Rui Cao

Rui Cao

Auto-generated profile, based on publicly available information

Rui Cao

Department of Electrical Engineering and Computer Science, University of California, Irvine, Irvine, CA, United States

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 January 2022 in Journal of Medical Internet Research
Verified
Journal Article
Open access
RCRui Cao
Rui Cao
IAIman Azimi
Iman Azimi
Fatemeh SarhaddiFatemeh Sarhaddi
Fatemeh Sarhaddi
HNHannakaisa Niela-Vilen
Hannakaisa Niela-Vilen
AAAnna Axelin
Anna Axelin
ARAmir Rahmani
Amir Rahmani
Background: Photoplethysmography is a noninvasive and low-cost method to remotely and continuously track vital signs. The Oura Ring is a compact photoplethysmography-based smart ring, which has recently drawn attention to remote health monitoring and wellness applications. The ring is used to acquire nocturnal heart rate (HR) and HR variability (HRV) parameters ubiquitously. However, these parameters are highly susceptible to motion artifacts and environmental noise. Therefore, a validity assessment of the parameters is required in everyday settings. Objective: This study aims to evaluate the accuracy of HR and time domain and frequency domain HRV parameters collected by the Oura Ring against a medical grade chest electrocardiogram monitor. Methods: We conducted overnight home-based monitoring using an Oura Ring and a Shimmer3 electrocardiogram device. The nocturnal HR and HRV parameters of 35 healthy individuals were collected and assessed. We evaluated the parameters within 2 tests, that is, values collected from 5-minute recordings (ie, short-term HRV analysis) and the average values per night sleep. A linear regression method, the Pearson correlation coefficient, and the Bland–Altman plot were used to compare the measurements of the 2 devices. Results: Our findings showed low mean biases of the HR and HRV parameters collected by the Oura Ring in both the 5-minute and average-per-night tests. In the 5-minute test, the error variances of the parameters were different. The parameters provided by the Oura Ring dashboard (ie, HR and root mean square of successive differences [RMSSD]) showed relatively low error variance compared with the HRV parameters extracted from the normal interbeat interval signals. The Pearson correlation coefficient tests (P<.001) indicated that HR, RMSSD, average of normal heart beat intervals (AVNN), and percentage of successive normal beat-to-beat intervals that differ by more than 50 ms (pNN50) had high positive correlations with the baseline values; SD of normal beat-to-beat intervals (SDNN) and high frequency (HF) had moderate positive correlations, and low frequency (LF) and LF:HF ratio had low positive correlations. The HR, RMSSD, AVNN, and pNN50 had narrow 95% CIs; however, SDNN, LF, HF, and LF:HF ratio had relatively wider 95% CIs. In contrast, the average-per-night test showed that the HR, RMSSD, SDNN, AVNN, pNN50, LF, and HF had high positive relationships (P<.001), and the LF:HF ratio had a moderate positive relationship (P<.001). The average-per-night test also indicated considerably lower error variances than the 5-minute test for the parameters. Conclusions: The Oura Ring could accurately measure nocturnal HR and RMSSD in both the 5-minute and average-per-night tests. It provided acceptable nocturnal AVNN, pNN50, HF, and SDNN accuracy in the average-per-night test but not in the 5-minute test. In contrast, the LF and LF:HF ratio of the ring had high error rates in both tests.

