Sentinel Node Status Prediction by Four Statistical Models
Authors:
- Simone MocellinSimone Mocellin
- John F. ThompsonJTJohn F. Thompson
- Sandro PasqualiSPSandro Pasquali
- Maria C. MontescoMMMaria C. Montesco
- Pierluigi PilatiPPPierluigi Pilati
- Donato NittiDNDonato Nitti
- Robyn P. SawRSRobyn P. Saw
- Richard A. ScolyerRichard A. Scolyer
- Jonathan R. StretchJSJonathan R. Stretch
- Carlo R. RossiCRCarlo R. Rossi
- 1 December 2009
- journal article
- research article
- Published by Wolters Kluwer Health in Annals of Surgery
- Vol. 250 (6) , 964-969
Abstract
To improve selection for sentinel node (SN) biopsy (SNB) in patients with cutaneous melanoma using statistical models predicting SN status. About 80% of patients currently undergoing SNB are node negative. In the absence of conclusive evidence of a SNB-associated survival benefit, these patients may be over-treated. Here, we tested the efficiency of 4 different models in predicting SN status. The clinicopathologic data (age, gender, tumor thickness, Clark level, regression, ulceration, histologic subtype, and mitotic index) of 1132 melanoma patients who had undergone SNB at institutions in Italy and Australia were analyzed. Logistic regression, classification tree, random forest, and support vector machine models were fitted to the data. The predictive models were built with the aim of maximizing the negative predictive value (NPV) and reducing the rate of SNB procedures though minimizing the error rate. After cross-validation logistic regression, classification tree, random forest, and support vector machine predictive models obtained clinically relevant NPV (93.6%, 94.0%, 97.1%, and 93.0%, respectively), SNB reduction (27.5%, 29.8%, 18.2%, and 30.1%, respectively), and error rates (1.8%, 1.8%, 0.5%, and 2.1%, respectively). Using commonly available clinicopathologic variables, predictive models can preoperatively identify a proportion of patients (∼25%) who might be spared SNB, with an acceptable (1%–2%) error. If validated in large prospective series, these models might be implemented in the clinical setting for improved patient selection, which ultimately would lead to better quality of life for patients and optimization of resource allocation for the health care system.Keywords
This publication has 18 references indexed in Scilit:
- The impact of factors beyond Breslow depth on predicting sentinel lymph node positivity in melanomaCancer, 2006
- Predicting sentinel node status in AJCC stage I/II primary cutaneous melanomaCancer, 2006
- Sentinel-Node Biopsy or Nodal Observation in MelanomaNew England Journal of Medicine, 2006
- Sentinel Node Biopsy for Early-Stage MelanomaAnnals of Surgery, 2005
- A Nomogram That Predicts the Presence of Sentinel Node Metastasis in Melanoma With Better Discrimination Than the American Joint Committee on CancerStaging SystemAnnals of Surgical Oncology, 2005
- Management of Cutaneous MelanomaNew England Journal of Medicine, 2004
- An Evidence-based Staging System for Cutaneous MelanomaCA: A Cancer Journal for Clinicians, 2004
- Mitotic Rate and Younger Age Are Predictors of Sentinel Lymph Node Positivity: Lessons Learned From the Generation of a Probabilistic ModelAnnals of Surgical Oncology, 2004
- Cost-effectiveness of sentinel lymph node biopsy in thin melanomasSurgery, 2003
- Prognostic Factors Analysis of 17,600 Melanoma Patients: Validation of the American Joint Committee on Cancer Melanoma Staging SystemJournal of Clinical Oncology, 2001