AstraMedica: An AI-Powered Multi-Modal Healthcare System for Clinical Decision Support and Lifestyle Intervention | IJCSE Volume 10 – Issue 5 | IJCSE-V10I5P21
IJCSE
International Journal of Computer Science Engineering Techniques
ISSN 2455-135X · Peer-Reviewed · Open Access
📚 Volume 10, Issue 5
📅 September 29, 2026
📄 Pages 174–181
🔖 ID: IJCSE-V10I5P21
AstraMedica: An AI-Powered Multi-Modal Healthcare System for Clinical Decision Support and Lifestyle Intervention
Author(s)
Padala Prashant Reddy, Kuragayala Umamaheswar, Puli Vivek, N. Krishna Reddy, Gangireddy Siva Sai Vivekananda Reddy
Abstract
—Modern healthcare infrastructure faces severe pres sure from rising chronic disease prevalence, unequal distribu tion of specialist physicians, and fragmented diagnostic ser vices. To resolve these systemic bottlenecks, this paper presents AstraMedica—an integrated, multi-modal artificial intelligence healthcare assistance platform engineered for end-to-end clin ical decision support. AstraMedica unifies five specialized mi croservices: (1) automated electrocardiogram (ECG) arrhyth mia classification via deep residual networks; (2) blood report parameter parsing using clinical natural language processing (NLP) and optical character recognition (OCR); (3) bone frac ture localization using YOLOv8 coupled with spatial-attention ResNet152V2; (4) multi-pathology lung radiological screening using DenseNet-121 and 3D CNNs; and (5) a clinically grounded food recommendation engine integrated with an automated medication adherence notification subsystem. Built on a modular microservices architecture utilizing React.js, a Node.js security API gateway, Python Flask model inference servers, and dual-tier MongoDB/MySQLstorage, AstraMedica achieves high diagnostic throughput while maintaining clinical data privacy. Experimental evaluation demonstrates robust clinical utility: 97.4% accuracy (AUC 0.982) for ECG analysis, 94.2% accuracy for blood parsing, 92.2% accuracy on bone fracture localization, 93.8% accuracy (AUC 0.945) for pulmonary screening, with sub-4.2s end-to-end system latency.
Keywords
AstraMedica, Artificial Intelligence, Multi Modal Diagnostics, Deep Residual Networks, ECG Arrhythmia, Clinical NLP, YOLOv8, Thoracic Radiography, Dietary Recom mendation, Medication Adherence, Microservices Architecture
Conclusion
In this paper, we presented AstraMedica, a comprehen sive multi-modal artificial intelligence framework designed to bridge the gap between complex medical diagnostics and accessible patient care [26][cite: 2]. By integrating five specialized clinical domains—ECG arrhythmia classification, blood parameter interpretation, bone fracture localization, lung disease screening, and clinically grounded nutrition and medication tracking—AstraMedica demonstrates the efficacy of unified healthcare AI [26][cite: 2]. Built on a resilient microservices architecture and validated against recognized medical benchmarks, the system provides high diagnostic precision, rapid processing speeds, and actionable, patient centric feedback [1, 8, 11, 16, 26][cite: 2].
References
[1] A. Y. Hannun et al., “Cardiologist-level arrhythmia detection and classi fication in ambulatory electrocardiograms using a deep neural network,” Nature Medicine, vol. 25, no. 1, pp. 65–69, Jan. 2019 [1][cite: 2].
[2] P. Rajpurkar et al., “Cardiologist-level arrhythmia detection with convo lutional neural networks,” IEEE Transactions on Biomedical Engineer ing, vol. 65, no. 9, pp. 1918–1927, Sept. 2017 [2][cite: 2].
[3] S. Kiranyaz et al., “Automatic ECG classification using dual-input convolutional neural networks,” IEEE Access, vol. 6, pp. 14730–14742, Feb. 2018 [3][cite: 2].
