Neoadjuvant Statistical Algorithm to Predict Individual Risk of Relapse in Patients with Resected Liver Metastases from Colorectal Cancer

• Published in: Biomedicines Vol. 12; no. 8; p. 1859
• Main Authors: Atienza, Ángel Vizcay, Iriarte, Olast Arrizibita, Sarrias, Oskitz Ruiz, Lizundia, Teresa Zumárraga, Beristain, Onintza Sayar, Casajús, Ana Ezponda, Gigli, Laura Álvarez, Sastre, Fernando Rotellar, García, Ignacio Matos, Rodríguez, Javier Rodríguez
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01-08-2024; MDPI
• Subjects: Accuracy; Adjuvants; Algorithms; Cancer; Cancer therapies; Care and treatment; Chemotherapy; Colorectal cancer; colorectal cancer (CRC); Colorectal carcinoma; Complications and side effects; gradient boosting machine (GBM); Liver; Liver cancer; liver metastases (LM); Mathematical models; Medical imaging; Medical prognosis; Metastases; Metastasis; Neoadjuvant therapy; Neutrophils; Nomograms; Patient outcomes; Patients; Prediction models; Prognosis; Relapse; statistical algorithms; Statistical analysis; Surgeons; Surgery; Survival; synthetic data; Variables; Spain; gradient boosting machine (GBM); colorectal cancer (CRC); statistical algorithms; liver metastases (LM); synthetic data
• ISSN: 2227-9059; 2227-9059
• DOI: 10.3390/biomedicines12081859

(1) Background: Liver metastases (LM) are the leading cause of death in colorectal cancer (CRC) patients. Despite advancements, relapse rates remain high and current prognostic nomograms lack accuracy. Our objective is to develop an interpretable neoadjuvant algorithm based on mathematical models to accurately predict individual risk, ensuring mathematical transparency and auditability. (2) Methods: We retrospectively evaluated 86 CRC patients with LM treated with neoadjuvant systemic therapy followed by complete surgical resection. A comprehensive analysis of 155 individual patient variables was performed. Logistic regression (LR) was utilized to develop the predictive model for relapse risk through significance testing and ANOVA analysis. Due to data limitations, gradient boosting machine (GBM) and synthetic data were also used. (3) Results: The model was based on data from 74 patients (12 were excluded). After a median follow-up of 58 months, 5-year relapse-free survival (RFS) rate was 33% and 5-year overall survival (OS) rate was 60.7%. Fifteen key variables were used to train the GBM model, which showed promising accuracy (0.82), sensitivity (0.59), and specificity (0.96) in predicting relapse. Similar results were obtained when external validation was performed as well. (4) Conclusions: This model offers an alternative for predicting individual relapse risk, aiding in personalized adjuvant therapy and follow-up strategies.