Jeffrey R. Petrella
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
Research Interests
Jeffrey R. Petrella has a total of 158 co-authors. Here are the top co-authors by number of shared publications:
P. Murali Doraiswamy
From the Departments of Radiology (J.R.P), Neurology (A.J.L.) and Psychiatry (P.M.D., L.A.W), Duke University School of Medicine, Durham NC, USA; Duke-UNC Alzheimer’s Disease Research Center (J.R.P, A.J.L., P.M.D.), Durham/Chapel Hill, NC, USA
17 shared publicationsFor The Alzheimer’s Disease Neuroimaging Initiative
5 shared publications- Chunlei Liu
Department of Electrical Engineering and Computer Sciences University of California, Berkeley Berkeley California USA
4 shared publications Kingshuk Roy Choudhury
4 shared publications- Steven E. Prince
Center for Cognitive Neuroscience, Duke University, Durham, NC 27708, USA
4 shared publications Melissa J. Slavin
3 shared publications
Latest Publications
- Open Access
Identifiability-Guided Assessment of Digital Twins in Alzheimer’s Disease Clinical Research and Care
Digital twins – personalized, data-driven computational models – are emerging as a powerful paradigm for representing and predicting disease trajectories at the individual level. These models have the potential to support diagnosis, monitor disease evolution, and evaluate therapeutic interventions in virtual settings in the context of clinical trials and patient care. Rigorous model assessment is thus critical for its implementation, but medical data are often sparse, noisy, and vary significantly across individuals, making it challenging to determine whether a digital twin optimized on such data is valid. In such settings, identifiability analysis becomes essential for evaluating whether model parameters can be reliably estimated and interpreted. To address this, we investigate how identifiability can support the clinical application of a computational causal digital twin model for Alzheimer’s Disease (AD), where data sparsity and variability are particularly pronounced. Our results show that the magnitude and distribution of biomarker data influence the parameter practical identifiability, and that constraints on the model structure and parameters can significantly affect identifiability. We also observe differences in identifiability across diagnostic groups, with several parameters showing significantly different values between individuals with AD, mild cognitive impairment (MCI), and cognitively normal (CN) subjects. Uncertainty quantification for identifiable parameters and their corresponding model trajectories provides visual insight into variability in disease progression and reveals mild trends related to biomarker data spread. This study represents a first step toward incorporating identifiability techniques into clinical digital twin frameworks, using a data-driven, interpretable example based on a previously published AD model.
Open AccessIdentifiability-Guided Assessment of Digital Twins in Alzheimer’s Disease Clinical Research and Care
Digital twins – personalized, data-driven computational models – are emerging as a powerful paradigm for representing and predicting disease trajectories at the individual level. These models have the potential to support diagnosis, monitor disease evolution, and evaluate therapeutic interventions in virtual settings in the context of clinical trials and patient care. Rigorous model assessment is thus critical for its implementation, but medical data are often sparse, noisy, and vary significantly across individuals, making it challenging to determine whether a digital twin optimized on such data is valid. In such settings, identifiability analysis becomes essential for evaluating whether model parameters can be reliably estimated and interpreted. To address this, we investigate how identifiability can support the clinical application of a computational causal digital twin model for Alzheimer’s Disease (AD), where data sparsity and variability are particularly pronounced. Our results show that the magnitude and distribution of biomarker data influence the parameter practical identifiability, and that constraints on the model structure and parameters can significantly affect identifiability. We also observe differences in identifiability across diagnostic groups, with several parameters showing significantly different values between individuals with AD, mild cognitive impairment (MCI), and cognitively normal (CN) subjects. Uncertainty quantification for identifiable parameters and their corresponding model trajectories provides visual insight into variability in disease progression and reveals mild trends related to biomarker data spread. This study represents a first step toward incorporating identifiability techniques into clinical digital twin frameworks, using a data-driven, interpretable example based on a previously published AD model.
