What is the clinical evidence from this study?

Study design: Observational. Population: Colorectal cancer (n=178). Intervention: Pre-treatment clinical factors. Primary outcome: Prediction of early adverse events leading to treatment delay or discontinuation within four courses (AUC 0.832, 95% CI 0.771-0.893).

January 1, 2024Open Access

Study on prediction of early adverse events by CapeOX therapy in patients with colorectal cancer

YKYuki KumihashiTokushima Red Cross Hospital YKYohei KasaiTokushima Red Cross Hospital TATakuya AkagawaTokushima Red Cross Hospital

Key Result

A logistic regression model incorporating pre-treatment clinical factors predicted early adverse events of CapeOX therapy in colorectal cancer patients with an AUC of 0.832.

Study Design

Type

Observational (n=178)

Multicenter

Structured PICO

Can pre-treatment medical records be used to predict early adverse events caused by CapeOX therapy in patients with colorectal cancer?

Population

178 patients aged 20 years or older with colorectal cancer receiving first-line CapeOX therapy, evaluated retrospectively to predict early adverse events within the first four courses.

Exposure

Prediction of early adverse events using machine learning models (logistic regression, support vector machine, random forest) based on pre-treatment medical records

Outcome

Prediction accuracy of early adverse events (defined as withdrawal or postponement of four or fewer courses)safety

A logistic regression model based on pre-treatment medical records may be a useful tool for predicting early adverse events in colorectal cancer patients receiving CapeOX therapy.

Main Result

Effect estimate: AUC 0.832 (95% CI 0.771-0.893)

Limitations

Retrospective study conducted in clinical practice
Patients who did not undergo CT before treatment initiation were excluded
Starting dose varied from patient to patient
Patient information was reviewed only until the end of the four courses, and subsequent adverse events and treatment efficacy were not evaluated

Abstract

CapeOX is a regimen used as postoperative adjuvant chemotherapy for the treatment of advanced recurrent colorectal cancer. If early adverse events occur, treatment may not progress as planned and further dose reduction may be necessary. In this study, we investigated whether pre-treatment medical records could be used to predict adverse events in order to prevent adverse events caused by CapeOX treatment. The 178 patients were classified into two groups (97 in the adverse event positive group and 81 in the adverse event-negative group) based on withdrawal or postponement of four or fewer courses. In univariate analysis, age, height, weight, body surface area (BSA), creatinine clearance, muscle mass, and lean body mass were associated with early adverse events (P<0.05). The area under the receiver operating characteristic curve obtained by Stepwise logistic regression analysis using the Akaike information criterion method was 0.832. For nested k-fold cross validation, the accuracy rates of the support vector machine, random forest, and logistic regression algorithms were 0.71, 0.70, and 0.75, respectively. The results of the present study suggest that a logistic regression prediction model may be useful in predicting early adverse events caused by CapeOX therapy in patients with colorectal cancer. J. Med. Invest. 71 : 141-147, February, 2024.

Ask AI

Helpful

Bookmark

View Full Paper