Po-Han Chiang

Mr. Po-Han Chiang


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
2 June 2021 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
JLJared Leitner
Jared Leitner
PCPo-Han Chiang
Po-Han Chiang
SDSujit Dey
Sujit Dey
In this paper, we present a personalized deep learning approach to estimate blood pressure (BP) using the photoplethysmogram (PPG) signal. We propose a hybrid neural network architecture consisting of convolutional, recurrent, and fully connected layers that operates directly on the raw PPG time series and provides BP estimation every 5 seconds. To address the problem of limited personal PPG and BP data for individuals, we propose a transfer learning technique that personalizes specific layers of a network pre-trained with abundant data from other patients. We use the MIMIC III database which contains PPG and continuous BP data measured invasively via an arterial catheter to develop and analyze our approach. Our transfer learning technique, namely BP-CRNN-Transfer, achieves a mean absolute error (MAE) of 3.52 and 2.20 mmHg for SBP and DBP estimation, respectively, outperforming existing methods. Our approach satisfies both the BHS and AAMI blood pressure measurement standards for SBP and DBP. Moreover, our results demonstrate that as little as 50 data samples per person are required to train accurate personalized models. We carry out Bland-Altman and correlation analysis to compare our method to the invasive arterial catheter, which is the gold-standard BP measurement method.

19 July 2021 in IEEE Journal of Translational Engineering in Health and Medicine
Verified
Journal Article
Open access
PCPo-Han Chiang
Po-Han Chiang
MWMelissa Wong
Melissa Wong
SDSujit Dey
Sujit Dey
Background: Blood pressure (BP) is an essential indicator for human health and is known to be greatly influenced by lifestyle factors, like activity and sleep factors. However, the degree of impact of each lifestyle factor on BP is unknown and may vary between individuals. Our goal is to investigate the relationships between BP and lifestyle factors and provide personalized and precise recommendations to improve BP, as opposed to the current practice of general lifestyle recommendations. Method: Our proposed system consists of automated data collection using home BP monitors and wearable activity trackers and feature engineering techniques to address time-series data and enhance interpretability. We propose Random Forest with Shapley-Value-based Feature Selection to offer personalized BP modeling and top lifestyle factor identification, and subsequent generation of precise recommendations based on the top factors. Result: In collaboration with UC San Diego Health and Altman Clinical and Translational Research Institute, we performed a clinical study, applying our system to 25 patients with elevated BP or stage I hypertension for three consecutive months. Our study results validate our system’s ability to provide accurate personalized BP models and identify the top features which can vary greatly between individuals. We also validate the effectiveness of personalized recommendations in a randomized controlled experiment. After receiving recommendations, the subjects in the experimental group decreased their BPs by 3.8 and 2.3 for systolic and diastolic BP, compared to the decrease of 0.3 and 0.9 for the subjects without recommendations. Conclusion: The study demonstrates the potential of using wearables and machine learning to develop personalized models and precise lifestyle recommendations to improve BP.

28 May 2024 in JMIR Cardio
Verified
Journal Article
Open access
JLJared Leitner
Jared Leitner
PCPo-Han Chiang
Po-Han Chiang
PAParag Agnihotri
Parag Agnihotri
SDSujit Dey
Sujit Dey
Background: Home blood pressure (BP) monitoring with lifestyle coaching is effective in managing hypertension and reducing cardiovascular risk. However, traditional manual lifestyle coaching models significantly limit availability due to high operating costs and personnel requirements. Furthermore, the lack of patient lifestyle monitoring and clinician time constraints can prevent personalized coaching on lifestyle modifications. Objective: This study assesses the effectiveness of a fully digital, autonomous, and artificial intelligence (AI)–based lifestyle coaching program on achieving BP control among adults with hypertension. Methods: Participants were enrolled in a single-arm nonrandomized trial in which they received a BP monitor and wearable activity tracker. Data were collected from these devices and a questionnaire mobile app, which were used to train personalized machine learning models that enabled precision lifestyle coaching delivered to participants via SMS text messaging and a mobile app. The primary outcomes included (1) the changes in systolic and diastolic BP from baseline to 12 and 24 weeks and (2) the percentage change of participants in the controlled, stage-1, and stage-2 hypertension categories from baseline to 12 and 24 weeks. Secondary outcomes included (1) the participant engagement rate as measured by data collection consistency and (2) the number of manual clinician outreaches. Results: In total, 141 participants were monitored over 24 weeks. At 12 weeks, systolic and diastolic BP decreased by 5.6 mm Hg (95% CI −7.1 to −4.2; P<.001) and 3.8 mm Hg (95% CI −4.7 to −2.8; P<.001), respectively. Particularly, for participants starting with stage-2 hypertension, systolic and diastolic BP decreased by 9.6 mm Hg (95% CI −12.2 to −6.9; P<.001) and 5.7 mm Hg (95% CI −7.6 to −3.9; P<.001), respectively. At 24 weeks, systolic and diastolic BP decreased by 8.1 mm Hg (95% CI −10.1 to −6.1; P<.001) and 5.1 mm Hg (95% CI −6.2 to −3.9; P<.001), respectively. For participants starting with stage-2 hypertension, systolic and diastolic BP decreased by 14.2 mm Hg (95% CI −17.7 to −10.7; P<.001) and 8.1 mm Hg (95% CI −10.4 to −5.7; P<.001), respectively, at 24 weeks. The percentage of participants with controlled BP increased by 17.2% (22/128; P<.001) and 26.5% (27/102; P<.001) from baseline to 12 and 24 weeks, respectively. The percentage of participants with stage-2 hypertension decreased by 25% (32/128; P<.001) and 26.5% (27/102; P<.001) from baseline to 12 and 24 weeks, respectively. The average weekly participant engagement rate was 92% (SD 3.9%), and only 5.9% (6/102) of the participants required manual outreach over 24 weeks. Conclusions: The study demonstrates the potential of fully digital, autonomous, and AI-based lifestyle coaching to achieve meaningful BP improvements and high engagement for patients with hypertension while substantially reducing clinician workloads. Trial Registration: ClinicalTrials.gov NCT06337734; https://clinicaltrials.gov/study/NCT06337734