- 30 July 2025
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 47 (2) , 289-292
Artificial Intelligence–Assisted Detection of Amyloid-Related Imaging Abnormalities: Promise and Pitfalls
The advent of anti-amyloid therapies (AATs) for Alzheimer’s disease (AD) has elevated the importance of MRI surveillance for amyloidrelated imaging abnormalities (ARIA) such as microhemorrhages and siderosis (ARIA-H) and edema (ARIA-E). We report a literature review and early quality assurance experience with an FDA-cleared assistive AI tool intended for detection of ARIA in MRI clinical workflows. The AI system improved sensitivity for detection of subtle ARIA-E and ARIA-H lesions but at the cost of a reduction in specificity. We propose a tiered workflow combining protocol harmonization and expert interpretation with AI overlay review. AI-assisted ARIA detection is a paradigm shift that offers great promise to enhance patient safety as disease-modifying therapies for AD gain broader clinical use; however, some pitfalls need to be considered. ABBREVIATIONS: AAT= anti-amyloid therapy; ARIA= amyloid-related imaging abnormalities, ARIA-H = amyloid-related imaging abnormality-hemorrhage, ARIA-E = amyloid-related imaging abnormality-edema.
- 30 July 2025
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 47 (2) , 289-292
Artificial Intelligence–Assisted Detection of Amyloid-Related Imaging Abnormalities: Promise and Pitfalls
The advent of anti-amyloid therapies (AATs) for Alzheimer’s disease (AD) has elevated the importance of MRI surveillance for amyloidrelated imaging abnormalities (ARIA) such as microhemorrhages and siderosis (ARIA-H) and edema (ARIA-E). We report a literature review and early quality assurance experience with an FDA-cleared assistive AI tool intended for detection of ARIA in MRI clinical workflows. The AI system improved sensitivity for detection of subtle ARIA-E and ARIA-H lesions but at the cost of a reduction in specificity. We propose a tiered workflow combining protocol harmonization and expert interpretation with AI overlay review. AI-assisted ARIA detection is a paradigm shift that offers great promise to enhance patient safety as disease-modifying therapies for AD gain broader clinical use; however, some pitfalls need to be considered. ABBREVIATIONS: AAT= anti-amyloid therapy; ARIA= amyloid-related imaging abnormalities, ARIA-H = amyloid-related imaging abnormality-hemorrhage, ARIA-E = amyloid-related imaging abnormality-edema.
- 10 July 2025
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 46 (8) , 1521-1527
Clinical Role of Brain PET in Alzheimer Disease in the Era of Disease-Modifying Therapies
SUMMARY: Alzheimer disease (AD) is the leading cause of dementia, with an estimated 6.9 million Americans aged 65 and older living with Alzheimer dementia today, with this number projected to grow to 13.8 million by 2060. Amyloid and τ accumulation underpin our understanding of the pathophysiology of AD, with the abnormal accumulation of these proteins leading to neurodegeneration. With the recent approval of antiamyloid monoclonal antibody therapies for patients with early-stage Alzheimer disease by the Food and Drug Administration, there is renewed energy and focus on brain imaging for diagnosis, triage, and monitoring of patients with neurodegenerative disease. Furthermore, PET imaging of amyloid and τ has revolutionized our understanding of dementia progression and staging, and influences patient management in the clinical setting. We aim to update radiologists on the evolving role of amyloid and τ PET in clinical practice, emphasizing the need for standardized workflows and the integration of molecular imaging data with other disease biomarkers. We also discuss the clinical implications of amyloid and τ PET, including their impact on diagnosis and treatment decisions, as well as the challenges of reimbursement and workforce capacity. With recent shifts in the AD management landscape, it is crucial for radiologists to keep abreast of recent advances in clinical practice, thereby ensuring effective patient care.
