An official website of the United States government
Diagnosis of anemia relies on the detection of hemoglobin levels in a blood sample. Conventional blood analyzers are not readily available in most low-resource regions where anemia is prevalent, so detection methods that are low-cost and point-of-care are needed. Here, we present a microfluidic approach to measure hemoglobin concentration in a sample of whole blood. Unlike conventional approaches, our microfluidic approach does not require hemolysis. We detect the level of hemoglobin in a blood sample optically by illuminating the blood in a microfluidic channel at a peak wavelength of 540 nm and measuring its absorbance using a CMOS sensor coupled with a lens to magnify the image onto the detector. We compare measurements in microchannels with channel heights of 50 and 115 μm and found the channel with the 50 μm height provided a better range of detection. Since we use whole blood and not lysed blood, we fit our data to an absorption model that includes optical scattering in order to obtain a calibration curve for our system. Based on this calibration curve and data collected, we can measure hemoglobin concentration within 1 g/dL for severe cases of anemia. In addition, we measured optical density for blood flowing at a shear rate of 500 s-1 and observed it did not affect the nonlinear model. With this method, we provide an approach that uses microfluidic detection of hemoglobin levels that can be integrated with other microfluidic approaches for blood analysis.
more »
« less
Using Monte Carlo simulated PPGs signals to train a deep learning model to predict hemoglobin levels
Measuring Hemoglobin (Hb) levels is required for the assessment of different health conditions, such as anemia, a condition where there are insufficient healthy red blood cells to carry enough oxygen to the body's tissues. Measuring Hb levels requires the extraction of a blood sample, which is then sent to a laboratory for analysis. This is an invasive procedure that may add challenges to the continuous monitoring of Hb levels. Noninvasive techniques, including imaging and photoplethysmography (PPG) signals combined with machine learning techniques, are being investigated for continuous measurements of Hb. However, the availability of real data to train the algorithms is limited to establishing a generalization and implementation of such techniques in healthcare settings. In this work, we present a computational model based on Monte Carlo simulations that can generate multispectral PPG signals that cover a broad range of Hb levels. These signals are then used to train a Deep Learning (DL) model to estimate hemoglobin levels. Through this approach, valuable insights about the relationships between PPG signals, oxygen saturation, and Hb levels are learned by the DL model. The signals were generated by propagating a source in a volume that contains the skin tissue properties and the target physiological parameters. The source consisted of plane waves using the 660 nm and 890 nm wavelengths. A range of 6 g/dL to 18 dL Hb values was used to generate 468 PPGs to train a Convolutional Neural Network (CNN). The initial results show high accuracy in detecting low levels of Hb. To the best of our knowledge, the complexity of biological interactions involved in measuring hemoglobin levels has yet to be fully modeled. The presented model offers an alternative approach to studying the effects of changes in Hb levels on the PPGs signal morphology and its interaction with other physiological parameters that are present in the optical path of the measured signals.
more »
« less
- Award ID(s):
- 1750970
- PAR ID:
- 10513265
- Editor(s):
- Volpe, Giovanni; Pereira, Joana B; Brunner, Daniel; Ozcan, Aydogan
- Publisher / Repository:
- SPIE
- Date Published:
- Journal Name:
- SPIE NANOSCIENCE + ENGINEERING | 20-25 AUGUST 2023 Emerging Topics in Artificial Intelligence (ETAI) 2023
- ISBN:
- 9781510665248
- Page Range / eLocation ID:
- 18
- Format(s):
- Medium: X
- Location:
- San Diego, United States
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
ABSTRACT Cave‐dwelling animals thrive in isolated caves despite the pressures of darkness, starvation, and reduced oxygen. Prior work revealed thatAstyanaxcave‐dwelling morphs derived from different cave localities express significantly higher levels of blood hemoglobin compared to surface‐dwelling fish. Interestingly, this elevation is maintained in different populations of cavefish, despite captive rearing in normal oxygen conditions. We capitalized on the consistent response of elevated hemoglobin in captive cavefish, which were derived from geographically distinct regions, to determine if this elevation is underpinned by expression of the sameHbgenes. Blood hemoglobin proteins are encoded by a large family ofhemoglobin(Hb) gene family members, which demonstrate coordinated expression patterns, subject to various organismal (e.g., period of life history) and environmental influences (e.g., oxygen availability). Surprisingly, we found that geographically distinct populations showed mostly divergent patterns ofHbgene expression. Cavefish from two cave localities, Pachón and Tinaja, have a more recent shared origin, and show more similarHbexpression patterns as adults. However, during embryonic phases, Pachón and Tinaja show significant variability in timing of peak expression ofHbfamily members. In sum, the transcriptomic underpinnings ofHbgene expression represents a complex composite of shared and divergent expression patterns across three captive cavefish populations. We conclude that these differential patterns are likely influenced by life history, and the unique cave conditions in which these animals evolved.more » « less
