Jinxin Liu

Jinxin Liu

Auto-generated profile, based on publicly available information

Jinxin Liu

Department of Neurosurgery, Chongqing Emergency Medical Center, Chongqing University Central Hospital, School of Medicine, Chongqing University

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
14 November 2024 in eLife
Verified
Journal Article
Open access
LJLiu Jinxin
Liu Jinxin
HHHaoyue He
Haoyue He
YWYanglingxi Wang
Yanglingxi Wang
JDJun Du
Jun Du
KLKaixin Liang
Kaixin Liang
YDYongbing Deng
Yongbing Deng
Background: Post-stroke epilepsy (PSE) is a critical complication that worsens both prognosis and quality of life in patients with ischemic stroke. An interpretable machine learning model was developed to predict PSE using medical records from four hospitals in Chongqing.Methods: Medical records, imaging reports, and laboratory test results from 21,459 ischemic stroke patients were collected and analyzed. Univariable and multivariable statistical analyses identified key predictive factors. The dataset was split into a 70% training set and a 30% testing set. To address the class imbalance, the Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors was employed. Nine widely used machine learning algorithms were evaluated using relevant prediction metrics, with SHAP (SHapley Additive exPlanations) used to interpret the model and assess the contributions of different features.Results: Regression analyses revealed that complications such as hydrocephalus, cerebral hernia, and deep vein thrombosis, as well as specific brain regions (frontal, parietal, and temporal lobes), significantly contributed to PSE. Factors such as age, gender, NIH Stroke Scale (NIHSS) scores, and laboratory results like WBC count and D-dimer levels were associated with increased PSE risk. Tree-based methods like Random Forest, XGBoost, and LightGBM showed strong predictive performance, achieving an AUC of 0.99.Conclusions: The model accurately predicts PSE risk, with tree-based models demonstrating superior performance. NIHSS score, WBC count, and D-dimer were identified as the most crucial predictors.Funding: The research is funded by Central University basic research young teachers and students research ability promotion sub-projec t(2023CDJYGRH-ZD06), and by Emergency Medicine Chongqing Key Laboratory Talent Innovation and development joint fund project (2024RCCX10).

13 May 2022 in ESC Heart Failure
Verified
Journal Article
Open access
LZLieguang Zhang
Lieguang Zhang
XWXiaoyu Wei
Xiaoyu Wei
HWHuimin Wang
Huimin Wang
RJRui Jiang
Rui Jiang
ZTZekun Tan
Zekun Tan
LJLiu Jinxin
Liu Jinxin
Aims: The cardiac injury and sequelae of Delta Variant of coronavirus disease 2019 (COVID-19) remain unknown. This study aimed to evaluate the presence of cardiac involvement in patients recovering from Delta Variant of COVID-19 based on multi-parametric cardiac magnetic resonance imaging (MRI). Methods and results: We prospectively assessed patients recovering from Delta Variant of COVID-19 using multi-parametric cardiac magnetic resonance imaging (MRI) between June 2021 and July 2021. Comparison was made with 25 healthy controls. Forty-four patients (median age 51 years, 28 women) recovering from Delta Variant were recruited and had a median time of 35 days between diagnosis and cardiac MRI. There were no patients with chest pain (0/44, 0%) and high sensitivity cardiac troponin T troponin elevation (median levels 2.20 pg/mL, IQR levels 0.85–4.40 pg/mL). Regarding the cardiac imaging findings, a total of 14 (32%) patients presented cardiac tissue feature abnormalities, and a total of 9 (20%) patients had a myocarditis-like injury based on cardiac MRI 2018 Lake Louise criteria. When we further assessed the T1 and T2 mapping values for of patients' individual, abnormal raised global native T1, T2, and extracellular volume were seen in 6 (14%), 6 (14%), and 4 (9%) patients, respectively. Comparing with controls, the patients had lower LV global longitudinal strain and (−22.2 ± 2.8% vs. −24.6 ± 2.0%, P < 0.001) and global circumferential strain (−20.7 ± 6.8% vs. −24.3 ± 2.9%, P = 0.014), but higher global native T1 (1318.8 ± 55.5 ms vs. 1282.9 ± 38.1 ms, P = 0.006). Four (9%) patients presented myocardial late gadolinium enhancement with subepicardial pattern mostly common seen, and two (5%) patients presented pericardial enhancement. Conclusions: The cardiac MRI could detect subclinical functional and myocardial tissue characteristic abnormalities in individuals who were recovering from Delta Variant without cardiac-related clinical findings. The native T1 mapping and strain imaging may be a sensitive tool for the noninvasive detection of a subset of patients who are at risk for cardiac sequelae and more prone to myocardial damage in survivors with Delta Variant.