Scalable GPU Computing for Population-Level Clinical Analytics
Keywords:
GPU-Accelerated Computing,Clinical Intelligence,Population Health Analytics,Healthcare Big Data,High-Performance Computing (HPC),Artificial Intelligence in Healthcare,Medical Data Analytics,Distributed Clinical Computing,Predictive Healthcare Modeling,Real-Time Healthcare Analytics,GPU acceleration, clinical intelligence, population-scale analytics, healthcare data, reproducibility, scalability, data governance.Abstract
This study presents an objective, evidence-based evaluation of GPU-accelerated clinical intelligence frameworks for population-scale healthcare analytics, with emphasis on validation, performance, and reproducibility. While two existing clinical intelligence frameworks leverage GPU acceleration for analytics and clinical decision support, neither has been rigorously assessed with respect to validation methodology, GPU performance characteristics, or reproducibility. This work addresses that gap through a structured evaluation of both frameworks' architecture, validation approach, performance, and scalability, accompanied by a novel reproducibility protocol. Both frameworks are shown to be suitable for population-scale studies that require robust data governance, privacy protection, and ethical compliance.
The frameworks exploit GPU computing paradigms—including Single Instruction Multiple Data (SIMD), Multiple Instruction Multiple Data (MIMD), and tensor-core execution—to accelerate analysis of electronic health record (EHR) data and support the development of clinical decision support systems. A case study using a simulated database of 731.3 million records (324.8 TB) demonstrates substantial speedups achieved through MIMD execution relative to standard CPU processing. Geometry-based approximation techniques are further applied to accelerate analytics on imbalanced clinical datasets.
GPU acceleration has been integrated into TensorFlow and TheiaGraph to support immersive machine learning model development on clinical data, with dedicated ingestion and preprocessing modules enabling seamless integration with EHRs and other data sources. Privacy-preserving synthetic data generation—via Python-based ECG synthesis and differentially private deep generative modeling—allows realistic ECG signal generation under MIMD or tensor-core execution while safeguarding patient privacy.
A novel reproducibility protocol enables execution of Framework-1's analysis modules on a private clinical database at Cardiff and Vale University Health Board, laying the groundwork for an international parallel hospital performance comparison. Finally, the study examines the barriers and opportunities for population-scale digital health research within, between, and across countries, with particular attention to real-world evidence-driven epidemiological and clinical research.
References
1. Gamaarachchi, H., Lam, C. W., Jayatilaka, G., Samarakoon, H., Simpson, J. T., Smith, M. A., & Parameswaran, S. (2020). GPU accelerated adaptive banded event alignment for rapid comparative nanopore signal analysis. BMC Bioinformatics, 21, 343.
2. Esteva, A., Chou, K., Yeung, S., Naik, N., Madani, A., Mottaghi, A., Liu, Y., Topol, E., Dean, J., & Socher, R. (2021). Deep learning-enabled medical computer vision. npj Digital Medicine, 4, 5.
3. Hanussek, M., Bartusch, F., & Krüger, J. (2021). Performance and scaling behavior of bioinformatic applications in virtualization environments to create awareness for the efficient use of compute resources. PLOS Computational Biology, 17(7), e1009244.
4. Kumar, S. S., Gadi, A. L., Sheelam, G. K., Kummari, D. N., Reddy Koppolu, H. K., & Pamisetty, A. (2026). AI-Driven Compliance and Audit Framework for Manufacturing Infrastructure in Automotive Connected Services and Financial Ecosystems. In 2026 IEEE International Conference for Convergence in Computing Technology (I3CTCON) (pp. 1–6). IEEE. 2026 IEEE International Conference for Convergence in Computing Technology (I3CTCON). https://doi.org/10.1109/i3ctcon68242.2026.11507231
5. Arabi, H., AkhavanAllaf, A., Sanaat, A., Shiri, I., & Zaidi, H. (2021). The promise of artificial intelligence and deep learning in PET and SPECT imaging. Physica Medica, 83, 122–137.
6. Sanaat, A., Shiri, I., Arabi, H., Mainta, I., Nkoulou, R., & Zaidi, H. (2021). Deep learning-assisted ultra-fast/low-dose whole-body PET/CT imaging. European Journal of Nuclear Medicine and Molecular Imaging, 48, 2405–2415.
