Page 297 - PowerPoint Presentation

1 International Congress of Artificial Intelligence
st
in Medical Sciences Posters

Developing Artificial Intelligence for Precision Diagnosis of Prostate
Cancer Using Tumor Biomarker Expression Patterns: A Systematic

Review

Iman Karimi-Sani , Kazem Jamali , Najmeh Zarei , Maryam Fadaei-Dashti , Amir Atapour 1*
4
1
2
3
1 Department of Medical Biotechnology, School of Advanced Medical Sciences and Technologies, Shiraz University of Medical Sciences, Shiraz, Iran.
2 Emergency Medicine Research Center, Shiraz University of Medical Sciences, Shiraz, Iran.
Trauma Research Center, Shahid Rajaee (Emtiaz) Trauma Hospital, Shiraz University of Medical Sciences, Shiraz, Iran.
3 Department of Emergency Medicine, Faculty of Medicine, Shiraz University of Medical Sciences, Shiraz, Iran.
4 Department of Emergency Medicine, School of Medicine Alborz University of Medical Sciences, Karaj, Iran.
*Corresponding author’s email: amir.atapoor58@yahoo.com

Background and aims: The development of artificial intelligence (AI) is essential for deploy-
ing community-wide, prostate cancer diagnosis. Prediction tools widely used and well-validated
depend on standard, readily available clinical and pathological parameters, but do not include
biomarkers, which can provide valuable insights into prediction or treatment options. Combining
traditional prediction methods with systems pathology may be provided a more personalized risk
assessment of clinically relevant outcomes of prostate cancer. Across a range of disease prev-
alence, AI systems can deliver the main benefits of biopsy avoidance while maintaining high
specificities.

In this review, we examined current developments in precancerous lesion detection and diagnosis
for prostate cancer.

Methods: A review was carried out by two reviewers independently and manually searching Eng-
lish databases (PubMed, Scopus, and Web of Science) for data till March 2023. After the quality
screening, 34 articles was made for further analysis. Database were searched using the terms ‘ar-
tificial intelligence’, ‘prostate cancer’, ‘precision diagnosis’, and ‘precision diagnosis’. Inclusion
criteria for paper selection were: 1) Paper must be peer reviewed. 2) Journals on which papers
published must be either PubMed, Scopus, or Web of Science indexed. 3) The paper should use
only AI techniques. Exclusion criteria for paper selection were: 1) Duplicate studies in different
databases. 2) Study which is less cited by other peer reviewed papers. 3) MSc and PhD papers.

Results: In the literature, a wide number of machine learning techniques have been applied to
biopsy material, including linear models, support vector machines, decision trees, and deep learn-
ing models for prostate cancer diagnosis. In the following comprehensive review article, we focus
on diagnostic (PHI®, 4K score, SelectMDx®, ConfirmMDx®, PCA3, MiPS, ExoDX®, mpM-
RI) biomarkers that are in widespread clinical use and are supported by evidence. In addition,
we discussed new biomarker-driven diagnosis for advanced prostate cancer that have been ob-
tained using artificial intelligence such as TELO2, ZMYND19, miR-143, miR-378a, cg00687383
(MED4), and cg02318866 (JMJD6; METTL23).

Conclusion: Such a variety of cancer molecular and clinical data calls for advancing the interop-
erability among AI approaches, with particular emphasis on the synergy between discriminative
and generative models that we discuss in this work with several examples of techniques and ap-
plications. To improve the predictive power of potential diagnostic biomarkers, experiments must
be carefully designed.

Keywords: prostate cancer, artificial intelligence, personalized medicine, precision medicine, p4
medicine, cancer treatment.

275