Yonghong Wang

Yonghong Wang


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
9 March 2022 in Computers in Biology and Medicine
Verified
Journal Article
Open access
XWXiaoxing Wu
Xiaoxing Wu
Hsin-Yao WangHsin-Yao Wang
Hsin-Yao Wang
PSPeichang Shi
Peichang Shi
RSRong Sun
Rong Sun
XWXiaolin Wang
Xiaolin Wang
YWYonghong Wang
Yonghong Wang
Machine learning (ML) has emerged as a superior method for the analysis of large datasets. Application of ML is often hindered by incompleteness of the data which is particularly evident when approaching disease screening data due to varied testing regimens across medical institutions. Here we explored the utility of multiple ML algorithms to predict cancer risk when trained using a large but incomplete real-world dataset of tumor marker (TM) values. TM screening data were collected from a large asymptomatic cohort (n = 163,174) at two independent medical centers. The cohort included 785 individuals who were subsequently diagnosed with cancer. Data included levels of up to eight TMs, but for most subjects, only a subset of the biomarkers were tested. In some instances, TM values were available at multiple time points, but intervals between tests varied widely. The data were used to train and test various machine learning models to evaluate their robustness for predicting cancer risk. Multiple methods for data imputation were explored and models were developed for both single time-point as well as time-series data. The ML algorithm, long short-term memory (LSTM), demonstrated superiority over other models for dealing with irregular medical data. A cancer risk prediction tool was trained and validated for a single time-point test of a TM panel including up to four biomarkers (AUROC = 0.831, 95% CI: 0.827-0.835) which outperformed a single threshold method using the same biomarkers. A second model relying on time series data of up to four time-points for 5 TMs had an AUROC of 0.931. A cancer risk prediction tool was developed by training a LSTM model using a large but incomplete real-world dataset of TM values. The LSTM model was best able to handle irregular data compared to other ML models. The use of time-series TM data can further improve the predictive performance of LSTM models even when the intervals between tests vary widely. These risk prediction tools are useful to direct subjects to further screening sooner, resulting in earlier detection of occult tumors.

1 March 2019 in Genes & Diseases
Verified
Journal Article
Open access
XWXiaolin Wang
Xiaolin Wang
YZYongli Zhou
Yongli Zhou
MZMingjun Zhang
Mingjun Zhang
YWYonghong Wang
Yonghong Wang
BQBo Qin
Bo Qin
The methylenetetrahydrofolate reductase (MTHFR) genotypes 677CT and 677TT are associated with elevated serum homocysteine (Hcy) levels by means of lowering the activity of MTHFR, and the increase in serum Hcy may be linked to increased susceptibility to non-alcoholic fatty liver disease (NAFLD). However, there are contradictory reports of the relationship among the MTHFR 677CT gene polymorphism, Hcy, and NAFLD. Therefore, the aim of this study was to identify potential associations and interactions of either Hcy levels or the MTHFR 677CT gene polymorphism with the susceptibility to NAFLD in a Chinese population. The association between the MTHFR 677 CT gene polymorphism and Hcy levels was determined in 243 subjects with NAFLD and 388 healthy subjects without NAFLD using polymerase chain reaction-restriction fragment length polymorphism analysis and high-performance liquid chromatography. In subjects with NAFLD, there was no statistical difference in the genotypic and allelic frequencies of the MTHFR 677 CT gene polymorphism, while serum Hcy levels were significantly higher in subjects with NAFLD. Furthermore, these results strongly suggest that the MTHFR 677CT gene polymorphism and NAFLD have a potential synergistic effect on Hcy elevation, although the MTHFR 677CT gene polymorphism was not correlated with NAFLD in a Chinese population.

13 May 2020 in BMC Cardiovascular Disorders
Verified
Journal Article
Open access
PDF file
XPXulei Peng
Xulei Peng
YZYongli Zhou
Yongli Zhou
XWXiaoxing Wu
Xiaoxing Wu
XWXiaolin Wang
Xiaolin Wang
HBHuili Bai
Huili Bai
YWYonghong Wang
Yonghong Wang
Background: Uncertainty still remains on the correlation of methylenetetrahydrofolate reductase (MTHFR) variant C677T with risk of carotid atherosclerosis (CAS), and there is a lack of reports on C677T/MTHFR in the Asian population. The association of C677T/MTHFR polymorphisms with CAS in the Chinese Han population in Chongqing was investigated in the present study. Methods: Subjects (n = 730, 214 females and 516 males, Han ethnicity) who provided an informed consent were randomly selected from the general population of Chongqing, China. Polymerase chain reaction-restriction fragment length polymorphism and Sanger sequencing genotyping assays were used to determine the MTHFR genotypes. The atherosclerosis index of the intima-media thickness (IMT) was measured by high-resolution ultrasound to evaluate the CAS. Less than 1.0 mm was considered as normal for IMT, 1.0–1.5 mm was considered as thickening, and ≥ 1.5 mm and a local bulge thickened in the lumen was considered as CAS. According to the carotid ultrasonography results, these subjects were divided into two groups: CAS-group (IMT ≥ 1.0 mm) and control group (IMT < 1.0 mm). Results: The frequency of C/T heterozygotes, T/T homozygotes genotype was significantly higher in the subjects with CAS (62% vs. 36.9%; 16.2% vs. 9.5%; 47.2% vs. 27.9%, P < 0.05), while the frequency of C/C homozygotes and C allele was significantly lower (21.8% vs. 53.7%; 52.8% vs. 72.1%, P < 0.05), when compared to the control group. The risk of CAS was higher for subjects with C/T heterozygotes and T/T homozygotes (OR = 4.06, 95% CI: 2.76–5.98, P < 0.001 and OR = 3.14, 95% CI: 1.73–5.69, P < 0.001, respectively), when compared to the subjects with the C/C genotype. In the model 1 (CT + TT versus CC), C677T/MTHFR was significantly associated with the prevalence of CAS, and the all adjusted OR values for CAS were 3.87 (95% CI, 2.67 to 5.62) in all, 17.18 (95% CI, 7.27 to 40.49) in women and 2.57 (95% CI, 1.65 to 3.99) in men after adjusting for potential confounding factors. Conclusions: The present study suggests that a mutation in the methylenetetrahydrofolate reductase gene is a risk factor of CAS in the Chinese Han population.