Haotian Zou
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
Haotian Zou has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Sheng Luo
Duke University
10 shared publications Alzheimer'S Disease Neuroimaging Initiative
2 shared publicationsGlenn T. Stebbins
Department of Neurological Sciences Rush University Medical Center Chicago Illinois USA
2 shared publicationsYuanyuan Guo
Department of Biostatistics and Bioinformatics Duke University Durham North Carolina USA
2 shared publicationsAnne Pedata
Critical Path Institute Tucson Arizona USA
1 shared publication- Baoshan Zhang
Department of Biostatistics and Bioinformatics Duke University Durham North Carolina USA
1 shared publication
Latest Publications
- 14 May 2026
- Published by Wiley in Statistics in Medicine
- Vol. 45 (10-12) , e70601
Longitudinal Sparse Single‐Omics Factor Analysis for High‐Dimensional Blood Biomarkers in Alzheimer's Disease
Alzheimer's disease (AD) is a progressive neurodegenerative disorder whose molecular mechanisms involve multiple biological pathways. Longitudinal blood‐based omics data, such as lipidomics and metabolomics profiles, offer promising noninvasive biomarkers for early detection and prognosis, yet they are high‐dimensional, sparse, and exhibit complex temporal and cross‐feature correlations. The primary goal of this study is to identify which omics data types are most strongly associated with time to dementia onset in patients with mild cognitive impairment (MCI) at baseline. To address this, we propose a longitudinal sparse single‐omics factor analysis (LS‐SOFA) framework that models each omics view through view‐specific latent factors and feature‐weight matrices, with temporal dynamics captured by functional principal component analysis (FPCA). The resulting functional principal component (FPC) scores are incorporated into a survival model to test whether each omics view is associated with time to dementia onset. An efficient covariance‐based estimation algorithm substantially reduces computational and memory cost, enabling large‐scale application in the Alzheimer's Disease Neuroimaging Initiative (ADNI) study. In simulations, LS‐SOFA achieves higher longitudinal estimation accuracy and more stable hypothesis testing than competing methods. Applied to five blood‐based omics views from ADNI, LS‐SOFA identified plasma lipidomics and serum metabolomics from FIA and UPLC as significantly associated with dementia risk after FDR adjustment, with nominal evidence of association for gut microbial metabolomics from serum. The top features within each omics view reveal biologically interpretable metabolic pathways that may serve as blood‐based biomarkers for AD progression.
- 14 May 2026
- Published by Wiley in Statistics in Medicine
- Vol. 45 (10-12) , e70601
Longitudinal Sparse Single‐Omics Factor Analysis for High‐Dimensional Blood Biomarkers in Alzheimer's Disease
Alzheimer's disease (AD) is a progressive neurodegenerative disorder whose molecular mechanisms involve multiple biological pathways. Longitudinal blood‐based omics data, such as lipidomics and metabolomics profiles, offer promising noninvasive biomarkers for early detection and prognosis, yet they are high‐dimensional, sparse, and exhibit complex temporal and cross‐feature correlations. The primary goal of this study is to identify which omics data types are most strongly associated with time to dementia onset in patients with mild cognitive impairment (MCI) at baseline. To address this, we propose a longitudinal sparse single‐omics factor analysis (LS‐SOFA) framework that models each omics view through view‐specific latent factors and feature‐weight matrices, with temporal dynamics captured by functional principal component analysis (FPCA). The resulting functional principal component (FPC) scores are incorporated into a survival model to test whether each omics view is associated with time to dementia onset. An efficient covariance‐based estimation algorithm substantially reduces computational and memory cost, enabling large‐scale application in the Alzheimer's Disease Neuroimaging Initiative (ADNI) study. In simulations, LS‐SOFA achieves higher longitudinal estimation accuracy and more stable hypothesis testing than competing methods. Applied to five blood‐based omics views from ADNI, LS‐SOFA identified plasma lipidomics and serum metabolomics from FIA and UPLC as significantly associated with dementia risk after FDR adjustment, with nominal evidence of association for gut microbial metabolomics from serum. The top features within each omics view reveal biologically interpretable metabolic pathways that may serve as blood‐based biomarkers for AD progression.
