Liang Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Liang Zhu has a total of 81 co-authors. Here are the top co-authors by number of shared publications:
- Jianguo Sun
Department of Statistics and Data Science Southern University of Science and Technology Shenzhen China
5 shared publications Leslie L. Robison
Department of Epidemiology and Cancer Control, St. Jude Children’s Research Hospital, Memphis, Tennessee
4 shared publications- Leslie L. Robison
Department of Epidemiology and Cancer Control, St. Jude Children’s Research Hospital, Memphis, TN 38105, USA
3 shared publications - Juneyoung Lee
Department of Neurology, McGovern Medical School, The University of Texas Health Science Center at Houston, Houston, USA
2 shared publications - Louise D. McCullough
Department of Neurology, McGovern Medical School, The University of Texas Health Science Center at Houston, Houston, USA
2 shared publications - Melissa M. Hudson
Department of Epidemiology and Cancer Control, St. Jude Children's Research Hospital, Memphis, TN, USA
2 shared publications
Latest Publications
- 2 March 2021
- Published by Wolters Kluwer Health in Journal of the American Society of Nephrology
- Vol. 32 (4) , 983-993
Kidney Function after Treatment for Childhood Cancer: A Report from the St. Jude Lifetime Cohort Study
Background Survivors of childhood cancer may be at increased risk for treatment-related kidney dysfunction. Although associations with acute kidney toxicity are well described, evidence informing late kidney sequelae is less robust. Methods To define the prevalence of and risk factors for impaired kidney function among adult survivors of childhood cancer who had been diagnosed ≥10 years earlier, we evaluated kidney function (eGFR and proteinuria). We abstracted information from medical records about exposure to chemotherapeutic agents, surgery, and radiation treatment and evaluated the latter as the percentage of the total kidney volume treated with ≥5 Gy (V5), ≥10 Gy (V10), ≥15 Gy (V15), and ≥20 Gy (V20). We also used multivariable logistic regression models to assess demographic and clinical factors associated with impaired kidney function and Elastic Net to perform model selection for outcomes of kidney function. Results Of the 2753 survivors, 51.3% were men, and 82.5% were non-Hispanic White. Median age at diagnosis was 7.3 years (interquartile range [IQR], 3.3–13.2), and mean age was 31.4 years (IQR, 25.8–37.8) at evaluation. Time from diagnosis was 23.2 years (IQR, 17.6–29.7). Approximately 2.1% had stages 3–5 CKD. Older age at evaluation; grade ≥2 hypertension; increasing cumulative dose of ifosfamide, cisplatin, or carboplatin; treatment ever with a calcineurin inhibitor; and volume of kidney irradiated to ≥5 or ≥10 Gy increased the odds for stages 3–5 CKD. Nephrectomy was significantly associated with stages 3–5 CKD in models for V15 or V20. Conclusions We found that 2.1% of our cohort of childhood cancer survivors had stages 3–5 CKD. These data may inform screening guidelines and new protocol development.
- 2 March 2021
- Published by Wolters Kluwer Health in Journal of the American Society of Nephrology
- Vol. 32 (4) , 983-993
Kidney Function after Treatment for Childhood Cancer: A Report from the St. Jude Lifetime Cohort Study
Background Survivors of childhood cancer may be at increased risk for treatment-related kidney dysfunction. Although associations with acute kidney toxicity are well described, evidence informing late kidney sequelae is less robust. Methods To define the prevalence of and risk factors for impaired kidney function among adult survivors of childhood cancer who had been diagnosed ≥10 years earlier, we evaluated kidney function (eGFR and proteinuria). We abstracted information from medical records about exposure to chemotherapeutic agents, surgery, and radiation treatment and evaluated the latter as the percentage of the total kidney volume treated with ≥5 Gy (V5), ≥10 Gy (V10), ≥15 Gy (V15), and ≥20 Gy (V20). We also used multivariable logistic regression models to assess demographic and clinical factors associated with impaired kidney function and Elastic Net to perform model selection for outcomes of kidney function. Results Of the 2753 survivors, 51.3% were men, and 82.5% were non-Hispanic White. Median age at diagnosis was 7.3 years (interquartile range [IQR], 3.3–13.2), and mean age was 31.4 years (IQR, 25.8–37.8) at evaluation. Time from diagnosis was 23.2 years (IQR, 17.6–29.7). Approximately 2.1% had stages 3–5 CKD. Older age at evaluation; grade ≥2 hypertension; increasing cumulative dose of ifosfamide, cisplatin, or carboplatin; treatment ever with a calcineurin inhibitor; and volume of kidney irradiated to ≥5 or ≥10 Gy increased the odds for stages 3–5 CKD. Nephrectomy was significantly associated with stages 3–5 CKD in models for V15 or V20. Conclusions We found that 2.1% of our cohort of childhood cancer survivors had stages 3–5 CKD. These data may inform screening guidelines and new protocol development.
