Business Intelligence Platform Research Articles

Application practice of case surveillance system for healthcare-associated infections

The healthcare-associated infections (HAI) cases monitoring system, automatic access to the medical record homepage and HAI early warning application of untreated early warning information interception and other means of information are introduced into the hospital. These means ensure the accuracy and integrity of the medical record homepage diagnostic and statistical data base information, and HAI consistency as well. Closed loop management of HAI cases provides accurate information for the hospital business intelligence platform, serving hospital administration and clinical management with accurate data. Hence precise decision-making basis can be provided for the improvement of medical quality of the hospital. Key words: Infection; Case surveillance; Informationization; Medical record homepage; Practice

A Business Intelligence Platform Implemented in a Big Data System Embedding Data Mining: A Case of Study

In this work is discussed a case study of a business intelligence –BI- platform developed within the framework of an industry project by following research and development –R&D- guidelines of ‘Frascati’. The proposed results are a part of the output of different jointed projects enabling the BI of the industry ACI Global working mainly in roadside assistance services. The main project goal is to upgrade the information system, the knowledge base –KB- and industry processes activating data mining algorithms and big data systems able to provide gain of knowledge. The proposed work concerns the development of the highly performing Cassandra big data system collecting data of two industry location. Data are processed by data mining algorithms in order to formulate a decision making system oriented on call center human resources optimization and on customer service improvement. Correlation Matrix, Decision Tree and Random Forest Decision Tree algorithms have been applied for the testing of the prototype system by finding a good accuracy of the output solutions. The Rapid Miner tool has been adopted for the data processing. The work describes all the system architectures adopted for the design and for the testing phases, providing information about Cassandra performance and showing some results of data mining processes matching with industry BI strategies.

Leveraging U.S. Army Administrative Data for Individual and Team Performance

The Army possesses vast amounts of administrative (archival) data about Soldiers. These data sources include screening tests, personnel action codes, training scores, global assessments, physical fitness scores, and more. However, the Army has yet to integrate these data to create a holistic operating picture. Our research focuses on repurposing Army administrative data to (1) operationalize social constructs of interest to the Army (e.g., Army Values, Warrior Ethos) and (2) model the predictive relationship between these constructs and individual (i.e., Soldier) and team (i.e., unit) performance and readiness. The goal of the project is to provide people analytics models to Army leadership for the purposes of optimizing human capital management decisions.
 Our talk will describe the theoretical underpinnings of our human performance model, drawing on disciplines such as social and industrial/organizational psychology, as well as our experience gaining access to and working with Army administrative data sources. Access to the archival administrative data is provided through the Army Analytics Group (AAG), Person-event Data Environment (PDE). The PDE is a business intelligence platform that has two central functions: (1) to provide a secure repository for data sources on U.S. military personnel; and (2) to provide a secure collaborative work environment where researchers can access unclassified but sensitive military data.

Управління конкурентним потенціалом підприємства на основі оцінювання комплексу маркетингу

Управління конкурентним потенціалом підприємства на основі оцінювання комплексу маркетингу

Business Intelligence for the detection of anomalies in records of fueling

Today, the organizations that store very large amounts of data need decision support technologies to achieve a satisfactory development of their organizational objectives. It is the case of the National Hydrocarbon Agency of Bolivia (ANH), which due the smuggling of fuel, implemented the RFID technology in order to store the records of fueling of all fleet vehicular in Bolivia. From the model of Anomaly Detection in Records of Fueling trough machine learning techniques proposed by Buarque et al., we propose a Business Intelligence (BI) solution able to deal with huge volume of information from records of fueling and anomalies scores in a local and global level. The proposal permitted the analysis of high anomalies presented in a specific time, by vehicle type, by department and also geo-referenced service stations (with this, the specialist could take decisions of control in some risk zones and specific service stations or vehicle type). We use the Open Source Pentaho Business Intelligence platform, one of the most used currently. This management platform covers data analysis integrated with R and reporting operations, making this a flexible solution to cover our study case: "Anomaly Detection in Records of Fueling in automobiles used for illegal fuel storage". So, the principal contribution in this paper is design and development a BI solution responsible of analyze in large amount of records of anomalies in Bolivia and in this way to allow to make better decisions of control of fuel smuggling by the ANH, having the right information in the right place at the right time.

