WhatsApp Channel
Telegram Group
🚨 Postdoctoral Position in Machine Learning, Deep Learning & Multimodal Prediction in Alzheimer’s Disease Risk | Mass General Brigham / Harvard
Institution: Mass General Brigham – Buckley Lab & Harvard Aging Brain Study (HABS) Data & Informatics Team
📍 Location: Boston, Massachusetts, USA 🇺🇸
🎓 Position: Postdoctoral Researcher
🔬 Research Area: Machine Learning | Deep Learning | Alzheimer’s Disease | Precision Medicine | Multimodal Data | Risk Prediction | Computational Neuroscience | Aging Research
The Buckley Lab and Harvard Aging Brain Study (HABS) Data & Informatics Team at Mass General Brigham are seeking a motivated Postdoctoral Researcher to work on an NIH-funded project focused on machine learning, deep learning, and multimodal prediction of Alzheimer’s disease risk.
The project aims to understand disease risk, resilience, and heterogeneity using large-scale multimodal data and advanced computational approaches. The researcher will develop predictive models integrating diverse longitudinal datasets to identify risk and resilience profiles relevant to precision medicine in Alzheimer’s disease.
🧠 What You’ll Work On
🤖 Machine Learning & Deep Learning
Develop advanced machine-learning and deep-learning approaches for predicting Alzheimer’s disease risk, resilience, and disease trajectories.
🔗 Multimodal Prediction
Integrate multiple types of large-scale data to develop multimodal predictive models for understanding individual differences in Alzheimer’s disease risk and progression.
📈 Longitudinal Modeling
Develop neural-network approaches capable of modeling longitudinal data and changes in disease-related measures over time.
⏳ Survival & Risk Modeling
Apply survival modeling and risk prediction techniques to investigate factors associated with Alzheimer’s disease outcomes and disease progression.
🧩 Clustering & Latent Subgroups
Identify latent subgroups and heterogeneous disease-risk profiles using clustering and related unsupervised-learning approaches.
🔍 Interpretable Machine Learning
Develop interpretable ML approaches to characterize risk and resilience profiles and improve understanding of model predictions.
🎯 Key Research Areas
The postdoctoral research will involve:
- Machine learning
- Deep learning
- Multimodal data integration
- Alzheimer’s disease research
- Dementia risk prediction
- Precision medicine
- Longitudinal modeling
- Survival analysis
- Risk prediction
- Neural networks
- Clustering
- Latent subgroup discovery
- Heterogeneity analysis
- Interpretable machine learning
- Computational neuroscience
- Biomedical data science
- Aging research
💻 Research & Computational Focus
The project will involve developing computational approaches capable of integrating complex, large-scale biomedical datasets.
Potential research activities include:
- Development of multimodal prediction models.
- Neural-network modeling of longitudinal data.
- Survival analysis and time-to-event modeling.
- Prediction of Alzheimer’s disease risk.
- Identification of disease-risk and resilience profiles.
- Clustering and latent subgroup discovery.
- Modeling heterogeneity in Alzheimer’s disease.
- Development of interpretable machine-learning frameworks.
- Evaluation and validation of predictive models.
- Integration and analysis of large-scale biomedical datasets.
- Translation of computational findings into clinically relevant insights.
👨💻 Ideal Candidate
Applicants should have a PhD or equivalent doctoral training in a quantitative field such as:
- Computer Science
- Bioinformatics
- Applied Mathematics
- Biostatistics
- Computational Neuroscience
- Data Science
- Statistics
- Biomedical Engineering
- Or another closely related quantitative discipline
Candidates should have:
- Strong programming and computational skills.
- Strong experience in data science and statistical analysis.
- Experience developing and evaluating machine-learning models.
- Familiarity with deep-learning methods.
- Experience handling large-scale or multimodal datasets.
- Strong quantitative and analytical skills.
- Ability to work independently and collaboratively.
- Strong scientific communication and writing skills.
Experience with longitudinal data, survival analysis, clustering, neural networks, or interpretable machine learning would be particularly relevant.
A background in Alzheimer’s disease, aging, neuroscience, or biomedical research is useful but the position emphasizes strong quantitative and computational expertise.
🌟 What You’ll Gain
- Postdoctoral research experience in Alzheimer’s disease and precision medicine.
- Advanced experience in machine learning and deep learning.
- Hands-on experience working with large-scale multimodal biomedical data.
- Experience developing longitudinal and survival prediction models.
- Training in computational approaches to disease heterogeneity and resilience.
- Experience with interpretable machine learning.
