Alan Lee Chang
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
Alan Lee Chang has a total of 259 co-authors. Here are the top co-authors by number of shared publications:
- Nima Aghaeepour
Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Palo Alto, CA, United States
13 shared publications - Thanaphong Phongpreecha
Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
9 shared publications - Camilo Espinosa
Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
8 shared publications - Eloise Berson
Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
8 shared publications - Samson Mataraso
Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, CA 94305, USA
8 shared publications - Martin Becker
Institute for Visual and Analytic Computing, University of Rostock, Rostock, GERMANY
7 shared publications
Latest Publications
- Open Access
- 10 July 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
PregMedNet: Multifaceted maternal medication impacts on neonatal complications
While medication use is common among pregnant women, medication safety remains insufficiently characterized because studies in pregnant women are challenging due to safety concerns. The recent digitization of healthcare databases and advances in computational methods have created new opportunities for large-scale, retrospective drug safety evaluations. Here, we present PregMedNet, a platform that characterizes multifaceted maternal medication associations on neonatal outcomes during pregnancy, covering more than 27,000 drug-disease pairs across 1,152 medications and 24 outcomes. These results encompass known and additional odds ratios (ORs), adjusted ORs, and drug-drug interactions, systematically analyzed using nationwide claims data and an advanced machine learning pipeline. Notably, one of the associations identified in this study is supported by in vivo experiments, increasing confidence in PregMedNet’s findings and highlighting the utility of claims data and machine learning for perinatal medication safety studies. Additionally, potential biological mechanisms underlying the associations are explored using a graph learning method, providing candidate pathways for future mechanistic investigations. We expect that PregMedNet will contribute to advancing maternal medication safety and improving neonatal outcomes by providing extensive, multifaceted drug safety information on this previously underrepresented population.
- 10 July 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Open AccessPregMedNet: Multifaceted maternal medication impacts on neonatal complications
While medication use is common among pregnant women, medication safety remains insufficiently characterized because studies in pregnant women are challenging due to safety concerns. The recent digitization of healthcare databases and advances in computational methods have created new opportunities for large-scale, retrospective drug safety evaluations. Here, we present PregMedNet, a platform that characterizes multifaceted maternal medication associations on neonatal outcomes during pregnancy, covering more than 27,000 drug-disease pairs across 1,152 medications and 24 outcomes. These results encompass known and additional odds ratios (ORs), adjusted ORs, and drug-drug interactions, systematically analyzed using nationwide claims data and an advanced machine learning pipeline. Notably, one of the associations identified in this study is supported by in vivo experiments, increasing confidence in PregMedNet’s findings and highlighting the utility of claims data and machine learning for perinatal medication safety studies. Additionally, potential biological mechanisms underlying the associations are explored using a graph learning method, providing candidate pathways for future mechanistic investigations. We expect that PregMedNet will contribute to advancing maternal medication safety and improving neonatal outcomes by providing extensive, multifaceted drug safety information on this previously underrepresented population.
- Open Access
- 13 April 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Multiomics characterization of acute child illness and mortality in Africa and South Asia
Childhood illnesses from infectious diseases in low- and middle-income countries contribute substantially to the global under-five mortality. Many hospitalized children experience incomplete recovery, readmission, and post-discharge mortality despite guideline-directed care. However, targeted interventions remain elusive due to limited understanding of underlying mechanisms. In this work, we employ multiomic profiling and multivariate modeling to investigate biological drivers of inpatient and post-discharge mortality in 3,101 acutely ill children across nine sites in sub-Saharan Africa and South Asia. In a nested case-cohort ( N = 1008), we generate plasma proteomics, serum metabolomics and lipidomics, stool metagenomics, and fecal pathogen data at admission and discharge. Additionally, we profile 270 geographically matched community children for biological baselines. We identify a generalizable mortality signature marked by immune, inflammatory, and metabolic dysregulation with gut dysbiosis. We show that mortality-associated signals persist from admission through discharge, indicating unresolved disease and that malnourished children show greater baseline perturbations, explaining elevated risk. We also find some children with low clinical severity display high predicted mortality risk from targeted biomarkers. Finally, we distill predictive models to a clinically feasible biomarker panel and validate our findings in an independent cohort ( N = 100). By linking inpatient and post-discharge mortality to specific biological mechanisms, our findings highlight why current care can fail and demonstrate how biomarker-guided risk stratification can identify vulnerable children currently missed by clinical assessments, enabling targeted interventions to reduce mortality in low- and middle-income countries.
