Artificial Neuronal Network Analysis Research Articles

Artificial Intelligence Estimates the Importance of Baseline Factors in Predicting Response to Anti-PD1 in Metastatic Melanoma.

Prognosis of patients with metastatic melanoma has dramatically improved over recent years because of the advent of antibodies targeting programmed cell death protein-1 (PD1). However, the response rate is ~40% and baseline biomarkers for the outcome are yet to be identified. Here, we aimed to determine whether artificial intelligence might be useful in weighting the importance of baseline variables in predicting response to anti-PD1. This is a retrospective study evaluating 173 patients receiving anti-PD1 for melanoma. Using an artificial neuronal network analysis, the importance of different variables was estimated and used in predicting response rate and overall survival. After a mean follow-up of 12.8 (±11.9) months, disease control rate was 51%. Using artificial neuronal network, we observed that 3 factors predicted response to anti-PD1: neutrophil-to-lymphocyte ratio (NLR) (importance: 0.195), presence of ≥3 metastatic sites (importance: 0.156), and baseline lactate dehydrogenase (LDH) > upper limit of normal (importance: 0.154). Looking at connections between different covariates and overall survival, the most important variables influencing survival were: presence of ≥3 metastatic sites (importance: 0.202), age (importance: 0.189), NLR (importance: 0.164), site of primary melanoma (cutaneous vs. noncutaneous) (importance: 0.112), and LDH > upper limit of normal (importance: 0.108). NLR, presence of ≥3 metastatic sites, LDH levels, age, and site of primary melanoma are important baseline factors influencing response and survival. Further studies are warranted to estimate a model to drive the choice to administered anti-PD1 treatments in patients with melanoma.

Yes, I can (get satisfaction): an artificial neuronal network analysis of satisfaction with a university

ABSTRACTThe principal factors that influence satisfaction with a university are analyzed in this paper. A distinction is drawn for that purpose between the factors that intervene before, during, and after the phase of university education, at all times from a graduate perspective. A sample of 9380 interviews with graduates from three separate academic courses is prepared to achieve our objective. Artificial neuronal networks are applied, with which both categorical and continuous variables may be processed, testing different network architectures (number of layers, type of learning, and algorithm). The results indicated that the variables reflecting the quality of the education received and entry into the employment market are the variables that determine satisfaction to a greater extent and less so than the motives for their choice of university course, scientific area, demographic variables, and academic records.

Preoperative prediction of perioperative risk in pancreatoduodenectomy by artificial neuronal network analysis

Preoperative prediction of perioperative risk in pancreatoduodenectomy by artificial neuronal network analysis

TOMM34 expression in early invasive breast cancer: a biomarker associated with poor outcome

Appropriate mitochondrial functioning in normal cells depends on proper functioning of mitochondrial translocation machinery, of which translocase of the outer membrane of mitochondria (TOMM) plays important role. The aim of this study was to explore the expression of TOMM34 in invasive breast cancer (BC) with relevance to BC molecular subtypes and patients' outcome. Gene expression data of 128 BC were analysed using artificial neuronal network (ANN) analysis to identify differentially expressed genes between BC with distant metastases and that without distant metastases. TOMM34 expression was assessed in a large series of BC (n = 1,061) with long-term follow-up using tissue microarray and immunohistochemistry. TOMM34 protein expression was quantitatively measured using the novel reverse phase protein microarray (RPPA) technique. ANN analysis revealed TOMM34 gene transcript as one of the top differentially expressed gene correlated with BC distant metastasis. Protein expression of TOMM34 was associated with features of aggressive behaviour including higher tumour grade, advanced nodal stage, larger tumour size and lymphovascular invasion. TOMM34 over-expression was significantly associated with shorter BC-specific survival and metastasis-free survival independent of standard prognostic parameters. TOMM34 protein expression was quantified by RPPA which showed that the mean expression values of TOMM34 were higher in samples demonstrating features of poor outcome. This study demonstrates at translational protein expression level that TOMM34 is a marker of poor prognosis in BC. Our findings underscore the role played by mitochondrial machinery in BC progression and warrant their validation on a prospective basis.