-
As part of the PI's outreach, a course-based undergraduate research experience engaged undergraduate women in research from examining the literature to identify a gap, formulating a research hypothesis, designing experiments to test the hypothesis, analyzing the data, writing and submitting an abstract and presenting the research to the scientific community. This project was as follows: in the US, 5 million people require blood transfusions each year. Although generally safe, there are drawbacks to blood transfusions including fever, acute immune or delayed hemolytic reactions, anaphylactic reactions, transfusion related acute lung injury, and bloodborne infections. Despite screening for diseases such as HIV and hepatitis, the risk of contraction is nonzero, and there are continually emerging bloodborne diseases such as Zika that are not yet screened for. Additionally, there are often blood bank shortages. These complications have driven decades of research into artificial blood, yet to date there are no blood substitutes clinically available. While hemoglobin based oxygen carriers have shown promise, they also show oxidative damage to tissues, particularly in cardiac and renal tissues. Both high and low oxygen PEGylated hemoglobin (Hb) have shown such oxidative stress. We hypothesized that this oxidative stress was due to direct delivery of the PEGylated Hb and conjugated PEGylated Hb onto PEG hydrogel microspheres. In this study, we probed the ability of the Hb microspheres to deliver oxygen.more » « less
-
null (Ed.)Spectral unmixing techniques for photoacoustic images are often used to isolate signal origins (e.g., blood, contrast agents, lipids). However, these techniques often require many (e.g., 12–59) wavelength transmissions for optimal performance to exploit the optical properties of different biological chromophores. Analysis of the acoustic frequency response of photoacoustic signals has the potential to provide additional discrimination of photoacoustic signals from different materials, with the added benefit of potentially requiring only a few optical wavelength emissions. This study presents our initial results testing this hypothesis in a phantom experiment, given the task of differentiating photoacoustic signals from deoxygenated hemoglobin (Hb) and methylene blue (MB). Coherence-based beamforming, principal component analysis, and nearest neighbor classification were employed to determine ground-truth labels, perform feature extraction, and classify image contents, respectively. The mean ± one standard deviation of classification accuracy was increased from 0.65 ± 0.16 to 0.88 ± 0.17 when increasing the number of wavelength emissions from one to two, respectively. When using an optimal laser wavelength pair of 710–870 nm, the sensitivity and specificity of detecting MB over Hb were 1.00 and 1.00, respectively. Results are highly promising for the differentiation of photoacoustic-sensitive materials with comparable performance to that achieved with more conventional multispectral laser wavelength approaches.more » « less
-
Sepsis is a severe medical illness with over 1.7 million cases reported each year in the United States. Early diagnosis of sepsis is cr- tical to adress adecuate tre remains a major challenge in healthcare due to the nonspecificity of the initial symptoms and the lack of currently available biomarkers that demonstrate sufficient specificity or sensitiv- ity suitable for clinical practice. Wearable optical technologies, such as photoplethysmography (PPG), whic uses optical technology to measure changes in blood volume in peripheral tissues, enabling continuous mon- itoring. Identifying modest physiological changes that indicate sepsis can be challenging since they occur without a body reaction. Deep Learning (DL) models can help overcome the diagnostic gap in sepsis diagnosis and intervention. This study analyzes sepsis-related characteristics in PPG signals utilizing a collection of waveform records from both sepsis and control cases. The proposed model consists of five layers: input sequence, long short-term memory (LSTM), fully-connected, softmax, and classi- fication. The LSTM layer is chosen to extract and filter features from cycles of PPG signals; then, the features pass through a fully-connected layer to be classified. We tested our LSTM-based model on 915 one- second intervals to identify and classify sepsis severity. Our LSTM-based model accurately detected sepsis (91.30% for training and 89.74% for testing). The sepsis severity categorization achieved an accuracy of 85.9% in training and 81.4% in testing. Multiple training attempts were con- ducted to validate the model’s detecting capabilities. Preliminary results show that a deep learning model utilizing an LSTM layer can detect and categorize sepsis using PPG data, potentially allowing for real-time diagnosis and monitoring within a single cycle.more » « less
