Mailan Liu

Dr. Mailan Liu


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
30 December 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
HLHonghua Liu
Honghua Liu
PZPeiqin Zhang
Peiqin Zhang
YHYini Huang
Yini Huang
SZShanshan Zuo
Shanshan Zuo
LLLu Li
Lu Li
MLMailan Liu
Mailan Liu
Stroke has become the leading cause of disability in adults worldwide. Early precise rehabilitation intervention is crucial for the recovery of stroke patients, with the key lying in accurately identifying patients’ physical characteristics during the rehabilitation phase. Compared to diagnostic techniques such as medical neuroimaging, traditional Chinese medicine(TCM) tongue diagnosis offers good accessibility and ease of application. However, conventional TCM tongue diagnosis relies on the experience of doctors, which introduces a degree of subjectivity, especially since stroke patients exhibit unique characteristics in tongue texture, shape, and coating, making accurate diagnosis more challenging. To address this issue, this paper proposes a deep learning-based automatic recognition approach for the tongue images of stroke patients, aiming to improve the accuracy of automatic extraction and recognition of stroke-related tongue features through image processing and machine learning techniques. First, this study performs image cropping and data augmentation on tongue images. Then, considering that tongue color, coating color, and coating texture are interrelated in TCM theory and jointly reflect the body’s physiological and pathological state, a label-guided multi-label recognition model for tongue images is designed. This model extracts features from the tongue images of stroke patients, learns the correlations among the features, and performs classification to automatically identify key characteristics such as tongue shape, color, and coating. Finally, the model’s performance is quantitatively evaluated. Experimental results show that the proposed deep learning model outperforms several advanced deep learning models, such as resnet and densenet, and existing single-task tongue classification models in automatically recognizing stroke patients’ tongue images. This research improves the accuracy of feature extraction and recognition of tongue characteristics in stroke patients during rehabilitation, providing a convenient and feasible technical approach for real-time evaluation and diagnosis in the stroke rehabilitation process. It has significant clinical application value and research significance.

1 August 2022 in Frontiers in Pain Research
Verified
Journal Article
Open access
ZYZhaobo Yan
Zhaobo Yan
ZMZhimiao MuRong
Zhimiao MuRong
BHBixiu Huo
Bixiu Huo
HZHuan Zhong
Huan Zhong
CYChun Yi
Chun Yi
MLMi Liu
Mi Liu
Background: Cancer-induced bone pain (CIBP) is a special type of cancer pain and lacks safe and effective treatments. Acupuncture is a potentially valuable treatment for CIBP, studies evaluating the effect of acupuncture on CIBP have increased significantly, but the safety and efficacy of acupuncture to control CIBP remains controversial.Objective: To provide the first meta-analysis to evaluate the safety and efficacy of acupuncture in CIBP management.Data Sources: CNKI, CBM, Wanfang, VIP Database, PubMed, Embase, and Cochrane Library were searched from their inception until 1 June 2022.Study Selection: RCTs with primary bone tumor patients or other types of primary cancer companied by bone metastases as the research subjects and to evaluate the efficacy of acupuncture treatment alone or combined with the control treatment were included. Meanwhile, RCTs should choose the pain score as the primary outcome and pain relief rate, frequency of breakthrough pain, analgesic onset time, analgesia duration, quality of life, and adverse events as reference outcomes.Data Collection and Analysis: We designed a data-extraction form that was used to extract key information from the articles. Data extraction study evaluation was conducted independently by two reviewers, and a third reviewer would resolve any disagreements. The risk of bias was assessed by the Cochrane Collaboration's tool for assessing the risk bias. The quality of the evidence for main outcomes was evaluated by the GRADE system. Mean differences (MD), relative risk (RR), and 95% confidence intervals (CIs) were calculated. The forest plots were performed using the Review Manager Software (5.3 version). Subgroup analysis was used to investigate the possible sources of potential heterogeneity. Descriptive analysis was performed in case of unacceptable clinical heterogeneity.Results: Thirteen RCTs (with 1,069 patients) were included, and all studies were at high risk of bias owing to lack of blinding or other bias. Eleven studies evaluated the effectiveness of acupuncture as a complementary therapy, and showed that acupuncture plus control treatment (compared with control treatment) was connected with reduced pain intensity (MD = −1.34, 95% CI −1.74 to −0.94; Q < 0.1; I2 = 98%, P < 0.01). Subgroup analyses based on acupoints type partly explain the potential heterogeneity. The results also showed that acupuncture plus control treatment (compared with control treatment) was connected with relieving pain intensity, increasing the pain relief rate, reducing the frequency of breakthrough pain, shortening analgesic onset time, extending the analgesic duration, and improving the quality of life. We have no sufficient evidence to prove the effectiveness of acupuncture alone. Four RCTs reported only adverse events related to opioids' side effects. Evidence was qualified as “very low” because of low methodological quality, considerable heterogeneity, or a low number of included studies.Conclusion: Acupuncture has a certain effect as a complementary therapy on pain management of CIBP, which not only mitigates the pain intensity but also improves the quality of life and reduces the incidence of opioids' side effects, although the evidence level was very low. In future, a larger sample size and rigorously designed RCTs are needed to provide sufficient evidence to identify the efficacy and safety of acupuncture as a treatment for CIBP.