- 10 July 2025
- Published by American Society of Neuroradiology (ASNR) in American Journal of Neuroradiology
- Vol. 46 (8) , 1521-1527
Clinical Role of Brain PET in Alzheimer Disease in the Era of Disease-Modifying Therapies
SUMMARY: Alzheimer disease (AD) is the leading cause of dementia, with an estimated 6.9 million Americans aged 65 and older living with Alzheimer dementia today, with this number projected to grow to 13.8 million by 2060. Amyloid and τ accumulation underpin our understanding of the pathophysiology of AD, with the abnormal accumulation of these proteins leading to neurodegeneration. With the recent approval of antiamyloid monoclonal antibody therapies for patients with early-stage Alzheimer disease by the Food and Drug Administration, there is renewed energy and focus on brain imaging for diagnosis, triage, and monitoring of patients with neurodegenerative disease. Furthermore, PET imaging of amyloid and τ has revolutionized our understanding of dementia progression and staging, and influences patient management in the clinical setting. We aim to update radiologists on the evolving role of amyloid and τ PET in clinical practice, emphasizing the need for standardized workflows and the integration of molecular imaging data with other disease biomarkers. We also discuss the clinical implications of amyloid and τ PET, including their impact on diagnosis and treatment decisions, as well as the challenges of reimbursement and workforce capacity. With recent shifts in the AD management landscape, it is crucial for radiologists to keep abreast of recent advances in clinical practice, thereby ensuring effective patient care.
- Open Access
- 3 January 2024
- Published by Elsevier in The Journal Of Prevention of Alzheimer's Disease
- Vol. 11 (2) , 435-444
Personalized Computational Causal Modeling of the Alzheimer Disease Biomarker Cascade
Mathematical models of complex diseases, such as Alzheimer’s disease, have the potential to play a significant role in personalized medicine. Specifi
- 3 January 2024
- Published by Elsevier in The Journal Of Prevention of Alzheimer's Disease
- Vol. 11 (2) , 435-444
Open AccessPersonalized Computational Causal Modeling of the Alzheimer Disease Biomarker Cascade
Mathematical models of complex diseases, such as Alzheimer’s disease, have the potential to play a significant role in personalized medicine. Specifi
- 1 October 2023
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 309 (1) , e222441
MRI-based Deep Learning Assessment of Amyloid, Tau, and Neurodegeneration Biomarker Status across the Alzheimer Disease Spectrum
Background PET can be used for amyloid-tau-neurodegeneration (ATN) classification in Alzheimer disease, but incurs considerable cost and exposure to ionizing radiation. MRI currently has limited use in characterizing ATN status. Deep learning techniques can detect complex patterns in MRI data and have potential for noninvasive characterization of ATN status. Purpose To use deep learning to predict PET-determined ATN biomarker status using MRI and readily available diagnostic data. Materials and Methods MRI and PET data were retrospectively collected from the Alzheimer's Disease Imaging Initiative. PET scans were paired with MRI scans acquired within 30 days, from August 2005 to September 2020. Pairs were randomly split into subsets as follows: 70% for training, 10% for validation, and 20% for final testing. A bimodal Gaussian mixture model was used to threshold PET scans into positive and negative labels. MRI data were fed into a convolutional neural network to generate imaging features. These features were combined in a logistic regression model with patient demographics, APOE gene status, cognitive scores, hippocampal volumes, and clinical diagnoses to classify each ATN biomarker component as positive or negative. Area under the receiver operating characteristic curve (AUC) analysis was used for model evaluation. Feature importance was derived from model coefficients and gradients. Results There were 2099 amyloid (mean patient age, 75 years ± 10 [SD]; 1110 male), 557 tau (mean patient age, 75 years ± 7; 280 male), and 2768 FDG PET (mean patient age, 75 years ± 7; 1645 male) and MRI pairs. Model AUCs for the test set were as follows: amyloid, 0.79 (95% CI: 0.74, 0.83); tau, 0.73 (95% CI: 0.58, 0.86); and neurodegeneration, 0.86 (95% CI: 0.83, 0.89). Within the networks, high gradients were present in key temporal, parietal, frontal, and occipital cortical regions. Model coefficients for cognitive scores, hippocampal volumes, and APOE status were highest. Conclusion A deep learning algorithm predicted each component of PET-determined ATN status with acceptable to excellent efficacy using MRI and other available diagnostic data. © RSNA, 2023 Supplemental material is available for this article.
