CASIDE: A data model for interoperable cancer survivorship information based on FHIR.

Cancer survivorship has traditionally received little research attention although it is associated with a variety of long-term consequences and also many other comorbidities. There is an urgent need to increase research on this area, and the secondary use of healthcare data has the potential to provide valuable insights on survivors' health trajectories. However, cancer survivors' data is often stored in silos and collected inconsistently. In this study we present CASIDE, an interoperable data model for cancer survivorship information that aims to accelerate the secondary use of healthcare data and data sharing across institutions. It is designed to provide a holistic view of the cancer survivor, taking into account not just the clinical data but also the patient's own perspective, and is built upon the emerging Health Level Seven (HL7) Fast Healthcare Interoperability Resources (FHIR) standard. Advantages of adopting FHIR and challenges in information modelling using this standard are discussed. CASIDE is a generalizable approach that is already being used as a support tool for the development of downstream applications to support clinical decision making and can contribute to translational collaborative research on cancer survivorship.

Systematic Review of Electricity Demand Forecast Using ANN-Based Machine Learning Algorithms.

The forecast of electricity demand has been a recurrent research topic for decades, due to its economical and strategic relevance. Several Machine Learning (ML) techniques have evolved in parallel with the complexity of the electric grid. This paper reviews a wide selection of approaches that have used Artificial Neural Networks (ANN) to forecast electricity demand, aiming to help newcomers and experienced researchers to appraise the common practices and to detect areas where there is room for improvement in the face of the current widespread deployment of smart meters and sensors, which yields an unprecedented amount of data to work with. The review looks at the specific problems tackled by each one of the selected papers, the results attained by their algorithms, and the strategies followed to validate and compare the results. This way, it is possible to highlight some peculiarities and algorithm configurations that seem to consistently outperform others in specific settings.

Intersection Intelligence: Supporting Urban Platooning with Virtual Traffic Lights over Virtualized Intersection-Based Routing.

The advent of the autonomous car is paving the road to the realization of ideas that will help optimize traffic flows, increase safety and reduce fuel consumption, among other advantages. We present one proposal to bring together Virtual Traffics Lights (VTLs) and platooning in urban scenarios, leaning on vehicle-to-vehicle (V2V) communication protocols that turn intersections into virtual containers of data. Newly-introduced protocols for the combined management of VTLs and platoons are validated by simulation, comparing a range of routing protocols for the vehicular networks with the baseline given by common deployments of traditional traffic lights ruled by state-of-the-art policies. The simulation results show that the combination of VTLs and platoons can achieve significant reductions in travel times and fuel consumption, provided that proper algorithms are used to handle the V2V communications.

Machine Learning Algorithms to Predict Breast Cancer Recurrence Using Structured and Unstructured Sources from Electronic Health Records.

Recurrence is a critical aspect of breast cancer (BC) that is inexorably tied to mortality. Reuse of healthcare data through Machine Learning (ML) algorithms offers great opportunities to improve the stratification of patients at risk of cancer recurrence. We hypothesized that combining features from structured and unstructured sources would provide better prediction results for 5-year cancer recurrence than either source alone. We collected and preprocessed clinical data from a cohort of BC patients, resulting in 823 valid subjects for analysis. We derived three sets of features: structured information, features from free text, and a combination of both. We evaluated the performance of five ML algorithms to predict 5-year cancer recurrence and selected the best-performing to test our hypothesis. The XGB (eXtreme Gradient Boosting) model yielded the best performance among the five evaluated algorithms, with precision = 0.900, recall = 0.907, F1-score = 0.897, and area under the receiver operating characteristic AUROC = 0.807. The best prediction results were achieved with the structured dataset, followed by the unstructured dataset, while the combined dataset achieved the poorest performance. ML algorithms for BC recurrence prediction are valuable tools to improve patient risk stratification, help with post-cancer monitoring, and plan more effective follow-up. Structured data provides the best results when fed to ML algorithms. However, an approach based on natural language processing offers comparable results while potentially requiring less mapping effort.

A Bespoke Social Network for Deaf Women in Ecuador to Access Information on Sexual and Reproductive Health.

Many deaf women face the lack of numerous resources related to their personal development. The unavailability of proper information on Sexual and Reproductive Health (SRH), in particular, causes problems of sexually transmitted infections, unwanted pregnancy in adolescence, sexual violence, complications during pregnancy, etc. In response to this, we have created a social network that delivers SRH content (verified and validated by experts) to women with different degrees of hearing loss. The site features a recommender system that selects the most relevant pieces of content to deliver to each woman, driven by her individual preferences, needs and levels of knowledge on the different subjects. We report experiments conducted in Cuenca, Ecuador, between 2017 and 2018 with 98 volunteers from low- and middle-income settings, aiming to evaluate the quality and appeal of the contents, the coherence of the methodology followed to create them, and the effectiveness of the content recommendations. The positive results encourage the frequent creation of new content and the refinement of the recommendation logic as the cohort of users expands over time.

Evaluation of an Expert System for the Generation of Speech and Language Therapy Plans.

BACKGROUND: Speech and language pathologists (SLPs) deal with a wide spectrum of disorders, arising from many different conditions, that affect voice, speech, language, and swallowing capabilities in different ways. Therefore, the outcomes of Speech and Language Therapy (SLT) are highly dependent on the accurate, consistent, and complete design of personalized therapy plans. However, SLPs often have very limited time to work with their patients and to browse the large (and growing) catalogue of activities and specific exercises that can be put into therapy plans. As a consequence, many plans are suboptimal and fail to address the specific needs of each patient. OBJECTIVE: We aimed to evaluate an expert system that automatically generates plans for speech and language therapy, containing semiannual activities in the five areas of hearing, oral structure and function, linguistic formulation, expressive language and articulation, and receptive language. The goal was to assess whether the expert system speeds up the SLPs' work and leads to more accurate, consistent, and complete therapy plans for their patients. METHODS: We examined the evaluation results of the SPELTA expert system in supporting the decision making of 4 SLPs treating children in three special education institutions in Ecuador. The expert system was first trained with data from 117 cases, including medical data; diagnosis for voice, speech, language and swallowing capabilities; and therapy plans created manually by the SLPs. It was then used to automatically generate new therapy plans for 13 new patients. The SLPs were finally asked to evaluate the accuracy, consistency, and completeness of those plans. A four-fold cross-validation experiment was also run on the original corpus of 117 cases in order to assess the significance of the results. RESULTS: The evaluation showed that 87% of the outputs provided by the SPELTA expert system were considered valid therapy plans for the different areas. The SLPs rated the overall accuracy, consistency, and completeness of the proposed activities with 4.65, 4.6, and 4.6 points (to a maximum of 5), respectively. The ratings for the subplans generated for the areas of hearing, oral structure and function, and linguistic formulation were nearly perfect, whereas the subplans for expressive language and articulation and for receptive language failed to deal properly with some of the subject cases. Overall, the SLPs indicated that over 90% of the subplans generated automatically were "better than" or "as good as" what the SLPs would have created manually if given the average time they can devote to the task. The cross-validation experiment yielded very similar results. CONCLUSIONS: The results show that the SPELTA expert system provides valuable input for SLPs to design proper therapy plans for their patients, in a shorter time and considering a larger set of activities than proceeding manually. The algorithms worked well even in the presence of a sparse corpus, and the evidence suggests that the system will become more reliable as it is trained with more subjects.

An Ecosystem of Intelligent ICT Tools for Speech-Language Therapy Based on a Formal Knowledge Model.

The language and communication constitute the development mainstays of several intellectual and cognitive skills in humans. However, there are millions of people around the world who suffer from several disabilities and disorders related with language and communication, while most of the countries present a lack of corresponding services related with health care and rehabilitation. On these grounds, we are working to develop an ecosystem of intelligent ICT tools to support speech and language pathologists, doctors, students, patients and their relatives. This ecosystem has several layers and components, integrating Electronic Health Records management, standardized vocabularies, a knowledge database, an ontology of concepts from the speech-language domain, and an expert system. We discuss the advantages of such an approach through experiments carried out in several institutions assisting children with a wide spectrum of disabilities.