7. Suganyadevi, S., Seethalakshmi, V., & Balasamy, K. (2021). A review on deep learning in medical image analysis. International Journal of Imaging Systems and Technology, 31(1), 19–38.
8. Gamaarachchi, H., Lam, C. W., Jayatilaka, G., Samarakoon, H., Simpson, J. T., Smith, M. A., & Parameswaran, S. (2020). Genopo: A nanopore sequencing analysis toolkit for portable Android devices. Communications Biology, 3, 540.
9. Nagabhyru, K. C., Gadi, A. L., Seenu, A., Davuluri, P. S. L. N., Segireddy, A. R., & Pamisetty, V. (2026). Towards Automated Financial Risk Scoring in Automotive Financing with Explainable Machine Learning. In 2026 IEEE International Conference on AI Engineering and Innovations (AIEI) (pp. 1–6). IEEE. 2026 IEEE International Conference on AI Engineering and Innovations (AIEI). https://doi.org/10.1109/aiei69164.2026.11496822
10. Decuyper, M., Maebe, J., Van Holen, R., & Vandenberghe, S. (2021). Artificial intelligence with deep learning in nuclear medicine and radiology. EJNMMI Physics, 8, 81.
11. Krishnan, M., Nandan, B. P., Rongali, S. K., Meda, R., Kalisetty, S., & Singireddy, J. (2026, June). AI-Driven Data Engineering and Predictive Analytics Framework for Semiconductor Supply Chain Optimization and Digital Infrastructure Modernization. In 2026 6th International Conference on Intelligent Technologies (CONIT) (pp. 1-6). IEEE.
12. Wood, D. A., Kafiabadi, S., Al Busaidi, A., Guilhem, E. L., Lynch, J., Townend, M. K., Montvila, A., et al. (2022). Deep learning to automate the labelling of head MRI datasets for computer vision applications. European Radiology, 32, 725–736.
13. Gai, N. D., et al. (2022). Highly efficient and accurate deep learning-based classification of MRI contrast on a CPU and GPU. Journal of Digital Imaging, 35(3), 482–495.
14. Szczykutowicz, T. P., Toia, G. V., Dhanantwari, A., & Nett, B. (2022). A review of deep learning CT reconstruction: Concepts, limitations, and promise in clinical practice. Current Radiology Reports, 10, 101–115.
15. Mohan, A. A., Maguluri, K. K., Yasmeen, Z., & Pandugula, C. (2026). Evaluating the structural performance of axially loaded stainless steel circular tubular columns with ultra‐high‐performance concrete using an optimized attention pyramid convolutional neural network. Structural Concrete, 27(3), 3589-3608.
16. Yaqub, M., Jinchao, F., Arshid, K., et al. (2022). Deep learning-based image reconstruction for different medical imaging modalities. Computational and Mathematical Methods in Medicine, 2022, 8750648.
17. Wei, T., Aviles-Rivero, A. I., Wang, S., Huang, Y., Gilbert, F. J., Schönlieb, C.-B., & Chen, C. W. (2022). Beyond fine-tuning: Classifying high resolution mammograms using function-preserving transformations. Medical Image Analysis, 82, 102618.
18. Feng, Y., Gudukbay Akbulut, G., Tang, X., Gunasekaran, J. R., Rahman, A., Medvedev, P., & Kandemir, M. (2022). GPU-accelerated and pipelined methylation calling. Bioinformatics Advances, 2(1), vbac088.
19. Madhavi, K. R., Gottimukkala, V. R. R., Pandiri, L., Sriram, H. K., Malempati, M., & Adusupalli, B. (2025, November). Hybrid Transformer–Federated Learning Model for Secure Release Engineering in Global Payment Networks. In 2025 IEEE 3rd Global Conference on Wireless Computing and Networking (GCWCN) (pp. 1-6). IEEE.
20. Carpi, G., Gorenstein, L., Harkins, T. T., Samadi, M., & Vats, P. (2022). A GPU-accelerated compute framework for pathogen genomic variant identification to aid genomic epidemiology of infectious disease: A malaria case study. Briefings in Bioinformatics, 23(5), bbac314.
21. Wood, D. A., Kafiabadi, S., Guilhem, E. L., et al. (2021). Deep learning to automate the labelling of head MRI datasets for computer vision applications. European Radiology, 32, 725–736.
