An XGBoost-based model for assessment of aortic stiffness from wrist photoplethysmogram

Li, Yunlong; Xu, Yang; Ma, Zuchang; Ye, Yuqi; Gao, Lei; Sun, Yining

doi:10.1016/j.cmpb.2022.107128

Cited by 8 publications

(6 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies have been using machine learning or deep learning models to estimate the cf-PWV based on PPG or BP signals (Tavallali et al, 2015;Jin et al, 2021;Li et al, 2022). However, a direct comparison between our work and many of the previous studies cannot be made given that these studies use real data for the estimation, in contrast with the in silico data used in this study.…”

Section: Discussionmentioning

confidence: 89%

“…It is important to notice that the model parameters used for the generation of the in silico pulse wave signals were changed with age, allowing the investigation of the effects of aging in the estimation of cf-PWV. Previous studies had demonstrated that there could exist a decrease in the performance of the estimation for high PWV values associated with the sensitivity to variations in the transit time during the cf-PWV estimation (Li et al, 2022;Jin et al, 2021). This same behavior was noticed in this project for some of the models where there is an increase of the error estimation for higher values of cf-PWV (usually higher than 9 m s ), these values are presented for virtual patients between 55 and 75 years old (Charlton et al, 2019).…”

Section: Discussionmentioning

confidence: 99%

“…In this study, feature extraction from a two-dimensional signal representation of the BP and PPG signals improved the estimation accuracy and robustness compared to the original one-dimensional signals' results. Finally, (Li et al, 2022) proposed the cf-PWV prediction based on the XGBoost algorithm using wrist photoplethysmogram (wPPG) signals acquired from wearable devices. Despite the promising results, AI-based algorithms are not yet reliable and require improvements in terms of accuracy but also in terms of the universality of the algorithms, which refers to the fact that they can perform well for data that have not been considered in the training of the machine learning model.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A learning-based image processing approach for pulse wave velocity estimation using spectrogram from peripheral pulse wave signals: An in silico study

Vargas

Bahloul²,

Laleg‐Kirati³

2023

Front. Physiol.

View full text Add to dashboard Cite

Carotid-to-femoral pulse wave velocity (cf-PWV) is considered a critical index to evaluate arterial stiffness. For this reason, estimating Carotid-to-femoral pulse wave velocity (cf-PWV) is essential for diagnosing and analyzing different cardiovascular diseases. Despite its broader adoption in the clinical routine, the measurement process of carotid-to-femoral pulse wave velocity is considered a demanding task for clinicians and patients making it prone to inaccuracies and errors in the estimation. A smart non-invasive, and peripheral measurement of carotid-to-femoral pulse wave velocity could overcome the challenges of the classical assessment process and improve the quality of patient care. This paper proposes a novel methodology for the carotid-to-femoral pulse wave velocity estimation based on the use of the spectrogram representation from single non-invasive peripheral pulse wave signals [photoplethysmography (PPG) or blood pressure (BP)]. This methodology was tested using three feature extraction methods based on the semi-classical signal analysis (SCSA) method, the Law’s mask for texture energy extraction, and the central statistical moments. Finally, each feature method was fed into different machine learning models for the carotid-to-femoral pulse wave velocity estimation. The proposed methodology obtained an $R2\geq0.90$ for all the peripheral signals for the noise-free case using the MLP model, and for the different noise levels added to the original signal, the SCSA-based features with the MLP model presented an $R2\geq0.91$ for all the peripheral signals at the level of noise. These results provide evidence of the capacity of spectrogram representation for efficiently assessing the carotid-to-femoral pulse wave velocity estimation using different feature methods. Future work will be done toward testing the proposed methodology for in-vivo signals.

show abstract

Section: Discussionmentioning

confidence: 89%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A learning-based image processing approach for pulse wave velocity estimation using spectrogram from peripheral pulse wave signals: An in silico study

Vargas

Bahloul²,

Laleg‐Kirati³

2023

Front. Physiol.

View full text Add to dashboard Cite

show abstract

“…Machine learning models can be widely used in the medical field due to their excellent performance in predicting classification problems ( Choi et al, 2020 ). Therefore, based on six machine learning algorithms, namely, GBM ( Dash et al, 2022 ), LASSO ( Kang et al, 2021 ), XGBoost ( Li et al, 2022a ), SVM ( Zhou, 2022 ), random forest ( Utkin and Konstantinov, 2022 ), and decision trees ( Streeb et al, 2022 ), the DEGs in the comparison pairs of C1 and C2+C3, C2 and C1+C3, and C3 and C1+C2 were comprehensively analyzed, and the characteristic genes were obtained by overlapping analysis. A stepwise regression method was used to further compress the characteristic genes.…”

Section: Methodsmentioning

confidence: 99%

Applying machine learning algorithms to develop a survival prediction model for lung adenocarcinoma based on genes related to fatty acid metabolism

Cong,

Zhao,

Zhang

et al. 2023

Front. Pharmacol.