- 13 April 2026
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Open AccessMultiomics characterization of acute child illness and mortality in Africa and South Asia
Childhood illnesses from infectious diseases in low- and middle-income countries contribute substantially to the global under-five mortality. Many hospitalized children experience incomplete recovery, readmission, and post-discharge mortality despite guideline-directed care. However, targeted interventions remain elusive due to limited understanding of underlying mechanisms. In this work, we employ multiomic profiling and multivariate modeling to investigate biological drivers of inpatient and post-discharge mortality in 3,101 acutely ill children across nine sites in sub-Saharan Africa and South Asia. In a nested case-cohort ( N = 1008), we generate plasma proteomics, serum metabolomics and lipidomics, stool metagenomics, and fecal pathogen data at admission and discharge. Additionally, we profile 270 geographically matched community children for biological baselines. We identify a generalizable mortality signature marked by immune, inflammatory, and metabolic dysregulation with gut dysbiosis. We show that mortality-associated signals persist from admission through discharge, indicating unresolved disease and that malnourished children show greater baseline perturbations, explaining elevated risk. We also find some children with low clinical severity display high predicted mortality risk from targeted biomarkers. Finally, we distill predictive models to a clinically feasible biomarker panel and validate our findings in an independent cohort ( N = 100). By linking inpatient and post-discharge mortality to specific biological mechanisms, our findings highlight why current care can fail and demonstrate how biomarker-guided risk stratification can identify vulnerable children currently missed by clinical assessments, enabling targeted interventions to reduce mortality in low- and middle-income countries.
- Open Access
- 6 April 2026
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 15, e84781
Targeted Real-Time Assessment of Chronic Pain (TRAC-Pain) in Youth: Protocol for a Digital Biosignature Development Through a Prospective Observational Cohort Study
Background: Approximately 1 in 5 children and adolescents live with chronic pain, with musculoskeletal (MSK) pain being one of the most prevalent subtypes. Unfortunately, some studies show that less than half of youth (<18 years) experience improvements with existing evidence-based treatments. Self-report measures—the current gold standard for monitoring the pain experience—are limited in their use as a single point-of-care assessment and their vulnerability to recall bias. The ubiquitous adoption of wearable technology presents a promising solution for improved monitoring of the pain experience via real-time tracking through a multisystemic lens. Objective: The purpose of this study is (1) to develop a digital biosignature of the pain experience in youth with chronic MSK pain and (2) to assess the feasibility, acceptability, and appropriateness of the captured data for future applications. Methods: All aspects of this study were designed in partnership with people with lived experience and patient advocacy partners. This is a longitudinal observational cohort study, with all study activities taking place remotely over a 12-week period. Up to 500 youth (between 14 and 24 years old) with chronic MSK pain will be enrolled through a multipronged recruitment strategy to ensure a representative sample. The participants will wear an Apple Watch throughout the study to continuously monitor physiological, sleep, and physical activity metrics. In addition, participants will complete brief “daily check-in” surveys that include gold-standard measures of the pain experience (eg, pain interference, mood, fatigue) and the option to report a “pain flare” (ie, a temporary but noticeable worsening of the usual pain symptoms). Participants will also complete a modified online Trier Social Stress Test and a 30-second sit-to-stand task to capture individual responses to standardized challenges. Traditional machine learning and deep representation learning methods will be used to develop a digital biosignature of the pain experience. The accuracy of the biosignature will be assessed through measures of model performance as compared to gold-standard self-reports. Results: This study was funded in September 2024, with data collection beginning in March 2025. As of December 15, 2025, 190 participants are enrolled, with data collection and analysis ongoing. Conclusions: This is the first study to leverage wearable health technology for real-time monitoring of the pain experience in youth with chronic MSK pain. The resulting digital end points are expected to heighten the rigor of clinical trials and provide opportunities for individually tailored interventions. The second phase of this study will investigate the implementation of “wellness alerts” triggered by abnormal smartwatch readings. Alerts would empower users toward preemptive self-management strategies, thereby enhancing self-efficacy in those living with chronic MSK pain. International Registered Report Identifier (IRRID): DERR1-10.2196/84781
