Artificial Intelligence in Healthcare: A
Literature Review
MOHAMMED FAZIL NAYAZ - 4SF23CI088
Department of CSE (AI-ML)
SAHYADRI COLLEGE OF ENGINEERING AND MANAGEMENT
ADYAR, MANGALORE – 575007
Abstract
—Artificial Intelligence (AI) is becoming very
Important in healthcare. AI helps in medical image analysis,
Disease prediction, patient monitoring, and drug discovery. This
Paper reviews recent research papers on AI in healthcare. The
Review shows that AI brings many benefits like faster diagnosis
And better patient care, but challenges such as data privacy,
Accuracy, and ethics remain.
Index Terms—Artificial Intelligence, Healthcare, Medical
Imaging, Diagnosis.
I. INTRODUCTION
Artificial Intelligence (AI) is widely used in different fields,
And healthcare is one of the most important. Doctors and
Hospitals are using AI systems for diagnosis and treatment
Support [1], [2]. For example, AI can analyze medical images
Such as X-rays or MRIs much faster than humans [3]. AI can
Also predict diseases like diabetes or heart problems based on
Patient data [4]. This paper reviews research on AI in
Healthcare to show progress and limitations.
II. LITERATURE REVIEW
A. Content
Researchers mainly focus on these areas:
- Medical imaging and diagnosis [5], [6].
- Predictive analytics and disease detection [7].
- Patient monitoring and hospital management [8].
- Drug discovery and personalized medicine [9].
B. Organization
The selected papers can be grouped as:
1) AI for medical imaging and cancer detection [10].
2) AI for prediction of diseases like heart and lung conditions
[11].
3) AI in hospital systems and patient care [12].
4) Ethical and legal issues in healthcare AI [13].
C. Synthesis
Most works agree that AI improves healthcare outcomes by
Helping doctors and reducing workload. However, problems
Like data privacy, medical errors, and lack of trust from
Patients are still challenges.
III. METHODOLOGY
This review collected about 26 papers, mainly from IEEE
Xplore and journals from 2020 to 2025. Papers were studied
And grouped into four main themes: imaging, prediction,
Patient care, and ethics.
IV. RESULTS
The key findings are:
-AI helps detect cancer, tumors, and lung disease with high
Accuracy [5], [10].
-Machine learning models can predict heart attacks or
Diabetes risks [7], [11].
- AI is used for patient monitoring in hospitals and at home
[8], [12].
- Ethical concerns include data misuse and lack of
Explainability [13].
V. DISCUSSION
AI has great potential to improve healthcare systems. It saves
Time, reduces cost, and helps doctors with diagnosis. But AI
Should not replace doctors completely. Human supervision is
Still necessary. More testing, regulation, and transparency are
Needed.
VI. CONCLUSION
AI is a powerful tool in healthcare. It improves diagnosis,
Treatment, and patient care. At the same time, privacy and
Ethical issues need attention. In the future, AI will be more
Common in hospitals if these problems are solved.
REFERENCES
[1] M. Esteva et al., “Dermatologist-level classification of skin cancer with deep
neural networks,” Nature, vol. 542, 2017.
[2] A. Rajpurkar et al., “CheXNet: Radiologist-level pneumonia detection on
chest X-rays with deep learning,” arXiv:1711.05225, 2017.
[3] G. Litjens et al., “A survey on deep learning in medical image analysis,” Med.
Image Anal., vol. 42, 2017.
[4] J. Choi et al., “Machine learning for diabetes prediction,” IEEE Access, vol. 8,
2020.
[5] T. Ardila et al., “End-to-end lung cancer screening with three-dimensional
deep learning,” Nat. Med., vol. 25, 2019.
[6] K. He et al., “Deep residual learning for image recognition,” Proc. IEEE
CVPR, 2016.
[7] S. Reddy et al., “AI in predicting heart disease,” IEEE Access, vol. 9, 2021.
[8] P. Kumar et al., “IoT and AI for patient health monitoring,” Proc. IEEE
ICCCIS, 2021.
[9] D. Zhavoronkov et al., “AI in drug discovery,” Nat. Biotechnol., vol. 37, 2019.
[10] A. Irvin et al., “CheXpert: A large chest radiograph dataset with uncertainty
labels,” Proc. AAAI, 2019.
[11] R. Miotto et al., “Deep learning for healthcare: Review, opportunities and
challenges,” Brief. Bioinform., vol. 19, 2018.
[12] H. Jiang et al., “Artificial intelligence in healthcare: Past, present and future,”
Stroke Vasc. Neurol., vol. 2, 2017.
[13] L. Floridi et al., “AI in healthcare: Ethical and social issues,” AI & Society,
vol. 35, 2020.
[14] Y. LeCun et al., “Deep learning,” Nature, vol. 521, 2015.
[15] D. Shen et al., “Deep learning in medical image analysis,” Annu. Rev.
Biomed. Eng., vol. 19, 2017.
[16] W. Yu et al., “Patient monitoring using machine learning,” IEEE J. Transl.
Eng. Health Med., vol. 8, 2020.
[17] Google Health, “AI for breast cancer detection,” Nature, vol. 577, 2020.
[18] S. Topol, “High-performance medicine: The convergence of human and AI,”
Nat. Med., vol. 25, 2019.
[19] J. Liu et al., “AI for brain tumor segmentation,” IEEE TMI, vol. 39, 2020.
[20] A. Holzinger et al., “Explainable AI in healthcare,” WIREs Data Mining, vol.
9, 2019.
[21] WHO, “Ethics and governance of AI for health,” World Health Organization
Report, 2021.
[22] Y. Zhang et al., “Federated learning for healthcare,” IEEE TNNLS, vol. 33,
2022.
[23] S. Krittanawong et al., “AI in cardiology,” J. Am. Coll. Cardiol., vol. 72,
2018.
[24] C. Lundervold and A. Lundervold, “An overview of deep learning in medical
imaging,” Z. Med. Phys., vol. 29, 2019.
[25] S. Kelly et al., “Challenges of AI in healthcare,” Front. Digital Health, vol. 3,
2021.
[26] H. Lee et al., “Deep learning for Alzheimer
