Yao Jiahui

Ms. Yao Jiahui


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
6 June 2025 in EBioMedicine
Verified
Journal Article
Open access
JCJuan Chen
Juan Chen
YJYao Jiahui
Yao Jiahui
WCWei Chen
Wei Chen
FZFeng Zhang
Feng Zhang
HWHeyuan Wang
Heyuan Wang
LZLan Zhu
Lan Zhu
Pelvic floor surface electromyography (sEMG) is widely used to evaluate and treat pelvic floor dysfunctions (PFDs). Based on sEMG, the Glazer protocol was developed over 20 years ago with a limited sample size, making it challenging to accurately diagnose PFDs across diverse populations and conditions. This study aims to establish a multidimensional database for monitoring pelvic floor sEMG, derive more reasonable reference ranges for sEMG parameters, and achieve accurate diagnosis of PFDs through artificial intelligence (AI). In this population-based, multicenter, cross-sectional study, we recruited 1605 participants from 21 centres across China, collected pelvic floor sEMG data, and established a multidimensional sEMG database. Based on the database, we developed an AI-Diagnostician-PFD diagnostic model, which leverages AI to derive AI-Reference ranges for sEMG parameters and diagnose PFDs. Data from 15 centres were divided into a training dataset (60%) and a test dataset (40%), while data from 6 additional centres were used to form an independent validation dataset. The proportions of normal and abnormal samples were consistent across the 15 and 6 centres, ensuring balanced representation. Additionally, both datasets encompassed diverse geographical regions, enhancing the model's generalizability. The diagnostic performance of the AI-Diagnostician-PFD model was evaluated on both the internal test dataset and the external validation dataset. In the external validation dataset, the area under the receiver operating characteristic curve (AUC) of the AI-Reference ranges was 11% higher than that of the Glazer standard. Specifically, the AUC values for the AI-Reference ranges on the internal and external validation datasets were 0.81 (95% CI: 8.13 × 10-1, 8.16 × 10-1) and 0.79 (95% CI: 7.90 × 10-1, 7.94 × 10-1), respectively, surpassing the AUC values of the Glazer standard of 0.76 (95% CI: 7.56 × 10-1, 7.59 × 10-1) and 0.68 (95% CI: 6.74 × 10-1, 6.78 × 10-1). Furthermore, the AI-Diagnostician-PFD model demonstrated superior diagnostic performance for PFDs, achieving an AUC 1% higher than other classical machine learning and deep learning models. The performance of the reference interval derived by AI surpassed that of the Glazer standard. Upon publication of this study, the AI-Diagnostician-PFD model for PFD prediction will be provided free via software on machines. Implementing this algorithm in clinical practice can enhance individual PFD diagnosis and improve population-level health outcomes. This study was supported by grants from the National Key R&D Program of China: The Establishment of a Comprehensive Network for PFD Prevention, Rehabilitation, Pelvic Floor Surgery and Related Complications (2021YFC2701300), Perception and Analysis of the Situation of Major Infectious Disease Outbreaks Based on Internet Big Data (2021ZD0111202), Research on New Models for Forecasting Major Infectious Diseases and Policy Evaluation (2021ZD0111205); Beijing Natural Science Foundation (7212073), National High-Level Hospital Clinical Research Funding (2022-PUMCH-B-087) and the Chinese Academy of Medical Sciences (CAMS) Innovation Fund for Medical Sciences (2021-I2M- C&T-B- 021).