- 6 April 2026
- Published by SAGE Publications in Journal of Alzheimer’s Disease
- Vol. 111 (2) , 651-662
Plasma lipid trajectories improve prediction of future Alzheimer's disease
Background: Early identification of individuals at elevated risk for Alzheimer's disease (AD) is critical for prevention. Blood-based biomarkers offer scalable alternatives to cerebrospinal fluid and imaging, but the prognostic value of longitudinal plasma lipid trajectories remains unclear. Objective: To evaluate whether multi-year plasma lipid trajectories improve prediction of AD conversion beyond demographic, clinical, genetic, and neuropsychological measures. Methods: We studied 1150 cognitively normal or mildly impaired Alzheimer's Disease Neuroimaging Initiative participants; 329 progressed to AD dementia over a mean follow-up of 2.3 years. Plasma lipidomics quantified 749 lipid species by high-resolution LC–MS. Trajectories were summarized using functional principal component analysis and related to time to conversion using covariate-adjusted Cox proportional hazards models. Predictive performance was assessed by concordance index and likelihood-ratio tests. Results: Cross-sectional lipid profiles modestly improved prediction beyond demographic and clinical covariates, and longitudinal lipid trajectories yielded small additional gains. Ether-linked triglycerides showed the strongest longitudinal associations with conversion, with TG(O-50:1) [NL-18:1] exhibiting the most robust signal. Neuropsychological measures provided substantially stronger discrimination, and lipid trajectories added limited value once cognitive information was included. Nevertheless, longitudinal lipid changes contributed consistent improvements in models without neuropsychological predictors, supporting their role as complementary blood-based markers in settings where standardized cognitive assessments are unavailable or impractical. Conclusions: Plasma lipid trajectories capture biologically relevant metabolic change associated with AD progression and provide complementary predictive information. Longitudinal lipidomic profiling may support early risk stratification and cohort enrichment when cognitive assessments are unavailable.
- 6 April 2026
- Published by SAGE Publications in Journal of Alzheimer’s Disease
- Vol. 111 (2) , 651-662
Plasma lipid trajectories improve prediction of future Alzheimer's disease
Background: Early identification of individuals at elevated risk for Alzheimer's disease (AD) is critical for prevention. Blood-based biomarkers offer scalable alternatives to cerebrospinal fluid and imaging, but the prognostic value of longitudinal plasma lipid trajectories remains unclear. Objective: To evaluate whether multi-year plasma lipid trajectories improve prediction of AD conversion beyond demographic, clinical, genetic, and neuropsychological measures. Methods: We studied 1150 cognitively normal or mildly impaired Alzheimer's Disease Neuroimaging Initiative participants; 329 progressed to AD dementia over a mean follow-up of 2.3 years. Plasma lipidomics quantified 749 lipid species by high-resolution LC–MS. Trajectories were summarized using functional principal component analysis and related to time to conversion using covariate-adjusted Cox proportional hazards models. Predictive performance was assessed by concordance index and likelihood-ratio tests. Results: Cross-sectional lipid profiles modestly improved prediction beyond demographic and clinical covariates, and longitudinal lipid trajectories yielded small additional gains. Ether-linked triglycerides showed the strongest longitudinal associations with conversion, with TG(O-50:1) [NL-18:1] exhibiting the most robust signal. Neuropsychological measures provided substantially stronger discrimination, and lipid trajectories added limited value once cognitive information was included. Nevertheless, longitudinal lipid changes contributed consistent improvements in models without neuropsychological predictors, supporting their role as complementary blood-based markers in settings where standardized cognitive assessments are unavailable or impractical. Conclusions: Plasma lipid trajectories capture biologically relevant metabolic change associated with AD progression and provide complementary predictive information. Longitudinal lipidomic profiling may support early risk stratification and cohort enrichment when cognitive assessments are unavailable.
