Vestnik Urologii (Mar 2024)

Artificial intelligence in molecular and genomic prostate cancer diagnostics

  • A. O. Morozov,
  • A. K. Bazarkin,
  • S. V. Vovdenko,
  • M. S. Taratkin,
  • M. S. Balashova,
  • D. V. Enikeev

DOI
https://doi.org/10.21886/2308-6424-2024-12-1-117-130
Journal volume & issue
Vol. 12, no. 1
pp. 117 – 130

Abstract

Read online

Introduction. Many molecular genetic analyses have been proposed to predict the course of prostate cancer (PCa). They have the potential to develop artificial intelligence (AI) algorithms by processing large amounts of data and define connections between them.Objective. To evaluate the possibilities of using artificial intelligence in early diagnosis and prognosis of prostate cancer.Materials & methods. We conducted a systematic review of the literature on the Medline citation database. We have selected papers that provide data on the use of AI in vitro, in vivo and in silico systems to determine biological and genetic markers and/or their relationship to clinical data of PCa-patients from 2020 to 2023. The quantitative synthesis includes 16 articles.Results. AI can identify metabolic and genetic «signature» of PCa, the key elements of signal pathways, thus fulfilling complex tasks in the field of bioinformatics. AI analyses various biomaterials: prostate tissue, blood, and urine. When evaluating prostate tissue for aberrations, AI can help a pathologist. For example, AI can predict the histological status of genes, eliminating the need for IHC or tissue sequencing, significantly reducing the economic cost of predicting the severity of the disease. In most cases, prostate tissue sequencing provides information to the attending physician, allowing the start of optimal treatment, considering the molecular or genetic «signature» of PCa. AI can be used as an alternative to existing population screening tools and a predictive castration-resistant PCa. The use of AI capabilities is more appropriate for blood and urine analysis, procedures that do not require additional economic costs for biomaterial sampling. In theory, this may be more affordable for the patient and the medical institution. It is worth noting that a few studies were conducted in silico (based on the analysis of molecular genetic databases without validation on cell lines or on real patients) and are useful as background information. However, the results can serve as a robust basis for further research in molecular diagnostics and genomics.Conclusion. It is possible to use AI in the search for key metabolites and genes of the elements of signalling pathways, as well as the determination of metastasis potential, because molecular or genetic «signature» of PCa allows the physician to start optimal treatment.

Keywords