- 6 April 2026
- Published by JMIR Publications Inc. in JMIR Research Protocols
- Vol. 15, e84781
Open AccessTargeted Real-Time Assessment of Chronic Pain (TRAC-Pain) in Youth: Protocol for a Digital Biosignature Development Through a Prospective Observational Cohort Study
Background: Approximately 1 in 5 children and adolescents live with chronic pain, with musculoskeletal (MSK) pain being one of the most prevalent subtypes. Unfortunately, some studies show that less than half of youth (<18 years) experience improvements with existing evidence-based treatments. Self-report measures—the current gold standard for monitoring the pain experience—are limited in their use as a single point-of-care assessment and their vulnerability to recall bias. The ubiquitous adoption of wearable technology presents a promising solution for improved monitoring of the pain experience via real-time tracking through a multisystemic lens. Objective: The purpose of this study is (1) to develop a digital biosignature of the pain experience in youth with chronic MSK pain and (2) to assess the feasibility, acceptability, and appropriateness of the captured data for future applications. Methods: All aspects of this study were designed in partnership with people with lived experience and patient advocacy partners. This is a longitudinal observational cohort study, with all study activities taking place remotely over a 12-week period. Up to 500 youth (between 14 and 24 years old) with chronic MSK pain will be enrolled through a multipronged recruitment strategy to ensure a representative sample. The participants will wear an Apple Watch throughout the study to continuously monitor physiological, sleep, and physical activity metrics. In addition, participants will complete brief “daily check-in” surveys that include gold-standard measures of the pain experience (eg, pain interference, mood, fatigue) and the option to report a “pain flare” (ie, a temporary but noticeable worsening of the usual pain symptoms). Participants will also complete a modified online Trier Social Stress Test and a 30-second sit-to-stand task to capture individual responses to standardized challenges. Traditional machine learning and deep representation learning methods will be used to develop a digital biosignature of the pain experience. The accuracy of the biosignature will be assessed through measures of model performance as compared to gold-standard self-reports. Results: This study was funded in September 2024, with data collection beginning in March 2025. As of December 15, 2025, 190 participants are enrolled, with data collection and analysis ongoing. Conclusions: This is the first study to leverage wearable health technology for real-time monitoring of the pain experience in youth with chronic MSK pain. The resulting digital end points are expected to heighten the rigor of clinical trials and provide opportunities for individually tailored interventions. The second phase of this study will investigate the implementation of “wellness alerts” triggered by abnormal smartwatch readings. Alerts would empower users toward preemptive self-management strategies, thereby enhancing self-efficacy in those living with chronic MSK pain. International Registered Report Identifier (IRRID): DERR1-10.2196/84781
- Open Access
- 3 April 2026
- Published by International Society of Global Health in Journal of Global Health
- Vol. 16, 05002
Multi-Omics for Mothers and Infants (MOMI) Consortium: a global initiative to study adverse pregnancy outcomes
Pregnancy complications such as preeclampsia (PE) and adverse pregnancy outcomes (APOs) such as preterm birth (PTB), small for gestational age (SGA), and stillbirth (SB) pose a serious global health challenge and collectively contribute to high rates of maternal and infant mortality and morbidity. Close to 2 million stillbirths were reported in 2020 [1,2] while […]
- 3 April 2026
- Published by International Society of Global Health in Journal of Global Health
- Vol. 16, 05002
Open AccessMulti-Omics for Mothers and Infants (MOMI) Consortium: a global initiative to study adverse pregnancy outcomes
Pregnancy complications such as preeclampsia (PE) and adverse pregnancy outcomes (APOs) such as preterm birth (PTB), small for gestational age (SGA), and stillbirth (SB) pose a serious global health challenge and collectively contribute to high rates of maternal and infant mortality and morbidity. Close to 2 million stillbirths were reported in 2020 [1,2] while […]
- Open Access
- 19 February 2026
- Published by Springer Nature in Communications Medicine
- Vol. 6 (1)
A machine learning model for frailty based on wearable device measurements
