January 2025 - Present | Baku, Azerbaijan

Leading technology strategy for Skolyn, an AI-driven clinical decision support platform focused on eliminating diagnostic errors through explainable AI.

Key Achievements:

• Architected platform processing 127+ pathological indicators in <3 seconds
• Achieved >95% diagnostic accuracy with full XAI interpretability
• Scaled to 50,000+ scans across Nordic and DACH hospitals
• Positioned for $2M Seed round with CE Mark/FDA 510(k) readiness

Tech Stack: Python, PyTorch, Docker, Kubernetes, HL7/FHIR

Seconded National Expert - European Research Council (Nov 2025 - Present)
Policy development and strategic evaluation of €16B research portfolio. ML-based evaluation workflows for 12,000+ ERC projects.

Postdoctoral Researcher - Uppsala University (Jul 2025 - Present)
Medical imaging and explainable AI for neuroradiology. Led federated learning benchmark across 5 Swedish hospitals with >0.9 accuracy.

Clinical Bioinformatician - Linköping University Hospital (2025 - Present)
Clinical genomics operations, rare disease diagnosis, variant interpretation using Nextflow/nf-core pipelines.

Data Science Specialist - DTU Bioengineering (2025 - Present)
Proteomics analysis and systems biology. Mass spectrometry data analysis, graph neural networks for protein interactions.

Trustworthy AI for Clinical Decision Support (2023-2026)
5.0M EUR | Academy of Finland | PI: Prof. Samuel Kaski

Large Language Models for Medical QA (2024-2025)
Google Health AI | Lead: Dr. Emily Chen

1. Imanov, O.Y.L., Schmidt, M., & Andersson, L. (2025) "Integrative machine learning framework for early-stage neurodegeneration biomarkers from multi-omics profiles." J Proteome Res [Forthcoming]

2. Imanov, O.Y.L., Chen, E., & Kumar, R. (2025) "Explainable AI in sonography: Transferring interpretability from proteomics to medical imaging." JAMIA [Forthcoming]

3. Imanov, O.Y.L., Christensen, A.N., & Nielsen, M. (2025) "Designing adaptive human-AI systems for collaborative problem solving in fetal ultrasound diagnostics." Med Image Anal, 85:102745. [IF: 10.9]

4. Imanov, O.Y.L., Kaski, S., & Virtanen, P. (2024) "Adaptive federated ensembles for heterogeneous medical imaging datasets." IEEE Trans Med Imaging, 43(12):4234-4247. [IF: 11.0, Citations: 3]

5. Chen, E., Imanov, O.Y.L., & Zhang, W. (2024) "Human-in-the-loop evaluation of large language models for medical question answering." Nat Digit Med, 7(1):245. [IF: 18.2, Citations: 8]

6. Imanov, O.Y.L., Bergström, S., & Andersson, J. (2023) "Trustworthy reinforcement learning with human-in-the-loop feedback for medical imaging." Med Image Anal, 89:102876. [IF: 10.9, Citations: 12] Best Paper Award - NeurIPS 2023

Full Publication List →

2025

• "Explainable AI for Medical Image Analysis" - European Congress of Radiology (ECR), Vienna
• "Federated Learning in Healthcare" - Nordic AI in Medicine Summit, Stockholm (Invited)

2024

• "Human-AI Collaboration in Radiology" - MICCAI, Marrakesh
• "Evaluating LLMs for Clinical QA" - Google Health AI Symposium (Invited)
• "Adaptive Federated Learning" - ICML, Vienna

2023

• "Trustworthy RL with Human Feedback" - NeurIPS Workshop, New Orleans Best Paper Award
• "Explainable AI in Clinical Genomics" - ESHG Conference, Glasgow

Course Coordinator - Linköping University (2025)

• TDDE15: Introduction to Data Analysis with Python (6 credits, ~120 students)
• TAMS41: Statistical Modelling with Regression Methods (6 credits, ~80 students)

Lecturer - Linköping University (2025)

• TNK128: Fundamental Programming for Data Analytics
• TAMS11: Probability and Statistics
• TAMS17: Statistical Theory (Advanced)
• TAMS39: Multivariate Statistical Methods

Guest Lectures

• "Explainable AI in Medical Imaging" - Uppsala/Linköping (Doctoral series)
• "Federated Learning for Healthcare" - DTU (2025)
• "Human-AI Collaboration" - FCAI (2024)

PhD Supervision (2 students)

• Anna Karlsson (Main) - Brain tumor detection in MRI
• Erik Johansson (Co) - Clinical genomics pipeline optimization

Master's Supervision (6 current, 1 completed)

• Sofia Bergström, Marcus Lindholm, Emma Svensson (Main supervisors)
• Johan Andersson, Lisa Pettersson (Co-supervisors)

Mentorship

• Maria Johansson (PhD, Uppsala) - Career development & research methodology
• Ahmed Ali (PhD, Linköping) - Technical skills & academic writing

• Deep Learning: CNNs, RNNs, Transformers, GANs, Graph Neural Networks
• Explainable AI: SHAP, LIME, Integrated Gradients, Attention mechanisms
• Federated Learning: Privacy-preserving distributed training
• Classical ML: Random Forests, XGBoost, SVM, Ensemble methods

• Bayesian Hierarchical Modeling
• Mixed-Effects Models & GLMs
• Causal Inference Methods
• Survival Analysis
• Time Series Analysis (ARIMA, GARCH)
• Dimensionality Reduction (PCA, t-SNE, UMAP)

• Genomics: Variant calling, annotation, GWAS, RNA-seq
• Proteomics: Mass spectrometry, MaxQuant, Perseus
• Multi-Omics: Data integration, network analysis
• Tools: Bioconductor, nf-core, Nextflow
• Formats: VCF, BAM, FASTQ, FASTA

• Modalities: MRI, CT, X-ray, Ultrasound
• Standards: DICOM, NIfTI, HL7/FHIR
• Tools: 3D Slicer, ITK-SNAP, SimpleITK
• Methods: Segmentation, classification, registration