- Open Access
- 1 March 2021
- Published by Elsevier in Journal of Stroke and Cerebrovascular Diseases
- Vol. 30 (3) , 105602
IAT-TiMeS: Intra-Arterial Thrombectomy Transfer Metric Study in Texas
- 1 March 2021
- Published by Elsevier in Journal of Stroke and Cerebrovascular Diseases
- Vol. 30 (3) , 105602
Open AccessIAT-TiMeS: Intra-Arterial Thrombectomy Transfer Metric Study in Texas
- Open Access
- 24 December 2020
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 22 (1) , 99
Post-Stroke Social Isolation Reduces Cell Proliferation in the Dentate Gyrus and Alters miRNA Profiles in the Aged Female Mice Brain
Social isolation and loneliness are risk factors for stroke. Elderly women are more likely to be isolated. Census data shows that in homeowners over the age of 65, women are much more likely to live alone. However, the underlying mechanisms of the detrimental effects of isolation have not been well studied in older females. In this study, we hypothesized that isolation impairs post-stroke recovery in aged female mice, leading to dysregulated microRNAs (miRNAs) in the brain, including those previously shown to be involved in response to social isolation (SI). Aged C57BL/6 female mice were subjected to a 60-min middle cerebral artery occlusion and were randomly assigned to either single housing (SI) or continued pair housing (PH) immediately after stroke for 15 days. SI immediately after stroke led to significantly more brain tissue loss after stroke and higher mortality. Furthermore, SI significantly delayed motor and sensory recovery and worsened cognitive function, compared to PH. A decrease in cell proliferation was seen in the dentate gyrus of SI mice assessed by bromodeoxyuridine (BrdU) labeling. miRNAome data analysis revealed changes in several miRNAs in the brain, such as miR-297a-3p and miR-200c-3p, which are known to regulate pathways involved in cell proliferation. In conclusion, our data suggest that SI can lead to a poor post-stroke recovery in aged females and dysregulation of miRNAs and reduced hippocampal cell proliferation.
- 24 December 2020
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 22 (1) , 99
Open AccessPost-Stroke Social Isolation Reduces Cell Proliferation in the Dentate Gyrus and Alters miRNA Profiles in the Aged Female Mice Brain
Social isolation and loneliness are risk factors for stroke. Elderly women are more likely to be isolated. Census data shows that in homeowners over the age of 65, women are much more likely to live alone. However, the underlying mechanisms of the detrimental effects of isolation have not been well studied in older females. In this study, we hypothesized that isolation impairs post-stroke recovery in aged female mice, leading to dysregulated microRNAs (miRNAs) in the brain, including those previously shown to be involved in response to social isolation (SI). Aged C57BL/6 female mice were subjected to a 60-min middle cerebral artery occlusion and were randomly assigned to either single housing (SI) or continued pair housing (PH) immediately after stroke for 15 days. SI immediately after stroke led to significantly more brain tissue loss after stroke and higher mortality. Furthermore, SI significantly delayed motor and sensory recovery and worsened cognitive function, compared to PH. A decrease in cell proliferation was seen in the dentate gyrus of SI mice assessed by bromodeoxyuridine (BrdU) labeling. miRNAome data analysis revealed changes in several miRNAs in the brain, such as miR-297a-3p and miR-200c-3p, which are known to regulate pathways involved in cell proliferation. In conclusion, our data suggest that SI can lead to a poor post-stroke recovery in aged females and dysregulation of miRNAs and reduced hippocampal cell proliferation.
- 3 December 2020
- Published by Wiley in Statistics in Medicine
- Vol. 40 (5) , 1262-1271
Regression analysis of mixed panel count data with informative indicator processes
Panel count data occur often in event history studies and in these situations, one observes only incomplete information, the number of events rather than the occurrence times of each event, about the point processes of interest.2 Sometimes one may have to face a more complicated type of panel count data, mixed panel count data in which instead of the number of events, one only knows if there is an occurrence of an event.3 Furthermore, this may depend on the underlying point process of interest or in other words, the point process of interest and the observation type process may be related. To address this, a sieve maximum likelihood estimation approach is proposed with the use of Bernstein polynomials, and for the implementation, an EM algorithm is developed. To assess the finite sample performance of the proposed approach, a simulation study is conducted and suggests that it works well for practical situations. The method is then applied to a motivating example about cancer survivors.