- Open Access
- 2 September 2025
- Published by Wiley in Alzheimer's & Dementia
- Vol. 21 (9) , e70094
Bayesian integration of longitudinal and survival outcomes in Alzheimer's disease prediction
INTRODUCTION: Accurate prediction of Alzheimer's disease (AD) dementia onset and progression to mild cognitive impairment (MCI) is crucial for early intervention and clinical trial design. This study presents a predictive framework leveraging Bayesian model averaging (BMA) with a multivariate functional mixed model (MFMM) to integrate multivariate longitudinal outcomes and survival data. METHODS: The training cohort included 1012 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI). The validation cohort comprised 2087 participants from the National Alzheimer's Coordinating Center (NACC). BMA methods, including stacking and pseudo‐BMA+, aggregated predictions across candidate models to enhance accuracy and robustness. Predictive performance was evaluated using the C‐index, a measure of discrimination. RESULTS: Compared to the composite model, BMA improved prediction accuracy. The C‐index was 0.777 (stacking) and 0.771 (pseudo‐BMA+) in ADNI and 0.743 and 0.738 in NACC. DISCUSSION: This framework offers a robust tool for personalized medicine, enabling accurate predictions and enhanced generalizability across diverse populations. Highlights: We introduced a novel joint modeling framework integrating multivariate longitudinal outcomes (Mini‐Mental State Examination and Clinical Dementia Rating Sum of Boxes) with survival data to predict Alzheimer's disease dementia onset and progression. We validated the framework across complementary datasets: Alzheimer's Disease Neuroimaging Initiative (training) and National Alzheimer's Coordinating Center (NACC; validation), with NACC providing a demographically diverse population to assess generalizability. The model enhanced predictive accuracy using Bayesian model averaging, which synthesizes insights across multiple models to reduce uncertainty and improve robustness. The model demonstrated consistent and clinically relevant performance, supporting its applicability for early intervention, precision medicine, and clinical trial design.
- 2 September 2025
- Published by Wiley in Alzheimer's & Dementia
- Vol. 21 (9) , e70094
Open AccessBayesian integration of longitudinal and survival outcomes in Alzheimer's disease prediction
INTRODUCTION: Accurate prediction of Alzheimer's disease (AD) dementia onset and progression to mild cognitive impairment (MCI) is crucial for early intervention and clinical trial design. This study presents a predictive framework leveraging Bayesian model averaging (BMA) with a multivariate functional mixed model (MFMM) to integrate multivariate longitudinal outcomes and survival data. METHODS: The training cohort included 1012 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI). The validation cohort comprised 2087 participants from the National Alzheimer's Coordinating Center (NACC). BMA methods, including stacking and pseudo‐BMA+, aggregated predictions across candidate models to enhance accuracy and robustness. Predictive performance was evaluated using the C‐index, a measure of discrimination. RESULTS: Compared to the composite model, BMA improved prediction accuracy. The C‐index was 0.777 (stacking) and 0.771 (pseudo‐BMA+) in ADNI and 0.743 and 0.738 in NACC. DISCUSSION: This framework offers a robust tool for personalized medicine, enabling accurate predictions and enhanced generalizability across diverse populations. Highlights: We introduced a novel joint modeling framework integrating multivariate longitudinal outcomes (Mini‐Mental State Examination and Clinical Dementia Rating Sum of Boxes) with survival data to predict Alzheimer's disease dementia onset and progression. We validated the framework across complementary datasets: Alzheimer's Disease Neuroimaging Initiative (training) and National Alzheimer's Coordinating Center (NACC; validation), with NACC providing a demographically diverse population to assess generalizability. The model enhanced predictive accuracy using Bayesian model averaging, which synthesizes insights across multiple models to reduce uncertainty and improve robustness. The model demonstrated consistent and clinically relevant performance, supporting its applicability for early intervention, precision medicine, and clinical trial design.