29 July 2024 in IEEE Access
Verified
Journal Article
Open access
JZJiabin Zheng
Jiabin Zheng
HWHanlin Wang
Hanlin Wang
YJYao Jiahui
Yao Jiahui
Large language models (LLMs) have demonstrated their vast potential and value in natural language processing tasks and beyond. However, when these models are applied to develop consultation systems for industrial domains, such as e-government, intelligent diagnosis, and legal consultancy, they encounter many unresolved technical issues. These include the vast scale of the models, lack of tight fusion with existing industry knowledge, along with occurrences of model hallucinations and inadequate explainability. Unlike general-purpose dialogue systems, building a consultation system for a specific industrial domain requires not only the integration of extensive external knowledge from the Internet but also the incorporation of precise, specialized knowledge from specific industries, making the challenges even more complex. In response to these challenges, we propose the Inter-External Knowledge Fusion Contrastive Learning Technique. This technique facilitates the integration of internal industry knowledge with widely accessible external knowledge from the Internet and provides a universal framework for building lightweight, domain-specific consultation systems. Utilizing this technique enables the straightforward creation of precise, professional, and constantly updated domain-specific consultation systems applicable across various industries. Overcoming the inherent limitations associated with LLMs, this technique achieves a performance level comparable to LLMs. To validate the effectiveness of our proposed technique, we conducted extensive experiments in the development of real-world industry consulting systems. By testing on seven real datasets covering diverse tasks, we demonstrate the system’s exceptional performance: our lightweight consultation system utilizes only 4% of the parameters of an LLM but achieves over 90% of its performance level.

31 January 2024 in Transactions of the Association for Computational Linguistics
Verified
Journal Article
Open access
PDF file
SZShiman Zhao
Shiman Zhao
YXYutao Xie
Yutao Xie
WCWei Chen
Wei Chen
TWTengjiao Wang
Tengjiao Wang
YJYao Jiahui
Yao Jiahui
JZJiabin Zheng
Jiabin Zheng
Few-shot Aspect Category Sentiment Analysis (ACSA) is a crucial task for aspect-based sentiment analysis, which aims to detect sentiment polarity for a given aspect category in a sentence with limited data. However, few-shot learning methods focus on distance metrics between the query and support sets to classify queries, heavily relying on aspect distributions in the embedding space. Thus, they suffer from overlapping distributions of aspect embeddings caused by irrelevant sentiment noise among sentences with multiple sentiment aspects, leading to misclassifications. To solve the above issues, we propose a metric-free method for few-shot ACSA, which models the associated relations among the aspects of support and query sentences by Dual Relations Propagation (DRP), addressing the passive effect of overlapping distributions. Specifically, DRP uses the dual relations (similarity and diversity) among the aspects of support and query sentences to explore intra-cluster commonality and inter-cluster uniqueness for alleviating sentiment noise and enhancing aspect features. Additionally, the dual relations are transformed from support-query to class-query to promote query inference by learning class knowledge. Experiments show that we achieve convincing performance on few-shot ACSA, especially an average improvement of 2.93% accuracy and 2.10% F1 score in the 3-way 1-shot setting.

30 April 2024 in IEEE Access
Verified
Journal Article
Open access
JZJiabin Zheng
Jiabin Zheng
FXFangyi Xu
Fangyi Xu
WCWei Chen
Wei Chen
ZFZihao Fang
Zihao Fang
YJYao Jiahui
Yao Jiahui
Cross-domain Consultation Systems have become essential in numerous critical applications, for instance, an online citizen complaint system. However, addressing complaints with distinct orality characteristics often necessitates retrieving and integrating knowledge from diverse professional domains. This scenario represents a typical cross-domain problem. Nevertheless, the prevailing approach of utilizing generative large language models to tackle this problem presents challenges including model scale and drawbacks like hallucination and limited interpretability. To address these challenges, we proposed a novel approach called the Core-View Contrastive Learning (CVCL) network. Leveraging contrastive learning techniques with an integrated core-adaptive augmentation module, the CVCL network achieves accuracy in cross-domain information matching. Our objective is to construct a lightweight, precise, and interpretable cross-domain consultation system, overcoming the limitations encountered with large language models in addressing such challenges. Empirical validation of our proposed method using real-world datasets demonstrates its effectiveness. Our experiments show that the proposed method achieves comparable performance to large language models in terms of accuracy in text-matching tasks and surpasses the best baseline model by over 24 percentage points in F1-score for classification tasks. Additionally, our lightweight model achieved a performance level of 96% compared to the full model, while utilizing only 6% of the parameters.