- 1 October 2023
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 309 (1) , e222441
MRI-based Deep Learning Assessment of Amyloid, Tau, and Neurodegeneration Biomarker Status across the Alzheimer Disease Spectrum
Background PET can be used for amyloid-tau-neurodegeneration (ATN) classification in Alzheimer disease, but incurs considerable cost and exposure to ionizing radiation. MRI currently has limited use in characterizing ATN status. Deep learning techniques can detect complex patterns in MRI data and have potential for noninvasive characterization of ATN status. Purpose To use deep learning to predict PET-determined ATN biomarker status using MRI and readily available diagnostic data. Materials and Methods MRI and PET data were retrospectively collected from the Alzheimer's Disease Imaging Initiative. PET scans were paired with MRI scans acquired within 30 days, from August 2005 to September 2020. Pairs were randomly split into subsets as follows: 70% for training, 10% for validation, and 20% for final testing. A bimodal Gaussian mixture model was used to threshold PET scans into positive and negative labels. MRI data were fed into a convolutional neural network to generate imaging features. These features were combined in a logistic regression model with patient demographics, APOE gene status, cognitive scores, hippocampal volumes, and clinical diagnoses to classify each ATN biomarker component as positive or negative. Area under the receiver operating characteristic curve (AUC) analysis was used for model evaluation. Feature importance was derived from model coefficients and gradients. Results There were 2099 amyloid (mean patient age, 75 years ± 10 [SD]; 1110 male), 557 tau (mean patient age, 75 years ± 7; 280 male), and 2768 FDG PET (mean patient age, 75 years ± 7; 1645 male) and MRI pairs. Model AUCs for the test set were as follows: amyloid, 0.79 (95% CI: 0.74, 0.83); tau, 0.73 (95% CI: 0.58, 0.86); and neurodegeneration, 0.86 (95% CI: 0.83, 0.89). Within the networks, high gradients were present in key temporal, parietal, frontal, and occipital cortical regions. Model coefficients for cognitive scores, hippocampal volumes, and APOE status were highest. Conclusion A deep learning algorithm predicted each component of PET-determined ATN status with acceptable to excellent efficacy using MRI and other available diagnostic data. © RSNA, 2023 Supplemental material is available for this article.
- Open Access
- 1 March 2023
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 96 (1144) , 20220359
Changes in resting state networks in high school football athletes across a single season
Objective: The aim of this pilot cohort study was to examine changes in the organization of resting-state brain networks in high school football athletes and its relationship to exposure to on-field head impacts over the course of a single season. Methods: Seventeen male high school football players underwent functional magnetic resonance imaging and computerized neurocognitive testing (CNS Vital Signs) before the start of contact practices and again after the conclusion of the season. The players were equipped with helmet accelerometer systems (Head Impact Telemetry System) to record head impacts in practices and games. Graph theory analysis was applied to study intranetwork local efficiency and strength of connectivity within six anatomically defined brain networks. Results: We observed a significant decrease in the local efficiency (−24.9 ± 51.4%, r = 0.7, p < 0.01) and strength (−14.5 ± 26.8%, r = 0.5, p < 0.01) of functional connectivity within the frontal lobe resting-state network and strength within the parietal lobe resting-state network (−7.5 ± 17.3%, r = 0.1, p < 0.01), as well as a concomitant increase in the local efficiency (+55.0 +/- 59.8%, r = 0.5, p < 0.01) and strength (+47.4 +/- 47.3%, r = 0.5, p < 0.01) within the mediotemporal networks. These alterations in network organization were associated with changes in performance on verbal memory (p < 0.05) and executive function (p < 0.05). We did not observe a significant relationship between the frequency or cumulative magnitude of impacts sustained during the season and neurocognitive or imaging outcomes (p > 0.05). Conclusion: Our findings suggest the efficiency and strength of resting-state networks are altered across a season of high school football, but the association of exposure levels to subconcussive impacts is unclear. Advances in knowledge: The efficiency of resting-state networks is dynamic in high school football athletes; such changes may be related to impacts sustained during the season, though further study is needed.
