Article Text

Download PDFPDF
304 Exploring mean platelet volume as a survival indicator in ovarian clear cell carcinoma: a retrospective analysis and random forest model assessment
  1. Nobuhisa Yoshikawa,
  2. Mei Kubokawa,
  3. Tetsuya Matsukawa and
  4. Hiroaki Kajiyama
  1. Nagoya University Graduate School of Medicine, Nagoya, Japan


Introduction/Background The study’s primary aim was to assess the prognostic significance of mean platelet volume (MPV) in ovarian clear cell carcinoma (OCCC) patients. Additionally, it sought to examine the efficacy of a random forest model that includes MPV and other critical clinicopathological factors in predicting patient outcomes.

Methodology We retrospectively reviewed data from 204 OCCC patients treated from January 2004 to December 2019. The study involved collecting clinicopathological details and preoperative lab data. Survival outcomes were analyzed using the Kaplan-Meier method and Cox proportional hazards models. The receiver operating characteristic (ROC) curve analysis was employed to identify an optimal MPV cutoff. Furthermore, a random forest model was developed based on independent prognostic factors, and its predictive accuracy was assessed.

Results ROC curve analysis pinpointed 9.3 fL as the critical MPV threshold for predicting 2-year survival. Patients with MPV below this threshold exhibited significantly lower 5-year overall and progression-free survival rates compared to those with higher MPV (p = 0.003 and p = 0.034, respectively). Elevated MPV was identified as an independent predictor of better outcomes (p = 0.006). The constructed random forest model, which included variables like FIGO stage, residual tumor presence, peritoneal cytology, and MPV, showed strong predictive capability (area under the curve: 0.905).

Conclusion Our findings highlight MPV as a valuable prognostic marker in OCCC, with lower levels associated with poorer survival rates. This underlines its potential role in optimizing treatment approaches. The random forest model’s impressive predictive performance, integrating MPV with other significant prognostic factors, opens avenues for improved survival prediction in OCCC, meriting further investigation.

Disclosures The authors declare no conflict of interest.

This study has been published in the International Journal of Clinical Oncology, October 7, 2023. DOI: 10.1007/s10147-023-02417-8.

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.