HYHuilin Yao

Huilin Yao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Huilin Yao has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Radiographic Knee Osteoarthritis Identification Using Wearable Plantar Pressure: Secondary Cross-Sectional Analysis of Interpretable Framework Integrating Biomechanical Descriptors and the Multiscale Synergy Index

    by Guanyu Xin, Hongbo Yao, Jingyuan Qiao, Huilin Yao, Siyuan Li, Lu Liu, Jingyi Zhang, Ke Qin, Lin Shu

    Background: Radiographic knee osteoarthritis (ROA) is associated with abnormal plantar loading and altered gait coordination. Insole-based plantar-pressure sensing offers a practical wearable approach to ROA identification, but existing methods typically use either conventional biomechanical descriptors or end-to-end temporal models. An interpretable subject-level framework that captures both local abnormalities and distributed coordination is, therefore, needed. Objective: This study aimed to develop an interpretable subject-level framework that combines conventional biomechanical descriptors with coordination-level plantar information to identify ROA. Methods: In secondary cross-sectional analysis, using a previously reported Pearl River Osteoarthritis Cohort plantar-pressure dataset from our group, we analyzed 92 participants (43 with ROA and 49 without ROA; mean age 63.0, SD 8.4 y). The source cohort was recruited from clinical and nearby community sources at Zhujiang Hospital of Southern Medical University, Guangzhou, China, between January 2022 and February 2023. We developed an interpretable participant-level classification framework integrating conventional biomechanical descriptors with a coordination-level Plantar Synergy Index (PSI). Participant-wise stratified split allocated 72 participants for 5-fold cross-validation, and 20 for locked independent evaluation. Feature selection used Fisher-score ranking (k=50). All point estimates are accompanied by 2000-iteration bootstrap 95% CIs, and paired model comparisons used DeLong tests. All statistical tests used α=.05. Additional analyses examined feature stability, phase-resolved PSI patterns, robustness to perturbation and design variation, and comparisons with representative end-to-end temporal baselines. Results: The fusion model achieved the best primary classification performance on the independent test set, with an F 1 -score of 0.842 (95% CI 0.615‐1.000) and accuracy of 0.850 (95% CI 0.700‐1.000). It also showed balanced performance across additional metrics, with area under the receiver operating characteristic curve (AUROC) of 0.818 (95% CI 0.576‐1.000), precision of 0.800 (95% CI 0.538‐1.000), recall of 0.889 (95% CI 0.636‐1.000), and specificity of 0.818 (95% CI 0.571‐1.000). DeLong testing showed that fusion outperformed PSI-only at the AUROC level ( P =.02). Stable retained descriptors were dominated by biomechanical features, with a reproducible PSI component. Phase-resolved analyses suggested distributed stance-phase coordination differences. Robustness and baseline comparisons supported the stability of the framework, but the wide CIs indicate that the findings remain preliminary. Conclusions: This study introduces an interpretable participant-level representation that integrates local biomechanical loading with multiscale interregional temporal coordination, extending plantar-pressure approaches based on summary descriptors or end-to-end models. Across evaluated settings, the framework showed competitive identification and preliminary robustness. Local biomechanical descriptors constituted the main discriminative basis, whereas PSI contributed a reproducible coordination-level component whose incremental predictive value remains to be established. This broadens plantar-pressure analysis from local loading to distributed coordination. External multicenter prospective validation is required before evaluating the framework as an imaging adjunct for functional assessment and longitudinal monitoring.

  • QRS Complexes Detection Using UNet-BiLSTM Model Combined With Adaptive Post-Processing for Multilead Wearable ECG Smart T-Shirt System

    by Kaikai Wang, Baoliang Feng, Fenghan Zhou, Changfu Zhong, Jingyuan Qiao, Junhong Luo, Huilin Yao, Jiyu Wang, Lin Shu

    In recent years, the rapid development of wearable devices and Internet of Things (IoT) technology has made realtime, continuous dynamic electrocardiogram (ECG) monitoring possible. However, robust universal multi-lead QRS complex detection under noise and high heart rate (HR) conditions remains challenging. In this study, we propose a smart T-shirtbased multi-lead dynamic ECG monitoring system and a highaccuracy QRS complex detection algorithm to solve the above problems. First, we develop a six-lead smart T-shirt system with integrated flexible dry electrodes for real-time acquisition of the ECG under three conditions: standing, walking, and jogging. The electrode structure and hardware circuit are designed to resist noise, while electrodes are combined with medical-grade conductive gels to replace conventional Ag/AgCl wet electrodes, ultimately realizing high signal-to-noise ratio (SNR) signal acquisition under dynamic conditions. The T-shirt-based system design not only enhances user comfort but also facilitates use for non-medical users, making long-term ECG monitoring more feasible. Second, we propose a novel Pro-APP algorithm combining the UNet and bidirectional long short-term memory (UNet-BiLSTM) model with adaptive post-processing (APP), which is robust and outperforms three existing QRS complex detection algorithms. The UNet-BiLSTM model can effectively extract multi-scale features and capture the timing information in the ECG. The APP algorithm further optimizes the R-peak localization by dynamically adjusting parameters. The results show that the system confirms the reliability of its signal quality, HR detection, and electrode performance through the signal quality assessment (SNR ≥ 24 dB), ECG simulator validation (RR interval error.4 ms), and skin-electrode impedance measurement (impedance≤117.27 KΩ at frequencies above 10 Hz). In addition, the Pro-APP algorithm significantly improves the sensitivity (93.67%), precision (97.13%), accuracy (91.08%), and F1-score (95.30%) for detecting QRS complexes, with a mean absolute error of only 3.63 ms, which achieves universal QRS complex detection in multi-lead ECG signals and optimizes wearable dynamic ECG monitoring. The research shows that the smart Tshirt system combined with the QRS complex detection algorithm can provide an important carrier and technical means for the new model of wise information technology of medicine.