Publications
For the most updated list of my publications, please visit my Google Scholar or Semantic Scholar page.
Journal articles (* indicates working and under review papers)
* Qiu, P, Yang, J, Kumar, S, Ghosh, S, Sotiras, A. AgileFormer: Spatially Agile Transformer UNet for Medical Image Segmentation. [IEEE Journal of Biomedical Health Informatics (JBHI), under review].[ArXiv] [Code]
Kumar, S, Oh, I, Schindler. S., Ghoshal. N., Abrams, Z., Payne, P. Revealing heterogeneity in dementia using data-driven unsupervised clustering of cognitive profiles. PLOS One Paper
Yang, B, Earnest, T, Kumar, S, Kothapalli, D, Gordon, B, Soritas, A. Evaluation of ComBat harmonization for reducing across-tracer biases in regional amyloid PET analyses. Human Brain Mapping Paper
Kumar, S, Yu, S, Michelson, A, Kannampallil, T, Payne, PRO. HiMAL: A Multimodal Hierarchical Multi-task Auxiliary Learning framework for predicting and explaining Alzheimer disease progression. JAMIA open, 7(3), ooae087. Paper
Kumar, S., Earnest, T., Yang, B.,… Sotiras, A. (2023). Analyzing heterogeneity in Alzheimer Disease using multimodal normative modeling on imaging-based ATN biomarkers. [Alzheimer’s & Dementia, Accepted, Minor revision]. BioRxiV
Ma W., Oh I., Luo Y.,Kumar S., Gupta A.,,… and Michelson A. Incorporating Donor Lung CT Images into Machine Learning Models to Predict Severe Primary Graft Dysfunction after Lung Transplantation, American Journal of Transplantation, 2025.
* Lou SS, Kumar S, Goss C, Avidan MS, Kheterpal S, Kannampallil T. Multi-center validation of a machine learning model for surgical transfusion risk at 45 US hospitals[JAMA Network Open, under review]
Kumar, S., Oh, I., Schindler, S., Lai, A. M., Payne, P. R., and Gupta, A. (2021). Machine learning for modeling the progression of Alzheimer disease dementia using clinical data: a systematic literature review. JAMIA open, 4(3), ooab052. [Paper]
Conference articles
Qiu, P, Zhu, W, Kumar, S, Chen, X, Yang, J, Sun, X, Razi, A, Wang, Y, Sotiras, A, Multimodal Variational Autoencoder: a Barycentric View. [AAAI 2025, Oral] [Paper]
Kumar, S, Payne, PR, and Sotiras, A. Improving Normative Modeling for Multi-modal Neuroimaging Data using mixture-of-product-of-experts variational autoencoders. Accepted in IEEE International Symposium in Biomedical Imaging (IEEE ISBI 2024) [Paper] [Code]
Kumar, S, Payne, PR, and Sotiras, A. (2023, April). Normative modeling using multimodal variational autoencoders to identify abnormal brain volume deviations in Alzheimer’s disease. In SPIE Medical Imaging 2023: Computer-Aided Diagnosis (Vol. 12465, p. 1246503). [Oral][Best paper award finalist] [Paper] [Code]
Kumar, S, Yu, S, Kannampallil, T, Abrams, Z, Michelson, A, and Payne, PR. (2022, August). Self-explaining neural network with concept-based explanations for ICU mortality prediction. In Proceedings of the 13th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (pp. 1-9) (ACM BCB 2022)[Oral] [Paper] [Code]
Peer-reviewed workshops and abstracts
Yang, B., Earnest, T., Kumar, S., Gordon, B. A., & Sotiras, A. (2024, July). Harmonization of amyloid PET radiotracers using ComBat and its influence on detecting treatment effects in a simulated clinical trial. In Alzheimer’s Association International Conference. ALZ.[Poster]
Lou SS, Kumar S, Avidan MS, Kheterpal S, Kannampallil T. External validation of a publicly available surgical transfusion risk prediction model: a multi-center perioperative outcomes group study. World Congress of Anaesthesiologists 2024. [Oral]
Kumar, S, Kannampallil, T., Sotiras, A., and Payne, P. (2023, October). Explaining Longitudinal Clinical Outcomes using Domain-Knowledge driven Intermediate Concepts In XAI in Action: Past, Present, and Future Applications Workshop NeurIPS 2023. [Poster] [Workshop Paper] [Code]
Kumar, S., Payne, P., and Sotiras, A. (2023, October). mmNormVAE: Normative Modeling on Multimodal Neuroimaging Data using Variational Autoencoders. In Deep Generative Models for Health Workshop NeurIPS 2023. [Poster] [Workshop Paper] [Code]
Kumar, S, Yu, S, Kannampallil, T, Abrams, Z, Michelson, A, and Payne, PR. Explaining Neural Network with Plausible Explanations. Symposium on Artificial Intelligence in Health (SAIL 2022).[Poster]
Kumar, S, Abrams, Z, Oh, I, Gupta, A, Schindler SE, Ghoshal, N, Lai, AM, Payne, PRO. Identifying Interpretable Clinical Subtypes within Heterogeneous Dementia Clinic Population. AMIA 2022 Informatics Summit.[Oral]
Kumar, S, Oh, I, Gupta, A, Oh, I, Lai, AM, Payne, PRO. Leveraging Electronic Health Records Data for Predicting Alzheimer’s Disease Progression. AMIA 2021 Informatics Summit(Virtual).[Poster]
Kumar, S, Gupta, A, Oh, I, Schindler, S, Lai, AM, Payne, PRO. Simplified Form of Recurrent Neural Networks for Predicting Alzheimer Disease Progression. Pacific Symposium on Biocomputing (PSB 2021). [Poster]