- 19 May 2025
- Published by Wiley in Statistics in Medicine
- Vol. 44 (10-12) , e70105
Integrative Multi‐Omics and Multivariate Longitudinal Data Analysis for Dynamic Risk Estimation in Alzheimer's Disease
Alzheimer's disease (AD) is a complex and progressive neurodegenerative disorder, characterized by diverse cognitive and functional impairments that manifest heterogeneously across individuals, domains, and time. The accurate assessment of AD's severity and progression requires integrating a variety of data modalities, including multivariate longitudinal neuropsychological tests and multi‐omics datasets such as metabolomics and lipidomics. These data sources provide valuable insights into risk factors associated with dementia onset. However, effectively utilizing omics data in dynamic risk estimation for AD progression is challenging due to issues including high dimensionality, heterogeneity, and complex intercorrelations. To address these challenges, we develop a novel joint‐modeling framework that effectively combines multi‐omics factor analysis (MOFA) for dimension reduction and feature extraction with a multivariate functional mixed model (MFMM) for modeling longitudinal outcomes. This integrative joint modeling approach enables dynamic evaluation of dementia risk by leveraging both omics and longitudinal data. We validate the efficacy of our integrative model through extensive simulation studies and its practical application to the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset.
- 19 May 2025
- Published by Wiley in Statistics in Medicine
- Vol. 44 (10-12) , e70105
Integrative Multi‐Omics and Multivariate Longitudinal Data Analysis for Dynamic Risk Estimation in Alzheimer's Disease
Alzheimer's disease (AD) is a complex and progressive neurodegenerative disorder, characterized by diverse cognitive and functional impairments that manifest heterogeneously across individuals, domains, and time. The accurate assessment of AD's severity and progression requires integrating a variety of data modalities, including multivariate longitudinal neuropsychological tests and multi‐omics datasets such as metabolomics and lipidomics. These data sources provide valuable insights into risk factors associated with dementia onset. However, effectively utilizing omics data in dynamic risk estimation for AD progression is challenging due to issues including high dimensionality, heterogeneity, and complex intercorrelations. To address these challenges, we develop a novel joint‐modeling framework that effectively combines multi‐omics factor analysis (MOFA) for dimension reduction and feature extraction with a multivariate functional mixed model (MFMM) for modeling longitudinal outcomes. This integrative joint modeling approach enables dynamic evaluation of dementia risk by leveraging both omics and longitudinal data. We validate the efficacy of our integrative model through extensive simulation studies and its practical application to the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset.
- 18 October 2024
- Published by Wiley in Movement Disorders Clinical Practice
- Vol. 12 (2) , 148-156
Increasing Sensitivity in Patient‐Reported MDS‐UPDRS Items for Predicting Medication Initiation in Early PD
Background: The MDS‐UPDRS Parts IB and II are self‐reported items providing a direct patient voice to the experiences of PD.Objective: To determine the most sensitive combination of MDS‐UPDRS Parts IB and II items that accurately predicted the clinically relevant target of dopaminergic therapy initiation.Methods: Utilizing a longitudinal cohort of de novo non‐treated PD patients, we applied item response theory (IRT) and survival analysis to assess the relationship between baseline patient‐reported symptoms and the later initiation of dopaminergic therapy. The 20 MDS‐UPDRS Parts IB and II items were analyzed for their relationship to PD severity (discrimination) and the amount of information they provided in this determination (information). These parameters were used to develop models of predictive accuracy for initiation of dopaminergic therapy.Results: A six‐item version showed a significantly higher C‐index as compared to the full 20 item model (P = 0.001). This shortened version of the MDS‐UPDRS contained only Part II items and provided a predictive accuracy for initiation of dopaminergic therapy better than the total combined scale score or any other combination.Conclusions: A six‐item “Baseline Outcome Voice” version of patient‐reported MDS‐UPDRS items significantly increases the sensitivity of predicting the key future clinical outcome of starting dopaminergic treatment in early PD. This study also demonstrates how IRT modeling can provide information useful to refining existing measures to identify the most sensitive combination of items honoring the voice of the patient in determining key clinically pertinent decisions. Further research is needed to validate these findings in underrepresented populations.