Congestive heart failure: Change in risk factors, comorbidity and age at the time of first hospitalization. Follow-up of a population cohort between 2011 and 2016 using real life data

Introduction The current health information systems offer an opportunity to implement advanced methodology to generate evidence within the context of the healthcare activity. This evidence could complement that of the clinical trials, often challenged due to poor external validity. This use of real world data (RWD) has also its limitations, mainly due to selection bias, confusion, and the comprehensiveness and quality of the data itself. Congestive heart failure (CHF) is one of the most prevalent and lethal diseases in Europe. It is currently increasing in frequency and complexity and, due to the aging of the population, its characteristics at the onset are also changing. Our objectives are to describe the changes over time of patients with a first hospitalization by CHF regarding age, the risk factors associated to the disease and the comorbidity, including Charlson index. Methods (1) Subjects: persons of 40 years or older, with a first hospitalization by CHF in the public hospitals of the Basque Country (population 2,100,00). (2) Sources of data: business Intelligence Platform, which includes all the information collected in hospitals, primary care, emergency rooms, day-hospitals of the Basque Health Service. Also, mortality data and socioeconomic status (SES) data provided by the Basque Health Department. The variables we looked for were: age, sex, SES, risk factors, comorbidity. (3) Analysis: linear regression, temporal trends. Analyses were conducted using the R version 3.3.2. Results (1) Demographic factors: between 2011 and 2015, the incidence of the disease has increased in both men (from 2.87 to 3.06 cases/1000 persons/year) and women (2.55 to 2.85 cases/1000 persons/year). This trend, however, almost disappears after standardizing by age. In fact, the average age is also increasing in men (76.6 ± 10.9 in 2011 to 78.1 ± 8.0 in 2015) and in women (82.2 ± 9.2 to 83.2 ± 8.7). (2) Risk factors: according with the older age of the patients when they hospitalized for the first time, the prevalence of accompanying diseases and other risk factors is also increasing. During the 5 years covered by this study, a monotonic increase has been observed between 2011 and 2015 in the prevalence of: hyperlipidemia (from 42.8% to 50.2%), heart valve disorders (32.8% to 43.8%), chronic renal failure (25.6% to 31.3%), degenerative eye problems (23.8% to 29.8%), pulmonary heart disease (16.4% to 24.9%), malnutrition-obesity (18.0% to 23.4%). (3) Charlson index: comorbidity, as measured by the Charlson index, increased from 3.4 ± 2.1 to 3.7 ± 2.2 in men, and from 2.7 ± 1.8 to 2.9 ± 1.8 in women. Conclusions In agreement with the most recent studies, ours has also detected a change towards older and more complex CHF patients over the last five years. Another aspect to highlight is the opportunity offered by the RWD to monitor the process and to do clinical epidemiology. A limitation is the completeness and quality of the information registered. Another one, a possible tendency to comorbidity overdiagnosis, due to a higher intensity in the diagnostic effort.

Congestive heart failure: Epidemiology and burden for the health system looking at real life data. Follow-up of a population cohort between 2011 and 2016

