Diagnosis Penyakit Menggunakan Artificial Intelligence (AI):Konsep, Bukti Ilmiah, dan Implikasi Klinis: Disease Diagnosis Using Artificial Intelligence (AI): Concepts, Scientific Evidence, and Clinical Implications

Fajar Presetya; Edward

doi:10.30872/jsk.v6i1.976

Authors

Fajar Presetya Faculty of Pharmacy, University of Mulawarman, Samarinda, Indonesia Author https://orcid.org/0000-0002-1020-0423
Edward Atma Jaya Teaching & Research Hospital, Jakarta, Indonesia Author

DOI:

https://doi.org/10.30872/jsk.v6i1.976

Keywords:

artificial intelligence; disease diagnosis; machine learning; deep learning; clinical decision support; medical imaging; electronic medical records

Abstract

Kecerdasan buatan (artificial intelligence/AI) telah berkembang menjadi teknologi transformatif dalam bidang diagnostik medis, terutama melalui kemampuannya menganalisis data klinis yang kompleks secara otomatis untuk mendukung deteksi penyakit, klasifikasi diagnosis, dan stratifikasi risiko. Kemajuan pesat dalam machine learning (ML) dan deep learning (DL) telah mendorong terobosan signifikan pada berbagai modalitas diagnostik, termasuk pencitraan medis, biosinyal, patologi, genomik, serta electronic health records (EHR). Artikel tinjauan ini mengkaji secara kritis peran AI dalam mendiagnosis masalah kesehatan dan penyakit, dengan fokus pada landasan metodologis, aplikasi klinis, evaluasi kinerja, serta tantangan translasi ke praktik klinik. Berbagai bukti dari studi-studi penting menunjukkan bahwa sistem AI mampu mencapai tingkat akurasi diagnostik yang sebanding atau bahkan melampaui tenaga kesehatan profesional pada tugas-tugas spesifik dan terdefinisi dengan baik, seperti skrining retinopati diabetik, deteksi kanker payudara, klasifikasi aritmia, dan skrining kanker paru. Namun demikian, meskipun hasil awal tampak menjanjikan, adopsi klinis secara luas masih menghadapi berbagai hambatan, antara lain bias dataset, keterbatasan validasi eksternal, kurangnya uji klinis prospektif, isu keterjelasan atau explainability model, serta ketidakpastian regulasi. Artikel ini mensintesis bukti ilmiah terkini, menyoroti standar metodologis dalam evaluasi AI diagnostik, serta membahas implikasi etis, hukum, dan klinis dari penerapan teknologi ini. AI sebaiknya dipahami bukan sebagai pengganti klinisi, melainkan sebagai alat pendukung keputusan yang dapat meningkatkan akurasi, konsistensi, dan efisiensi diagnosis apabila diintegrasikan secara bertanggung jawab ke dalam sistem pelayanan kesehatan.

References

[1] H. Singh, T. D. Giardina, E. N. Meyer, M. Forjuoh, R. D. Reis, and E. J. Thomas, “Types and origins of diagnostic errors in primary care settings,” JAMA Internal Medicine, vol. 173, no. 6, pp. 418–425, 2013.

[2] E. J. Topol, “High-performance medicine: the convergence of human and artificial intelligence,” Nature Medicine, vol. 25, no. 1, pp. 44–56, 2019.

[3] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, 2015.

[4] G. Campanella et al., “Clinical-grade computational pathology using weakly supervised deep learning on whole-slide images,” Nature Medicine, vol. 25, no. 8, pp. 1301–1309, 2019.

[5] A. Rajkomar et al., “Scalable and accurate deep learning for electronic health records,” npj Digital Medicine, vol. 1, no. 18, 2018.

[6] G. Litjens et al., “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, 2017.

[7] M. Nagendran et al., “Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims,” BMJ, vol. 368, m689, 2020.

[8] R. Aggarwal et al., “Diagnostic accuracy of deep learning in medical imaging: A systematic review and meta-analysis,” npj Digital Medicine, vol. 4, no. 65, 2021.

[9] M. D. Abràmoff et al., “Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices,” npj Digital Medicine, vol. 1, no. 39, 2018.

[10] V. Gulshan et al., “Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs,” JAMA, vol. 316, no. 22, pp. 2402–2410, 2016.

[11] D. Ardila et al., “End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography,” Nature Medicine, vol. 25, no. 6, pp. 954–961, 2019.

[12] D. A. Bluemke et al., “Assessing radiology research on artificial intelligence: a brief guide for authors, reviewers, and readers,” Radiology, vol. 294, no. 3, pp. 487–489, 2020.

[13] S. M. McKinney et al., “International evaluation of an AI system for breast cancer screening,” Nature, vol. 577, pp. 89–94, 2020.

[14] A. Y. Hannun et al., “Cardiologist-level arrhythmia detection with convolutional neural networks,” Nature Medicine, vol. 25, pp. 65–69, 2019.

[15] Z. Obermeyer and E. J. Emanuel, “Predicting the future — Big data, machine learning, and clinical medicine,” New England Journal of Medicine, vol. 375, no. 13, pp. 1216–1219, 2016.

[16] Z. Obermeyer, B. Powers, C. Vogeli, and S. Mullainathan, “Dissecting racial bias in an algorithm used to manage the health of populations,” Science, vol. 366, no. 6464, pp. 447–453, 2019.

[17] T. J. Hwang, A. S. Kesselheim, and K. N. Vokinger, “Lifecycle regulation of artificial intelligence–based medical devices,” JAMA, vol. 322, no. 23, pp. 2285–2286, 2019.

[18] X. Liu et al., “CONSORT-AI: Extension of the CONSORT statement for artificial intelligence trials,” BMJ, vol. 370, m3164, 2020.

[19] S. Cruz Rivera et al., “SPIRIT-AI extension for clinical trial protocols,” Nature Medicine, vol. 26, pp. 1351–1363, 2020.

[20] G. S. Collins, J. B. Reitsma, D. G. Altman, and K. G. M. Moons, “TRIPOD: Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis,” Annals of Internal Medicine, vol. 162, no. 1, pp. 55–63, 2015.

[21] G. S. Collins et al., “TRIPOD+AI: A reporting guideline for clinical prediction models developed using artificial intelligence,” BMJ, vol. 385, e078378, 2024.

[22] E. W. Steyerberg et al., “Assessing the performance of prediction models: calibration,” Statistics in Medicine, vol. 29, no. 27, pp. 2869–2884, 2010.

[23] R. F. Wolff et al., “PROBAST: A tool to assess the risk of bias and applicability of prediction model studies,” Annals of Internal Medicine, vol. 170, no. 1, pp. 51–58, 2019.

[24] C. Patrício et al., “Explainable deep learning models in medical imaging: A survey,” ACM Computing Surveys, 2023.

[25] B. N. Green, C. D. Johnson, and A. Adams, “Writing narrative literature reviews for peer-reviewed journals: secrets of the trade,” Journal of Chiropractic Medicine, vol. 5, no. 3, pp. 101–117, 2006.