SOM for classifying data sets with missing values: application to clinical data of bladder cancer patients

In this paper we investigate applying SOM (Self-Organizing Maps) for classification and rule extraction in data sets with missing values, in particular from real clinical data of bladder cancer patients. For this experiment, we used real data of bladder cancer patients provided by Kitasato University Hospital. When using input data with missing values for SOM, the missing value is either interpolated in the preprocessing stage, or the missing value is replaced with a specific value or property that marks it as a missing value. In either case, there is a possibility some rules can be extracted from data with missing values. On the other hand, these data can have a negative influence for the classification for data sets for which missing values should be neglected. In this research we propose a method where SOM is trained using an input vector in which the properties for the missing values are excluded. The influence of information on the missing values can be reduced by using the proposed method. Through computer simulation, we showed that the proposed method gave good results in classification and rule extraction from clinical data of bladder cancer patients. This work was presented in part at the 13th International Symposium on Artificial Life and Robotics, Oita, Japan, January 31–February 2, 2008     

Grand rounds in proteomics at the FDA white oak, silver spring, MD, USA, april 3, 2007

The application of proteomics in drug development could be a major source of novel biomarkers to improve the efficacy and safety of new drugs. Training of US Food and Drug Administration (FDA) reviewers on current applications of proteomics is important for the future review of proteomic data. A Grand Rounds in Proteomics was held on April 3, 2007 at the FDA in White Oak, Silver Spring, MD, USA. The goal of this activity was to contribute to reviewer training as well as to generate discussions regarding the readiness of proteomic platforms in drug development, similar in scope to applications in genomics and metabolomics. Several speakers from industry and academia presented data on proteomic applications in drug development (meeting agenda available in the Supporting Information). An additional goal of this meeting was to encourage proteomic data submissions within the Voluntary eXploratory Data Submissions (VXDS) at the FDA. VXDS meetings represent key venues for exchange between the FDA and sponsors of scientific and clinical data on exploratory biomarkers. The FDA has received a limited number of VXDS submissions containing proteomic data. This meeting was an opportunity to identify possible areas in proteomics where future VXDS submissions may be received. Voluntary submissions have been transformed into regulatory submissions in genomics, and a similar path may also be followed by proteomic data in the future. Proteomic biomarkers may also be suitable for submission to the Pilot Process for Biomarker Qualification at the FDA.     

Evolutionary assembled neural networks for making medical decisions with minimal regret: Application for predicting advanced bladder cancer outcome

Development of reliable medical decision support systems has been the subject of many studies among which Artificial Neural Networks (ANNs) gained increasing popularity and gave promising results. However, wider application of ANNs in clinical practice remains limited due to the lack of a standard and intuitive procedure for their configuration and evaluation which is traditionally a slow process depending on human experts. The principal contribution of this study is a novel procedure for obtaining ANN predictive models with high performances. In order to reach those considerations with minimal user effort, optimal configuration of ANN was performed automatically by Genetic Algorithms (GA). The only two user dependent tasks were selecting data (input and output variables) and evaluation of ANN threshold probability with respect to the Regret Theory (RT). The goal of the GA optimization was reaching the best prognostic performances relevant for clinicians: correctness, discrimination and calibration. After optimally configuring ANNs with respect to these criteria, the clinical usefulness was evaluated by the RT Decision Curve Analysis. The method is initially proposed for the prediction of advanced bladder cancer (BC) in patients undergoing radical cystectomy, due to the fact that it is clinically relevant problem with profound influence on health care. Testing on the data of the ten years cohort study, which included 183 evaluable patients, showed that soft max activation functions and good calibration were the most important for obtaining reliable BC predictive models for the given dataset. Extensive analysis and comparison with the solutions commonly used in literature showed that better prognostic performances were achieved while user-dependency was significantly reduced. It is concluded that presented procedure represents a suitable, robust and user-friendly framework with potential to have wide applications and influence in further development of health care decision support systems.     

Formalin-fixed paraffin-embedded tissue: The holy grail of clinical proteomics?

Tissue is the most relevant biological material to gather insight in disease mechanisms by means of omics technologies. However, fresh frozen tissue, which is generally regarded as the best imaginable source for such studies, is often not available. In case it is available, the different ways of storage (e.g. −20°C, −80°C, liquid nitrogen, etc.) hamper the conduction of reproducible multicenter studies because of different protein degradation rates. Formalin-fixed paraffin-embedded (FFPE) tissue on the contrary is considered as a valuable alternative for fresh frozen tissue, because only a few standard operation procedures are applied worldwide for the preparation of these tissues and because they are all stored in the same way. However, a study on the impact of the different preparation protocols for FFPE tissue was still lacking. Therefore, Bronsert et al. in this issue [Bronsert, P., Weißer, J., Biniossek, M. L., Kuehs, M. et al., Proteomics Clin. Appl. 2014, 8 786–804] conducted such a study that provides proof that there is no significant effect between these sample preparations procedures, and thereby they further open the gate for FFPE tissues to enter the field of clinical proteomics.     

Proteomics in aortic aneurysm – What have we learnt so far?

Aortic aneurysm is a deceptively indolent disease that can cause severe complications such as aortic rupture and dissection. In the normal aorta, vascular smooth muscle cells within the medial layer produce and sustain the extracellular matrix (ECM) that provides structural support but also retains soluble growth factors and regulates their distribution. Although the ECM is an obvious target to identify molecular processes leading to structural failure within the vessel wall, an in-depth proteomics analysis of this important sub-proteome has not been performed. Most proteomics analyses of the vasculature to date used homogenized tissue devoid of spatial information. In such homogenates, quantitative proteomics comparisons are hampered by the heterogeneity of clinical samples (i.e. cellular composition) and the dynamic range limitations stemming from highly abundant cellular proteins. An unbiased proteomics discovery approach targeting the ECM instead of the cellular proteome may decipher the complex, multivalent signals that are presented to cells during aortic remodelling. A better understanding of the ECM in healthy and diseased vessels will provide important pathogenic insights and has potential to reveal novel biomarkers.