[4] M. Blanco-Velasco et al., “ECG signal denoising and baseline wander correction based on empirical mode decomposition and wavelet trans form,” Biomedical Signal Processing and Control, vol. 3, no. 1, pp. 16–22, Jan. 2008 [4][cite: 2].
[5] U. R. Acharya et al., “Deep learning for real-time atrial fibrillation detection from ECG signals,” Physiological Measurement, vol. 39, no. 6, p. 064003, June 2018 [5][cite: 2].
[6] A. E. W. Johnson et al., “MIMIC-III, a freely accessible critical care database,” Scientific Data, vol. 3, p. 160035, May 2016 [6][cite: 2].
[7] J. Devlin et al., “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, Minneapolis, MN, USA, June 2019, pp. 4171–4186 [7][cite: 2].
[8] K. Kandula et al., “Med7: A transferable clinical natural language processing model for electronic health records,” Artificial Intelligence in Medicine, vol. 118, p. 102086, Aug. 2021 [8][cite: 2].
[9] M. Zhang and J. Wang, “Drug-drug interaction prediction using knowl edge graphs and deep learning,” IEEE Access, vol. 8, pp. 101154 101165, June 2020 [9][cite: 2].
[10] S. R. Patel and N. Shah, “Automated extraction and analysis of clinical parameters from handwritten medical reports using OCR,” Int. Journal of Image Processing, vol. 14, no. 2, pp. 44–56, 2020 [10][cite: 2].
[11] P. Rajpurkar et al., “CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning,” arXiv preprint arXiv:1711.05225, Stanford ML Group, Dec. 2017 [11][cite: 2].
[12] P. Lakhani and B. Sundaram, “Deep learning at chest radiography: Au tomated classification of pulmonary tuberculosis by using convolutional neural networks,” Radiology, vol. 284, no. 2, pp. 574–582, Aug. 2017
[12][cite: 2].
[13] A. A. A. Setio et al., “Pulmonary nodule detection in CT images: False positive reduction using multi-view convolutional networks,” IEEE Trans. Med. Imaging, vol. 35, no. 5, pp. 1160–1169, May 2016 [13][cite: 2].
[14] G. Gonzalez et al., “Disease staging and prognosis in smokers using deep learning in chest computed tomography,” Am. J. Respir. Critical Care Med., vol. 197, no. 2, pp. 193–203, Jan. 2018 [14][cite: 2].
[15] L. Li et al., “Artificial intelligence distinguishes COVID-19 from com munity acquired pneumonia on chest CT,” Radiology, vol. 296, no. 2, pp. E65–E71, Aug. 2020 [15][cite: 2].
[16] M. V. Reddy and K. Sudha, “Bone fracture detection using deep learning with YOLOv8 architecture,” Int. Research Journal of Engineering and Technology (IRJET), vol. 12, no. 10, pp. 432–439, Oct. 2024 [16][cite: 2].
[17] S. Venkatesamanne et al., “Bone fracture detection through advanced neural network architectures,” in Proc. ICSGET 2025, E3S Web of Conferences, vol. 619, p. 03012, 2025 [17][cite: 2].
[18] R. K. Gupta et al., “Diagnosis and detection of bone fracture in radio graphic images using deep learning approaches,” Frontiers in Medicine, vol. 11, p. 1358372, Apr. 2024 [18][cite: 2].
[19] W. Chen et al., “Multimodal deep learning for bone tumor diagnosis: Integration of radiographic, clinical, and pathological data,” Comput. Methods Programs Biomed., vol. 245, p. 108011, Mar. 2025 [19][cite: 2].
[20] W. Yuan et al., “Bone age assessment using various medical imaging techniques enhanced by artificial intelligence: A systematic review,” Diagnostics, vol. 15, no. 3, p. 322, Feb. 2025 [20][cite: 2].
[21] S. Hussain et al., “AI-driven personalized meal planning and dietary recommendations for chronic disease management,” Int. Journal of Computer Applications, vol. 187, no. 57, pp. 17–29, Nov. 2025 [21][cite: 2].