- Opportunity to collaborate with researchers working in aging, neuroscience, biomedical imaging, and informatics.
- Exposure to clinically relevant Alzheimer’s disease research.
- Opportunity to contribute to NIH-funded research projects.
- Development of expertise at the intersection of AI, data science, and neurodegenerative disease research.
🧪 Research Focus
The overall research framework follows:
Large-Scale Multimodal Data → Machine Learning & Deep Learning → Risk Prediction → Disease Heterogeneity & Resilience → Precision Medicine
The project seeks to use computational methods to better characterize Alzheimer’s disease risk, resilience, and heterogeneity at the individual level.
The research combines multimodal prediction, longitudinal modeling, survival analysis, clustering, latent subgroup discovery, and interpretable machine learning.
🧬 Potential Research Questions
The postdoctoral researcher may investigate questions such as:
- How can multimodal data be combined to improve prediction of Alzheimer’s disease risk?
- Which longitudinal patterns are associated with disease progression?
- Can machine learning identify distinct risk or resilience profiles?
- How can latent subgroups of individuals with different disease trajectories be identified?
- Which computational features contribute most strongly to risk prediction?
- How can machine-learning models provide interpretable insights into Alzheimer’s disease heterogeneity?
- How can computational predictions contribute to precision medicine approaches for Alzheimer’s disease?
👩🔬 Key Responsibilities
The successful postdoctoral researcher will be expected to:
- Develop and implement machine-learning and deep-learning models.
- Build multimodal prediction frameworks.
- Analyze longitudinal biomedical datasets.
- Develop survival and risk-prediction models.
- Perform clustering and latent subgroup analyses.
- Investigate heterogeneity in Alzheimer’s disease risk and resilience.
- Develop interpretable machine-learning approaches.
- Evaluate model performance and robustness.
- Conduct statistical and computational analyses.
- Organize, process, and analyze large-scale datasets.
- Collaborate with researchers across computational and biomedical disciplines.
- Interpret computational findings in the context of Alzheimer’s disease.
- Prepare scientific manuscripts and presentations.
- Contribute to NIH-funded research activities.
🏥 Research Environment
The researcher will work with the Buckley Lab and Harvard Aging Brain Study (HABS) Data & Informatics Team within the Mass General Brigham research environment.
The position is based at the Martinos Center for Biomedical Imaging in Boston, providing an interdisciplinary environment connecting computational research with biomedical imaging, aging, neuroscience, and Alzheimer’s disease research.
The project is NIH funded and focuses on developing computational approaches for precision medicine in Alzheimer’s disease.
📌 Position Details
Institution: Mass General Brigham
Research Group: Buckley Lab & Harvard Aging Brain Study (HABS) Data & Informatics Team
Contact: Rachel Buckley
Position: Postdoctoral Researcher
Location: Boston, Massachusetts, USA
Research Center: Martinos Center for Biomedical Imaging
Funding: NIH Funded
Research Area: Machine Learning | Deep Learning | Alzheimer’s Disease | Precision Medicine
Major Focus: Multimodal Prediction | Disease Risk | Resilience | Heterogeneity
Computational Methods: Neural Networks | Longitudinal Modeling | Survival Analysis | Risk Prediction | Clustering | Latent Subgroup Discovery | Interpretable ML
Preferred Background: Computer Science | Bioinformatics | Applied Mathematics | Biostatistics | Computational Neuroscience | Related Quantitative Field
Core Skills: Programming | Data Science | Machine Learning | Statistical Analysis
Duration: Open until filled
Application Mode: Email
Application Email: rfbuckley@mgh.harvard.edu
Location: Boston, USA
📄 How to Apply
Interested candidates should apply directly by email to:
📩 Rachel Buckley: rfbuckley@mgh.harvard.edu
Applicants should highlight their:
- Quantitative research background
- Programming and data-science experience
- Machine-learning/deep-learning experience
- Experience with large-scale or multimodal datasets
- Relevant computational or biomedical research experience
📅 Application Status: Open until filled
Category
Postdoctoral Position | Postdoc USA | Machine Learning | Deep Learning | Alzheimer’s Disease | Computational Neuroscience | Bioinformatics | Mass General Brigham | Harvard Aging Brain Study | Harvard Research | Neuroscience Research
🏷️ Tags
#Postdoc #PostdoctoralResearcher #MachineLearning #DeepLearning #AlzheimersDisease #PrecisionMedicine #Bioinformatics #DataScience
Follow Biopractify for more & Join our community : https://chat.whatsapp.com/F38FNCU0nfvFCDf1mYJDbm
About The Author