Background Frailty is an important factor in human aging associated with a broad range of adverse outcomes. Frailty metrics are time intensive to collect making them difficult for larger scale application. Methods We apply machine learning to predict these frailty metrics, associated risk factors, and adverse outcomes from activity data. We use activity data collected using Actigraphy wearable accelerometer sensors, which are devices that measure acceleration along three axes of movement. Models were evaluated using Area Under the receiver operator Curve (AUC), Area Under Precision Recall Curve (AUPRC), Spearman rank test, Mann-Whitney U test, or Kruskal-Wallis test on repeated subsampling of train and test sets. All statistical tests are reported using -log10(P-value). Results Machine learning models show strong predictive performance even with small amounts of accelerometry data available. They are also able to better determine adverse outcomes such as hospitalization and mortality than frailty metrics themselves in our geriatric population. Conclusions This approach of wearable activity data-based prediction of frailty offers a surrogate (proxy or estimate) for determining frailty metrics in a scalable manner. It can also be used to determine adverse outcomes such as hospitalizations and mortality, allowing frailty to be used as a metric in other studies or medical practices.
- 19 February 2026
- Published by Springer Nature in Communications Medicine
- Vol. 6 (1)
Open AccessA machine learning model for frailty based on wearable device measurements
Background Frailty is an important factor in human aging associated with a broad range of adverse outcomes. Frailty metrics are time intensive to collect making them difficult for larger scale application. Methods We apply machine learning to predict these frailty metrics, associated risk factors, and adverse outcomes from activity data. We use activity data collected using Actigraphy wearable accelerometer sensors, which are devices that measure acceleration along three axes of movement. Models were evaluated using Area Under the receiver operator Curve (AUC), Area Under Precision Recall Curve (AUPRC), Spearman rank test, Mann-Whitney U test, or Kruskal-Wallis test on repeated subsampling of train and test sets. All statistical tests are reported using -log10(P-value). Results Machine learning models show strong predictive performance even with small amounts of accelerometry data available. They are also able to better determine adverse outcomes such as hospitalization and mortality than frailty metrics themselves in our geriatric population. Conclusions This approach of wearable activity data-based prediction of frailty offers a surrogate (proxy or estimate) for determining frailty metrics in a scalable manner. It can also be used to determine adverse outcomes such as hospitalizations and mortality, allowing frailty to be used as a metric in other studies or medical practices.
- Open Access
- 21 January 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Translational Medicine
- Vol. 18 (833) , eadv4942
Quantitative assessment of neonatal health using dried blood spot metabolite profiles and deep learning
Neonatal prematurity leads to considerable morbidity and mortality, partly because of acquired conditions such as bronchopulmonary dysplasia (BPD), intraventricular hemorrhage (IVH), necrotizing enterocolitis (NEC), and retinopathy of prematurity (ROP). Standard gestational age and birthweight-based classifications of prematurity inadequately capture the variation in newborns’ health outcomes, creating an urgent need to develop risk stratification tools for vulnerable newborn infants to initiate the most appropriate care pathways as early as possible. We hypothesized that the metabolic profiles of newborn infants capture additional risk information beyond current measures. A total of 13,536 newborn screening (NBS) blood spot tests from preterm infants in California with linked clinical outcomes of prematurity were used to develop an NBS-based metabolic health index to stratify preterm infants at risk for BPD, IVH, NEC, and ROP (12,096 cases with one or more conditions and 1440 controls) through a deep learning model that provides a single index score in tandem with subgroup discovery to identify individuals with the strongest metabolite biomarker signals for adverse outcomes of prematurity. This metabolic health index captured risk signals that were distinct from gestational age and birthweight and outperformed other machine learning algorithms and clinical risk variable-based models in stratifying at-risk individuals for adverse outcomes of prematurity. The metabolic health index was externally validated in an independent retrospective cohort of 3299 very premature newborns from Ontario, Canada (2117 cases and 1182 controls), which recapitulated common metabolic risk subgroups. In summary, combining widespread metabolite screening with deep learning established a generalizable biological risk metric of prematurity.
