Merging person-specific bio-markers for predicting oral cancer recurrence through an ontology

One of the major problems related to cancer treatment is its recurrence. Without knowing in advance how likely the cancer will relapse, clinical practice usually recommends adjuvant treatments that have strong side effects. A way to optimize treatments is to predict the recurrence probability by analyzing a set of bio-markers. The NeoMark European project has identified a set of preliminary bio-markers for the case of oral cancer by collecting a large series of data from genomic, imaging, and clinical evidence. This heterogeneous set of data needs a proper representation in order to be stored, computed, and communicated efficiently. Ontologies are often considered the proper mean to integrate biomedical data, for their high level of formality and for the need of interoperable, universally accepted models. This paper presents the NeoMark system and how an ontology has been designed to integrate all its heterogeneous data. The system has been validated in a pilot in which data will populate the ontology and will be made public for further research.

Approaching unbanked people: a person-to-person payment application on Facebook

More than 2.5 billion people are still unbanked and they do not access or use financial services. In this paper, we present an innovative service that allows Santander University Smart Card holders to make person-to-person payments to their friends, using different social channels, such as Telegram, Facebook or Twitter. Our first implementation is based on Facebook, one of the most used social networks. This approach allows the service to reach a great number of potential users but the delivery and stability of the service depends on an external provider. We include the description of the service architecture, its implementation, tests, and the lessons learned from the development. We also discuss pros and cons of the third party service dependency from the technical and business viewpoints.