Improving the Quality of Point of Care Diagnostics with Real-Time Machine Learning in Low Literacy LMIC Settings

Valderrama, Camilo E.; Marzbanrad, Faezeh; Stroux, Lisa; Martinez, Boris; Hall-Clifford, Rachel; Liu, Chengyu; Katebi, Nasim; Rohloff, Peter; Clifford, Gari D.

doi:10.1145/3209811.3209815

Cited by 18 publications

(18 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to estimate the FHR, the quality of the 3.75-s window was also assessed and stored for further prepossessing steps. The quality was assessed using the method presented in Valderrama et al ( 2018a ) (see subsection 3.1.3).…”

Section: Methodsmentioning

confidence: 99%

“…The features were fed into a classifier composed of a logistic regression and a multiclass support vector machine to classify the 3.75-s window into good quality, interference, silence, talking in the background, or low signal to noise ratio. More details of the quality assessment method can be found in Valderrama et al (2017Valderrama et al ( , 2018a.…”

Section: Data Inclusion Criteriamentioning

confidence: 99%

See 1 more Smart Citation

A Proxy for Detecting IUGR Based on Gestational Age Estimation in a Guatemalan Rural Population

Valderrama

Marzbanrad

Hall-Clifford

et al. 2020

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

In-utero progress of fetal development is normally assessed through manual measurements taken from ultrasound images, requiring relatively expensive equipment and well-trained personnel. Such monitoring is therefore unavailable in low-and middle-income countries (LMICs), where most of the perinatal mortality and morbidity exists. The work presented here attempts to identify a proxy for IUGR, which is a significant contributor to perinatal death in LMICs, by determining gestational age (GA) from data derived from simple-to-use, low-cost one-dimensional Doppler ultrasound (1D-DUS) and blood pressure devices. A total of 114 paired 1D-DUS recordings and maternal blood pressure recordings were selected, based on previously described signal quality measures. The average length of 1D-DUS recording was 10.43 ± 1.41 min. The min/median/max systolic and diastolic maternal blood pressures were 79/102/121 and 50.5/63.5/78.5 mmHg, respectively. GA was estimated using features derived from the 1D-DUS and maternal blood pressure using a support vector regression (SVR) approach and GA based on the last menstrual period as a reference target. A total of 50 trials of 5-fold cross-validation were performed for feature selection. The final SVR model was retrained on the training data and then tested on a held-out set comprising 28 normal weight and 25 low birth weight (LBW) newborns. The mean absolute GA error with respect to the last menstrual period was found to be 0.72 and 1.01 months for the normal and LBW newborns, respectively. The mean error in the GA estimate was shown to be negatively correlated with the birth weight. Thus, if the estimated GA is lower than the (remembered) GA calculated from last menstruation, then this could be interpreted as a potential sign of IUGR associated with LBW, and referral and intervention may be necessary. The assessment system may, therefore, have an immediate impact if coupled with suitable intervention, such as nutritional supplementation. However, a prospective clinical trial is required to show the efficacy of such a metric in the detection of IUGR and the impact of the intervention.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Data Inclusion Criteriamentioning

confidence: 99%

A Proxy for Detecting IUGR Based on Gestational Age Estimation in a Guatemalan Rural Population

Valderrama

Marzbanrad

Hall-Clifford

et al. 2020

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The removal of features meant feature extraction times were markedly reduced from 1.12 s to 130 ms, and 2.16 s to 120 ms for heart and lung respectively. Real-time processing is less than 400 ms processing time, which is satisfied with both feature-based classifiers and the deep learning model; however, these processing times were achieved with a MacBook Pro [10]. Similar results would be expected if a desktop computer in a hospital setting or phone connected to cloud computing, whereas using phone onboard processing would be slower.…”