- 21 January 2026
- Published by American Association for the Advancement of Science (AAAS) in Science Translational Medicine
- Vol. 18 (833) , eadv4942
Open AccessQuantitative assessment of neonatal health using dried blood spot metabolite profiles and deep learning
Neonatal prematurity leads to considerable morbidity and mortality, partly because of acquired conditions such as bronchopulmonary dysplasia (BPD), intraventricular hemorrhage (IVH), necrotizing enterocolitis (NEC), and retinopathy of prematurity (ROP). Standard gestational age and birthweight-based classifications of prematurity inadequately capture the variation in newborns’ health outcomes, creating an urgent need to develop risk stratification tools for vulnerable newborn infants to initiate the most appropriate care pathways as early as possible. We hypothesized that the metabolic profiles of newborn infants capture additional risk information beyond current measures. A total of 13,536 newborn screening (NBS) blood spot tests from preterm infants in California with linked clinical outcomes of prematurity were used to develop an NBS-based metabolic health index to stratify preterm infants at risk for BPD, IVH, NEC, and ROP (12,096 cases with one or more conditions and 1440 controls) through a deep learning model that provides a single index score in tandem with subgroup discovery to identify individuals with the strongest metabolite biomarker signals for adverse outcomes of prematurity. This metabolic health index captured risk signals that were distinct from gestational age and birthweight and outperformed other machine learning algorithms and clinical risk variable-based models in stratifying at-risk individuals for adverse outcomes of prematurity. The metabolic health index was externally validated in an independent retrospective cohort of 3299 very premature newborns from Ontario, Canada (2117 cases and 1182 controls), which recapitulated common metabolic risk subgroups. In summary, combining widespread metabolite screening with deep learning established a generalizable biological risk metric of prematurity.
- Open Access
- 29 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Targeted Real-Time Assessment of Chronic Pain (TRAC-Pain) in Youth: Protocol for a Digital Biosignature Development Through a Prospective Observational Cohort Study (Preprint)
BACKGROUND Approximately 1 in 5 children and adolescents live with chronic pain, with musculoskeletal (MSK) pain being one of the most prevalent subtypes. Unfortunately, some studies show that less than half of youth (<18 years) experience improvements with existing evidence-based treatments. Self-report measures—the current gold standard for monitoring the pain experience—are limited in their use as a single point-of-care assessment and their vulnerability to recall bias. The ubiquitous adoption of wearable technology presents a promising solution for improved monitoring of the pain experience via real-time tracking through a multisystemic lens. OBJECTIVE The purpose of this study is (1) to develop a digital biosignature of the pain experience in youth with chronic MSK pain and (2) to assess the feasibility, acceptability, and appropriateness of the captured data for future applications. METHODS All aspects of this study were designed in partnership with people with lived experience and patient advocacy partners. This is a longitudinal observational cohort study, with all study activities taking place remotely over a 12-week period. Up to 500 youth (between 14 and 24 years old) with chronic MSK pain will be enrolled through a multipronged recruitment strategy to ensure a representative sample. The participants will wear an Apple Watch throughout the study to continuously monitor physiological, sleep, and physical activity metrics. In addition, participants will complete brief “daily check-in” surveys that include gold-standard measures of the pain experience (eg, pain interference, mood, fatigue) and the option to report a “pain flare” (ie, a temporary but noticeable worsening of the usual pain symptoms). Participants will also complete a modified online Trier Social Stress Test and a 30-second sit-to-stand task to capture individual responses to standardized challenges. Traditional machine learning and deep representation learning methods will be used to develop a digital biosignature of the pain experience. The accuracy of the biosignature will be assessed through measures of model performance as compared to gold-standard self-reports. RESULTS This study was funded in September 2024, with data collection beginning in March 2025. As of December 15, 2025, 190 participants are enrolled, with data collection and analysis ongoing. CONCLUSIONS This is the first study to leverage wearable health technology for real-time monitoring of the pain experience in youth with chronic MSK pain. The resulting digital end points are expected to heighten the rigor of clinical trials and provide opportunities for individually tailored interventions. The second phase of this study will investigate the implementation of “wellness alerts” triggered by abnormal smartwatch readings. Alerts would empower users toward preemptive self-management strategies, thereby enhancing self-efficacy in those living with chronic MSK pain. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/84781
