Chunting Wang

Chunting Wang

Auto-generated profile, based on publicly available information

Chunting Wang

Department of Critical Care Medicine, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, China

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
1 July 2021 in International Journal of Medical Informatics
Verified
Journal Article
Open access
XSXuan Song
Xuan Song
XLXinyan Liu
Xinyan Liu
FLFei Liu
Fei Liu
CWChunting Wang
Chunting Wang
We aimed to assess whether machine learning models are superior at predicting acute kidney injury (AKI) compared to logistic regression (LR), a conventional prediction model. Eligible studies were identified using PubMed and Embase. A total of 24 studies consisting of 84 prediction models met inclusion criteria. Independent samples t-test was performed to detect mean differences in area under the curve (AUC) between ML and LR models. One-way ANOVA and post-hoc t-tests were performed to assess mean differences in AUC between ML methods. AUC data were similar between ML (0.736 ± 0.116) and LR (0.748 ± 0.057) models (p = 0.538). However, specific ML models, such as gradient boosting (0.838 ± 0.077), exhibited superior performance at predicting AKI as compared to other ML models in the literature (p < 0.05). Creatinine and urine output, standard variables assessed for AKI staging, were classified as significant predictors across multiple ML models, although the majority of significant predictors were unique and study specific. These data suggest that ML models perform equally to that of LR, however ML models exhibit variable performance with some ML models displaying exceptional performance. The variability in ML prediction of AKI can be attributed, in part, to the specific ML model utilized, variable selection and processing, study and subject characteristics, and the steps associated with model training, validation, testing, and calibration.

4 April 2016 in Intensive Care Medicine
Verified
Journal Article
Closed access
PDF file
JZJuan Zeng
Juan Zeng
CWChun-Ting Wang
Chun-Ting Wang
FZFu-Shen Zhang
Fu-Shen Zhang
FQFeng Qi
Feng Qi
SWShi-Fu Wang
Shi-Fu Wang
YWYu-Ping Wang
Yu-Ping Wang

28 April 2020 in Critical Care
Verified
Journal Article
Open access
PDF file
XSXuan Song
Xuan Song
XLXinyan Liu
Xinyan Liu
CWChunting Wang
Chunting Wang

1 September 2020 in Telemedicine and e-Health
Verified
Journal Article
Closed access
PGPeng Guo
Peng Guo
WQWei Qiao
Wei Qiao
YSYing Sun
Ying Sun
FLFenglin Liu
Fenglin Liu
CWChunting Wang
Chunting Wang
Background: Since 1990s, directly observed therapy (DOT) has been the standard-of-care for tuberculosis (TB), although it is cumbersome for patients as well as service providers. For raising implementation, an alternative delivery method with good potential is telehealth. The current study assessed the clinical and cost benefit of video directly observed therapy (VDOT), compared with DOT service. Methods: This prospective randomized controlled trial randomized adults with bacteriologically confirmed pulmonary TB to the intervention (VDOT) or control (DOT) group. The observation data for DOT and VDOT were updated by observers until the end of treatment or until the study concluded. The primary outcome was the TB treatment result defined by the World Health Organization (WHO) as used in some other studies conducted in North India and England as follows: good (cured and treatment completed), poor (death and failure), relocation, and lost to follow-up and others (refused, adverse reaction, not a TB case). Other secondary measures were treatment adherence, patient satisfaction, time and cost spent on DOT or VDOT. Results: On analyzing the results from 405 participants from each study arm, we found very high rates of treatment completion (96.1% with VDOT vs. 94.6% with DOT). The two observed treatment methods had no statistical differences, and all could accomplish their tasks well. Average time per dose observed was 16.5 min (standard deviation [SD] 12.1) for VDOT, while 44.1 min (SD 3.7) for DOT (including travel time), p < 0.01. And the cost incurred on VDOT was ¥34.3 (SD 3.8) manmo, which was statistically lower compared with ¥71.6 (SD 49.7) manmo in the DOT group, p < 0.01. Most of the patients in both groups believed that observed treatment (VDOT/DOT) helped them not to miss doses (185 [93.0%] vs. 171 [86.7%], p = 0.057). Patients in the VDOT group had a better experience compared with those in DOT group. They thought the way was convenient and comfortable (191 [96.0%] vs. 111 [56.6%], p < 0.001), would choose the original way if necessary (191 [96.0%] vs. 113 [57.7%], p < 0.001), and would recommend the method to other patients (191 [96.0%] vs. 113 [57.7%], p < 0.001). Conclusion: The study showed that VDOT enabled meaningful direct observation for TB patients through mobile devices, which was highly acceptable to patients and health care providers. It also saved time and is a cost-effective method, enabling the use of the saved money to other much-needed areas for TB.

1 June 2016 in Biochemical and Biophysical Research Communications
Verified
Journal Article
Closed access
CLChunping Li
Chunping Li
DMDandan Ma
Dandan Ma
MCMan Chen
Man Chen
LZLinlin Zhang
Linlin Zhang
LZLin Zhang
Lin Zhang
CWChunting Wang
Chunting Wang

21 January 2019 in Frontiers in Pharmacology
Verified
Journal Article
Open access
PDF file
LGLisha Guo
Lisha Guo
MMMei Meng
Mei Meng
YWYaping Wei
Yaping Wei
FLFeixue Lin
Feixue Lin
YJYing Jiang
Ying Jiang
XGXiaosun Guo
Xiaosun Guo
Aims: Clinical studies showed that the use of probiotics during critical illness reduced nosocomial infection and improved clinical outcome. However, the functional mechanisms of probiotics is remains unclear. Therefore the aim of current study is to explore the protective effects and understand the underlying mechanisms for the beneficial effects of live combined Bacillus subtilis and Enterococcus faecium (LCBE) in cecal ligation puncture (CLP)-induced sepsis. Methods and Results: Seven-week-old C57BL/6J mice were divided into three groups: sham group (6 mice), CLP-control group (20 mice, pretreatment with saline for 7 days before CLP surgery) and CLP-probiotics group (14 mice, pretreatment with LCBE enteric-coated capsules for 7 days before CLP surgery). In survival experiment, mice were monitored for 7 days after CLP. After the procedure, mice were sacrificed, and, serum, and peritoneal lavage fluid were collected and intestinal ileal samples were harvested. Results: Our results showed that the mortality was significantly reduced in mice CLP-probiotics group vs. CLP-control group (P < 0.05). Also, treatment CLP-probiotics group decreased the injury scores CLP-probiotics group when compared to CLP-control group. Additionally, levels of pro-inflammatory cytokines IL-6 and TNF-α levels in the serum and intestinal ileal tissues of CLP-probiotics group were reduced when compared to CLP-control group (P < 0.05). However, no significant differences in anti-inflammatory levels of IL-10 and TGF-β1 were observed between CLP-control and CLP-probiotic groups. Furthermore, our experiments showed that that probiotic treatment suppressed the macrophage activation and transformation from M-type to M1-type, inhibited the mast cells (MCs) degranulation, and activation of AKT (kinase B) pathway. Conclusion: In conclusion, our data shows that probiotics have a protective role in CLP septic mice through reducing intestinal inflammation, altering macrophage polarization and MCs degranulation, and regulating AKT signaling. Significance and Impact of Study: This study demonstrated the protective effects and mechanisms involved in the protective role of live combined Bacillus subtilis and Enterococcus faecium (LCBE) in CLP-induced septic mice model.