Prediction of gastric cancer lymph node status by sentinel lymph node biopsy and the Maruyama computer model.

AIMS: The extent of lymph node dissection in gastric cancer remains controversial. The Maruyama computer model and the sentinel lymph node biopsy (SLNB) are compared for their value to predict the nodal status and lead to stage-adapted surgery.

METHODS: Thirty four patients with stage I-IV gastric cancer underwent both staging procedures. For SLNB, 15 patients underwent endoscopic, peri-tumoural injection of (99m)Tc-colloid, and 19 patients were injected of Patent blue V. All 'hot' or blue sentinel lymph nodes (SLNs) were separately excised and histopathologically assessed. If the SLN was negative after routine staining by H&E, it was processed completely and reanalysed after immunohistochemistry.

RESULTS: At least, one SLN was detected by means of SLNB in 33/34 of the patients. The sensitivity to identify a positive nodal status was 22/33 and the specificity/positive predictive value was 10/10 and 22/22. Additional micrometastases or isolated tumour cells in the SLN led to 'upstaging' of 5/15, initially classified as nodal negative by H&E-staining. Using the Maruyama computer model, a sensitivity of 22/23 for the correct prediction of the lymph node involvement was associated with a specificity of 2/10 and a positive predictive value of 22/30.

CONCLUSIONS: The clinical impact of the Maruyama computer model is limited due to low specificity and a low positive predictive value, rendering the method less useful as an indicator for individualised surgery.