KEY TAKEAWAYS
- The study aimed to investigate the impact of surgery on postoperative survival in patients with advanced PC and develop a predictive model for prognosis.
- Researchers noticed that surgery for advanced PC patients improves survival, backed by an accurate prognostic model, aiding clinical decisions.
The effect of surgery on advanced prostate cancer (PC) is unclear, and a predictive model for postoperative survival is lacking.
Shanshan Li and the team aimed to investigate the impact of surgery on postoperative survival in patients with advanced PC and develop a predictive model for prognosis.
Researchers performed an inclusive analysis using the National Cancer Institute’s Surveillance, Epidemiology, and End Results (SEER) database to collect clinical features of advanced PC patients. According to clinical experience, potential predictive variables such as age, race, grade, pathology, T, N, M, stage, size, regional nodes positive, regional nodes examined, surgery, radiotherapy, chemotherapy, history of malignancy, clinical Gleason score, pathological Gleason score, and prostate-specific antigen (PSA) were considered.
All samples were divided into train (70%) and test (30%) cohorts for model training and validation, respectively, via random sampling. Subsequently, a neural network was developed to predict overall survival in advanced PC patients, with the model’s performance assessed using the Area under the Receiver Operating Characteristic Curve (AUC).
About 6380 patients diagnosed with advanced (stage III-IV) PC and undergoing surgery were included. The model utilizing all collected clinical features as predictors, based on a neural network algorithm, demonstrated superior performance, with an AUC of 0.7058 (95% CIs, 0.7021-0.7068) in the training cohort and 0.6925 (95% CIs, 0.6906-0.6956) in the test cohort. Subsequently, the model was packaged into a Windows 64-bit software for practical application.
The study concluded that a clinical features-based prognostic model effectively forecasts overall survival in patients with advanced PC undergoing surgery. This model’s accuracy suggests its potential to provide valuable references for clinical decision-making in such cases.
Source: https://pubmed.ncbi.nlm.nih.gov/38577575/
Li S, Cai S, Huang J, et al. (2024). “Develop prediction model to help forecast advanced prostate cancer patients’ prognosis after surgery using neural network.” Front Endocrinol (Lausanne). 2024 Mar 21;15:1293953. doi: 10.3389/fendo.2024.1293953. PMID: 38577575; PMCID: PMC10991752.
