Yihang Jiang

Mr. Yihang Jiang

Duke University, Durham, California, USA
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
20 October 2022 in Sensors
Verified
Journal Article
Open access
PDF file
WWWill Ke Wang
Will Ke Wang
ICIna Chen
Ina Chen
LHLeeor Hershkovich
Leeor Hershkovich
JYJiamu Yang
Jiamu Yang
ASAyush Shetty
Ayush Shetty
Jessilyn DunnJessilyn Dunn
Jessilyn Dunn
Background: Digital clinical measures collected via various digital sensing technologies such as smartphones, smartwatches, wearables, and ingestible and implantable sensors are increasingly used by individuals and clinicians to capture the health outcomes or behavioral and physiological characteristics of individuals. Time series classification (TSC) is very commonly used for modeling digital clinical measures. While deep learning models for TSC are very common and powerful, there exist some fundamental challenges. This review presents the non-deep learning models that are commonly used for time series classification in biomedical applications that can achieve high performance. Objective: We performed a systematic review to characterize the techniques that are used in time series classification of digital clinical measures throughout all the stages of data processing and model building. Methods: We conducted a literature search on PubMed, as well as the Institute of Electrical and Electronics Engineers (IEEE), Web of Science, and SCOPUS databases using a range of search terms to retrieve peer-reviewed articles that report on the academic research about digital clinical measures from a five-year period between June 2016 and June 2021. We identified and categorized the research studies based on the types of classification algorithms and sensor input types. Results: We found 452 papers in total from four different databases: PubMed, IEEE, Web of Science Database, and SCOPUS. After removing duplicates and irrelevant papers, 135 articles remained for detailed review and data extraction. Among these, engineered features using time series methods that were subsequently fed into widely used machine learning classifiers were the most commonly used technique, and also most frequently achieved the best performance metrics (77 out of 135 articles). Statistical modeling (24 out of 135 articles) algorithms were the second most common and also the second-best classification technique. Conclusions: In this review paper, summaries of the time series classification models and interpretation methods for biomedical applications are summarized and categorized. While high time series classification performance has been achieved in digital clinical, physiological, or biomedical measures, no standard benchmark datasets, modeling methods, or reporting methodology exist. There is no single widely used method for time series model development or feature interpretation, however many different methods have proven successful.

12 July 2023 in PLOS Digital Health
Verified
Journal Article
Open access
PDF file
YJYihang Jiang
Yihang Jiang
CSConnor Spies
Connor Spies
JMJustin Magin
Justin Magin
SBSatasuk Joy Bhosai
Satasuk Joy Bhosai
LSLaurie Snyder
Laurie Snyder
Jessilyn DunnJessilyn Dunn
Jessilyn Dunn
Blood oxygen saturation (SpO2) is an important measurement for monitoring patients with acute and chronic conditions that are associated with low blood oxygen levels. While smartwatches may provide a new method for continuous and unobtrusive SpO2 monitoring, it is necessary to understand their accuracy and limitations to ensure that they are used in a fit-for-purpose manner. To determine whether the accuracy of and ability to take SpO2 measurements from consumer smartwatches is different by device type and/or by skin tone, our study recruited patients aged 18–85 years old, with and without chronic pulmonary disease, who were able to provide informed consent. The mean absolute error (MAE), mean directional error (MDE) and root mean squared error (RMSE) were used to evaluate the accuracy of the smartwatches as compared to a clinical grade pulse oximeter. The percent of data unobtainable due to inability of the smartwatch to record SpO2 (missingness) was used to evaluate the measurability of SpO2 from the smartwatches. Skin tones were quantified based on the Fitzpatrick (FP) scale and Individual Typology Angle (ITA), a continuous measure of skin tone. A total of 49 individuals (18 female) were enrolled and completed the study. Using a clinical-grade pulse oximeter as the reference standard, there were statistically significant differences in accuracy between devices, with Apple Watch Series 7 having measurements closest to the reference standard (MAE = 2.2%, MDE = -0.4%, RMSE = 2.9%) and the Garmin Venu 2s having measurements farthest from the reference standard (MAE = 5.8%, MDE = 5.5%, RMSE = 6.7%). There were also significant differences in measurability across devices, with the highest data presence from the Apple Watch Series 7 (88.9% of attempted measurements were successful) and the highest data missingness from the Withings ScanWatch (only 69.5% of attempted measurements were successful). The MAE, RMSE and missingness did not vary significantly across FP skin tone groups, however, there may be a relationship between FP skin tone and MDE (intercept = 0.04, beta coefficient = 0.47, p = 0.04). No statistically significant difference was found between skin tone as measured by ITA and MAE, MDE, RMSE or missingness.

