★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★Open research. Global perspectives.
editor@theamericanjournals.comPublisher Home ↗
Articles OPEN ACCESS

ARTIFICIAL INTELLIGENCE IN CLINICAL LABORATORY MEDICINE: APPLICATIONS IN BIOMARKER INTERPRE-TATION, DIAGNOSTIC PREDICTION, AND CANCER SCREENING

Shakhnoza Khamidova
Independent Researcher
tajiir 2024
VOL. 6 / NO. 11 NOVEMBER
FULL TEXT PP. 252-280
DOWNLOAD PDF

View all articles in this issue ↗

VOLUME 6
ISSUE 11
YEAR 2024
PAGES 252-280
RESEARCH OVERVIEW

Abstract

The increasing complexity of clinical laboratory data has led to the growing research and investigation of the use of artificial intelligence (AI) to aid in the interpretation of such data and to support diagnostic decision-making. With increasing availability of biochemical, hematological, molecular, proteomic, and image-based laboratory information, machine learning (ML) and deep learning (DL) approaches have provided opportunities to uncover clinically relevant patterns that may not be easily detected by traditional methods. In this review, the uses of AI in clinical laboratory medicine are discussed, focusing on the interpretation of biomarkers, the prediction of diagnosis, optimization of laboratory workflows, and cancer screening. AI-based methods can help to combine multiple biomarkers to capture multivariable signatures, aid in disease classification and risk prediction, and enable the analysis of high-dimensional molecular and proteomic datasets. AI has been explored in cancer screening for the interpretation of circulating biomarkers, liquid biopsies, and digital pathology to aid in early cancer detection and risk assessment. In addition to its role in the preanalytical stage of laboratory testing, AI can also help with the analytical phase and the postanalytical stage by performing quality control, detecting anomalies, interpreting tests automatically, and providing clinical decision support. Despite all these opportunities, implementation in the clinic is limited by data quality, missing information, varying measurements, class imbalance, selection bias, limited external validation, model interpretability, and differences between laboratories. In addition to these considerations, ethical issues related to patient privacy, data security, algorithmic biases, and accountability play a role in responsible AI implementation. Standardization and representativeness of the datasets, multicenter and prospective validation, proper calibration, assessment of usefulness in clinical practice, incorporation in laboratory information and health records, and ongoing monitoring following implementation are necessary for successful translation into routine use. In conclusion, AI shows great promise to not only revolutionize the way clinical laboratory medicine is practiced but also to serve as an integral element in a multivariable and increasingly individualized diagnostic process, with human oversight as a crucial part of the clinical decision-making process.

RESEARCH TOPICS

Keywords

Artificial intelligence machine learning deep learning clinical laboratory medicine

