Authors : C. M. Odii; F. U. Onu; Titus Ikechukwu Offiah; Christain Nweze

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/2zyberm3

Scribd : https://tinyurl.com/4j4dk6va

DOI : https://doi.org/10.38124/ijisrt/26mar1378

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Lumbar spondylosis is a prevalent degenerative spinal condition whose diagnosis traditionally relies on the manual interpretation of X-ray images a process that is time-consuming, subjective, and difficult to scale for populationlevel analytics. This research addresses this challenge by developing an integrated, cloud-based diagnostic and analytics platform for the automated detection and management of lumbar spondylosis. The work employs an Agile software development methodology, enabling iterative prototyping and stakeholder feedback. The system is built on a microservices architecture implemented in Python. Its core consists of: (1) a diagnostic module featuring a Convolutional Neural Network (CNN) developed in PyTorch to detect degenerative features such as osteophytes and disc space narrowing from lumbar spine X-rays, and (2) a cloud platform orchestrated with Docker and served via RESTful APIs (Laravel framework). Backend analytics are powered by Pandas and Scikit-learn. In a pilot evaluation using a retrospectively collected dataset, the diagnostic module achieved an overall accuracy of 94.2%, with 96.5% sensitivity and 92.1% specificity, while significantly reducing preliminary screening time. The cloud analytics engine enabled large-scale data aggregation, population trend identification, and patient risk stratification. The results validate that a cloud-based AI system can effectively augment clinical decision-making, offering a consistent, efficient screening tool for clinicians, supporting faster patient assessment, and enabling scalable analytics for healthcare systems.

Keywords : Lumbar Spondylosis, Artificial Intelligence, Convolutional Neural Network (CNN), Cloud Computing, Medical Diagnostics, Predictive Analytics, PyTorch, Agile Development.

References :

1. Van der Kraan PM, van den Berg WB. Osteophytes: relevance and biology. Osteoarthritis Cartilage. 2007.
2. Brinjikji W, et al. MRI findings of disc degeneration are more prevalent in adults with low back pain than in asymptomatic controls: a systematic review and meta-analysis. AJNR Am J Neuroradiol. 2015.
3. Rothschild B. Lumbar Spondylosis. Medscape. 2011.
4. Pfirrmann CW, et al. Magnetic resonance classification of lumbar intervertebral disc degeneration. Spine. 2001.
5. Alomari RS, et al. Computer-aided diagnosis of lumbar spine stenosis using a Bayesian classifier. Proc Int Conf Bioinform Biomed. 2011.
6. Han Z, et al. Spine-GAN: Semantic segmentation of multiple spinal structures. Med Image Anal. 2018.
7. Lessmann N, et al. Iterative fully convolutional neural networks for automatic vertebra segmentation and identification. Med Image Anal. 2019.
8. Puliafito A, et al. Cloud-based Healthcare Systems: A Review. IEEE Access. 2019.
9. Sultan N. Making use of cloud computing for healthcare provision: Opportunities and challenges. Int J Inf Manage. 2014.
10. Gillies RJ, et al. Radiomics: Images Are More than Pictures, They Are Data. Radiology. 2016.
11. Raghupathi W, Raghupathi V. Predictive analytics in healthcare: Challenges and opportunities. IEEE Trans Inf Technol Biomed. 2014.
12. Oakden-Rayner L. Exploring large-scale public medical image datasets. Acad Radiol. 2020.