Patterns Prediction of Chemotherapy Sensitivity in Cancer Cell lines Using FTIR Spectrum, Neural Network and Principal Components Analysis.

Drug resistance enables cancer cells to break away from cytotoxic effect of anticancer drugs. Identification of resistant phenotype is very important because it can lead to effective treatment plan. There is an interest in developing classifying models of resistance phenotype based on the multivariate data. We have investigated a vibrational spectroscopic approach in order to characterize a sensitive human ovarian cell line, A2780, and its cisplatin-resistant derivative, A2780-cp. In this study FTIR method have been evaluated via the use of principal components analysis (PCA), ANN (artificial neuronal network) and LDA (linear discriminate analysis). FTIR spectroscopy on these cells in the range of 400-4000 cm(-1) showed alteration in the secondary structure of proteins and a CH stretching vibration. We have found that the ANN models correctly classified more than 95% of the cell lines, while the LDA models with the same data sets could classify 85% of cases. In the process of different ranges of spectra, the best classification of data set in the range of 1000-2000 cm(-1) was done using ANN model, while the data set between 2500-3000 cm(-1) was more correctly classified with the LDA model. PCA of the spectral data also provide a good separation for representing the variety of cell line spectra. Our work supports the promise of ANN analysis of FTIR spectrum as a supervised powerful approach and PCA as unsupervised modeling for the development of automated methods to determine the resistant phenotype of cancer classification.

TaqMan ® Low-Density Arrays and Analysis by Artificial Neuronal Networks Predict Response to Neoadjuvant Chemoradiation in Esophageal Cancer

Neoadjuvant radiochemotherapy of locally advanced esophageal cancer is only effective for patients with major histopathological response. A total of 17 genes were selected to predict histopathologic tumor response to chemoradiation (cisplatin, 5-fluorouracil, 36 Gy). For gene-expression analysis quantitative TaqMan low-density arrays were applied. Expression levels in pretreatment biopsies of 41 patients (cT2-4, Nx, M0) were compared with the degree of histopathologic regression in resected specimens applying univariate, multivariate and artificial neuronal network analyses. Dihydropyrimidine dehydrogenase was identified as an independent predictor associated with major response (p < 0.002). Multivariate analysis of the marker combination provided response prediction with 75.0% sensitivity, 81.0% specificity and 78.1% accuracy. Artificial neuronal network analysis was the best predictive model for major histopathologic response (80% sensitivity, 90.5% specificity and 85.4% accuracy), representing a clinically practical system. Low-density-array RT-PCR analyzed by artificial neuronal network predicts histopathologic response to neoadjuvant chemoradiation in our patient collective, and could be used to further individualize treatment strategies in esophageal cancer.

Identification of genes involved in endometrial cancer etiopathogenesis by the mean of MacroArray technique

20102 Endometrial cancer is one of the most common neoplasms of reproductive system. According to data accumulated in last decades it has been concluded that microsatellite instability and PTEN, K-ras, β-catenin gene mutations are crucial for endometrial cancer etiopathogenesis. Moreover, it is well known that all genes encoded proteins involved in cell cycle regulation, cell differentiation or surrounding tissues infiltration contribute to tumor and metastases development. It has been stressed that different factors such as VEGF, which play a key role in neoplastic angiogenesis are also very important for tumor growth. Complexity of molecular mechanisms leading to endometrial cancer development implies that only experiments utilizing array technique can collect enough data to understand all relationships between different molecular pathways during tumor development and to identify new clinically usable markers of neoplasm. Using MacroArray technique we analyzed expression profile of neoplastic tissue derived from 40 patients diagnosed with endometrial cancer. After data collection all genes present on chip were assigned to different groups according to their role in oncogenesis and artificial neuronal network analysis were performed in order to individuate genes those expression was significantly different in neoplastic tissue regarding to controls. Such procedure allowed us to give shape to preliminary gene expression profile typical for neoplastic tissue and to estimate protein expression of the most significant predictors of neoplastic transformation. Comparison of obtained data with tumor grade can reveal new markers of endometrial cancer useful in routine diagnostic procedures. No significant financial relationships to disclose.