Abstract

Artificial Intelligence (AI) is revolutionizing healthcare by enhancing diagnostic precision, optimizing treatment plans, and streamlining operational workflows. This survey paper explores the current landscape of AI applications in healthcare, focusing on technologies such as machine learning, deep learning, natural language processing, and computer vision. We review their roles in disease detection, drug discovery, patient monitoring, and data security, drawing insights from recent studies. While AI offers significant benefits, including improved patient outcomes and cost efficiency, challenges such as data privacy, ethical concerns, and algorithmic bias persist. This paper synthesizes findings from diverse research efforts, identifies trends, and proposes directions for future investigation to ensure responsible AI integration in healthcare.

References

  1. 1. Aswathy et al. “Using ResNet-50 and DenseNet-201 for COVID-19 Severity Detection with High Accuracy.” Journal of Infection and Public Health, vol. 14, no. 10, Oct. 2021, pp. 1435–1445, https://doi.org/10.1016/j.jiph.2021.07.015.
  2. 2. Andres et al. “Generalizable Machine-Learning Models for Early Detection and Containment of Ebola Outbreaks.” EClinicalMedicine, vol. 11, May-june. 2019, pp. 54–64, https://doi.org/10.1016/j.eclinm.2019.06.003.
  3. 3. Md Alamin et al. “EfficientNetB4 for COVID-19 Lung Diagnosis: Achieving 100% Accuracy in Detection.” Computers in Biology and Medicine, vol. 168, January. 2024, p. 107789, https://doi.org/10.1016/j.compbiomed.2023.107789.
  4. 4. Zongyao et al. “Deep Learning-Based Cough Monitoring with Hourly Histograms.” IEEE Access, vol. 12, Aug. 2024, pp. 118816-118829, https://doi.org/10.1109/ACCESS.2024.3449370.
  5. 5. Julian et al. “Random Forest Framework for Predicting Drug Effects on SARS-CoV-2.” CPT: Pharmacometrics & Systems Pharmacology, vol. 13, no. 3, Nov. 2023, pp. 257-269, https://doi.org/10.1002/psp4.13076.
  6. 6. Ahmed et al. “Machine-Learning Framework for SARS-CoV-2 Drug Effect Prediction Using Random Forests.” BMC Bioinformatics, vol. 25, no. 1, March. 2024, p. 56, https://doi.org/10.1186/s12859-024-05648-2.
  7. 7. Syed Nisar et al. “Ensemble Model Evaluation for Zika Virus Vaccine Development.” Scientific Reports, vol. 12, May 2022, p. 11731, https://doi.org/10.1038/s41598-022-11731-6.
  8. 8. Pranav et al. “CheXNet: Achieving 95% Accuracy in Pneumonia Detection Using Deep Learning.” arXiv Preprint, arXiv: 1711.05225, 14 Nov. 2017, https://doi.org/10.48550/arXiv.1711.05225.
  9. 9. Sarthak et al. “Improved Encryption Methods for Data Privacy Using Federated Learning.” Patterns, vol. 5, no. 6, July 2024, p. 100974, https://doi.org/10.1016/j.patter.2024.100974.
  10. 10. Ziad et al. “AI Bias in Diagnosis: Addressing Disparities with Explainable AI.” Science, vol. 366, no. 6464, 25 Oct. 2019, pp. 447–453, https://doi.org/10.1126/science.aax2342.
  11. 11. Yinlong et al. “Cybersecurity Threats in Healthcare: 92% Malware Detection Accuracy.” IEEE Transactions on Consumer Electronics, vol. 70, no. 4, Aug. 2023, pp. 2414 - 2422, https://doi.org/10.1109/TCE.2023.3309852.
  12. 12. Laila et al. “Med-BERT: 90% Accuracy in Treatment Recommendations Using NLP.” NPJ Digital Medicine, vol. 4, no. 1, May 2021, p. 82, https://doi.org/10.1038/s41746-021-00455-y.
  13. 13. Haval et al. “Radiology Image Misinterpretation: 96% Tumor Detection Accuracy with CNN.” Journal of Thoracic Oncology, vol. 14, no. 10, Sept. 2019, pp. 1513-1527, https://doi.org/10.1016/j.jtho.2019.06.011.
  14. 14. Omar et al. “EHR Data Misuse Prevention Using Blockchain AI.” arXiv Preprint, arXiv: 2206.02760, 6 June 2022, https://doi.org/10.48550/arXiv.2206.02760.
  15. 15. [15] Abhyuday et al. “Medication Error Detection with 94% Precision Using NLP and Machine Learning.” Drug Safety, vol. 42, no. 5, January 2019, pp. 99–11, https://doi.org/10.1007/s40264-018-0762-z.
  16. 16. Daniel et al. “AI-Assisted Surgery Risks: 89% Success Rate with Reinforcement Learning.” Annals of Surgery, vol. 269, no. 4, July. 2018, pp. 70–2018, https://doi.org/10.1097/SLA.0000000000002693.
  17. 17. Kaiwen et al. “Predicting Disease Outbreaks: Early COVID-19 Trend Detection.” Environmental Science and Pollution Research, vol. 30, no. 15, March. 2023, pp. 63323–63334, https://doi.org/10.1007/s11356-023-26571-8.
  18. 18. Adrain et al. “Mental Health Chatbot Limitations: 85% Depression Detection Accuracy.” arXiv Preprint, arXiv: 1712.03538, 10 Dec. 2017, https://doi.org/10.48550/arXiv.1712.03538.
  19. 19. Alex Zhavoronokov. “AI-Driven Drug Discovery: 80% Success in Identifying Candidates.” DrugBank and PubChem Analysis, ORCID: 0000-0001-7067-8966, 2023, http://orcid.org/0000-0001-7067-8966.
  20. 20. Richard et al.. “Insurance Fraud Detection with 97% Accuracy Using SVM and Random Forest.” 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), Dec. 2017, pp. 123–129, https://doi.org/10.1109/ICMLA.2017.00-48.
  21. 21. Peng et al. “Patient Monitoring Errors: 93% Anomaly Detection with IoT and AI.” Future Internet, vol. 15, no. 9, Sept. 2023, p. 286, https://doi.org/10.3390/fi15090286.
  22. 22. Christiane Floyd. “AI Chatbot Misdiagnosis: 86% Accuracy in Basic Consultations.” Weizenbaum Journal of the Digital Society, vol. 3, no. 3, 2023, https://doi.org/10.34669/WI.WJDS/3.3.3.