22. Segireddy, A. R., Nagabhyru, K. C., Gadi, A. L., Pandiri, L., Paleti, S., Nandan, B. P., ... & Meda, R. (2026). U.S. Patent Application No. 19/389,116.
23. Lin, C.-H., et al. (2021). Automated coronary calcium scoring using deep learning with multicenter external validation. npj Digital Medicine, 4, 88.
24. Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., & Dean, J. (2021). A guide to deep learning in healthcare. Nature Medicine, 27, 829–838.
25. Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2020). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60–88.
26. Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J., & Maier-Hein, K. H. (2021). nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation. Nature Methods, 18, 203–211.
27. Babu, A. J., Yandamuri, U. S., Recharla, M., Pamisetty, A., Goli, M., & Kolla, S. H. (2026, June). Data Analytics and AI Solutions for Digital Transformation in Hospitality and AgriTech Industries. In 2026 5th OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 5.0 (pp. 1-7). IEEE.
28. Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H. R., & Xu, D. (2022). UNETR: Transformers for 3D medical image segmentation. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (pp. 574–584).
29. Tang, Y., Yang, D., Li, W., Roth, H. R., Landman, B., Xu, D., & Hatamizadeh, A. (2022). Self-supervised pre-training of Swin transformers for 3D medical image analysis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 20730–20740).
30. Hatamizadeh, A., Yang, D., Roth, H. R., Xu, D., & Myronenko, A. (2022). Unetr++: Delving into efficient and accurate 3D medical image segmentation. arXiv.
31. Isensee, F., Petersen, J., Klein, A., Zimmerer, D., Jaeger, P. F., Kohl, S. A. A., Wasserthal, J., Koehler, G., Norajitra, T., Wirkert, S., & Maier-Hein, K. H. (2021). nnU-Net: Self-adapting framework for U-Net-based medical image segmentation. Nature Methods, 18, 203–211.
32. Vadisetty, R., Nuka, S. T., Kalisetty, S., Pandugula, C., Burugulla, J. K. R., & Annapareddy, V. N. (2026). Generative AI for Advanced Recycling Processes in Polyethylene and Polypropylene Manufacturing. In Lecture Notes in Networks and Systems (pp. 269–284). Springer Nature Singapore. https://doi.org/10.1007/978-981-96-8632-2_15
33. Milletari, F., Navab, N., & Ahmadi, S.-A. (2020). V-Net: Fully convolutional neural networks for volumetric medical image segmentation. Medical Image Analysis, 41, 140–151.
34. Fang, X., et al. (2023). GaNDLF: The generally nuanced deep learning framework for scalable end-to-end clinical workflows. Communications Engineering, 2, 23.
35. Dicks, S., Nolet, C., et al. (2023). GPU-accelerated single-cell RNA analysis with RAPIDS-singlecell. NVIDIA Technical Blog / RAPIDS ecosystem publication.
36. Fedorov, A., et al. (2024). End-to-end reproducible AI pipelines in radiology using the cloud. Nature Communications, 15, 6931.
37. Bick, A. G., Metcalf, G. A., Mayo, K. R., et al. (2024). Genomic data in the All of Us Research Program. Nature, 627, 340–346.
38. Garapati, R. S., Paleti, S., Meda, R., Nagabhyru, K. C., & Deepa Priya, B. S. (2026). Physical-Unclonable-Function-Based Secure and Anonymous User Authentication for Smart Homes. In Lecture Notes in Electrical Engineering (pp. 367–378). Springer Nature Switzerland. https://doi.org/10.1007/978-3-032-20235-2_33
39. Rodriguez, A., Kim, Y., Nandi, T., Keat, K., Kumar, R., Conery, M., Bhukar, R., Liu, M., Hessington, J., Maheshwari, K., Begoli, E., Tourassi, G., Muralidhar, S., Natarajan, P., Voight, B. F., Cho, K., Gaziano, M., Damrauer, S., Liao, K., Zhou, W., Huffman, J., Verma, A., Madduri, R., & VA Million Veteran Program. (2025). SAIGE-GPU: Accelerating genome- and phenome-wide association studies using GPUs. Bioinformatics, 42(3), btag032.a
