Information Management in IoT Cloud-Based Tele-Rehabilitation as a Service for Smart Cities: Comparison of NoSQL Approaches

A Data Warehouse (DW) is a database that stores information oriented to satisfy decisionmaking requests. It is a database with some particular features concerning the data it contains and its utilisation. The features of DWs cause the DW design process and strategies to be different from the ones for OLTP Systems. This work presents a brief description of different approaches and techniques that address the DW Design problem.

/pdf/an-overview-of-data-warehouse-design-approaches-and-2go9nh45vt.pdf

An overview of data warehouse design approaches and tecbniques

Background
EHR (Electronic Health Record) system has led to development of specialized form of clinical databases which enable storage of information in temporal prospective. It has been a big challenge for mining this form of clinical data considering varied temporal points. This study proposes a conjoined solution to analyze the clinical parameters akin to a disease. We have used “association rule mining algorithm” to discover association rules among clinical parameters that can be augmented with the disease. Furthermore, we have proposed a new algorithm, SN algorithm, to map clinical parameters along with a disease state at various temporal points.

https://link.springer.com/content/pdf/10.1186%2F2043-9113-3-24.pdf

SN algorithm: analysis of temporal clinical data for mining periodic patterns and impending augury.

This paper presents a hybrid storage solution for the management of e-health data. Such a solution merges SQL-like strategies with NoSQL document based approaches in order to provide an efficient, scalable and secure storage system that can be used from one or many health care units. Starting from an Entity Relationship (E-R) model for e-health data, the paper discusses how pieces of information should be organized and stored for a quick and efficient retrieval. The paper also discusses a real use case where the proposed storage solution is adopted to manage data for neurologic Tele-Rehabilitation (TR) of patients at home. During the treatment at home, patients use wireless sensing devices to monitor their status and to provide real-time feedback during exercises. Such devices produce a hugh amount of e-health data that are sent and stored into the hybrid storage system. Experiments are performed adopting the e-health data model on both NoSQL and SQL-like implementations.

A Hybrid Storage Service for the Management of Big e-Health Data: A Tele-Rehabilitation Case of Study

Current research in the field of Life and Medical Sciences is generating chunk of data on daily basis. It has thus become a necessity to find solutions for efficient storage of this data, trying to correlate and extract knowledge from it. Clinical data generated in Hospitals, Clinics & Diagnostics centers is falling under a similar paradigm. Patient's records in various hospitals are increasing at an exponential rate, thus adding to the problem of data management and storage. Major problem being faced corresponding to storage, is the varied dimensionality of the data, ranging from images to numerical form. Therefore there is a need for development of efficient data model which can handle this multi-dimensionality data issue and store the data with historical aspect. For the stated problem lying in facade of clinical informatics we propose a clinical dimensional model design which can be used for development of a clinical data mart. The model has been designed keeping in consideration temporal storage of patient's data with respect to all possible clinical parameters which can include both textual and image based data. Availability of said data for each patient can be then used for application of data mining techniques for finding the correlation of all the parameters at the level of individual and population.

/pdf/design-of-dimensional-model-for-clinical-data-storage-and-ml62u63yhw.pdf

Priyanka Arora

Papers

Design of Dimensional Model for Clinical Data Storage and Analysis