8 July 2020 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
YKYu-Jen Ku
Yu-Jen Ku
PCPo-Han Chiang
Po-Han Chiang
SDSujit Dey
Sujit Dey
To sustainably provide low-latency communication and edge computing for connected vehicles, a promising solution is using Solar-powered Roadside Units (SRSUs), which consist of small cell base stations and Mobile Edge Computing servers. However, due to the intermittent nature of solar power, SRSUs may suffer from a high risk of power deficiency, which will lead to severe disruption of vehicular edge computing applications. In this paper, we aim to address this challenge of Quality of Service (QoS) loss (i.e., edge computing service outage for vehicle users (VUs)). We formulate a QoS optimization problem for VUs and solve it in two phases: an offline solar energy scheduling phase, and an online user association and SRSU resource allocation phase. We simulate our proposed technique in a dense SRSU network environment with real-world urban vehicular traffic data and solar generation profile. The simulation results show that our proposed approach can significantly reduce QoS loss of vehicular edge computing applications using SRSUs, compared to existing techniques. Further, the results are beneficial to service providers and city planners to identify adequate SRSU configurations for expected solar energy generation and edge computing service demands.

9 May 2018 in IEEE Transactions on Green Communications and Networking
Verified
Journal Article
Closed access
PCPo-Han Chiang
Po-Han Chiang
RGRanjini B. Guruprasad
Ranjini B. Guruprasad
SDSujit Dey
Sujit Dey
Renewable energy (RE) is a promising solution to reduce grid energy consumption and carbon dioxide emissions of cellular networks. However, the benefit of utilizing RE is limited by its highly intermittent and unreliable nature, resulting in low savings in grid energy. To minimize the grid energy cost, we propose to utilize data buffer of user equipments as well as energy storage at the base station (BS) to better adapt the BS resource allocation and hence its energy consumption to the dynamic nature of RE. We consider the scenario of downlink orthogonal frequency division multiple access networks with non-ideal hybrid energy supply. To jointly optimize the energy consumption and the quality of service (QoS) of users, we adopt the weighted sum of users’ utility of data rates and grid energy consumption as our performance metric. We propose a low-complexity online control scheme based on Lyapunov optimization framework. The proposed technique can provide asymptotically optimal performance bound without requiring the stochastic distribution information of RE arrival and channel state condition. The experimental results demonstrate the ability of the proposed approach to significantly improve the performance in terms of grid power consumption and user QoS compared with the existing schemes.

24 January 2023 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
JLJared Leitner
Jared Leitner
ABAlexander Behnke
Alexander Behnke
PCPo-Han Chiang
Po-Han Chiang
MRMichele Ritter
Michele Ritter
MMMarlene Millen
Marlene Millen
SDSujit Dey
Sujit Dey
Current remote monitoring of COVID-19 patients relies on manual symptom reporting, which is highly dependent on patient compliance. In this research, we present a machine learning (ML)-based remote monitoring method to estimate patient recovery from COVID-19 symptoms using automatically collected wearable device data, instead of relying on manually collected symptom data. We deploy our remote monitoring system, namely eCOVID, in two COVID-19 telemedicine clinics. Our system utilizes a Garmin wearable and symptom tracker mobile app for data collection. The data consists of vitals, lifestyle, and symptom information which is fused into an online report for clinicians to review. Symptom data collected via our mobile app is used to label the recovery status of each patient daily. We propose a ML-based binary patient recovery classifier which uses wearable data to estimate whether a patient has recovered from COVID-19 symptoms. We evaluate our method using leave-one-subject-out (LOSO) cross-validation, and find that Random Forest (RF) is the top performing model. Our method achieves an F1-score of 0.88 when applying our RF-based model personalization technique using weighted bootstrap aggregation. Our results demonstrate that ML-assisted remote monitoring using automatically collected wearable data can supplement or be used in place of manual daily symptom tracking which relies on patient compliance.