Oops, you're using an old version of your browser so some of the features on this page may not be displaying properly.

MINIMAL Requirements: Google Chrome 24+Mozilla Firefox 20+Internet Explorer 11Opera 15–18Apple Safari 7SeaMonkey 2.15-2.23

Poster Display session

138P - Do overweight, obesity and nutritional status affect survival rates in colorectal cancer treated with systemic treatment: An AI-driven retrospective study

Date

27 Jun 2024

Session

Poster Display session

Presenters

Filip Kohutek

Citation

Annals of Oncology (2024) 35 (suppl_1): S1-S74. 10.1016/annonc/annonc1477

Authors

F. Kohutek1, J. Homolova1, B. Bystricky2

Author affiliations

  • 1 Faculty Hospital TN-Fakultna nemocnica Trencin, Trencin/SK
  • 2 Faculty Hospital TN-Fakultna nemocnica Trencin, 91101 - Trencin/SK

Resources

Login to get immediate access to this content.

If you do not have an ESMO account, please create one for free.

Abstract 138P

Background

Overweight, obesity and nutritional status may affect the risk of developing colorectal cancer (CRC). The aim of this retrospective study was to assess the impact of obesity, overweight and nutritional status, as measured by the Prognostic Nutritional Index (PNI), on disease- free survival, progression- free survival and overall survival in treated early and advanced CRC and to evaluate the effectiveness of artificial intelligence (AI) in conducting a retrospective study.

Methods

238 patients with CRC were retrospectively analysed, 154 with early CRC, 84 with advanced CRC. Obesity and overweight were calculated from weight and height according to the World Health Organisation’s definition. PNI was calculated as 10× albumin (g/dL) + 0.005× total lymphocyte count. The impact of obesity, overweight, PNI at cutoff of 40 and 45 on disease-free survival (DFS), progression- free survival (PFS) and overall survival (OS) were assessed. AI, specifically ChatGPT v.4 (2024), was used for data cleansing, statistical analysis (Kaplan- Meier and Cox- regression analysis) and interpretation of results.

Results

PNI ≤ 40 significantly worsened DFS (HR 2.12, p=0.0061) and OS (HR 3.11, p=0.0011) in early CRC. The results were confirmed in Cox- regression analysis with covariates such as age, nodal status, used treatment, grade and localisation of primary tumour (right colon) (PFS HR 2.27; OS HR 2.78, p- values <0.05). Surprisingly, PNI ≤ 40 did not significantly affect PFS or OS in advanced CRC. Additionally, obesity, overweight and PNI ≤ 45 did not significantly affect survival rates in early or advanced CRC. Using targeted prompts, AI effectively assisted in data cleansing and interpretation of our results directly. AI performed statistical analysis by preparing 2 dedicated scripts using Python libraries (lifelines, matplotlib). The scripts have been uploaded to public repositories for public use.

Conclusions

Severe malnutrition significantly worsened DFS and OS in early CRC but not in advanced CRC. AI substantially aided in performing a retrospective study in a regional hospital setting.

Legal entity responsible for the study

The authors.

Funding

Has not received any funding.

Disclosure

All authors have declared no conflicts of interest.

This site uses cookies. Some of these cookies are essential, while others help us improve your experience by providing insights into how the site is being used.

For more detailed information on the cookies we use, please check our Privacy Policy.

Customise settings
  • Necessary cookies enable core functionality. The website cannot function properly without these cookies, and you can only disable them by changing your browser preferences.