Development and interpretability of a machine learning-derived model for the identification of latent prostate cancer in patients initially diagnosed with benign prostatic hyperplasia: a retrospective cohort study

Sheng Liang, Yuansi Lao, Peiling Ma, Changhuan Shang, Rukun Li, Zengfu Li, Yongtao Le, Wenhui Cao, Chunling Chen, Ke Liu, Liqing Li · 2026

Read Development and interpretability of a machine learning-derived model for the identification of latent prostate cancer in patients initially diagnosed with benign prostatic hyperplasia: a retrospective cohort study by Sheng Liang, Yuansi Lao, Peiling Ma, Changhuan Shang, Rukun Li, Zengfu Li, Yongtao Le, Wenhui Cao, Chunling Chen, Ke Liu, Liqing Li (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13474970.txt.

Description

Liang and colleagues built an interpretable machine learning model in 2026 to spot hidden prostate cancer in men first diagnosed with benign prostate enlargement. Blood PSA testing alone cannot cleanly separate the two conditions, so cancers get missed at the first visit. The team used records from 1,071 patients, defining hidden cancer as cancer found at least six months after the benign diagnosis, and trained six algorithms on routine blood measures.

Feature selection narrowed the signal to four blood markers: total PSA, lactate dehydrogenase, red blood cell count, and creatine kinase-MB, an enzyme usually tied to heart muscle. The neural network and logistic regression models scored best on held-out patients, reaching accuracy areas of 0.949 and 0.946 on the standard curve measure used. Explanation tools showed how each marker pushed a prediction up or down, and the authors stress the model is for research use, not clinic decisions.

Catalog record

CREATORSheng Liang, Yuansi Lao, Peiling Ma, Changhuan Shang, Rukun Li, Zengfu Li, Yongtao Le, Wenhui Cao, Chunling Chen, Ke Liu, Liqing Li
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE45 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13474970

Browse the full library · About the Tower of Babel