- 18 October 2024
- Published by Wiley in Movement Disorders Clinical Practice
- Vol. 12 (2) , 148-156
Increasing Sensitivity in Patient‐Reported MDS‐UPDRS Items for Predicting Medication Initiation in Early PD
Background: The MDS‐UPDRS Parts IB and II are self‐reported items providing a direct patient voice to the experiences of PD.Objective: To determine the most sensitive combination of MDS‐UPDRS Parts IB and II items that accurately predicted the clinically relevant target of dopaminergic therapy initiation.Methods: Utilizing a longitudinal cohort of de novo non‐treated PD patients, we applied item response theory (IRT) and survival analysis to assess the relationship between baseline patient‐reported symptoms and the later initiation of dopaminergic therapy. The 20 MDS‐UPDRS Parts IB and II items were analyzed for their relationship to PD severity (discrimination) and the amount of information they provided in this determination (information). These parameters were used to develop models of predictive accuracy for initiation of dopaminergic therapy.Results: A six‐item version showed a significantly higher C‐index as compared to the full 20 item model (P = 0.001). This shortened version of the MDS‐UPDRS contained only Part II items and provided a predictive accuracy for initiation of dopaminergic therapy better than the total combined scale score or any other combination.Conclusions: A six‐item “Baseline Outcome Voice” version of patient‐reported MDS‐UPDRS items significantly increases the sensitivity of predicting the key future clinical outcome of starting dopaminergic treatment in early PD. This study also demonstrates how IRT modeling can provide information useful to refining existing measures to identify the most sensitive combination of items honoring the voice of the patient in determining key clinically pertinent decisions. Further research is needed to validate these findings in underrepresented populations.
- Open Access
- 10 September 2024
- Published by Elsevier in Parkinsonism & Related Disorders
- Vol. 128, 107118
Validating new symptom emergence as a patient-centric outcome measure for PD clinical trials
- 10 September 2024
- Published by Elsevier in Parkinsonism & Related Disorders
- Vol. 128, 107118
Open AccessValidating new symptom emergence as a patient-centric outcome measure for PD clinical trials
- Open Access
- 10 June 2024
- Published by Elsevier in EBioMedicine
- Vol. 105, 105186
Clinical efficacy of CDK4/6 inhibitor plus endocrine therapy in HR-positive/HER2-0 and HER2-low-positive metastatic breast cancer: a secondary analysis of PALOMA-2 and PALOMA-3 trials
- 10 June 2024
- Published by Elsevier in EBioMedicine
- Vol. 105, 105186
Open AccessClinical efficacy of CDK4/6 inhibitor plus endocrine therapy in HR-positive/HER2-0 and HER2-low-positive metastatic breast cancer: a secondary analysis of PALOMA-2 and PALOMA-3 trials
- 20 February 2023
- Published by Wiley in Statistics in Medicine
- Vol. 42 (10) , 1492-1511
Multivariate functional mixed model with MRI data: An application to Alzheimer's disease
Summary: Alzheimer's Disease (AD) is the leading cause of dementia and impairment in various domains. Recent AD studies, (ie, Alzheimer's Disease Neuroimaging Initiative (ADNI) study), collect multimodal data, including longitudinal neurological assessments and magnetic resonance imaging (MRI) data, to better study the disease progression. Adopting early interventions is essential to slow AD progression for subjects with mild cognitive impairment (MCI). It is of particular interest to develop an AD predictive model that leverages multimodal data and provides accurate personalized predictions. In this article, we propose a multivariate functional mixed model with MRI data (MFMM‐MRI) that simultaneously models longitudinal neurological assessments, baseline MRI data, and the survival outcome (ie, dementia onset) for subjects with MCI at baseline. Two functional forms (the random‐effects model and instantaneous model) linking the longitudinal and survival process are investigated. We use Markov Chain Monte Carlo (MCMC) method based on No‐U‐Turn Sampling (NUTS) algorithm to obtain posterior samples. We develop a dynamic prediction framework that provides accurate personalized predictions of longitudinal trajectories and survival probability. We apply MFMM‐MRI to the ADNI study and identify significant associations among longitudinal outcomes, MRI data, and the risk of dementia onset. The instantaneous model with voxels from the whole brain has the best prediction performance among all candidate models. The simulation study supports the validity of the estimation and dynamic prediction method.
