Dynamic Prediction of Rectal Cancer Relapse and Mortality Using a Landmarking-Based Machine Learning Model: A Multicenter Retrospective Study from the Italian Society of Surgical Oncology—Colorectal Cancer Network Collaborative Group.
Simple Summary: Rectal cancer relapse after curative surgery usually results in poorer survival and quality of life, so early identification of patients at high risk of relapse from rectal tumors is crucial. It is essential to offer risk-based recommendations that address the unique needs of survivo...
| Publicado en: | Cancers Vol. 17; no. 8; pp. 1294 - 1315 |
|---|---|
| Autores principales: | , , , , , , , , , , , , , , , , , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
MDPI
Apr2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=184758920&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 184758920 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 20726694 B74B jtl: Cancers issn: 20726694 maglogo: N pubinfo: dt: Apr2025 vid: 17 iid: 8 pid: 97109 pub: MDPI artinfo: ui: 184758920 184758920 184758920 10.3390/cancers17081294 184758920 ppf: 1294 ppct: 21 formats: tig: atl: Dynamic Prediction of Rectal Cancer Relapse and Mortality Using a Landmarking-Based Machine Learning Model: A Multicenter Retrospective Study from the Italian Society of Surgical Oncology—Colorectal Cancer Network Collaborative Group. aug: au: Reddavid, Rossella Elmore, Ugo Moro, Jacopo De Nardi, Paola Biondi, Alberto Persiani, Roberto Solaini, Leonardo Pafundi, Donato P. Cianflocca, Desiree Sasia, Diego Milone, Marco Turri, Giulia Mineccia, Michela Pecchini, Francesca Gallo, Gaetano Rega, Daniela Gili, Simona Maiello, Fabio Barberis, Andrea Costanzo, Federico affil: Division of Surgical Oncology and Digestive Surgery, Department of Oncology, San Luigi University Hospital, University of Turin, Orbassano, 10043 Turin, Italy sug: subj: Rectal Neoplasms Surgery Rectal Neoplasms Prognosis Rectal Neoplasms Mortality Neoplasm Recurrence, Local Risk Factors Mortality Risk Factors Machine Learning Algorithms Prediction Models Prediction Algorithms Random Forest Risk Assessment Treatment Outcomes Human Multicenter Studies Retrospective Design Record Review Cancer Patients Prospective Studies Predictive Validity Evaluation Comparative Studies Sensitivity and Specificity Cox Proportional Hazards Model Neoplasm Metastasis Age of Onset Male Female Middle Age Aged Descriptive Statistics Italy Medical Organizations Italy Middle Aged: 45-64 years Aged: 65+ years Male Female ab: Simple Summary: Rectal cancer relapse after curative surgery usually results in poorer survival and quality of life, so early identification of patients at high risk of relapse from rectal tumors is crucial. It is essential to offer risk-based recommendations that address the unique needs of survivors and caregivers while reducing the impact of provider shortages and managing costs for healthcare systems, survivors, and families. This large retrospective study aims to develop a machine learning algorithm using data from the RALAR study for profiling the risk and the onset of rectal cancer relapse after curative resection. Specifically, we proposed a machine learning algorithm that could assist clinicians in predicting patient prognosis by minimizing late relapse diagnosis, consequent delayed treatment, and the inefficient use of economic resources. Background: Almost 30% of patients with rectal cancer (RC) who submit to comprehensive treatment experience relapse. Surveillance plays a leading role in early detection. The landmark approach provides a more flexible and dynamic framework for survival prediction. Objective: This large retrospective study aims to develop a machine learning algorithm to profile the patient prognosis, especially the risk and the onset of RC relapse after curative resection. Methods: A cohort of 2450 RC patients were analyzed using landmark analysis. Model A applied a classical cause-specific Cox approach with a landmarking approach, while Model B implemented a landmarking-based RSF (random survival forest) competing risk algorithm. The two models were compared in terms of predictive and interpretative ability. A bootstrapped validation strategy was employed to validate the model's performance and prevent overfitting. The best-performing hyperparameters were selected systematically, ensuring the model's robustness within the landmark approach. The study assessed these factors' importance and interactions using RSF and compared the predictive accuracy to that of the classical Cox model. Results: Model B outperformed Model A (mean C-index 0.95 vs. 0.78), capturing complex interactions and providing dynamic, individualized relapse predictions. Clinical factors influencing survival outcomes were identified across time with the landmark approach allowing for more accurate and timely predictions. Conclusions: The landmark approach offers an improvement over traditional methods in survival analysis. By accommodating time-dependent variables and the evolving nature of patient data, this approach provides a precise tool for profiling RC survival, thereby supporting more informed and dynamic clinical decision-making. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|