View full text Add to dashboard Cite

Background: The progression of lung adenocarcinoma (LUAD) may be related to abnormal fatty acid metabolism (FAM). The present study investigated the relationship between FAM-related genes and LUAD prognosis.Methods: LUAD samples from The Cancer Genome Atlas were collected. The scores of FAM-associated pathways from the Kyoto Encyclopedia of Genes and Genomes website were calculated using the single sample gene set enrichment analysis. ConsensusClusterPlus and cumulative distribution function were used to classify molecular subtypes for LUAD. Key genes were obtained using limma package, Cox regression analysis, and six machine learning algorithms (GBM, LASSO, XGBoost, SVM, random forest, and decision trees), and a RiskScore model was established. According to the RiskScore model and clinical features, a nomogram was developed and evaluated for its prediction performance using a calibration curve. Differences in immune abnormalities among patients with different subtypes and RiskScores were analyzed by the Estimation of STromal and Immune cells in MAlignant Tumours using Expression data, CIBERSORT, and single sample gene set enrichment analysis. Patients’ drug sensitivity was predicted by the pRRophetic package in R language.Results: LUAD samples had lower scores of FAM-related pathways. Three molecular subtypes (C1, C2, and C3) were defined. Analysis on differential prognosis showed that the C1 subtype had the most favorable prognosis, followed by the C2 subtype, and the C3 subtype had the worst prognosis. The C3 subtype had lower immune infiltration. A total of 12 key genes (SLC2A1, PKP2, FAM83A, TCN1, MS4A1, CLIC6, UBE2S, RRM2, CDC45, IGF2BP1, ANGPTL4, and CD109) were screened and used to develop a RiskScore model. Survival chance of patients in the high-RiskScore group was significantly lower. The low-RiskScore group showed higher immune score and higher expression of most immune checkpoint genes. Patients with a high RiskScore were more likely to benefit from the six anticancer drugs we screened in this study.Conclusion: We developed a RiskScore model using FAM-related genes to help predict LUAD prognosis and develop new targeted drugs.

show abstract

“…Modern machine learning (ML) methods offer new possibilities to evaluate large biomedical datasets and develop prediction models. Given its tradition of analysing waveform features, the field of PPG is well suited for these methods ( 12 ), and some previous studies have used ML and finger PPG for the classification of high vs. low cfPWV ( 13 ) and wrist PPG for the estimation of cfPWV ( 14 ). Jang et al also used finger PPG features in linear regression models to predict brachial–ankle PWV ( 15 ).…”

Section: Introductionmentioning

confidence: 99%

Estimation of aortic stiffness by finger photoplethysmography using enhanced pulse wave analysis and machine learning

Hellqvist,

Karlsson,

Hoffman

et al. 2024

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

IntroductionAortic stiffness plays a critical role in the evolution of cardiovascular diseases, but the assessment requires specialized equipment. Photoplethysmography (PPG) and single-lead electrocardiogram (ECG) are readily available in healthcare and wearable devices. We studied whether a brief PPG registration, alone or in combination with single-lead ECG, could be used to reliably estimate aortic stiffness.MethodsA proof-of-concept study with simultaneous high-resolution index finger recordings of infrared PPG, single-lead ECG, and finger blood pressure (Finapres) was performed in 33 participants [median age 44 (range 21–66) years, 19 men] and repeated within 2 weeks. Carotid–femoral pulse wave velocity (cfPWV; two-site tonometry with SphygmoCor) was used as a reference. A brachial single-cuff oscillometric device assessed aortic pulse wave velocity (aoPWV; Arteriograph) for further comparisons. We extracted 136 established PPG waveform features and engineered 13 new with improved coupling to the finger blood pressure curve. Height-normalized pulse arrival time (NPAT) was derived using ECG. Machine learning methods were used to develop prediction models.ResultsThe best PPG-based models predicted cfPWV and aoPWV well (root-mean-square errors of 0.70 and 0.52 m/s, respectively), with minor improvements by adding NPAT. Repeatability and agreement were on par with the reference equipment. A new PPG feature, an amplitude ratio from the early phase of the waveform, was most important in modelling, showing strong correlations with cfPWV and aoPWV (r = −0.81 and −0.75, respectively, both P < 0.001).ConclusionUsing new features and machine learning methods, a brief finger PPG registration can estimate aortic stiffness without requiring additional information on age, anthropometry, or blood pressure. Repeatability and agreement were comparable to those obtained using non-invasive reference equipment. Provided further validation, this readily available simple method could improve cardiovascular risk evaluation, treatment, and prognosis.

show abstract

An XGBoost-based model for assessment of aortic stiffness from wrist photoplethysmogram

Cited by 8 publications

References 64 publications

A learning-based image processing approach for pulse wave velocity estimation using spectrogram from peripheral pulse wave signals: An in silico study

A learning-based image processing approach for pulse wave velocity estimation using spectrogram from peripheral pulse wave signals: An in silico study

Applying machine learning algorithms to develop a survival prediction model for lung adenocarcinoma based on genes related to fatty acid metabolism

Estimation of aortic stiffness by finger photoplethysmography using enhanced pulse wave analysis and machine learning

Contact Info

Product

Resources

About