Section: Discussionmentioning

confidence: 56%

Real-Time Multi-Level Neonatal Heart and Lung Sound Quality Assessment for Telehealth Applications

et al. 2022

View full text Add to dashboard Cite

In this study, a new method is proposed to assess heart and lung signal quality objectively and automatically on a 5-level scale in real-time, and to assess the effect of signal quality on vital sign estimation. A total of 207 10 s long chest sounds were taken from 119 preterm and full-term babies. Thirty of the recordings from ten subjects were obtained with synchronous vital signs from the Neonatal Intensive Care Unit (NICU). As a reference, seven annotators independently assessed the signal quality. For automatic quality classification, 400 features were extracted from the chest sounds. After feature ranking and selection, class balancing, and hyperparameter optimization, a variety of multi-class and ordinal classification and regression algorithms were trained. Then, heart rate and breathing rate were automatically estimated from the chest sounds. For the deep learning model, YAMNet, a deep convolutional neural network pre-trained on the AudioSet-Youtube corpus for sound classification was used. After modification of the final output layers of the neural network and class balancing, transfer learning was applied to YAMNet for heart and lung signal quality classification. The results of subject-wise leave-one-out cross-validation show that the best-performing models had a balanced accuracy of 56.8% and 51.2% for heart and lung qualities, respectively. The best-performing models for real-time analysis (<200 ms) had a balanced accuracy of 56.7% and 46.3%, respectively. Our experimental results underscore that increasing the signal quality leads to a reduction in vital sign error.

show abstract

“…By observing the frequency components of the 1D-DUS signals, the cut-off frequencies were set to 25 and 600 Hz, corresponding to cardiac oscillations. In addition, the signal quality assessment method presented in (29) was used before processing to exclude low quality recordings. After the quality assessment, each 5 minutes recording was devided into 3.75 seconds and the scalogram was generated using 50 ms Hanning window for better representation of the signal in time and frequency.…”

Section: Methodsmentioning

confidence: 99%

Deep Sequence Learning for Assessing Hypertension in Pregnancy from Doppler Signals

Katebi

Clifford

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Measuring blood pressure during pregnancy is an essential component of antenatal care, and is critical for detecting adverse conditions such as pre-eclampsia. The standard approach for measuring blood pressure is via manual auscultation by a trained expert or via an oscillometric self-inflating cuff. While both methods can provide reasonably accurate blood pressure measurements when used correctly, non-expert use can lead to significant error. Moreover, such techniques are uncomfortable and can cause bruising, pain and consequential resistance to use / low compliance. In this work, we propose a low-cost one-dimensional Doppler-based method for the detection of hypertension in pregnancy. Using a sample of 653 pregnant women of Mayan descent in highland Guatemala, we recorded up to 10 minutes of 1D Doppler data of the fetus, and blood pressure from both arms using an Omron M7 oscillometric cuff. A hierarchical LSTM network with attention mechanism was trained to classify hypertension in pregnancy, producing an area under the receiver-operator curve of 0.94. A projection of the data into lower dimensions indicates hypertensive cases are located at the periphery of the distribution of the output of the distribution. This work presents the first demonstration that blood pressure can be measured using Doppler (without occlusion) and may lead to a novel class of blood pressure monitors which allow rapid blood pressure estimation from multiple body locations. Moreover, the association of the predictor with the fetal blood flow indicates that hypertension in the mother has a significant effect on the fetal blood flow.

show abstract

Improving the Quality of Point of Care Diagnostics with Real-Time Machine Learning in Low Literacy LMIC Settings

Cited by 18 publications

References 29 publications

A Proxy for Detecting IUGR Based on Gestational Age Estimation in a Guatemalan Rural Population

A Proxy for Detecting IUGR Based on Gestational Age Estimation in a Guatemalan Rural Population

Real-Time Multi-Level Neonatal Heart and Lung Sound Quality Assessment for Telehealth Applications

Deep Sequence Learning for Assessing Hypertension in Pregnancy from Doppler Signals

Contact Info

Product

Resources

About