- 1 March 2023
- Published by Oxford University Press (OUP) in British Journal of Radiology
- Vol. 96 (1144) , 20220359
Open AccessChanges in resting state networks in high school football athletes across a single season
Objective: The aim of this pilot cohort study was to examine changes in the organization of resting-state brain networks in high school football athletes and its relationship to exposure to on-field head impacts over the course of a single season. Methods: Seventeen male high school football players underwent functional magnetic resonance imaging and computerized neurocognitive testing (CNS Vital Signs) before the start of contact practices and again after the conclusion of the season. The players were equipped with helmet accelerometer systems (Head Impact Telemetry System) to record head impacts in practices and games. Graph theory analysis was applied to study intranetwork local efficiency and strength of connectivity within six anatomically defined brain networks. Results: We observed a significant decrease in the local efficiency (−24.9 ± 51.4%, r = 0.7, p < 0.01) and strength (−14.5 ± 26.8%, r = 0.5, p < 0.01) of functional connectivity within the frontal lobe resting-state network and strength within the parietal lobe resting-state network (−7.5 ± 17.3%, r = 0.1, p < 0.01), as well as a concomitant increase in the local efficiency (+55.0 +/- 59.8%, r = 0.5, p < 0.01) and strength (+47.4 +/- 47.3%, r = 0.5, p < 0.01) within the mediotemporal networks. These alterations in network organization were associated with changes in performance on verbal memory (p < 0.05) and executive function (p < 0.05). We did not observe a significant relationship between the frequency or cumulative magnitude of impacts sustained during the season and neurocognitive or imaging outcomes (p > 0.05). Conclusion: Our findings suggest the efficiency and strength of resting-state networks are altered across a season of high school football, but the association of exposure levels to subconcussive impacts is unclear. Advances in knowledge: The efficiency of resting-state networks is dynamic in high school football athletes; such changes may be related to impacts sustained during the season, though further study is needed.
- Open Access
- 3 January 2023
- Published by SAGE Publications in Journal of Alzheimer’s Disease
- Vol. 91 (1) , 483-494
Impact of Computerized Cognitive Training on Default Mode Network Connectivity in Subjects at Risk for Alzheimer’s Disease: A 78-week Randomized Controlled Trial
Background: Mild cognitive impairment (MCI) represents a high risk group for Alzheimer’s disease (AD). Computerized Cognitive Games Training (CCT) is an investigational strategy to improve targeted functions in MCI through the modulation of cognitive networks. Objective: The goal of this study was to examine the effect of CCT versus a non-targeted active brain exercise on functional cognitive networks. Methods: 107 patients with MCI were randomized to CCT or web-based crossword puzzles. Resting-state functional MRI (fMRI) was obtained at baseline and 18 months to evaluate differences in fMRI measured within- and between-network functional connectivity (FC) of the default mode network (DMN) and other large-scale brain networks: the executive control, salience, and sensorimotor networks. Results: There were no differences between crosswords and games in the primary outcome, within-network DMN FC across all subjects. However, secondary analyses suggest differential effects on between-network connectivity involving the DMN and SLN, and within-network connectivity of the DMN in subjects with late MCI. Paradoxically, in both cases, there was a decrease in FC for games and an increase for the crosswords control (p < 0.05), accompanied by lesser cognitive decline in the crosswords group. Conclusion: Results do not support a differential impact on within-network DMN FC between games and crossword puzzle interventions. However, crossword puzzles might result in cognitively beneficial remodeling between the DMN and other networks in more severely impaired MCI subjects, parallel to the observed clinical benefits.
- 3 January 2023
- Published by SAGE Publications in Journal of Alzheimer’s Disease
- Vol. 91 (1) , 483-494
Open AccessImpact of Computerized Cognitive Training on Default Mode Network Connectivity in Subjects at Risk for Alzheimer’s Disease: A 78-week Randomized Controlled Trial
Background: Mild cognitive impairment (MCI) represents a high risk group for Alzheimer’s disease (AD). Computerized Cognitive Games Training (CCT) is an investigational strategy to improve targeted functions in MCI through the modulation of cognitive networks. Objective: The goal of this study was to examine the effect of CCT versus a non-targeted active brain exercise on functional cognitive networks. Methods: 107 patients with MCI were randomized to CCT or web-based crossword puzzles. Resting-state functional MRI (fMRI) was obtained at baseline and 18 months to evaluate differences in fMRI measured within- and between-network functional connectivity (FC) of the default mode network (DMN) and other large-scale brain networks: the executive control, salience, and sensorimotor networks. Results: There were no differences between crosswords and games in the primary outcome, within-network DMN FC across all subjects. However, secondary analyses suggest differential effects on between-network connectivity involving the DMN and SLN, and within-network connectivity of the DMN in subjects with late MCI. Paradoxically, in both cases, there was a decrease in FC for games and an increase for the crosswords control (p < 0.05), accompanied by lesser cognitive decline in the crosswords group. Conclusion: Results do not support a differential impact on within-network DMN FC between games and crossword puzzle interventions. However, crossword puzzles might result in cognitively beneficial remodeling between the DMN and other networks in more severely impaired MCI subjects, parallel to the observed clinical benefits.