[22] B. Santo et al., “Development of a mobile application to improve medication adherence in patients with hypertension,” JMIR mHealth and uHealth, vol. 4, no. 2, p. e32, Jan. 2016 [22][cite: 2].
[23] C. Trattner and D. Elsweiler, “Food recommendations in the internet age,” in Proc. WWW 2016 Companion, Montreal, Canada, Apr. 2016, pp. 127–137 [23][cite: 2]. 8
[24] L. Free et al., “The effectiveness of mobile-health technology-based health behaviour change or disease management interventions for health care consumers,” PLoS Medicine, vol. 10, no. 1, p. e1001362, Jan. 2013
[24][cite: 2].
[25] D. Carter et al., “Effectiveness of a smartphone app to promote healthy weight management and dietary behaviour change among community members,” JMIR mHealth and uHealth, vol. 3, no. 4, p. e101, Oct. 2015 [25][cite: 2].
[26] R. Miotto et al., “Deep learning for healthcare: Review, opportunities and challenges,” Briefings in Bioinformatics, vol. 19, no. 6, pp. 1236 1246, Nov. 2018 [26][cite: 2].
[27] G. Litjens et al., “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, Dec. 2017 [27][cite: 2].
[28] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE CVPR, Las Vegas, NV, USA, June 2016, pp. 770–778 [28][cite: 2]
[2] P. Rajpurkar et al., “Cardiologist-level arrhythmia detection with convo lutional neural networks,” IEEE Transactions on Biomedical Engineer ing, vol. 65, no. 9, pp. 1918–1927, Sept. 2017 [2][cite: 2].
[3] S. Kiranyaz et al., “Automatic ECG classification using dual-input convolutional neural networks,” IEEE Access, vol. 6, pp. 14730–14742, Feb. 2018 [3][cite: 2].
[4] M. Blanco-Velasco et al., “ECG signal denoising and baseline wander correction based on empirical mode decomposition and wavelet trans form,” Biomedical Signal Processing and Control, vol. 3, no. 1, pp. 16–22, Jan. 2008 [4][cite: 2].
[5] U. R. Acharya et al., “Deep learning for real-time atrial fibrillation detection from ECG signals,” Physiological Measurement, vol. 39, no. 6, p. 064003, June 2018 [5][cite: 2].
[6] A. E. W. Johnson et al., “MIMIC-III, a freely accessible critical care database,” Scientific Data, vol. 3, p. 160035, May 2016 [6][cite: 2].
[7] J. Devlin et al., “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, Minneapolis, MN, USA, June 2019, pp. 4171–4186 [7][cite: 2].
[8] K. Kandula et al., “Med7: A transferable clinical natural language processing model for electronic health records,” Artificial Intelligence in Medicine, vol. 118, p. 102086, Aug. 2021 [8][cite: 2].
[9] M. Zhang and J. Wang, “Drug-drug interaction prediction using knowl edge graphs and deep learning,” IEEE Access, vol. 8, pp. 101154 101165, June 2020 [9][cite: 2].
[10] S. R. Patel and N. Shah, “Automated extraction and analysis of clinical parameters from handwritten medical reports using OCR,” Int. Journal of Image Processing, vol. 14, no. 2, pp. 44–56, 2020 [10][cite: 2].
[11] P. Rajpurkar et al., “CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning,” arXiv preprint arXiv:1711.05225, Stanford ML Group, Dec. 2017 [11][cite: 2].
[12] P. Lakhani and B. Sundaram, “Deep learning at chest radiography: Au tomated classification of pulmonary tuberculosis by using convolutional neural networks,” Radiology, vol. 284, no. 2, pp. 574–582, Aug. 2017
[12][cite: 2].