Introduction The current Health Information Systems offer an opportunity to implement advanced methodology to generate evidence within the context of the healthcare activity. This evidence could complement that of the clinical trials, often challenged due to poor external validity. This use of real world data (RWD) has also its limitations, mainly due to selection bias, confusion, and the comprehensiveness and quality of the data itself. Congestive Heart Failure (CHF) is one of the most prevalent and lethal diseases in Europe. It is currently increasing in frequency and complexity and, therefore, the burden over the Health System is also growing. These elements make CHF a good touchstone to learn to manage these data and to explore its epidemiological and predictive possibilities. Our objectives are to describe: –the clinical and demographic characteristics of the population diagnosed of CHF over a 5-year period (2011–2015); –the epidemiology of the disease; –the burden on the health system in terms of use of services. Methods Subjects: people of 40 years or older, alive after a first hospitalization by CHF in the public hospitals of the Basque Country (population 2,100,000). Sources of data: business Intelligence Platform, which includes all the information collected in hospitals, primary care, emergency rooms, day-hospitals of the Basque Health Service. Also, mortality data and socioeconomic data provided by the Basque Health Department. The variables we looked for were: demographics; use of health services during the 12 months previous to the index event; comorbidity at baseline (Charlson Index); socioeconomic status; mortality, no programmed hospitalizations - including potentially preventable hospitalizations - during one year after the index event. Analysis: descriptive, variation estimators (systematic coefficient of variation - SCV), rates of events, temporal trends. Analyses were conducted using the R version 3.3.2. Results Baseline characteristics: 15,489 patients were included in the cohort, 7679 (49.6%) men and 7810 (50.4%) women. Women were older than men (82 ± 9 vs. 77 ± 11), but the Charlson index was greater in men (3.5 ± 2.1 vs. 2.8 ± 1.7 in women). Among the patients, 5640 (36%) had been hospitalized during the previous year. Among the patients, 4354 (28%) were in hospital and received a cardiovascular disease (CVD) diagnosis, other than CHF. Among the subjects, 12,755 (82%) had had a consultation in an outpatient clinic and in 6381 cases (41% overall) the consultation was with a cardiologist. Finally, the persons in the cohort visited their general practitioner an average of 14 (sd = 11) times and the nurse an average of 16 (sd = 13) times. Epidemiology: as of 31 of December 2015, the number of cases with the disease registered was 15,152 (prevalence in > 40 years = 1.2%). During the five years under study, the age-standardized incidence of first hospitalizations by CHD varied between 2.2 and 2.4 per thousand persons/year (women) and between 3.6 and 3.8 per thousand persons/year (men), without an identifiable temporal pattern. Regarding the geographical areas of the Basque Country, the variation was small (SCV Conclusions Our results replicate those obtained by other studies developed with very different methodologies, which means that RWD, if adequately managed and analysed, is a good method to do clinical research. As this data is collected in a continuous way, rather than point-to-point, it will allow using all the information of a given patient, without the restrictions of the ad-hoc research.

The Implementation of a Business Intelligence Platform to Leverage the Army Logistics Support Command's Balanced Scorecard – A Case Study

AbstractMany complex organizations struggle to optimize the use of their assets and resources. The Logistics Support Command of the Spanish Army was aware, about a decade ago, of a number of inefficiencies that had a negative influence on the effectiveness of the weapon systems that it had to sustain in their operational lives. In order to improve the management of its allocated resources, it decided to develop and implement a balanced scorecard and a business intelligence platform. The job was performed with the support of ISDEFE (Engineering Systems for the Defence of Spain) the systems engineering firm of the Ministry of Defence. The systems approach led to a successful implementation of the needed platform, which substantially enhanced the effectiveness and efficiency of the Logistics Support Command. This paper shows what was done, and how. This case study of applied systems engineering enables the issuing of a number of recommendations for organizations that plan to develop similar business intelligence platforms, as a mechanism to becoming more competent and successful at the managing of their resources.

Architecture for Business Intelligence in the Healthcare Sector

Healthcare environment is growing to include not only the traditional information systems, but also a business intelligence platform. For executive leaders, consultants, and analysts, there is no longer a need to spend hours in design and develop of typical reports or charts, the entire solution can be completed through using Business Intelligence software. The current paper highlights the advantages of big data analytics and business intelligence in the healthcare industry. In this paper, In this paper we focus our discussion around intelligent techniques and methodologies which are recently used for business intelligence in healthcare.