- 20 February 2023
- Published by Wiley in Statistics in Medicine
- Vol. 42 (10) , 1492-1511
Multivariate functional mixed model with MRI data: An application to Alzheimer's disease
Summary: Alzheimer's Disease (AD) is the leading cause of dementia and impairment in various domains. Recent AD studies, (ie, Alzheimer's Disease Neuroimaging Initiative (ADNI) study), collect multimodal data, including longitudinal neurological assessments and magnetic resonance imaging (MRI) data, to better study the disease progression. Adopting early interventions is essential to slow AD progression for subjects with mild cognitive impairment (MCI). It is of particular interest to develop an AD predictive model that leverages multimodal data and provides accurate personalized predictions. In this article, we propose a multivariate functional mixed model with MRI data (MFMM‐MRI) that simultaneously models longitudinal neurological assessments, baseline MRI data, and the survival outcome (ie, dementia onset) for subjects with MCI at baseline. Two functional forms (the random‐effects model and instantaneous model) linking the longitudinal and survival process are investigated. We use Markov Chain Monte Carlo (MCMC) method based on No‐U‐Turn Sampling (NUTS) algorithm to obtain posterior samples. We develop a dynamic prediction framework that provides accurate personalized predictions of longitudinal trajectories and survival probability. We apply MFMM‐MRI to the ADNI study and identify significant associations among longitudinal outcomes, MRI data, and the risk of dementia onset. The instantaneous model with voxels from the whole brain has the best prediction performance among all candidate models. The simulation study supports the validity of the estimation and dynamic prediction method.
- Open Access
- 9 August 2022
- Published by Wiley in CPT: Pharmacometrics & Systems Pharmacology
- Vol. 11 (10) , 1382-1392
Application of longitudinal item response theory models to modeling Parkinson’s disease progression
The Movement Disorder Society revised version of the Unified Parkinson’s Disease Rating Scale (MDS‐UPDRS) parts 2 and 3 reflect patient‐reported functional impact and clinician‐reported severity of motor signs of Parkinson’s disease (PD), respectively. Total scores are common clinical outcomes but may obscure important time‐based changes in items. We aim to analyze longitudinal disease progression based on MDS‐UPRDS parts 2 and 3 item‐level responses over time and as functions of Hoehn & Yahr (H&Y) stages 1 and 2 for subjects with early PD. The longitudinal item response theory (IRT) modeling is a novel statistical method addressing limitations in traditional linear regression approaches, such as ignoring varying item sensitivities and the sum score balancing out improvements and declines. We utilized a harmonized dataset consisting of six studies with 3573 subjects with early PD and 14,904 visits, and mean follow‐up time of 2.5 years (±1.57). We applied both a unidimensional (each part separately) and multidimensional (both parts combined) longitudinal IRT models. We assessed the progression rates for both parts, anchored to baseline H&Y stages 1 and 2. Both the uni‐ and multidimensional longitudinal IRT models indicate significant worsening time effects in both parts 2 and 3. Baseline H&Y stage 2 was associated with significantly higher baseline severities, but slower progression rates in both parts, as compared with stage 1. Patients with baseline H&Y stage 1 demonstrated slower progression in part 2 severity compared to part 3, whereas patients with baseline H&Y stage 2 progressed faster in part 2 than part 3. The multidimensional model had a superior fit compared to the unidimensional models and it had excellent model performance.