- 3 December 2020
- Published by Wiley in Statistics in Medicine
- Vol. 40 (5) , 1262-1271
Regression analysis of mixed panel count data with informative indicator processes
Panel count data occur often in event history studies and in these situations, one observes only incomplete information, the number of events rather than the occurrence times of each event, about the point processes of interest.2 Sometimes one may have to face a more complicated type of panel count data, mixed panel count data in which instead of the number of events, one only knows if there is an occurrence of an event.3 Furthermore, this may depend on the underlying point process of interest or in other words, the point process of interest and the observation type process may be related. To address this, a sieve maximum likelihood estimation approach is proposed with the use of Bernstein polynomials, and for the implementation, an EM algorithm is developed. To assess the finite sample performance of the proposed approach, a simulation study is conducted and suggests that it works well for practical situations. The method is then applied to a motivating example about cancer survivors.
- Open Access
- 1 November 2020
- Published by Elsevier in Brain, Behavior, and Immunity
- Vol. 90, 235-247
Peripherally-sourced myeloid antigen presenting cells increase with advanced aging
- 1 November 2020
- Published by Elsevier in Brain, Behavior, and Immunity
- Vol. 90, 235-247
Open AccessPeripherally-sourced myeloid antigen presenting cells increase with advanced aging
- 17 August 2020
- Published by Springer Nature in Statistics in Biosciences
- Vol. 13 (1) , 178-195
Regression Analysis of Mixed Panel-Count Data with Application to Cancer Studies
Both panel-count data and panel-binary data are common data types in recurrent event studies. Because of inconsistent questionnaires or missing data during the follow-ups, mixed data types need to be addressed frequently. A recently proposed semiparametric approach uses a proportional means model to facilitate regression analyses of mixed panel-count and panel-binary data. This method can use all available information regardless of the record type and provide unbiased estimates. However, the large number of nuisance parameters in the nonparametric baseline hazard function makes the estimating procedure very complicated and time-consuming. We approximated the baseline hazard function to simplify the estimating procedure. Simulation studies showed that our method performed similarly to that of the previous semiparametric likelihood-based method, but with much faster speed. Approximating the baseline hazard not only reduced the computational burden but also made it possible to implement the estimating procedure in a standard software, such as SAS.
- 17 August 2020
- Published by Springer Nature in Statistics in Biosciences
- Vol. 13 (1) , 178-195
Regression Analysis of Mixed Panel-Count Data with Application to Cancer Studies
Both panel-count data and panel-binary data are common data types in recurrent event studies. Because of inconsistent questionnaires or missing data during the follow-ups, mixed data types need to be addressed frequently. A recently proposed semiparametric approach uses a proportional means model to facilitate regression analyses of mixed panel-count and panel-binary data. This method can use all available information regardless of the record type and provide unbiased estimates. However, the large number of nuisance parameters in the nonparametric baseline hazard function makes the estimating procedure very complicated and time-consuming. We approximated the baseline hazard function to simplify the estimating procedure. Simulation studies showed that our method performed similarly to that of the previous semiparametric likelihood-based method, but with much faster speed. Approximating the baseline hazard not only reduced the computational burden but also made it possible to implement the estimating procedure in a standard software, such as SAS.
- 16 July 2020
- Published by Wiley in Biometrical Journal
- Vol. 62 (8) , 1909-1925
Nonparametric screening and feature selection for ultrahigh‐dimensional Case II interval‐censored failure time data
For the analysis of ultrahigh‐dimensional data, the first step is often to perform screening and feature selection to effectively reduce the dimensionality while retaining all the active or relevant variables with high probability. For this, many methods have been developed under various frameworks but most of them only apply to complete data. In this paper, we consider an incomplete data situation, case II interval‐censored failure time data, for which there seems to be no screening procedure. Basing on the idea of cumulative residual, a model‐free or nonparametric method is developed and shown to have the sure independent screening property. In particular, the approach is shown to tend to rank the active variables above the inactive ones in terms of their association with the failure time of interest. A simulation study is conducted to demonstrate the usefulness of the proposed method and, in particular, indicates that it works well with general survival models and is capable of capturing the nonlinear covariates with interactions. Also the approach is applied to a childhood cancer survivor study that motivated this investigation.