- 29 September 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessTargeted Real-Time Assessment of Chronic Pain (TRAC-Pain) in Youth: Protocol for a Digital Biosignature Development Through a Prospective Observational Cohort Study (Preprint)
BACKGROUND Approximately 1 in 5 children and adolescents live with chronic pain, with musculoskeletal (MSK) pain being one of the most prevalent subtypes. Unfortunately, some studies show that less than half of youth (<18 years) experience improvements with existing evidence-based treatments. Self-report measures—the current gold standard for monitoring the pain experience—are limited in their use as a single point-of-care assessment and their vulnerability to recall bias. The ubiquitous adoption of wearable technology presents a promising solution for improved monitoring of the pain experience via real-time tracking through a multisystemic lens. OBJECTIVE The purpose of this study is (1) to develop a digital biosignature of the pain experience in youth with chronic MSK pain and (2) to assess the feasibility, acceptability, and appropriateness of the captured data for future applications. METHODS All aspects of this study were designed in partnership with people with lived experience and patient advocacy partners. This is a longitudinal observational cohort study, with all study activities taking place remotely over a 12-week period. Up to 500 youth (between 14 and 24 years old) with chronic MSK pain will be enrolled through a multipronged recruitment strategy to ensure a representative sample. The participants will wear an Apple Watch throughout the study to continuously monitor physiological, sleep, and physical activity metrics. In addition, participants will complete brief “daily check-in” surveys that include gold-standard measures of the pain experience (eg, pain interference, mood, fatigue) and the option to report a “pain flare” (ie, a temporary but noticeable worsening of the usual pain symptoms). Participants will also complete a modified online Trier Social Stress Test and a 30-second sit-to-stand task to capture individual responses to standardized challenges. Traditional machine learning and deep representation learning methods will be used to develop a digital biosignature of the pain experience. The accuracy of the biosignature will be assessed through measures of model performance as compared to gold-standard self-reports. RESULTS This study was funded in September 2024, with data collection beginning in March 2025. As of December 15, 2025, 190 participants are enrolled, with data collection and analysis ongoing. CONCLUSIONS This is the first study to leverage wearable health technology for real-time monitoring of the pain experience in youth with chronic MSK pain. The resulting digital end points are expected to heighten the rigor of clinical trials and provide opportunities for individually tailored interventions. The second phase of this study will investigate the implementation of “wellness alerts” triggered by abnormal smartwatch readings. Alerts would empower users toward preemptive self-management strategies, thereby enhancing self-efficacy in those living with chronic MSK pain. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/84781
- Open Access
- 16 August 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-11
Whole genome deconvolution unveils Alzheimer’s resilient epigenetic signature
Assay for Transposase Accessible Chromatin by sequencing (ATAC-seq) accurately depicts the chromatin regulatory state and altered mechanisms guiding gene expression in disease. However, bulk sequencing entangles information from different cell types and obscures cellular heterogeneity. To address this, we developed Cellformer, a deep learning method that deconvolutes bulk ATAC-seq into cell type-specific expression across the whole genome. Cellformer enables cost-effective cell type-specific open chromatin profiling in large cohorts. Applied to 191 bulk samples from 3 brain regions, Cellformer identifies cell type-specific gene regulatory mechanisms involved in resilience to Alzheimer’s disease, an uncommon group of cognitively healthy individuals that harbor a high pathological load of Alzheimer’s disease. Cell type-resolved chromatin profiling unveils cell type-specific pathways and nominates potential epigenetic mediators underlying resilience that may illuminate therapeutic opportunities to limit the cognitive impact of the disease. Cellformer is freely available to facilitate future investigations using high-throughput bulk ATAC-seq data.
