This study presents a comprehensive feature engineering process for the early detection of prostate cancer using machine learning methodology. The dataset consisted of key clinical indicators — PSA level, patient age, prostate volume, Gleason score, and clinical stage — which were processed using ANOVA, Chi-square, PCA, RFE, LASSO, and SHAP techniques. The primary objective was to identify the most influential diagnostic features that improve model performance and ensure interpretability.
| Mualliflar | Madolimov, F., Мадолимов, Ф., Madolimov, F. |
|---|---|
| Jurnal | Ilim ha’m ja’miyet |
| Nashr sanasi | 2026-02-16 |
| Son | 1-1 |
| Betlar | 24-26 |
| Til | uz_Latn |
prostata saratoni, mashinaviy o‘rganish, feature engineering, PCA, SHAP, diagnostika, рак предстательной железы, машинное обучение, инженерия признаков, PCA, SHAP, диагностика, prostate cancer, machine learning, feature engineering, PCA, SHAP, diagnostics
In this work, a boundary-value problem for systems of Volterra-type integro-differential equations with nonlinear boundary conditions is investigated using the numerical-analytic method of successive approximations.
In this work, methods for computing volumes of cone manifolds for knots in hyperbolic geometry are presented, along with differences between computations performed in the computer programs SnapPy and Wolfram Mathematica…
In this work, the projection-iterative method is applied to finding periodic solutions of Fredholm-type integro-differential equations.
This article studies the impact of the taxpayer's risk status and tax evasion on the final distribution based on the Markov process. A number of experiments were conducted to model networks and the process of…
This work presents the results of studying radiation-induced defect formation in KCl crystals exposed to X-ray and gamma irradiation. It is shown that F-centers begin to form from the early stages of irradiation and…
This article examines some applications of comparisons. The divisibility of some numbers is proven and examples are given.
This article focuses on the computation of the GNDVI and CVI vegetation indices, which exhibit high sensitivity to vegetation condition, particularly to chlorophyll content. It is also noted that the module architecture…
The paper presents modeling and experimental study of thermal processes in silicon-based Ni (5 at. % Pt)/Si heterostructures under rapid photon annealing. Three heat transfer regimes are analyzed: adiabatic, heat-flow…
From the system of non-stationary equations of two-velocity hydrodynamics, a system of equations of the Burgers and Hopf type was obtained. It should be taken into account that energy dissipation occurs due to the…
A novel bionic optimization algorithm inspired by mountain goats’ natural strategies of risk assessment and energy management is presented. The model employs a dedicated risk-avoidance coefficient and adaptive energy…