- Open Access
- 23 November 2022
- Published by Wiley in NMR in Biomedicine
- Vol. 36 (2) , e4842
Prenatal heroin exposure alters brain morphology and connectivity in adolescent mice
The United States is experiencing a dramatic increase in maternal opioid misuse and, consequently, the number of individuals exposed to opioids in utero. Prenatal opioid exposure has both acute and long‐lasting effects on health and wellbeing. Effects on the brain, often identified at school age, manifest as cognitive impairment, attention deficit, and reduced scholastic achievement. The neurobiological basis for these effects is poorly understood. Here, we examine how in utero exposure to heroin affects brain development into early adolescence in a mouse model. Pregnant C57BL/6J mice received escalating doses of heroin twice daily on gestational days 4–18. The brains of offspring were assessed on postnatal day 28 using 9.4 T diffusion MRI of postmortem specimens at 36 μm resolution. Whole‐brain volumes and the volumes of 166 bilateral regions were compared between heroin‐exposed and control offspring. We identified a reduction in whole‐brain volume in heroin‐exposed offspring and heroin‐associated volume changes in 29 regions after standardizing for whole‐brain volume. Regions with bilaterally reduced standardized volumes in heroin‐exposed offspring relative to controls include the ectorhinal and insular cortices. Regions with bilaterally increased standardized volumes in heroin‐exposed offspring relative to controls include the periaqueductal gray, septal region, striatum, and hypothalamus. Leveraging microscopic resolution diffusion tensor imaging and precise regional parcellation, we generated whole‐brain structural MRI diffusion connectomes. Using a dimension reduction approach with multivariate analysis of variance to assess group differences in the connectome, we found that in utero heroin exposure altered structure‐based connectivity of the left septal region and the region that acts as a hub for limbic regulatory actions. Consistent with clinical evidence, our findings suggest that prenatal opioid exposure may have effects on brain morphology, connectivity, and, consequently, function that persist into adolescence. This work expands our understanding of the risks associated with opioid misuse during pregnancy and identifies biomarkers that may facilitate diagnosis and treatment.
- 23 November 2022
- Published by Wiley in NMR in Biomedicine
- Vol. 36 (2) , e4842
Open AccessPrenatal heroin exposure alters brain morphology and connectivity in adolescent mice
The United States is experiencing a dramatic increase in maternal opioid misuse and, consequently, the number of individuals exposed to opioids in utero. Prenatal opioid exposure has both acute and long‐lasting effects on health and wellbeing. Effects on the brain, often identified at school age, manifest as cognitive impairment, attention deficit, and reduced scholastic achievement. The neurobiological basis for these effects is poorly understood. Here, we examine how in utero exposure to heroin affects brain development into early adolescence in a mouse model. Pregnant C57BL/6J mice received escalating doses of heroin twice daily on gestational days 4–18. The brains of offspring were assessed on postnatal day 28 using 9.4 T diffusion MRI of postmortem specimens at 36 μm resolution. Whole‐brain volumes and the volumes of 166 bilateral regions were compared between heroin‐exposed and control offspring. We identified a reduction in whole‐brain volume in heroin‐exposed offspring and heroin‐associated volume changes in 29 regions after standardizing for whole‐brain volume. Regions with bilaterally reduced standardized volumes in heroin‐exposed offspring relative to controls include the ectorhinal and insular cortices. Regions with bilaterally increased standardized volumes in heroin‐exposed offspring relative to controls include the periaqueductal gray, septal region, striatum, and hypothalamus. Leveraging microscopic resolution diffusion tensor imaging and precise regional parcellation, we generated whole‐brain structural MRI diffusion connectomes. Using a dimension reduction approach with multivariate analysis of variance to assess group differences in the connectome, we found that in utero heroin exposure altered structure‐based connectivity of the left septal region and the region that acts as a hub for limbic regulatory actions. Consistent with clinical evidence, our findings suggest that prenatal opioid exposure may have effects on brain morphology, connectivity, and, consequently, function that persist into adolescence. This work expands our understanding of the risks associated with opioid misuse during pregnancy and identifies biomarkers that may facilitate diagnosis and treatment.