- 16 August 2023
- Published by Springer Nature in Nature Communications
- Vol. 14 (1) , 1-11
Open AccessWhole genome deconvolution unveils Alzheimer’s resilient epigenetic signature
Assay for Transposase Accessible Chromatin by sequencing (ATAC-seq) accurately depicts the chromatin regulatory state and altered mechanisms guiding gene expression in disease. However, bulk sequencing entangles information from different cell types and obscures cellular heterogeneity. To address this, we developed Cellformer, a deep learning method that deconvolutes bulk ATAC-seq into cell type-specific expression across the whole genome. Cellformer enables cost-effective cell type-specific open chromatin profiling in large cohorts. Applied to 191 bulk samples from 3 brain regions, Cellformer identifies cell type-specific gene regulatory mechanisms involved in resilience to Alzheimer’s disease, an uncommon group of cognitively healthy individuals that harbor a high pathological load of Alzheimer’s disease. Cell type-resolved chromatin profiling unveils cell type-specific pathways and nominates potential epigenetic mediators underlying resilience that may illuminate therapeutic opportunities to limit the cognitive impact of the disease. Cellformer is freely available to facilitate future investigations using high-throughput bulk ATAC-seq data.
- Open Access
- 16 June 2023
- Published by Wiley in Alzheimer's & Dementia
- Vol. 19 (S1)
Prediction of multiple neuropathologic changes from features available during life
Background: Neuropathologic changes are central for both understanding of the patients’ brains and making the definitive diagnosis of dementia‐related diseases. However, many of them are only obtainable post‐mortem. To make this information available while an individual is still alive, this study developed machine learning models that predict neuropathologic changes based on features obtainable during life.Method: The multi‐site post‐mortem data (n∼5000) was obtained from National Alzheimer’s Coordinating Center. A multitask long‐short term memory‐based neural network architecture was developed with custom loss to predict the 13 neuropathologic changes from features during life measured longitudinally. The performance of the model was evaluated using entire unseen sites as test sets. Evaluation metrics include area under receiver’s operating curve (AUROC) and area under precision recall curve (AUPRC).Result: The model was able to predict Alzheimer’s Disease neuropathologic changes (ADNC) and any Alzheimer’s‐related pathologies, such as Braak score, with great sensitivity, specificity, and precision (for example AUROC = 0.85; AUPRC = 0.96 for ADNC). Apart from these, the model can also predict hippocampal sclerosis accurately (AUROC = 0.79; AUPRC = 0.80) and Lewy Body disease at higher precision than clinician’s diagnosis. Model interpretation shows patterns in neuropsychological tests that are predictive of pathologic changes. Additionally, model error analysis revealed factors, such as resilient case ratios, that explain variation in performance between sites.Conclusion: Patterns of measurable features during life can be used by machine learning to predict ADNC, hippocampal sclerosis, and to lesser extent Lewy Body.