5 May 2021 in JMIR mHealth and uHealth
Verified
Journal Article
Open access
SASeyed Amir Hossein Aqajari
Seyed Amir Hossein Aqajari
RCRui Cao
Rui Cao
ENEmad Kasaeyan Naeini
Emad Kasaeyan Naeini
MCMichael-David Calderon
Michael-David Calderon
KZKai Zheng
Kai Zheng
ARAmir Rahmani
Amir Rahmani
Background: Accurate, objective pain assessment is required in the health care domain and clinical settings for appropriate pain management. Automated, objective pain detection from physiological data in patients provides valuable information to hospital staff and caregivers to better manage pain, particularly for patients who are unable to self-report. Galvanic skin response (GSR) is one of the physiologic signals that refers to the changes in sweat gland activity, which can identify features of emotional states and anxiety induced by varying pain levels. This study used different statistical features extracted from GSR data collected from postoperative patients to detect their pain intensity. To the best of our knowledge, this is the first work building pain models using postoperative adult patients instead of healthy subjects. Objective: The goal of this study was to present an automatic pain assessment tool using GSR signals to predict different pain intensities in noncommunicative, postoperative patients. Methods: The study was designed to collect biomedical data from postoperative patients reporting moderate to high pain levels. We recruited 25 participants aged 23-89 years. First, a transcutaneous electrical nerve stimulation (TENS) unit was employed to obtain patients' baseline data. In the second part, the Empatica E4 wristband was worn by patients while they were performing low-intensity activities. Patient self-report based on the numeric rating scale (NRS) was used to record pain intensities that were correlated with objectively measured data. The labels were down-sampled from 11 pain levels to 5 different pain intensities, including the baseline. We used 2 different machine learning algorithms to construct the models. The mean decrease impurity method was used to find the top important features for pain prediction and improve the accuracy. We compared our results with a previously published research study to estimate the true performance of our models. Results: Four different binary classification models were constructed using each machine learning algorithm to classify the baseline and other pain intensities (Baseline [BL] vs Pain Level [PL] 1, BL vs PL2, BL vs PL3, and BL vs PL4). Our models achieved higher accuracy for the first 3 pain models than the BioVid paper approach despite the challenges in analyzing real patient data. For BL vs PL1, BL vs PL2, and BL vs PL4, the highest prediction accuracies were achieved when using a random forest classifier (86.0, 70.0, and 61.5, respectively). For BL vs PL3, we achieved an accuracy of 72.1 using a k-nearest-neighbor classifier. Conclusions: We are the first to propose and validate a pain assessment tool to predict different pain levels in real postoperative adult patients using GSR signals. We also exploited feature selection algorithms to find the top important features related to different pain intensities. International Registered Report Identifier (IRRID): RR2-10.2196/17783

1 September 2018
Verified
Conference Paper
Closed access
STShigeyuki Tateno
Shigeyuki Tateno
XGXia Guan
Xia Guan
RCRui Cao
Rui Cao
ZQZhaoxian Qu
Zhaoxian Qu

27 January 2025 in JMIR Formative Research
Verified
Journal Article
Open access
ASAjan Subramanian
Ajan Subramanian
RCRui Cao
Rui Cao
ENEmad Kasaeyan Naeini
Emad Kasaeyan Naeini
SASeyed Amir Hossein Aqajari
Seyed Amir Hossein Aqajari
THThomas D Hughes
Thomas D Hughes
ARAmir Rahmani
Amir Rahmani
Background: Acute pain management is critical in postoperative care, especially in vulnerable patient populations that may be unable to self-report pain levels effectively. Current methods of pain assessment often rely on subjective patient reports or behavioral pain observation tools, which can lead to inconsistencies in pain management. Multimodal pain assessment, integrating physiological and behavioral data, presents an opportunity to create more objective and accurate pain measurement systems. However, most previous work has focused on healthy subjects in controlled environments, with limited attention to real-world postoperative pain scenarios. This gap necessitates the development of robust, multimodal approaches capable of addressing the unique challenges associated with assessing pain in clinical settings, where factors like motion artifacts, imbalanced label distribution, and sparse data further complicate pain monitoring. Objective: This study aimed to develop and evaluate a multimodal machine learning–based framework for the objective assessment of pain in postoperative patients in real clinical settings using biosignals such as electrocardiogram, electromyogram, electrodermal activity, and respiration rate (RR) signals. Methods: The iHurt study was conducted on 25 postoperative patients at the University of California, Irvine Medical Center. The study captured multimodal biosignals during light physical activities, with concurrent self-reported pain levels using the Numerical Rating Scale. Data preprocessing involved noise filtering, feature extraction, and combining handcrafted and automatic features through convolutional and long-short-term memory autoencoders. Machine learning classifiers, including support vector machine, random forest, adaptive boosting, and k-nearest neighbors, were trained using weak supervision and minority oversampling to handle sparse and imbalanced pain labels. Pain levels were categorized into baseline and 3 levels of pain intensity (1-3). Results: The multimodal pain recognition models achieved an average balanced accuracy of over 80% across the different pain levels. RR models consistently outperformed other single modalities, particularly for lower pain intensities, while facial muscle activity (electromyogram) was most effective for distinguishing higher pain intensities. Although single-modality models, especially RR, generally provided higher performance compared to multimodal approaches, our multimodal framework still delivered results that surpassed most previous works in terms of overall accuracy. Conclusions: This study presents a novel, multimodal machine learning framework for objective pain recognition in postoperative patients. The results highlight the potential of integrating multiple biosignal modalities for more accurate pain assessment, with particular value in real-world clinical settings.

