PubMed · 4565295
The source did not provide an abstract. Follow the original record for more information.
Explore connections, maps & timelines
Y Kashida, M Saito, S Ogi, T Nishimuta, S Kaibara. 1972. [Symposium: mass screening system].. https://pubmed.ncbi.nlm.nih.gov/4565295/
Cite the original work for its findings. Save a collection to share your selection of sources.
KEEP EXPLORING
BACKGROUND: Accurate estimation of outcome in patients with malignant disease is an important component of the clinical decision-making process. To create a comprehensive prognostic model for esophageal carcinoma, artificial neural networks (ANNs) were applied to the analysis of a range of patient-related and tumor-related variables. METHODS: Clinical and pathologic data were collected from 418 patients with esophageal carcinoma who underwent resection with curative intent. A data base that included 199 variables was constructed. Using ANN-based sensitivity analysis, the optimal combination of variables was determined to allow creation of a survival prediction model. The accuracy (area under the receiver operator characteristic curve [AUR]) of this ANN model subsequently was compared with the accuracy of the conventional statistical technique: linear discriminant analysis (LDA). RESULTS: The optimal ANN models for predicting outcomes at 1 year and 5 years consisted of 65 variables (AUR = 0.883) and 60 variables (AUR = 0.884), respectively. These filtered, optimal data sets were significantly more accurate (P < 0.0001) than the original data set of 199 variables. The majority of ANN models demonstrated improved accuracy compared with corresponding LDA models for 1-year and 5-year survival predictions. Furthermore, ANN models based on the optimal data set were superior predictors of survival compared with a model based solely on TNM staging criteria (P < 0.0001). CONCLUSIONS: ANNs can be used to construct a highly accurate prognostic model for patients with esophageal carcinoma. Sensitivity analysis based on ANNs is a powerful tool for seeking optimal data sets.
Explore the source record for details and available documents.
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.