Early Warning of Health Condition and Visual Analytics for Multivariable Vital Signs

Woo, Wai Lok; Koh, Bee Hock David; Gao, Bin; Nwoye, E. O.; Wei, Bo; Dlay, S.S.

doi:10.1145/3398329.3398356

Cited by 3 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work will be focused on analyzing some promising previous approaches like the enhanced k-NN algorithm, which was successfully tested in [70] for biometric recognition, and the gradient boosting algorithm, using other databases like the D1NAMO project [71], which implied the monitoring of 20 healthy subjects and 9 patients by recording their electrocardiograms, breathing, accelerometer signals as well as glucose levels, including more biosensors that provide more variables in real time and thereby improving the accuracy of the glycaemia prediction and extending the PH within the glycemic series, and providing early warning of health monitoring [72].…”

Section: Discussionmentioning

confidence: 99%

A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus

et al. 2021

Self Cite

View full text Add to dashboard Cite

Type 1 diabetes mellitus (DM1) is a metabolic disease derived from falls in pancreatic insulin production resulting in chronic hyperglycemia. DM1 subjects usually have to undertake a number of assessments of blood glucose levels every day, employing capillary glucometers for the monitoring of blood glucose dynamics. In recent years, advances in technology have allowed for the creation of revolutionary biosensors and continuous glucose monitoring (CGM) techniques. This has enabled the monitoring of a subject’s blood glucose level in real time. On the other hand, few attempts have been made to apply machine learning techniques to predicting glycaemia levels, but dealing with a database containing such a high level of variables is problematic. In this sense, to the best of the authors’ knowledge, the issues of proper feature selection (FS)—the stage before applying predictive algorithms—have not been subject to in-depth discussion and comparison in past research when it comes to forecasting glycaemia. Therefore, in order to assess how a proper FS stage could improve the accuracy of the glycaemia forecasted, this work has developed six FS techniques alongside four predictive algorithms, applying them to a full dataset of biomedical features related to glycaemia. These were harvested through a wide-ranging passive monitoring process involving 25 patients with DM1 in practical real-life scenarios. From the obtained results, we affirm that Random Forest (RF) as both predictive algorithm and FS strategy offers the best average performance (Root Median Square Error, RMSE = 18.54 mg/dL) throughout the 12 considered predictive horizons (up to 60 min in steps of 5 min), showing Support Vector Machines (SVM) to have the best accuracy as a forecasting algorithm when considering, in turn, the average of the six FS techniques applied (RMSE = 20.58 mg/dL).

show abstract

Section: Discussionmentioning

confidence: 99%

A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Interpolation methods refer to "best guesses" about missing values using nearby valid data. Common approaches to vital sign interpolation include nearest-neighbor [65], linear interpolation [66], and spline interpolation [67] (Table 3). The accuracy of these methods to estimate missing data is directly related to the length of missing data and the complexity of the approach used.…”

Section: Interpolationmentioning

confidence: 99%

Neonatal NIRS monitoring: recommendations for data capture and review of analytics

2021

View full text Add to dashboard Cite

Brain injury is one of the most consequential problems facing neonates, with many preterm and term infants at risk for cerebral hypoxia and ischemia. To develop effective neuroprotective strategies, the mechanistic basis for brain injury must be understood. The fragile state of neonates presents unique research challenges; invasive measures of cerebral blood flow and oxygenation assessment exceed tolerable risk profiles. Near-infrared spectroscopy (NIRS) can safely and non-invasively estimate cerebral oxygenation, a correlate of cerebral perfusion, offering insight into brain injury-related mechanisms. Unfortunately, lack of standardization in device application, recording methods, and error/artifact correction have left the field fractured. In this article, we provide a framework for neonatal NIRS research. Our goal is to provide a rational basis for NIRS data capture and processing that may result in better comparability between studies. It is also intended to serve as a primer for new NIRS researchers and assist with investigation initiation.

show abstract

“…With the proliferation of sensors, time series data are now widely available. They are encountered in many real-world applications, such as human activity recognition [ 1 ], identification of epileptic condition [ 2 ], diagnostic of heart diseases [ 3 ], defect detection [ 4 ], and many others [ 5 , 6 ].…”

Section: Introductionmentioning

confidence: 99%

Deep Temporal Convolution Network for Time Series Classification

Koh

Lim

Rahimi

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

A neural network that matches with a complex data function is likely to boost the classification performance as it is able to learn the useful aspect of the highly varying data. In this work, the temporal context of the time series data is chosen as the useful aspect of the data that is passed through the network for learning. By exploiting the compositional locality of the time series data at each level of the network, shift-invariant features can be extracted layer by layer at different time scales. The temporal context is made available to the deeper layers of the network by a set of data processing operations based on the concatenation operation. A matching learning algorithm for the revised network is described in this paper. It uses gradient routing in the backpropagation path. The framework as proposed in this work attains better generalization without overfitting the network to the data, as the weights can be pretrained appropriately. It can be used end-to-end with multivariate time series data in their raw form, without the need for manual feature crafting or data transformation. Data experiments with electroencephalogram signals and human activity signals show that with the right amount of concatenation in the deeper layers of the proposed network, it can improve the performance in signal classification.

show abstract

Early Warning of Health Condition and Visual Analytics for Multivariable Vital Signs

Cited by 3 publications

References 11 publications

A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus

A Comparison of Feature Selection and Forecasting Machine Learning Algorithms for Predicting Glycaemia in Type 1 Diabetes Mellitus

Neonatal NIRS monitoring: recommendations for data capture and review of analytics

Deep Temporal Convolution Network for Time Series Classification

Contact Info

Product

Resources

About