Yueqi Huang

Mrs. Yueqi Huang

Affiliated Mental Health Center & Hangzhou Seventh People's Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China
orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
1 April 2019 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
TRTong Ruan
Tong Ruan
YHYueqi Huang
Yueqi Huang
XLXuli Liu
Xuli Liu
YXYuhang Xia
Yuhang Xia
JGJu Gao
Ju Gao
While doctors should analyze a large amount of electronic medical record (EMR) data to conduct clinical research, the analyzing process requires information technology (IT) skills, which is difficult for most doctors in China. In this paper, we build a novel tool QAnalysis, where doctors enter their analytic requirements in their natural language and then the tool returns charts and tables to the doctors. For a given question from a user, we first segment the sentence, and then we use grammar parser to analyze the structure of the sentence. After linking the segmentations to concepts and predicates in knowledge graphs, we convert the question into a set of triples connected with different kinds of operators. These triples are converted to queries in Cypher, the query language for Neo4j. Finally, the query is executed on Neo4j, and the results shown in terms of tables and charts are returned to the user. The tool supports top 50 questions we gathered from two hospital departments with the Delphi method. We also gathered 161 questions from clinical research papers with statistical requirements on EMR data. Experimental results show that our tool can directly cover 78.20% of these statistical questions and the precision is as high as 96.36%. Such extension is easy to achieve with the help of knowledge-graph technology we have adopted. The recorded demo can be accessed from https://github.com/NLP-BigDataLab/QAnalysis-project . Our tool shows great flexibility in processing different kinds of statistic questions, which provides a convenient way for doctors to get statistical results directly in natural language.

8 January 2024 in Frontiers in Oncology
Verified
Journal Article
Open access
PDF file
RLRuipeng Li
Ruipeng Li
JYJianming Ye
Jianming Ye
YHYueqi Huang
Yueqi Huang
WJWei Jin
Wei Jin
PXPeng Xu
Peng Xu
LGLilin Guo
Lilin Guo
Introduction: This study presents a novel continuous learning framework tailored for brain tumour segmentation, addressing a critical step in both diagnosis and treatment planning. This framework addresses common challenges in brain tumour segmentation, such as computational complexity, limited generalisability, and the extensive need for manual annotation.Methods: Our approach uniquely combines multi-scale spatial distillation with pseudo-labelling strategies, exploiting the coordinated capabilities of the ResNet18 and DeepLabV3+ network architectures. This integration enhances feature extraction and efficiently manages model size, promoting accurate and fast segmentation. To mitigate the problem of catastrophic forgetting during model training, our methodology incorporates a multi-scale spatial distillation scheme. This scheme is essential for maintaining model diversity and preserving knowledge from previous training phases. In addition, a confidence-based pseudo-labelling technique is employed, allowing the model to self-improve based on its predictions and ensuring a balanced treatment of data categories.Results: The effectiveness of our framework has been evaluated on three publicly available datasets (BraTS2019, BraTS2020, BraTS2021) and one proprietary dataset (BraTS_FAHZU) using performance metrics such as Dice coefficient, sensitivity, specificity and Hausdorff95 distance. The results consistently show competitive performance against other state-of-the-art segmentation techniques, demonstrating improved accuracy and efficiency.Discussion: This advance has significant implications for the field of medical image segmentation. Our code is freely available at https://github.com/smallboy-code/A-brain-tumor-segmentation-frameworkusing-continual-learning.

28 September 2022 in Brain Sciences
Verified
Journal Article
Open access
PDF file
YHYueqi Huang
Yueqi Huang
Hangyi yangHangyi yang
Hangyi yang
CZCheng Zhu
Cheng Zhu
XJXiaoying Jiang
Xiaoying Jiang
WZWenjing Zhu
Wenjing Zhu
WTWenxin Tang
Wenxin Tang
Objective: To explore whether a systematic combined therapeutic modality (CTM) could quickly and effectively improve the severity of obsessive–compulsive disorder (OCD) and the insight of OCD patients. Methods: Included in this study were 100 patients with OCD according to the 5th Edition of the Diagnostic and Statistical Manual of Mental Disorders (DSM-5), for a 2-week short-term treatment. They were assigned to a drug-alone group (n = 57), and a CTM group (n = 43) using drug treatment in combination with cognitive behavioral treatment (CBT) and repetitive transcranial magnetic stimulation (rTMS). The therapeutic outcome was assessed by the Yale–Brown Obsessive–Compulsive Scale (Y-BOCS), Brown Assessment of Beliefs Scale (BABS), 24-item Hamilton Depression Scale (HAMD-24) and Hamilton Anxiety Scale (HAMA) before and after treatment. All data were treated with SPSS25.0 Software. Results: After the 2-week treatment, the success rate in the CTM group was significantly higher than that in the drug-alone group. Y-BOCS overall and factor scores were decreased as compared with those before treatment in both groups. HAMD, HAMA and BABS overall scores were all decreased after treatment in the CTM group. In addition, compared with the drug-alone group, the Y-BOCS overall score and factor score, HAMD overall score and HAMA overall score were all decreased significantly in CTM group, while the Y-BOCS score reduction rate was increased significantly. Insight was improved in eight cases (57.14%) in the CTM group containing 14 cases with poor insight. Multinomial logistic regression analysis showed that CTM was beneficial for the insight improvement of OCD patients (OR = 91.04–139.68); this improvement was more pronounced in patients with low baseline BABS overall scores (OR = 0.07). Conclusion: CTM may be an effective short-term strategy to improve the severity of OCD and insight of OCD patients and, therefore, is worthy of clinical promotion and application.

