Gnosis Data Analysis recently participated in the creation of an on-line tool, namely the HUNT Lung Cancer Model Risk Calculator, for assessing the individual risk of developing lung cancer in smokers. The scientific study describing the tool was published in the EBioMedicine journal (link), while the tool is available here (see also our original post).[…]
Gnosis Data Analysis contributed in creating a precise tool for evaluating the personal risk of developing lung cancer in smokers. The tool is based on a mathematical model, namely the “HUNT Lung Cancer Model”, which accepts seven different clinical parameters and computes the probability of developing lung cancer within 6 and 16 years. Several characteristics[…]
The University of Huddersfield and Gnosis are leading a project for creating predictive, machine learning models able to precisely evaluate the risk of committing suicide in mental health patients. These models will help physicians in identifying the patients that need the highest level of support. Recently, two more scientific works from this project have been[…]
Gnosis, in collaboration with Huddersfield University, is developing risk assessment models based on machine learning for identifying mental hospital patients at risk of suicide. The first results of this collaboration will be presented in a poster in the UK Healthcare Text Analytics Conference (HealTAC), April 18-19, Manchester, UK. These results indicate that predictive analytics can[…]
Gnosis personnel presented two posters at the World Conference on Lung Cancer 2017, held in Yokohama, Japan, from the 15th to the 18th of October. The first poster illustrates a new stratification model for identifying subjects at high risk of developing lung cancer, and that should undergo further clinical assessment. Massive application of this model[…]
The first scientific publication involving Just Add Data Bio (JADBio), our predictive analytics tool and the successor of BioSignature Discoverer, appeared today on the prestigious journal Scientific Reports. In this work JADBio provides a classifier able to predict secreted protein from information from their mature regions. Check the online paper for more info: link to paper
On the 14th of August 2017 Prof. Tsamardinos will give an invited talk at the 2017 ACM SIGKDD Workshop on Causal Discovery. Title: “Advances in Causal-Based Feature Selection” The talk will illustrate the past and explore the future of feature selection algorithms based on Causal Discovery theory. These algorithms allow the identification of the predictors,[…]
Gnosis DA is involved in an initiative aiming at producing predictive tools for assessing the risk of committing suicide in individual patients treated in mental services. These tools will help clinicians in prioritizing their intervention on cases at high risks. During the project Gnosis DA will use state-of-the-art techniques from artificial intelligence and data analysis[…]
In the last few months we have concentrated our efforts in developing a new tool for predictive analytics. While the tool is still under active development, we are already applying it to challenging scientific tasks and the first publication sprouting from this activity has just been submitted! Stay tuned for further news.
A recent publication on BMC Bioinformatics employs BioSignature Discoverer for identifying biomarkers characterizing leaf senescence in sunflower plants. The biomarkers allow a net separation across the senescence stages of the plants, and were identified by integratively analyzing transcriptomics and metabolomics information. The original publication is now available at BMC Bioinformatics website: http://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-016-1045-2 BioSignature Discoverer page:[…]