AD-SISCOLO: a decision-support tool to aid the management of a cervical cancer screening program

AbstractIntroduction: This paper aims to develop a data warehouse (AD-SISCOLO) in order to support the management of the cervical cancer screening program in the municipality of Rio de Janeiro/Brazil. As a part of the management process, the program managers of the municipality perform tedious manual work in order to calculate a series of performance indicators and then take decisions based on them. Methods AD-SISCOLO was implemented using the Pentaho BI Suite Business Intelligence Platform and the MySQL database management system. The indicators to be calculated and visualized in the tool were based on the municipal data of the cytopathology and histopathology tests from January 2012 until December 2014, which was obtained from the Information System of Cervical Cancer (SISCOLO) after a record linkage process. The follow-up indicators were based on a simplified version of the Brazilian guidelines for the cervical cancer screening. Results AD-SISCOLO allows the visualization of a set of test-based and follow-up indicators from different views and dimensions, which enable managers to monitor all the phases of the screening process and to identify the process’ failures. Conclusions Compared with the current available environments in Brazil, AD-SISCOLO is unique in its visualization of the follow-up indicators of groups of women, according to their test results and age. Thereby it provides presentation flexibility to suit the program manager's needs.

Intellivent: A Business Intelligence Platform for Event Management Using Gamified Mobile Application and QR Code

One way for a company to communicate to their customer and promote their products is by participating or holding an event, like an exhibition or a seminar. For the event holder and organizer, it will be their best interest to gat her as much data as they can, however for now some of the company may find it hard to find those data. From the visitor perspective, there may be less incentive on the user to interact and engage more in an event. Intellivent is a platform for event manage ment, which features a gamification using gamified QR code. The gamification can be used as a tool for the event organizer to obtain more data regarding on activity in an event, and the visitor will be rewarded when they engage more in an event. A prototyp e has been created and tested on Islamic Book Fair 2019 where it is downloaded by 2000 users from the Play Store. Another version is created to be used in SGU Open House and Patjar Merah Malang 2019, a book bazaar that is predicted to gross around 5 Billion Rupiah. The implementation of the first prototype receive a very positive result from both the Event Organizer and the visitor of the event.

The automatic creation of OLAP cube using an MDA approach

SummaryThe Model‐Driven Architecture (MDA) is an approach that aligns modeling and automation for software development. By applying such an approach to data warehouse (DW) projects, we can minimize a great deal of time and cost. Furthermore, most of OnLine Analytical Processing (OLAP) platforms seem to be like black boxes that provide wizards only to business intelligence developers to create and manipulate OLAP objects without allowing their sustainability and migration from a platform to another. That is why many works in the literature have proposed using the MDA approach in DW projects. However, most of them have mainly focused on the generation of the DW relational model from the conceptual one, and they overlooked the OLAP model and the cube implementation.To deal with this problem, we propose in this paper an MDA solution to automate the process of getting OLAP cube and its implementation through a set of metamodels and automatic transformations among them. In fact, the proposal generates the OLAP and DW relational models (PSMs) from the conceptual one, using also a PDM model that describes the target business intelligence platform. After that, the source code to create the cube is got from both PSM models. For this aim, we define a set of transformation rules implemented using the Atlas transformation language. Finally, a case study will be provided to validate our approach.

Process querying: Enabling business intelligence through query-based process analytics

The volume of process-related data is growing rapidly: more and more business operations are being supported and monitored by information systems. Industry 4.0 and the corresponding industrial Internet of Things are about to generate new waves of process-related data, next to the abundance of event data already present in enterprise systems. However, organizations often fail to convert such data into strategic and tactical intelligence. This is due to the lack of dedicated technologies that are tailored to effectively manage the information on processes encoded in process models and process execution records. Process-related information is a core organizational asset which requires dedicated analytics to unlock its full potential. This paper proposes a framework for devising process querying methods, i.e., techniques for the (automated) management of repositories of designed and executed processes, as well as models that describe relationships between processes. The framework is composed of generic components that can be configured to create a range of process querying methods. The motivation for the framework stems from use cases in the field of Business Process Management. The design of the framework is informed by and validated via a systematic literature review. The framework structures the state of the art and points to gaps in existing research. Process querying methods need to address these gaps to better support strategic decision-making and provide the next generation of Business Intelligence platforms.