15 September 2021 in Journal of Medical Internet Research
Verified
Journal Article
Open access
MSMobashir Hasan Shandhi
Mobashir Hasan Shandhi
JGJennifer C Goldsack
Jennifer C Goldsack
KRKyle Ryan
Kyle Ryan
ABAlexandra Jeannette Bennion
Alexandra Jeannette Bennion
AKAditya V Kotla
Aditya V Kotla
Jessilyn DunnJessilyn Dunn
Jessilyn Dunn
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Digital clinical measures collected via various digital sensing technologies such as smartphones, smartwatches, wearables, ingestibles, and implantables are increasingly used by individuals and clinicians to capture health outcomes or behavioral and physiological characteristics of individuals. Although academia is taking an active role in evaluating digital sensing products, academic contributions to advancing the safe, effective, ethical, and equitable use of digital clinical measures are poorly characterized. Objective: We performed a systematic review to characterize the nature of academic research on digital clinical measures and to compare and contrast the types of sensors used and the sources of funding support for specific subareas of this research. Methods: We conducted a PubMed search using a range of search terms to retrieve peer-reviewed articles reporting US-led academic research on digital clinical measures between January 2019 and February 2021. We screened each publication against specific inclusion and exclusion criteria. We then identified and categorized research studies based on the types of academic research, sensors used, and funding sources. Finally, we compared and contrasted the funding support for these specific subareas of research and sensor types. Results: The search retrieved 4240 articles of interest. Following the screening, 295 articles remained for data extraction and categorization. The top five research subareas included operations research (research analysis; n=225, 76%), analytical validation (n=173, 59%), usability and utility (data visualization; n=123, 42%), verification (n=93, 32%), and clinical validation (n=83, 28%). The three most underrepresented areas of research into digital clinical measures were ethics (n=0, 0%), security (n=1, 0.5%), and data rights and governance (n=1, 0.5%). Movement and activity trackers were the most commonly studied sensor type, and physiological (mechanical) sensors were the least frequently studied. We found that government agencies are providing the most funding for research on digital clinical measures (n=192, 65%), followed by independent foundations (n=109, 37%) and industries (n=56, 19%), with the remaining 12% (n=36) of these studies completely unfunded. Conclusions: Specific subareas of academic research related to digital clinical measures are not keeping pace with the rapid expansion and adoption of digital sensing products. An integrated and coordinated effort is required across academia, academic partners, and academic funders to establish the field of digital clinical measures as an evidence-based field worthy of our trust.

29 August 2022 in Preprints.org
Verified
Preprint
Open access
PDF file
WWWill Ke Wang
Will Ke Wang
ICIna Chen
Ina Chen
LHLeeor Hershkovich
Leeor Hershkovich
JYJiamu Yang
Jiamu Yang
ASAyush Shetty
Ayush Shetty
Jessilyn DunnJessilyn Dunn
Jessilyn Dunn
Background: Digital clinical measures collected via various digital sensing technologies such as smartphones, smartwatches, wearables, ingestible, and implantable are increasingly used by individuals and clinicians to capture health outcomes or behavioral and physiological characteristics of individuals. Time series classification (TSC) is very commonly used in modeling digital clinical measures. While deep learning models for TSC are very common and powerful, there exist some fundamental challenges. This review presents non-deep learning models commonly used for time series classification in biomedical applications that achieve high performance. Objective: We performed a systematic review to characterize the techniques used in time series classification of digital clinical measures throughout all stages of data processing and model building. Methods: We conducted a literature search on PubMed, and the Institute of Electrical and Electronics Engineers (IEEE), Web of Science, and SCOPUS databases using a range of search terms to retrieve peer-reviewed articles reporting academic research on digital clinical measures in the five year period between June 2016 and June 2021. We identified and categorized research studies based on the types of classification algorithms and sensor input types. Results: We found 452 papers in total from four different databases: PubMed, IEEE, Web of Science Database, and SCOPUS. After removing duplicates and irrelevant papers, 135 articles remained for detailed review and data extraction. Among these, engineered features using time series methods that were subsequently fed into widely-used machine learning classifiers was the most commonly used technique and also most frequently achieved the best performance metrics (77 out of 135 articles). Statistical modeling (24 out of 135 articles) algorithms were the second most common and also second best classification technique. Wavelet-based classification models (8 out of 135 articles) were also common. Electroencephalogram (29 out of 135 articles) was the most common data type used as an input. Accuracy was the most commonly reported performance metric, with 67.65% of articles reporting on accuracy. In this review paper, we provide summaries of signal pre-processing methods, feature engineering and selection methods, time series models, as well as model interpretations. Importantly, we found that about 50% of the papers only report one performance metric, which may result in a skewed view of overall performance. Conclusion: While high time series classification performance has been achieved in digital clinical, physiological, or biomedical measures, no standard benchmark datasets, modeling methods, or reporting methodology exist. There is no single widely used method for time series model development or feature interpretation– many different methods have proven successful.