- 9 August 2022
- Published by Wiley in CPT: Pharmacometrics & Systems Pharmacology
- Vol. 11 (10) , 1382-1392
Open AccessApplication of longitudinal item response theory models to modeling Parkinson’s disease progression
The Movement Disorder Society revised version of the Unified Parkinson’s Disease Rating Scale (MDS‐UPDRS) parts 2 and 3 reflect patient‐reported functional impact and clinician‐reported severity of motor signs of Parkinson’s disease (PD), respectively. Total scores are common clinical outcomes but may obscure important time‐based changes in items. We aim to analyze longitudinal disease progression based on MDS‐UPRDS parts 2 and 3 item‐level responses over time and as functions of Hoehn & Yahr (H&Y) stages 1 and 2 for subjects with early PD. The longitudinal item response theory (IRT) modeling is a novel statistical method addressing limitations in traditional linear regression approaches, such as ignoring varying item sensitivities and the sum score balancing out improvements and declines. We utilized a harmonized dataset consisting of six studies with 3573 subjects with early PD and 14,904 visits, and mean follow‐up time of 2.5 years (±1.57). We applied both a unidimensional (each part separately) and multidimensional (both parts combined) longitudinal IRT models. We assessed the progression rates for both parts, anchored to baseline H&Y stages 1 and 2. Both the uni‐ and multidimensional longitudinal IRT models indicate significant worsening time effects in both parts 2 and 3. Baseline H&Y stage 2 was associated with significantly higher baseline severities, but slower progression rates in both parts, as compared with stage 1. Patients with baseline H&Y stage 1 demonstrated slower progression in part 2 severity compared to part 3, whereas patients with baseline H&Y stage 2 progressed faster in part 2 than part 3. The multidimensional model had a superior fit compared to the unidimensional models and it had excellent model performance.
- 14 October 2021
- Published by Wiley in Statistics in Medicine
- Vol. 40 (30) , 6855-6872
Bayesian inference and dynamic prediction of multivariate joint model with functional data: An application to Alzheimer's disease
Alzheimer's disease (AD) is a severe neurodegenerative disorder impairing multiple domains, for example, cognition and behavior. Assessing the risk of AD progression and initiating timely interventions at early stages are critical to improve the quality of life for AD patients. Due to the heterogeneous nature and complex mechanisms of AD, one single longitudinal outcome is insufficient to assess AD severity and disease progression. Therefore, AD studies collect multiple longitudinal outcomes, including cognitive and behavioral measurements, as well as structural brain images such as magnetic resonance imaging (MRI). How to utilize the multivariate longitudinal outcomes and MRI data to make efficient statistical inference and prediction is an open question. In this article, we propose a multivariate joint model with functional data (MJM‐FD) framework that relates multiple correlated longitudinal outcomes to a survival outcome, and use the scalar‐on‐function regression method to include voxel‐based whole‐brain MRI data as functional predictors in both longitudinal and survival models. We adopt a Bayesian paradigm to make statistical inference and develop a dynamic prediction framework to predict an individual's future longitudinal outcomes and risk of a survival event. We validate the MJM‐FD framework through extensive simulation studies and apply it to the motivating Alzheimer's Disease Neuroimaging Initiative (ADNI) study.
- 14 October 2021
- Published by Wiley in Statistics in Medicine
- Vol. 40 (30) , 6855-6872
Bayesian inference and dynamic prediction of multivariate joint model with functional data: An application to Alzheimer's disease
Alzheimer's disease (AD) is a severe neurodegenerative disorder impairing multiple domains, for example, cognition and behavior. Assessing the risk of AD progression and initiating timely interventions at early stages are critical to improve the quality of life for AD patients. Due to the heterogeneous nature and complex mechanisms of AD, one single longitudinal outcome is insufficient to assess AD severity and disease progression. Therefore, AD studies collect multiple longitudinal outcomes, including cognitive and behavioral measurements, as well as structural brain images such as magnetic resonance imaging (MRI). How to utilize the multivariate longitudinal outcomes and MRI data to make efficient statistical inference and prediction is an open question. In this article, we propose a multivariate joint model with functional data (MJM‐FD) framework that relates multiple correlated longitudinal outcomes to a survival outcome, and use the scalar‐on‐function regression method to include voxel‐based whole‐brain MRI data as functional predictors in both longitudinal and survival models. We adopt a Bayesian paradigm to make statistical inference and develop a dynamic prediction framework to predict an individual's future longitudinal outcomes and risk of a survival event. We validate the MJM‐FD framework through extensive simulation studies and apply it to the motivating Alzheimer's Disease Neuroimaging Initiative (ADNI) study.