10 July 2017 in Trials
Verified
Journal Article
Open access
PDF file
MLMailan Liu
Mailan Liu
QZQian Zhang
Qian Zhang
SJShan Jiang
Shan Jiang
MLMi Liu
Mi Liu
GZGuoshan Zhang
Guoshan Zhang
XCXiaorong Chang
Xiaorong Chang
Acupuncture and moxibustion has been widely applied to hyperlipidemia treatment in clinical practice in China, serving as an alternative treatment to statins. Warm-needling acupuncture and medicinal cake-separated moxibustion have been separately reported with potential therapeutic effects on hyperlipidemia treatment in several studies but with limitations in study methodology. Combining these two modalities may provide a more advantageous strategy in treating hyperlipidemia. Therefore, a strict evaluation through well-designed randomized controlled trials (RCT) is necessary to determine their efficacy and safety on hyperlipidemia. The study a multicenter, open-label, randomized, stratified, active-controlled, noninferiority trial with two parallel groups. Subjects with hyperlipidemia will be stratified into different groups by risk levels of heart diseases. They then will be instructed to the Therapeutic Lifestyle Change (TLC) diet. Those who have not reached the target lipid level will be randomly assigned to the treatments of either acupuncture and moxibustion or simvastatin with a 1:1 allocation. One hundred and thirty subjects are aimed to be recruited. The duration of intervention for this study will be 12 weeks, followed by another 4 weeks for post-treatment assessment. The primary outcome is percentage change from baseline to the end of the study in low-density lipoprotein cholesterol (LDL-C). Other indicators in lipid change, safety and adherence will also be assessed secondarily. The repeated measures, linear mixed-effects model will be applied to the analysis. Acupuncture and moxibustion could be a potentially effective treatment alternative for hyperlipidemia. A study with careful design is developed to evaluate the efficacy and safety of combined acupuncture and moxibustion, by integrating the traditional Chinese Medicine (TCM) regimens with the standardized Western medicine appraisal approach. ClinicalTrials.gov, NCT02269046 . Registered on 26 September 2014.

27 January 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
HLHonghua Liu
Honghua Liu
MZMingwei Zhao
Mingwei Zhao
CSChang She
Chang She
HPHan Peng
Han Peng
MLMailan Liu
Mailan Liu
BLBo Li
Bo Li
In 2019, the novel coronavirus swept the world, exposing the monitoring and early warning problems of the medical system. Computer-aided diagnosis models based on deep learning have good universality and can well alleviate these problems. However, traditional image processing methods may lead to high false positive rates, which is unacceptable in disease monitoring and early warning. This paper proposes a low false positive rate disease detection method based on COVID-19 lung images and establishes a two-stage optimization model. In the first stage, the model is trained using classical gradient descent, and relevant features are extracted; in the second stage, an objective function that minimizes the false positive rate is constructed to obtain a network model with high accuracy and low false positive rate. Therefore, the proposed method has the potential to effectively classify medical images. The proposed model was verified using a public COVID-19 radiology dataset and a public COVID-19 lung CT scan dataset. The results show that the model has made significant progress, with the false positive rate reduced to 11.3% and 7.5%, and the area under the ROC curve increased to 92.8% and 97.01%.

9 May 2025 in Journal of Ethnopharmacology
Verified
Journal Article
Closed access
ZZZiyan Zhong
Ziyan Zhong
HLHongping Long
Hongping Long
NLNuokun Li
Nuokun Li
TLTongtong Liu
Tongtong Liu
MWMei Wu
Mei Wu
PMPan Meng
Pan Meng

12 June 2020 in Medicine
Verified
Journal Article
Open access
JZJun Zhou
Jun Zhou
SCShirui Cheng
Shirui Cheng
HYHan Yang
Han Yang
LLLei Lan
Lei Lan
YCYijia Bd Chen
Yijia Bd Chen
MLMailan Liu
Mailan Liu
Objective: The aim of this systematic review and meta-analysis is to improve the understanding of the pathophysiology of tension-type headache (TTH), as well as propose avenues for future neuroimaging studies of TTH. Methods: From the inception dates to May 1, 2020, a systematic literature will search in Medline (Ovid SP), Embase (Ovid SP), Cochrane Central Register of Controlled Trials, Web of Science, and 4 Chinese databases without limitation on language or publication. Additionally, International Clinical Trials Registry Platform , reference lists, and relevant gray literatures will be searched. After screening of eligible references, included studies will be determined according to included criteria, and then data extraction and a methodological quality assessment with a customized checklist will be conducted. Each process will be independently implemented by 2 reviewers, any disagreement will be resolved by consensus to the third researcher. If the extracted data is feasible, anisotropic effect-size version of signed differential mapping will be conducted to perform the meta-analysis of the structural and functional brain alterations in TTH patients.