translation in this area.”
Although blood hemoglobin (Hgb) testing is a routine procedure in a variety of clinical situations, noninvasive, continuous, and real-time blood Hgb measurements are still challenging. Optical spectroscopy can offer noninvasive blood Hgb quantification, but requires bulky optical components that intrinsically limit the development of mobile health (mHealth) technologies. Here, we report spectral super-resolution (SSR) spectroscopy that virtually transforms the built-in camera (RGB sensor) of a smartphone into a hyperspectral imager for accurate and precise blood Hgb analyses. Statistical learning of SSR enables us to reconstruct detailed spectra from three color RGB data. Peripheral tissue imaging with a mobile application is further combined to compute exact blood Hgb content without a priori personalized calibration. Measurements over a wide range of blood Hgb values show reliable performance of SSR blood Hgb quantification. Given that SSR does not require additional hardware accessories, the mobility, simplicity, and affordability of conventional smartphones support the idea that SSR blood Hgb measurements can be used as an mHealth method.
Sang Mok Park, Michelle A Visbal-Onufrak, Munirul Haque, Martin C Were, Violet Naanyu, Md Kamrul Hasan, Young L Kim
The Optical Society material