Downloads

Download data is not yet available.
SOURCES & SCHOLARSHIP

References

  1. R. A. McPherson and M. R. Pincus, Henry's Clin-ical Diagnosis and Management by Laborato-ry Methods E-Book. Elsevier Health Sciences, 2021.
  2. J. Luo et al., “Big data application in biomedical research and health care: A literature review,” Biomedical Informatics Insights, vol. 8, p. BII-S31559, 2016.
  3. K. Felekkis and C. Papaneophytou, “Challenges in using circulating micro-RNAs as biomarkers for cardiovascular diseases,” International Journal of Molecular Sciences, vol. 21, no. 2, p. 561, 2020.
  4. Z. Ahmed et al., “Artificial intelligence with multi-functional machine learning platform development for better healthcare and preci-sion medicine,” Database, vol. 2020, p. baaa010, 2020.
  5. M. Saberi-Karimian et al., “Potential value and impact of data mining and machine learning in clinical diagnostics,” Critical Reviews in Clini-cal Laboratory Sciences, vol. 58, no. 4, pp. 275–296, 2021.
  6. S. R. Master et al., “Machine learning in labora-tory medicine: Recommendations of the IFCC working group,” Clinical Chemistry, vol. 69, no. 7, pp. 690–698, 2023.
  7. P. Choudhury, R. T. Allen, and M. G. Endres, “Machine learning for pattern discovery in management research,” Strategic Manage-ment Journal, vol. 42, no. 1, pp. 30–57, 2021.
  8. A. N. Bhatt et al., “Cancer biomarkers—Current perspectives,” Indian Journal of Medical Re-search, vol. 132, no. 2, pp. 129–149, 2010.
  9. S. A. Alowais et al., “Revolutionizing healthcare: The role of artificial intelligence in clinical practice,” BMC Medical Education, vol. 23, no. 1, p. 689, 2023.
  10. M. A. Shipp et al., “Diffuse large B-cell lym-phoma outcome prediction by gene-expression profiling and supervised machine learning,” Nature Medicine, vol. 8, no. 1, pp. 68–74, 2002.
  11. M. Li et al., “Medical image analysis using deep learning algorithms,” Frontiers in Public Health, vol. 11, p. 1273253, 2023.
  12. Y. Li et al., “Proteogenomic data and resources for pan-cancer analysis,” Cancer Cell, vol. 41, no. 8, pp. 1397–1406, 2023.
  13. M. Mann et al., “Artificial intelligence for pro-teomics and biomarker discovery,” Cell Sys-tems, vol. 12, no. 8, pp. 759–770, 2021.
  14. J. Xia et al., “Translational biomarker discov-ery in clinical metabolomics: An introductory tutorial,” Metabolomics, vol. 9, no. 2, pp. 280–299, 2013.
  15. A. E. Obstfeld, “Hematology and machine learning,” The Journal of Applied Laboratory Medicine, vol. 8, no. 1, pp. 129–144, 2023.
  16. F. M. Altelaar, J. Muñoz, and A. J. R. Heck, “Next-generation proteomics: Towards an integra-tive view of proteome dynamics,” Nature Re-views Genetics, vol. 14, no. 1, pp. 35–48, 2013.
  17. T. A. Lasko, J. C. Denny, and M. A. Levy, “Com-putational phenotype discovery using unsu-pervised feature learning over noisy, sparse, and irregular clinical data,” PLOS ONE, vol. 8, no. 6, p. e66341, 2013.
  18. R. Qureshi et al., “Artificial intelligence and bi-osensors in healthcare and its clinical rele-vance: A review,” IEEE Access, vol. 11, pp. 61600–61620, 2023.
  19. H. Liang et al., “Evaluation and accurate diag-noses of pediatric diseases using artificial intel-ligence,” Nature Medicine, vol. 25, no. 3, pp. 433–438, 2019.
  20. Comito, D. Falcone, and A. Forestiero, “AI-driven clinical decision support: Enhancing disease diagnosis exploiting patients similari-ty,” IEEE Access, vol. 10, pp. 6878–6888, 2022.
  21. S. Syed-Abdul et al., “Artificial intelligence based models for screening of hematologic malignancies using cell population data,” Sci-entific Reports, vol. 10, no. 1, p. 4583, 2020.
  22. A. Agibetov et al., “Machine learning enables prediction of cardiac amyloidosis by routine laboratory parameters: A proof-of-concept study,” Journal of Clinical Medicine, vol. 9, no. 5, p. 1334, 2020.
  23. M. Cui and D. Y. Zhang, “Artificial intelligence and computational pathology,” Laboratory In-vestigation, vol. 101, no. 4, pp. 412–422, 2021.
  24. K. H. Zou, A. J. O’Malley, and L. Mauri, “Receiv-er-operating characteristic analysis for evalu-ating diagnostic tests and predictive models,” Circulation, vol. 115, no. 5, pp. 654–657, 2007.
  25. Bhinder et al., “Artificial intelligence in cancer research and precision medicine,” Cancer Dis-covery, vol. 11, no. 4, pp. 900–915, 2021.
  26. K. Lång et al., “Artificial intelligence-supported screen reading versus standard double reading in the Mammography Screening with Artificial Intelligence trial (MASAI): A clinical safety analysis of a randomised, controlled, non-inferiority, single-blinded, screening accuracy study,” The Lancet Oncology, vol. 24, no. 8, pp. 936–944, 2023.
  27. Crosby et al., “Early detection of cancer,” Sci-ence, vol. 375, no. 6586, p. eaay9040, 2022.
  28. A. Egli, “ChatGPT, GPT-4, and other large lan-guage models: The next revolution for clinical microbiology?,” Clinical Infectious Diseases, vol. 77, no. 9, pp. 1322–1328, 2023.
  29. A. H. de Hond et al., “Guidelines and quality cri-teria for artificial intelligence-based prediction models in healthcare: A scoping review,” NPJ Digital Medicine, vol. 5, no. 1, p. 2, 2022.
  30. P. Linardatos, V. Papastefanopoulos, and S. Ko-tsiantis, “Explainable AI: A review of machine learning interpretability methods,” Entropy, vol. 23, no. 1, p. 18, 2021.
  31. Jiménez et al., “Simplification of the pulmo-nary embolism severity index for prognostica-tion in patients with acute symptomatic pul-monary embolism,” Archives of Internal Medi-cine, vol. 170, no. 15, pp. 1383–1389, 2010.
  32. A. Fiske, P. Henningsen, and A. Buyx, “Your ro-bot therapist will see you now: Ethical impli-cations of embodied artificial intelligence in psychiatry, psychology, and psychotherapy,” Journal of Medical Internet Research, vol. 21, no. 5, p. e13216, 2019.
CONTINUE EXPLORING

Most read articles by the same author(s)

Explore other published research by the authors of this article.