Heal Me: Your Pocket Doctor

Abstract

Introduction

The text presents an AI-based healthcare system called HealMe designed to improve early detection and management of lung cancer by integrating multiple digital health technologies. Lung cancer remains a major global health issue largely due to late diagnosis and limited access to specialized screening, especially in rural and resource-poor regions. Traditional methods like CT scans are effective but expensive and require expert interpretation, while symptom-based diagnosis alone is often unreliable.

HealMe addresses these challenges by combining machine learning, deep learning (CNNs), and telemedicine into a unified platform. The system uses three main components: (1) a symptom-based risk prediction model using patient data, (2) CNN-based analysis of CT scans for detecting lung abnormalities, and (3) telemedicine services with hospital recommendations and remote consultations. This hybrid approach improves accessibility, supports early screening, and enables faster clinical decision-making.

The literature shows that CNN models achieve high accuracy in lung cancer detection from CT images, while symptom-based models provide moderate predictive ability useful for population screening. Telemedicine enhances access to healthcare by connecting patients with specialists remotely. However, existing systems lack integration of these components into a single platform.

Conclusion

HealMe provides successful integration of AI-based lung cancer screening, teleconsultation telephonic and hospital routing, into one unified digital platform. The hybridised diagnostic approach using both questionnaire risk assessment and deep learning imaging correlates with recent advances in precision oncology that support multimodal screening approaches [1], [2] In terms of limitations, although the system is strong diagnostically, there are limitations such as; the scale of the dataset, false positives (dependent on the accuracy/ validity of the responses obtained), degree of self-reported symptomology (e.g., variance between two people’s descriptions or reporting of symptoms). Future improvements could include multimodality fusion models, increased sizes of datasets, the application of explainable AI (XAI) techniques to visualisation models [2], improved telehealth workflows [5], & compliance with HIPAA/GDPR guidelines [7]. In conclusion, HealMe is an important milestone toward providing accessible, affordable, and intelligent healthcare solutions utilising AI and telemedicine which will help facilitate early detection and intervention.

References

[1] E. Zhu, A. Muneer, J. Zhang, et al., “Progress and challenges of artificial intelligence in lung cancer clinical translation,” npj Precision Oncology, vol. 9, p. 210, 2025. [2] JR Jim, M.E. Rayed, M. Mridha, K. Nur, “XLLC-Net: A lightweight and explainable CNN for accurate lung cancer classification using histopathological images,” PLOS ONE, vol. 20, no. 5, e0322488, 2025. [3] V. Shariff, C. Paritala, K. Ankala, “Optimizing non–small cell lung cancer detection with convolutional neural networks and differential augmentation,” Scientific Reports, vol. 15, p. 15640, 2025. [4] C. Frick, et al., “Head-to-head comparisons of risk discrimination by questionnaire-based lung cancer risk prediction models: A systematic review and meta-analysis,” eClinicalMedicine, vol. 80, p. 103075, 2025. [5] A. Haleem, M. Javaid, R.P. Singh, R. Suman, “Telemedicine for healthcare: Capabilities, features, barriers, and applications,” Sensors International, vol. 2, p. 100117, 2021. [6] V. Shariff, C. Paritala, K. Ankala, “Optimizing lung cancer detection with CNN and augmentation,” Scientific Reports, vol. 15, p. 15640, 2025. (Duplicate in PDF; kept for citation integrity.) [7] Supabase Documentation, “Authentication, database security, and RLS policies,” 2025. Available: https://supabase.com. [8] S.G. Armato III, et al., “The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A completed reference database of lung nodules on CT scans,” Medical Physics, vol. 38, no. 2, pp. 915–931, 2011. [9] IQ-OTH/NCCD Dataset, cited in Shariff et al., “Optimizing non-small cell lung cancer detection,” Scientific Reports, 2025.

Copyright

Copyright © 2026 Abhinav Srivastava, Aditya Jaiswal, Aastha Gupta, Ayush Kr. Rai, Mr. Indrajeet Sinha. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.