3 February 2026 in Journal of Medical Internet Research
Verified
Journal Article
Open access
YLYing-Ying Li
Ying-Ying Li
AHA-Qian Hu
A-Qian Hu
LYLing-Li Yi
Ling-Li Yi
ZMZi-Xin Mao
Zi-Xin Mao
QLQiu-Yue Lü
Qiu-Yue Lü
WGWan-Jun Guo
Wan-Jun Guo
Background: Both internet gaming disorder (IGD) and internet addiction (IA) have been associated with diverse psychopathological symptoms. However, how the 2 conditions relate to each other and which is more strongly associated with psychopathology remain unclear. Objective: This study aimed to examine the association between IGD and IA and compare the strength of their associations with various types of psychopathological symptoms. Methods: This cross-sectional study surveyed 3 independent samples of Chinese adolescents: the first sample (S1) comprised 8194 first-year undergraduates at a comprehensive university in Chengdu, the second sample (S2) comprised 1720 students from a high school in Hangzhou, and the third sample (S3) comprised 551 inpatients aged 13 to 19 years recruited from 2 tertiary psychiatric hospitals in Hangzhou and Chengdu. IGD was defined as a score of 22 or more on the Internet Gaming Disorder Scale–Short Form (IGDS9-SF), whereas IA was defined as a score of 50 or more on Young’s 20-item Internet Addiction Test (IAT-20). Symptoms of depression, anxiety, psychoticism, paranoid ideation, and attention-deficit or hyperactivity were assessed using internationally validated scales including 9-item the Patient Health Questionnaire, 7-item Generalized Anxiety Disorder, psychoticism and paranoid ideation subscales of the Symptom Checklist 90 (absent for S2), and Adult ADHD Self-Report Scale (absent for S1), through online surveys in S1 (October 2020) and S3 (January 2022 to February 2025) and via an offline survey in S2 (March 2024). Results: The prevalence estimates (95% CI) of IGD were 4.8% (4.3%‐5.2%) in S1, 15.8% (14.0%‐17.5%) in S2, and 32.3% (28.4%‐36.2%) in S3, whereas prevalence estimates (95% CI) of IA were consistently higher across samples, ranging from 7.3% (6.8%‐7.9%) in S1 and 18.8% (17.0%‐20.6%) in S2 to 45.9% (41.8%‐50.1%) in S3. The IGDS9-SF and the IAT-20 were moderately correlated (Pearson r =0.51‐0.57; all P <.001) and were associated with the severity of most psychopathological symptom domains, with consistently stronger associations observed for IAT-20 scores. In multivariate models including all psychopathological symptoms as independent variables, the coefficients of determination ( R ², 95% CIs) were consistently higher for the IAT-20 than for the IGDS9-SF in S1 (0.33, 0.30‐0.35 vs 0.13, 0.11‐0.16) and S2 (0.44, 0.39‐0.49 vs 0.23, 0.18‐0.27), with a similar but nonsignificant pattern observed in S3 (0.13, 0.06‐0.26 vs 0.06, 0.03‐0.16). Post hoc analyses indicated that psychopathological symptoms were generally more severe in individuals with IA, either alone or comorbid with IGD, than in those with IGD only. Conclusions: This study provides additional evidence that IGD and IA are distinct yet interrelated constructs, and further demonstrates that IA consistently exhibits stronger associations with the severity of psychopathological symptoms than IGD. These findings underscore the importance of recognizing and addressing compulsive and problematic online behaviors that extend beyond gaming, highlighting the need to refine diagnostic frameworks and prioritize targeted clinical interventions.

15 October 2026 in Journal of Behavioral Addictions
Verified
Journal Article
Open access
PDF file
AHA-Qian Hu
A-Qian Hu
ZMZi-Xin Mao
Zi-Xin Mao
YLYing-Ying Li
Ying-Ying Li
GCGuo-Dong Chen
Guo-Dong Chen
TCTao Chen
Tao Chen
WGWan-Jun Guo
Wan-Jun Guo
Background and aims: Self-harm imposes a substantial burden among adolescents, yet targeted interventions remain limited. This study examined the interrelationships among clinically relevant characteristics of self-harm outcomes, non-suicidal motives (NSMs), addictive features (AF), self-injury methods (SIMs), and suicidality (SUI), to identify core clinical features for more precise intervention. Methods: A total of 547 adolescent patients (13–19 years) who had engaged in self-harm during the past year were recruited from two Chinese hospitals. Self-report questionnaires assessed NSMs, AF, SUI, frequencies of non-suicidal self-injury (NSSI) and suicidal self-injury (SSI), and SIMs. Exploratory factor analysis (EFA) was used as a data-driven approach to identify patterns of co-occurrence among SIMs. Network and exploratory mediation analyses were subsequently conducted to evaluate statistical interrelationships among clinical features. Results: Among participants, 69.8% engaged in both NSSI and SSI. EFA identified two empirically derived groupings of SIMs: self-injury using external tools (SIET) and self-injury involving direct bodily actions (SIDBA). Network analysis identified AF as the strongest bridge symptom and SIET with the highest node strength. Exploratory mediation analyses suggested that AF statistically accounted for substantial proportions of the associations between NSMs and multiple self-harm related outcomes, including NSSI (41.3%), SSI (75.0%), SIET (62.3%), SIDBA (45.4%), and SUI (75.7%). Discussion and Conclusions: AF and SIET emerged as important clinically relevant features of self-harm. Greater attention to these features may help improve clinical assessment and targeted intervention for adolescents with self-harm.