Improving non-invasive hemoglobin measurement accuracy using nonparametric models

Man, Jianing; Zielinski, Martin D.; Das, Devashish; Wutthisirisart, Phichet; Pasupathy, Kalyan S.

doi:10.1016/j.jbi.2021.103975

Cited by 6 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proportion of agreement failure and 95% CI adjusted for repeated measurements will be calculated 64. This will also be done using two other reference standards for agreement as a secondary analysis, being an allowable difference of ±10 g/L often used in similar studies based on expert opinion and an allowable difference of ±7%, based on guidelines by the Clinical Laboratory Improvement Amendments of 1988 41 42 65–71…”

Section: Methodsmentioning

confidence: 99%

Point-of-care haemoglobin accuracy and transfusion outcomes in non-cardiac surgery at a Canadian tertiary academic hospital: protocol for the PREMISE observational study

Brousseau,

Monette,

McIsaac

et al. 2023

BMJ Open

View full text Add to dashboard Cite

IntroductionTransfusions in surgery can be life-saving interventions, but inappropriate transfusions may lack clinical benefit and cause harm. Transfusion decision-making in surgery is complex and frequently informed by haemoglobin (Hgb) measurement in the operating room. Point-of-care testing for haemoglobin (POCT-Hgb) is increasingly relied on given its simplicity and rapid provision of results. POCT-Hgb devices lack adequate validation in the operative setting, particularly for Hgb values within the transfusion zone (60–100 g/L). This study aims to examine the accuracy of intraoperative POCT-Hgb instruments in non-cardiac surgery, and the association between POCT-Hgb measurements and transfusion decision-making.Methods and analysisPREMISE is an observational prospective method comparison study. Enrolment will occur when adult patients undergoing major non-cardiac surgery require POCT-Hgb, as determined by the treating team. Three concurrent POCT-Hgb results, considered as index tests, will be compared with a laboratory analysis of Hgb (lab-Hgb), considered the gold standard. Participants may have multiple POCT-Hgb measurements during surgery. The primary outcome is the difference in individual Hgb measurements between POCT-Hgb and lab-Hgb, primarily among measurements that are within the transfusion zone. Secondary outcomes include POCT-Hgb accuracy within the entire cohort, postoperative morbidity, mortality and transfusion rates. The sample size is 1750 POCT-Hgb measurements to obtain a minimum of 652 Hgb measurements <100 g/L, based on an estimated incidence of 38%. The sample size was calculated to fit a logistic regression model to predict instances when POCT-Hgb are inaccurate, using 4 g/L as an acceptable margin of error.Ethics and disseminationInstitutional ethics approval has been obtained by the Ottawa Health Science Network—Research Ethics Board prior to initiating the study. Findings from this study will be published in peer-reviewed journals and presented at relevant scientific conferences. Social media will be leveraged to further disseminate the study results and engage with clinicians.

show abstract

Section: Methodsmentioning

confidence: 99%

Point-of-care haemoglobin accuracy and transfusion outcomes in non-cardiac surgery at a Canadian tertiary academic hospital: protocol for the PREMISE observational study

Brousseau,

Monette,

McIsaac

et al. 2023

BMJ Open

View full text Add to dashboard Cite

show abstract

“…This not only poses challenges in emergency or mobile medical settings where rapid assessment is crucial but also limits the frequency of testing due to the discomfort and risk of infection associated with invasive procedures. The quest for non-invasive alternatives has led to the development of non-invasive techniques to gauge hemoglobin levels [ 1 , 2 ], including pulse oximetry and spectrophotometry. These methods, which measure oxygen saturation and the absorption of light by hemoglobin respectively, however, come with their limitations.…”

Section: Introductionmentioning

confidence: 99%

Real-time non-invasive hemoglobin prediction using deep learning-enabled smartphone imaging

Chen,

Hu,

Zhu

et al. 2024

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Accurate measurement of hemoglobin concentration is essential for various medical scenarios, including preoperative evaluations and determining blood loss. Traditional invasive methods are inconvenient and not suitable for rapid, point-of-care testing. Moreover, current models, due to their complex parameters, are not well-suited for mobile medical settings, which limits the ability to conduct frequent and rapid testing. This study aims to introduce a novel, compact, and efficient system that leverages deep learning and smartphone technology to accurately estimate hemoglobin levels, thereby facilitating rapid and accessible medical assessments. Methods The study employed a smartphone application to capture images of the eye, which were subsequently analyzed by a deep neural network trained on data from invasive blood test data. Specifically, the EGE-Unet model was utilized for eyelid segmentation, while the DHA(C3AE) model was employed for hemoglobin level prediction. The performance of the EGE-Unet was evaluated using statistical metrics including mean intersection over union (MIOU), F1 Score, accuracy, specificity, and sensitivity. The DHA(C3AE) model’s performance was assessed using mean absolute error (MAE), mean-square error (MSE), root mean square error (RMSE), and R^2. Results The EGE-Unet model demonstrated robust performance in eyelid segmentation, achieving an MIOU of 0.78, an F1 Score of 0.87, an accuracy of 0.97, a specificity of 0.98, and a sensitivity of 0.86. The DHA(C3AE) model for hemoglobin level prediction yielded promising outcomes with an MAE of 1.34, an MSE of 2.85, an RMSE of 1.69, and an R^2 of 0.34. The overall size of the model is modest at 1.08 M, with a computational complexity of 0.12 FLOPs (G). Conclusions This system presents a groundbreaking approach that eliminates the need for supplementary devices, providing a cost-effective, swift, and accurate method for healthcare professionals to enhance treatment planning and improve patient care in perioperative environments. The proposed system has the potential to enable frequent and rapid testing of hemoglobin levels, which can be particularly beneficial in mobile medical settings. Trial Registration The clinical trial was registered on the Chinese Clinical Trial Registry (No. ChiCTR2100044138) on 20/02/2021.

show abstract

“…According to the model form, the identified system models can be divided into two categories: parametric models and non-parametric models. The so-called parametric model refers to mathematical models in the form of differential equations, difference equations, and state equations; nonparametric models refer to mathematical models with implicit parameters such as frequency response, impulse response, and transfer function [ 16 , 17 ].…”

Section: Introductionmentioning

confidence: 99%

Estimation and Identification of Nonlinear Parameter of Motion Index Based on Least Squares Algorithm

Qin

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Parameter identification is an important branch of automatic control. Due to its special function, it has been widely used in various fields, especially the modeling of complex systems or systems whose parameters are not easy to determine. With the development of control technology, the scale of the control object is getting larger and larger, which makes the calculation amount of the identification algorithm larger and larger. For the nonlinear system with complex structure, especially the nonlinear system containing the product of unknown parameters, the number of parameters of the over-parameterized identification method increases greatly, and the calculation amount of the identification algorithm also increases sharply. Therefore, a parameter estimation method with a small amount of calculation is explored. The results show that the proposed method can overcome the phenomenon of “data saturation”, thus improving the parameter identification results.

show abstract

Improving non-invasive hemoglobin measurement accuracy using nonparametric models

Cited by 6 publications

References 24 publications

Point-of-care haemoglobin accuracy and transfusion outcomes in non-cardiac surgery at a Canadian tertiary academic hospital: protocol for the PREMISE observational study

Point-of-care haemoglobin accuracy and transfusion outcomes in non-cardiac surgery at a Canadian tertiary academic hospital: protocol for the PREMISE observational study

Real-time non-invasive hemoglobin prediction using deep learning-enabled smartphone imaging

Estimation and Identification of Nonlinear Parameter of Motion Index Based on Least Squares Algorithm

Contact Info

Product

Resources

About