9 September 2022 in PLOS ONE
Verified
Journal Article
Open access
PDF file
RCRui Cao
Rui Cao
ARAmir M. Rahmani
Amir M. Rahmani
Karen LindsayKaren Lindsay
Karen Lindsay
To develop a machine learning algorithm utilizing heart rate variability (HRV) and salivary cortisol to detect the presence of acute stress among pregnant women that may be applied to future clinical research. ECG signals and salivary cortisol were analyzed from 29 pregnant women as part of a crossover study involving a standardized acute psychological stress exposure and a control non-stress condition. A filter-based features selection method was used to identify the importance of different features [heart rate (HR), time- and frequency-domain HRV parameters and salivary cortisol] for stress assessment and reduce the computational complexity. Five machine learning algorithms were implemented to assess the presence of stress with and without salivary cortisol values. On graphical visualization, an obvious difference in heart rate (HR), HRV parameters and cortisol were evident among 17 participants between the two visits, which helped the stress assessment model to distinguish between stress and non-stress exposures with greater accuracy. Eight participants did not display a clear difference in HR and HRV parameters but displayed a large increase in cortisol following stress compared to the non-stress conditions. The remaining four participants did not demonstrate an obvious difference in any feature. Six out of nine features emerged from the feature selection method: cortisol, three time-domain HRV parameters, and two frequency-domain parameters. Cortisol was the strongest contributing feature, increasing the assessment accuracy by 10.3% on average across all five classifiers. The highest assessment accuracy achieved was 92.3%, and the highest average assessment accuracy was 76.5%. Salivary cortisol contributed a significant increase in accuracy of the assessment model compared to using a range of HRV parameters alone. Our machine learning model demonstrates acceptable accuracy in detection of acute stress among pregnant women when combining salivary cortisol with HR and HRV parameters.

26 January 2021 in JMIR Preprints
Verified
Preprint
Open access
RCRui Cao
Rui Cao
IAIman Azimi
Iman Azimi
Fatemeh SarhaddiFatemeh Sarhaddi
Fatemeh Sarhaddi
HNHannakaisa Niela-Vilen
Hannakaisa Niela-Vilen
AAAnna Axelin
Anna Axelin
ARAmir Rahmani
Amir Rahmani
BACKGROUND Photoplethysmography is a noninvasive and low-cost method to remotely and continuously track vital signs. The Oura Ring is a compact photoplethysmography-based smart ring, which has recently drawn attention to remote health monitoring and wellness applications. The ring is used to acquire nocturnal heart rate (HR) and HR variability (HRV) parameters ubiquitously. However, these parameters are highly susceptible to motion artifacts and environmental noise. Therefore, a validity assessment of the parameters is required in everyday settings. OBJECTIVE This study aims to evaluate the accuracy of HR and time domain and frequency domain HRV parameters collected by the Oura Ring against a medical grade chest electrocardiogram monitor. METHODS We conducted overnight home-based monitoring using an Oura Ring and a Shimmer3 electrocardiogram device. The nocturnal HR and HRV parameters of 35 healthy individuals were collected and assessed. We evaluated the parameters within 2 tests, that is, values collected from 5-minute recordings (ie, short-term HRV analysis) and the average values per night sleep. A linear regression method, the Pearson correlation coefficient, and the Bland–Altman plot were used to compare the measurements of the 2 devices. RESULTS Our findings showed low mean biases of the HR and HRV parameters collected by the Oura Ring in both the 5-minute and average-per-night tests. In the 5-minute test, the error variances of the parameters were different. The parameters provided by the Oura Ring dashboard (ie, HR and root mean square of successive differences [RMSSD]) showed relatively low error variance compared with the HRV parameters extracted from the normal interbeat interval signals. The Pearson correlation coefficient tests (P<.001) indicated that HR, RMSSD, average of normal heart beat intervals (AVNN), and percentage of successive normal beat-to-beat intervals that differ by more than 50 ms (pNN50) had high positive correlations with the baseline values; SD of normal beat-to-beat intervals (SDNN) and high frequency (HF) had moderate positive correlations, and low frequency (LF) and LF:HF ratio had low positive correlations. The HR, RMSSD, AVNN, and pNN50 had narrow 95% CIs; however, SDNN, LF, HF, and LF:HF ratio had relatively wider 95% CIs. In contrast, the average-per-night test showed that the HR, RMSSD, SDNN, AVNN, pNN50, LF, and HF had high positive relationships (P<.001), and the LF:HF ratio had a moderate positive relationship (P<.001). The average-per-night test also indicated considerably lower error variances than the 5-minute test for the parameters. CONCLUSIONS The Oura Ring could accurately measure nocturnal HR and RMSSD in both the 5-minute and average-per-night tests. It provided acceptable nocturnal AVNN, pNN50, HF, and SDNN accuracy in the average-per-night test but not in the 5-minute test. In contrast, the LF and LF:HF ratio of the ring had high error rates in both tests.