[13] A. A. A. Setio et al., “Pulmonary nodule detection in CT images: False positive reduction using multi-view convolutional networks,” IEEE Trans. Med. Imaging, vol. 35, no. 5, pp. 1160–1169, May 2016 [13][cite: 2].
[14] G. Gonzalez et al., “Disease staging and prognosis in smokers using deep learning in chest computed tomography,” Am. J. Respir. Critical Care Med., vol. 197, no. 2, pp. 193–203, Jan. 2018 [14][cite: 2].
[15] L. Li et al., “Artificial intelligence distinguishes COVID-19 from com munity acquired pneumonia on chest CT,” Radiology, vol. 296, no. 2, pp. E65–E71, Aug. 2020 [15][cite: 2].
[16] M. V. Reddy and K. Sudha, “Bone fracture detection using deep learning with YOLOv8 architecture,” Int. Research Journal of Engineering and Technology (IRJET), vol. 12, no. 10, pp. 432–439, Oct. 2024 [16][cite: 2].
[17] S. Venkatesamanne et al., “Bone fracture detection through advanced neural network architectures,” in Proc. ICSGET 2025, E3S Web of Conferences, vol. 619, p. 03012, 2025 [17][cite: 2].
[18] R. K. Gupta et al., “Diagnosis and detection of bone fracture in radio graphic images using deep learning approaches,” Frontiers in Medicine, vol. 11, p. 1358372, Apr. 2024 [18][cite: 2].
[19] W. Chen et al., “Multimodal deep learning for bone tumor diagnosis: Integration of radiographic, clinical, and pathological data,” Comput. Methods Programs Biomed., vol. 245, p. 108011, Mar. 2025 [19][cite: 2].
[20] W. Yuan et al., “Bone age assessment using various medical imaging techniques enhanced by artificial intelligence: A systematic review,” Diagnostics, vol. 15, no. 3, p. 322, Feb. 2025 [20][cite: 2].
[21] S. Hussain et al., “AI-driven personalized meal planning and dietary recommendations for chronic disease management,” Int. Journal of Computer Applications, vol. 187, no. 57, pp. 17–29, Nov. 2025 [21][cite: 2].
[22] B. Santo et al., “Development of a mobile application to improve medication adherence in patients with hypertension,” JMIR mHealth and uHealth, vol. 4, no. 2, p. e32, Jan. 2016 [22][cite: 2].
[23] C. Trattner and D. Elsweiler, “Food recommendations in the internet age,” in Proc. WWW 2016 Companion, Montreal, Canada, Apr. 2016, pp. 127–137 [23][cite: 2]. 8
[24] L. Free et al., “The effectiveness of mobile-health technology-based health behaviour change or disease management interventions for health care consumers,” PLoS Medicine, vol. 10, no. 1, p. e1001362, Jan. 2013
[24][cite: 2].
[25] D. Carter et al., “Effectiveness of a smartphone app to promote healthy weight management and dietary behaviour change among community members,” JMIR mHealth and uHealth, vol. 3, no. 4, p. e101, Oct. 2015 [25][cite: 2].
[26] R. Miotto et al., “Deep learning for healthcare: Review, opportunities and challenges,” Briefings in Bioinformatics, vol. 19, no. 6, pp. 1236 1246, Nov. 2018 [26][cite: 2].
[27] G. Litjens et al., “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, Dec. 2017 [27][cite: 2].
[28] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE CVPR, Las Vegas, NV, USA, June 2016, pp. 770–778 [28][cite: 2]
📋 How to Cite This Paper
Padala Prashant Reddy, Kuragayala Umamaheswar, Puli Vivek, N. Krishna Reddy, Gangireddy Siva Sai Vivekananda Reddy (2026). AstraMedica: An AI-Powered Multi-Modal Healthcare System for Clinical Decision Support and Lifestyle Intervention. International Journal of Computer Science Engineering Techniques, 10(5), 174–181. ISSN: 2455-135X. DOI: https://doi.org/10.5281/zenodo.23031540
Related Posts:
