Extracting Temporal Relationships in EHR: Application to COVID-19 Patients.

Association rules are one of the most used data mining techniques. The first proposals have considered relations over time in different ways, resulting in the so-called Temporal Association Rules (TAR). Although there are some proposals to extract association rules in OLAP systems, to the best of our knowledge, there is no method proposed to extract temporal association rules over multidimensional models in these kinds of systems. In this paper we study the adaptation of TAR to multidimensional structures, identifying the dimension that establishes the number of transactions and how to find time relative correlations between the other dimensions. A new method called COGtARE is presented as an extension of a previous approach proposed to reduce the complexity of the resulting set of association rules. The method is tested in application to COVID-19 patients data.

Digital Phenotypes for Personalized Medicine.

In this paper we propose a new definition of digital phenotype to enrich the formulation with information stored in the Electronic Health Records (EHR) plus data obtained using wearables. On this basis, we describe how to use this formalism to represent the health state of a patient in a given moment (retrospective, present, or future) and how can it be applied for personalized medicine to find out the mutations that should be introduced at present to reach a better health status in the future.

Federated Mining of Interesting Association Rules Over EHRs.

Federated learning has a great potential to create solutions working over different sources without data transfer. However current federated methods are not explainable nor auditable. In this paper we propose a Federated data mining method to discover association rules. More accurately, we define what we consider as interesting itemsets and propose an algorithm to obtain them. This approach facilitates the interoperability and reusability, and it is based on the accessibility to data. These properties are quite aligned with the FAIR principles.

Electronic Health Records Aggregators (EHRagg ).

BACKGROUND: Integration of health data systems is an open problem. Most of the active initiatives are based on the use of standards. However, achieving a widely and generalized compliment of such standards still seems a costly task that will take a long time to be completed. Even more, most of the standards are proposed for a specific use, without integrating other needs. OBJECTIVES: We propose an alternative to get a unified view of health-related data, valid for several uses, that unites heterogeneous data sources. METHODS: Our proposal integrates developments made so far to automatically learn how to extract and convert data from different health-related systems. It enables the creation of a single multipurpose point of access. RESULTS: We present the EhRagg notion and its related concepts. EHRagg is defined as a middleware that, following the FAIR principles, integrates health data sources offering a unified view over them.

Providing an Integrated Access to EHR Using Electronic Health Records Aggregators.

The integration of health data systems is an open problem. Most of the active initiatives are based on the use of standards, each one proposed for a concrete use, without integrating other needs or standards allowing on homogenous use. We propose an alternative to get an unified view of health related data, valid for several uses, that can integrate heterogeneous sources. The proposal set the framework to integrate the developments made so far to automatically learn the extraction and conversion of the data. All the sources are integrated under a single access point. We present the main concepts of EHRagg as a middleware between systems that can incorporate several sources giving an unified access following the FAIR principles.

Improving hospital decision making with interpretable associations over datacubes.

In this paper we propose a new Classification based on Association Rules (CAR) algorithm that improves the interpretability of the results, works over real data from the electronic health records (EHRs), and allows the study of the patient as a whole. It enables tasks such as the discovery of relationships between diseases, or offering several alternative and reasoned diagnoses for the cases of patients with several diseases that analysed separately could lead to mistaken diagnosis. We aim to achieve several goals: to discover hidden relationships; to improve the interpretability and reduce the complexity of the result; to obtain more reliable diagnosis (getting alternative reasoned diagnoses and higher robustness to noisy rules), and to improve the quality of the classifier avoiding the usual over-fitting problem. To this purpose, we define and exploit hierarchies defined over datacubes dimensions, and change the way the association rules are obtained, and their evaluation at the classification process. To prove the utility of our proposal we have used it in an example of cancer discrimination.

Contextualized access to electronical health records in cardiology.

In this paper, we propose a new approach for accessing the electronical health records (EHR), and we apply it to the cardiology medical specialty. Though the use of EHR improves the storage and access to the information in it regarding the previous health records in papers, it entails the risk of having the same problems of huge size and of becoming inoperative and really difficult to handle, especially if the user is looking for a specific data item. Our proposal is based on the contextualization of the access, providing the user with the most important information for the assistance act in which he/she is involved. To do this, we define the set of possible contexts and consider different aspects of the pertinence of the documents to each context. We do it by using fuzzy logic and pay special attention to the efficiency, due to the huge size of the involved databases. Our proposal does not limit the access to the EHR, but establishes a prioritization based on the access needs, which provides the system with an additional advantage, easily enabling the use of new terminals and devices like tablet PCs and PDAs, which have great limitations in the interfaces.