- 16 June 2023
- Published by Wiley in Alzheimer's & Dementia
- Vol. 19 (S1)
Open AccessPrediction of multiple neuropathologic changes from features available during life
Background: Neuropathologic changes are central for both understanding of the patients’ brains and making the definitive diagnosis of dementia‐related diseases. However, many of them are only obtainable post‐mortem. To make this information available while an individual is still alive, this study developed machine learning models that predict neuropathologic changes based on features obtainable during life.Method: The multi‐site post‐mortem data (n∼5000) was obtained from National Alzheimer’s Coordinating Center. A multitask long‐short term memory‐based neural network architecture was developed with custom loss to predict the 13 neuropathologic changes from features during life measured longitudinally. The performance of the model was evaluated using entire unseen sites as test sets. Evaluation metrics include area under receiver’s operating curve (AUROC) and area under precision recall curve (AUPRC).Result: The model was able to predict Alzheimer’s Disease neuropathologic changes (ADNC) and any Alzheimer’s‐related pathologies, such as Braak score, with great sensitivity, specificity, and precision (for example AUROC = 0.85; AUPRC = 0.96 for ADNC). Apart from these, the model can also predict hippocampal sclerosis accurately (AUROC = 0.79; AUPRC = 0.80) and Lewy Body disease at higher precision than clinician’s diagnosis. Model interpretation shows patterns in neuropsychological tests that are predictive of pathologic changes. Additionally, model error analysis revealed factors, such as resilient case ratios, that explain variation in performance between sites.Conclusion: Patterns of measurable features during life can be used by machine learning to predict ADNC, hippocampal sclerosis, and to lesser extent Lewy Body.
- 26 May 2023
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 9 (21) , eade7692
Multiomic signals associated with maternal epidemiological factors contributing to preterm birth in low- and middle-income countries
Preterm birth (PTB) is the leading cause of death in children under five, yet comprehensive studies are hindered by its multiple complex etiologies. Epidemiological associations between PTB and maternal characteristics have been previously described. This work used multiomic profiling and multivariate modeling to investigate the biological signatures of these characteristics. Maternal covariates were collected during pregnancy from 13,841 pregnant women across five sites. Plasma samples from 231 participants were analyzed to generate proteomic, metabolomic, and lipidomic datasets. Machine learning models showed robust performance for the prediction of PTB (AUROC = 0.70), time-to-delivery ( r = 0.65), maternal age ( r = 0.59), gravidity ( r = 0.56), and BMI ( r = 0.81). Time-to-delivery biological correlates included fetal-associated proteins (e.g., ALPP, AFP, and PGF) and immune proteins (e.g., PD-L1, CCL28, and LIFR). Maternal age negatively correlated with collagen COL9A1, gravidity with endothelial NOS and inflammatory chemokine CXCL13, and BMI with leptin and structural protein FABP4. These results provide an integrated view of epidemiological factors associated with PTB and identify biological signatures of clinical covariates affecting this disease.
- 26 May 2023
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 9 (21) , eade7692
Multiomic signals associated with maternal epidemiological factors contributing to preterm birth in low- and middle-income countries
Preterm birth (PTB) is the leading cause of death in children under five, yet comprehensive studies are hindered by its multiple complex etiologies. Epidemiological associations between PTB and maternal characteristics have been previously described. This work used multiomic profiling and multivariate modeling to investigate the biological signatures of these characteristics. Maternal covariates were collected during pregnancy from 13,841 pregnant women across five sites. Plasma samples from 231 participants were analyzed to generate proteomic, metabolomic, and lipidomic datasets. Machine learning models showed robust performance for the prediction of PTB (AUROC = 0.70), time-to-delivery ( r = 0.65), maternal age ( r = 0.59), gravidity ( r = 0.56), and BMI ( r = 0.81). Time-to-delivery biological correlates included fetal-associated proteins (e.g., ALPP, AFP, and PGF) and immune proteins (e.g., PD-L1, CCL28, and LIFR). Maternal age negatively correlated with collagen COL9A1, gravidity with endothelial NOS and inflammatory chemokine CXCL13, and BMI with leptin and structural protein FABP4. These results provide an integrated view of epidemiological factors associated with PTB and identify biological signatures of clinical covariates affecting this disease.