- Open Access
- 8 September 2022
- Published by Springer Nature in npj Digital Medicine
- Vol. 5 (1) , 1-12
Data-driven causal model discovery and personalized prediction in Alzheimer's disease
With the explosive growth of biomarker data in Alzheimer’s disease (AD) clinical trials, numerous mathematical models have been developed to characterize disease-relevant biomarker trajectories over time. While some of these models are purely empiric, others are causal, built upon various hypotheses of AD pathophysiology, a complex and incompletely understood area of research. One of the most challenging problems in computational causal modeling is using a purely data-driven approach to derive the model’s parameters and the mathematical model itself, without any prior hypothesis bias. In this paper, we develop an innovative data-driven modeling approach to build and parameterize a causal model to characterize the trajectories of AD biomarkers. This approach integrates causal model learning, population parameterization, parameter sensitivity analysis, and personalized prediction. By applying this integrated approach to a large multicenter database of AD biomarkers, the Alzheimer’s Disease Neuroimaging Initiative, several causal models for different AD stages are revealed. In addition, personalized models for each subject are calibrated and provide accurate predictions of future cognitive status.
- 8 September 2022
- Published by Springer Nature in npj Digital Medicine
- Vol. 5 (1) , 1-12
Open AccessData-driven causal model discovery and personalized prediction in Alzheimer's disease
With the explosive growth of biomarker data in Alzheimer’s disease (AD) clinical trials, numerous mathematical models have been developed to characterize disease-relevant biomarker trajectories over time. While some of these models are purely empiric, others are causal, built upon various hypotheses of AD pathophysiology, a complex and incompletely understood area of research. One of the most challenging problems in computational causal modeling is using a purely data-driven approach to derive the model’s parameters and the mathematical model itself, without any prior hypothesis bias. In this paper, we develop an innovative data-driven modeling approach to build and parameterize a causal model to characterize the trajectories of AD biomarkers. This approach integrates causal model learning, population parameterization, parameter sensitivity analysis, and personalized prediction. By applying this integrated approach to a large multicenter database of AD biomarkers, the Alzheimer’s Disease Neuroimaging Initiative, several causal models for different AD stages are revealed. In addition, personalized models for each subject are calibrated and provide accurate predictions of future cognitive status.
- 12 October 2021
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 302 (1) , 143-150
Diffusion Tensor MRI Structural Connectivity and PET Amyloid Burden in Preclinical Autosomal Dominant Alzheimer Disease: The DIAN Cohort
Structural integrity of white matter networks at diffusion tensor MRI in autosomal dominant Alzheimer disease mutation carriers was associated with disease progression (P = .01). Background Pathologic evidence of Alzheimer disease (AD) is detectable years before onset of clinical symptoms. Imaging-based identification of structural changes of the brain in people at genetic ...
- 12 October 2021
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 302 (1) , 143-150
Diffusion Tensor MRI Structural Connectivity and PET Amyloid Burden in Preclinical Autosomal Dominant Alzheimer Disease: The DIAN Cohort
Structural integrity of white matter networks at diffusion tensor MRI in autosomal dominant Alzheimer disease mutation carriers was associated with disease progression (P = .01). Background Pathologic evidence of Alzheimer disease (AD) is detectable years before onset of clinical symptoms. Imaging-based identification of structural changes of the brain in people at genetic ...