27 March 2026 in JMIR Formative Research
Verified
Journal Article
Open access
YJYihang Jiang
Yihang Jiang
CSConnor Spies
Connor Spies
ARAli R Roghanizad
Ali R Roghanizad
WWWill Ke Wang
Will Ke Wang
SBSatasuk Joy Bhosai
Satasuk Joy Bhosai
Jessilyn DunnJessilyn Dunn
Jessilyn Dunn
Background: Oxygen saturation is a crucial metric used for monitoring patients with lung disease or respiratory illness who are at risk of hypoxemia (low blood oxygen saturation). Early and accurate identification of abnormal oxygen saturation is important for these patients, who may develop significant desaturation and hypoxemia symptoms during their daily activities. Objective: This study aimed to evaluate the accuracy of Apple Watch Series 7 and a clinical-grade pulse oximeter, Masimo MightySat Rx, under hypoxemia and to assess whether measurement error is influenced by the oxygen desaturation rate (ODR). Methods: We calculated the ODR of each measurement and conducted a comparative analysis of the displayed oxygen saturation readings from both the Masimo MightySat Rx finger pulse oximeter and Apple Watch Series 7 with arterial blood oxygen saturation (SaO 2 ) readings obtained from a blood gas analyzer. Results: Both the Masimo MightySat Rx pulse oximeter and the Apple Watch Series 7 tended to overestimate oxygen saturation. The pulse oximeter readings were more likely to fall within 2% of the acceptable (as specified by Masimo) peripheral oxygen saturation (SpO ₂ ) error range than the Apple Watch (49.03% vs 32.14%). Notably, both devices had limitations under low oxygen saturation levels (<88%), with an accuracy root mean square difference (A rms ) of 3.52% (95% CI 3.18%‐3.86%) and 5.82% (95% CI 5.32%‐6.31%) for the Masimo MightySat Rx and Apple Watch Series 7, respectively. Among the blood oxygen measurements taken during a high ODR (ie, ≥2% SpO 2 per minute), which is a rate clinically correlated with sleep apnea, the A rms increased slightly by 0.75% for the Masimo MightySat Rx and decreased by 0.28% for the Apple Watch Series 7. Conclusions: Both devices consistently overestimated SpO 2 , with accuracy declining notably during hypoxemia. The Apple Watch Series 7 mean bias suggests a likelihood of missing instances of hypoxemia, particularly at arterial oxygen saturation values below but close to 88%. Both the Apple Watch Series 7 and Masimo MightySat Rx exhibited A rms values exceeding the US Food and Drug Administration threshold under conditions of hypoxemia. While past studies have implicated high ODRs in increasing measurement error, we found no statistically significant relationship between ODR and measurement error for either device. Overall, our findings of SpO 2 overestimation and high A rms values underscore the need for caution when interpreting oxygen saturation values from these devices. The small sample size and limited diversity in skin tone and age restrict the generalizability of our findings. Future studies should include larger and more diverse populations to evaluate the performance of wearable-based pulse oximetry.

16 July 2024 in medRxiv
Verified
Preprint
Open access
PDF file
YJYihang Jiang
Yihang Jiang
CSConnor Spies
Connor Spies
WWWill Ke Wang
Will Ke Wang
ARAli R. Roghanizad
Ali R. Roghanizad
SBSatasuk Joy Bhosai
Satasuk Joy Bhosai
Jessilyn DunnJessilyn Dunn
Jessilyn Dunn
Oxygen saturation is a crucial metric used for monitoring patients with lung disease or respiratory illness who are at risk of hypoxemia (low blood oxygen saturation). Early and accurate identification of abnormal oxygen saturation is important for these patients who may develop significant desaturation and hypoxemia symptoms during their daily activities. To investigate the performance of two pulse oximeters during desaturation, we recruited nine healthy participants and performed a controlled oxygen desaturation study that reduces the blood oxygen saturation levels from 100% to 60% using a gas delivery system. We calculated the oxygen desaturation rate (ODR) of each measurement and conducted a comparative analysis of the displayed oxygen saturation readings from both the Masimo MightySat Rx finger pulse oximeter and Apple Watch Series 7 with arterial blood oxygen saturation readings obtained from a blood gas analyzer. Both the Masimo MightySat Rx pulse oximeter and the Apple Watch Series 7 tended to overestimate oxygen saturation. The pulse oximeter readings were more likely to fall within 2% of the acceptable (as specified by Masimo) peripheral oxygen saturation (SpO 2 ) error range than the Apple Watch (49.03% compared to 32.14%). Notably, both devices had limitations under low oxygen saturation levels (<88%) with an accuracy root mean square difference (A rms ) of 3.52 [3.18-3.86]% and 5.82 [5.32-6.31]% for the Masimo MightySat Rx and Apple Watch Series 7, respectively. Among the blood oxygen measurements taken during a high oxygen desaturation rate (ODR) (i.e., ≥ 2% SpO 2 per minute), which is a rate clinically correlated with sleep apnea, the A rms increased slightly by 0.75% for the Masimo MightySat Rx and decreased by 0.28% for the Apple Watch Series 7. However, no statistically significant relationship was found between the oxygen desaturation rate and the device measurement errors.