A Personalized Blood Pressure Prediction Model Using Recurrent Kernel Extreme Reservoir Machine

Abrar, Sundus; Tahir, Ghalib Ahmad; Kakudi, Habeebah Adamu; Loo, Chu Kiong

doi:10.1007/978-3-030-12388-8_62

Cited by 2 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, PPG-based prediction is only applicable for a very short time horizon (~10 minutes), while our technique aims to predict BP in a longer time horizon, to provide actionable information to users. In [19] , the 24-hour time series of BP and heart rate were trained with Extreme Learning Machine (ELM) to provide hourly BP prediction. However, the length of collected data in [19] was only a single day, and the prediction performance was not compared with other ML methods.…”

Section: Related Workmentioning

confidence: 99%

“…In [19] , the 24-hour time series of BP and heart rate were trained with Extreme Learning Machine (ELM) to provide hourly BP prediction. However, the length of collected data in [19] was only a single day, and the prediction performance was not compared with other ML methods. The authors in [20] proposed to predict BP using Long Short-Term Memory (LSTM) models [47] with additional contextual data (e.g., age, BMI and BP medication) layer.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Using Wearables and Machine Learning to Enable Personalized Lifestyle Recommendations to Improve Blood Pressure

Chiang

Wong

Dey

2021

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Using Wearables and Machine Learning to Enable Personalized Lifestyle Recommendations to Improve Blood Pressure

Chiang

Wong

Dey

2021

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

show abstract

“…However, PPG-based prediction is only applicable for a very short time horizon (∼10 minutes) while our technique aims to predict BP one day ahead, which provides timely and actionable information to users. In [15], the 24-hour time series of BP and heart rate are trained with Extreme Learning Machine (ELM) to provide hourly BP prediction. However, the sample size in [15] is limited to a single day, and the prediction performance is only compared with other ELM variants.…”

Section: Related Workmentioning

confidence: 99%

“…In [15], the 24-hour time series of BP and heart rate are trained with Extreme Learning Machine (ELM) to provide hourly BP prediction. However, the sample size in [15] is limited to a single day, and the prediction performance is only compared with other ELM variants. The authors in [16] propose to solve the temporal dependency between BP and contextual data by using Long Short-Term Memory (LSTM) models.…”

Section: Related Workmentioning

confidence: 99%

Offline and Online Learning Techniques for Personalized Blood Pressure Prediction and Health Behavior Recommendations

Chiang

Dey

2019

IEEE Access

View full text Add to dashboard Cite

Blood pressure (BP) is one of the essential indicators of human health and highly correlated to health behavior (e.g., exercise and sleep). However, the degree of impact of each health behavior on BP is unknown and may vary significantly between individuals. In this paper, we investigate the relationship between BP and health behavior using data collected from off-the-shelf wearable devices and wireless home BP monitors. We propose a personalized BP model based on random forest (RF), which can predict individual's BP using health behavior and historical BP, and identify the most important factors in predicting an individual's BP. The latter can be used to provide personalized health behavior recommendations to improve and manage BP. We propose RF with Feature Selection (RFFS), which performs RF-based feature selection to enhance the prediction. Furthermore, since BP and health behavior data are collected and learned sequentially, the performance of prediction is prone to the existence of concept drifts and anomaly points. To solve this problem, we propose an Online Weighted-Resampling (OWR) technique to enhance RFFS in an online learning scenario. To show the effectiveness of RFFS and OWR, we use existing machine learning methods on the proposed dataset as a comparison. Our experimental results show that the proposed approach achieves the lowest prediction error. We also validate the effectiveness of personalized recommendations based on feature importance, which influences the user to change lifestyle to improve his/her BP. INDEX TERMS Machine learning, data mining, prediction methods, smart healthcare.

show abstract

A Personalized Blood Pressure Prediction Model Using Recurrent Kernel Extreme Reservoir Machine

Cited by 2 publications

References 27 publications

Using Wearables and Machine Learning to Enable Personalized Lifestyle Recommendations to Improve Blood Pressure

Using Wearables and Machine Learning to Enable Personalized Lifestyle Recommendations to Improve Blood Pressure

Offline and Online Learning Techniques for Personalized Blood Pressure Prediction and Health Behavior Recommendations

Contact Info

Product

Resources

About