- 16 July 2020
- Published by Wiley in Biometrical Journal
- Vol. 62 (8) , 1909-1925
Nonparametric screening and feature selection for ultrahigh‐dimensional Case II interval‐censored failure time data
For the analysis of ultrahigh‐dimensional data, the first step is often to perform screening and feature selection to effectively reduce the dimensionality while retaining all the active or relevant variables with high probability. For this, many methods have been developed under various frameworks but most of them only apply to complete data. In this paper, we consider an incomplete data situation, case II interval‐censored failure time data, for which there seems to be no screening procedure. Basing on the idea of cumulative residual, a model‐free or nonparametric method is developed and shown to have the sure independent screening property. In particular, the approach is shown to tend to rank the active variables above the inactive ones in terms of their association with the failure time of interest. A simulation study is conducted to demonstrate the usefulness of the proposed method and, in particular, indicates that it works well with general survival models and is capable of capturing the nonlinear covariates with interactions. Also the approach is applied to a childhood cancer survivor study that motivated this investigation.
- 11 July 2020
- Published by Wiley in Statistics in Medicine
- Vol. 39 (23) , 3120-3134
Variable selection for high‐dimensional partly linear additive Cox model with application to Alzheimer's disease
Variable selection has been discussed under many contexts and especially, a large literature has been established for the analysis of right‐censored failure time data. In this article, we discuss an interval‐censored failure time situation where there exist two sets of covariates with one being low‐dimensional and having possible nonlinear effects and the other being high‐dimensional. For the problem, we present a penalized estimation procedure for simultaneous variable selection and estimation, and in the method, Bernstein polynomials are used to approximate the involved nonlinear functions. Furthermore, for implementation, a coordinate‐wise optimization algorithm, which can accommodate most commonly used penalty functions, is developed. A numerical study is performed for the evaluation of the proposed approach and suggests that it works well in practical situations. Finally the method is applied to an Alzheimer's disease study that motivated this investigation.
- 11 July 2020
- Published by Wiley in Statistics in Medicine
- Vol. 39 (23) , 3120-3134
Variable selection for high‐dimensional partly linear additive Cox model with application to Alzheimer's disease
Variable selection has been discussed under many contexts and especially, a large literature has been established for the analysis of right‐censored failure time data. In this article, we discuss an interval‐censored failure time situation where there exist two sets of covariates with one being low‐dimensional and having possible nonlinear effects and the other being high‐dimensional. For the problem, we present a penalized estimation procedure for simultaneous variable selection and estimation, and in the method, Bernstein polynomials are used to approximate the involved nonlinear functions. Furthermore, for implementation, a coordinate‐wise optimization algorithm, which can accommodate most commonly used penalty functions, is developed. A numerical study is performed for the evaluation of the proposed approach and suggests that it works well in practical situations. Finally the method is applied to an Alzheimer's disease study that motivated this investigation.
- Open Access
- 1 May 2018
- Published by Scilight Press Pty Ltd in Journal of Modern Applied Statistical Methods
- Vol. 17 (1) , 18
Robust Estimation and Inference on Current Status Data with Applications to Phase IV Cancer Trial
The use of piecewise exponential distributions was proposed by Rai et al. (2013) for analyzing cardiotoxicity data. Some parametric models are proposed, but the focus is on the Weibull distribution, which overcomes the limitation of piecewise exponential.
- 1 May 2018
- Published by Scilight Press Pty Ltd in Journal of Modern Applied Statistical Methods
- Vol. 17 (1) , 18
Open AccessRobust Estimation and Inference on Current Status Data with Applications to Phase IV Cancer Trial
The use of piecewise exponential distributions was proposed by Rai et al. (2013) for analyzing cardiotoxicity data. Some parametric models are proposed, but the focus is on the Weibull distribution, which overcomes the limitation of piecewise exponential.
- Open Access
- 1 January 2018
- Published by International Press of Boston in Statistics and Its Interface
- Vol. 11 (1) , 91-97
Regression analysis of incomplete data from event history studies with the proportional rates model
International Press of Boston - publishers of scholarly mathematical and scientific journals and books
- 1 January 2018
- Published by International Press of Boston in Statistics and Its Interface
- Vol. 11 (1) , 91-97
Open AccessRegression analysis of incomplete data from event history studies with the proportional rates model
International Press of Boston - publishers of scholarly mathematical and scientific journals and books