Group Decision Analysis with Interval Type-2 Fuzzy Numbers

Abstract This paper presentsagroup multi-criteria DEMATELand VIKORdecision analysis method with interval type-2 fuzzy sets. In order to compare normal fuzzy trapezoidal numbers, we convert them into crisp values using graded mean integration representation. Byacase study for selection of business intelligence platform, we prove that the proposed combination isafeasible solution that can work with benefits and costs criteria, while also reducing uncertainty in experts’assessments.

Business Intelligence Platform for Nosocomial Infection Incidence

Background/Objectives: Nosocomial infection prevention is essential for patients’ safety and well-being. It can be efficiently performed through the analysis of the information available. With this analysis, it is possible to build knowledge that helps to identify the risk factors and the activities related to the nosocomial infection occurrence and it also allows characterizing the infection. Methods/Statistical Analysis: This paper presents a Business Intelligence (BI) system built to allow the study of nosocomial infection incidence in the Medicine Units of Centro Hospitalar do Porto (CHP), a hospital center in the north of Portugal. This BI platform is responsible for presenting nosocomial infection indicators. Findings: This platform enables to query important information and to analyze it, supporting healthcare professionals in their decisions. The knowledge obtained by this analysis allows preventing, monitoring and reducing nosocomial infections. So, the system acts as a Clinical Decision Support System (CDSS) capable of increasing patient safety and well-being. The platform developed shows that, for example, in 2013 the rate of nosocomial infection in CHP Medicine Units varied between 9.43% and 12.95% and the respiratory and the urinary tract infections were the most frequent nosocomial infections. Application/Improvements: This work and the platform developed demonstrate that BI technology can be applied to healthcare with utility.

The Impact of Electronic Monitoring on Healthcare Associated Infections: The Role of the HViTAL Platform

In Portugal, 9.8% of patients admitted were inflicted with healthcare associated infections, corresponding to a prevalence of 11.7%. The Hospital de São João has developed a business intelligence platform able to supervise (the patients), monitor (the clinical condition) and notify (the healthcare personnel): HViTAL. This study aims to assess the impact of electronic monitoring on healthcare associated infections since the year of HViTAL implementation. We evaluated data since January 2008 (moment from which computerized records exist) until December 2011, comparing them with subsequent data, those corresponding to January 2012 (implementation date of HViTAL) until 19 October 2015. There was an upward trend of infection parameters in the 2008 - 2011 period. Since January 2012 and October 2015, all parameters of the infection indicator showed a negative linear trend. The results are very suggestive that the HVITAL may have had an impact on improving parameters associated to healthcare associated infections. Basic measures of infection control were highlighted since 2005, with an increasing number of health professional awareness campaigns, a fact which, although not analyzed in this report, may also have contributed to the observed improvement. Our study did not include other variables such as investment in human capital. There was a clear improvement in all areas characterizing the healthcare associated infections, with obvious positive impact with the introduction of HViTAL.

A Benchmarking Analysis of Open-Source Business Intelligence Tools in Healthcare Environments

In recent years, a wide range of Business Intelligence (BI) technologies have been applied to different areas in order to support the decision-making process. BI enables the extraction of knowledge from the data stored. The healthcare industry is no exception, and so BI applications have been under investigation across multiple units of different institutions. Thus, in this article, we intend to analyze some open-source/free BI tools on the market and their applicability in the clinical sphere, taking into consideration the general characteristics of the clinical environment. For this purpose, six BI tools were selected, analyzed, and tested in a practical environment. Then, a comparison metric and a ranking were defined for the tested applications in order to choose the one that best applies to the extraction of useful knowledge and clinical data in a healthcare environment. Finally, a pervasive BI platform was developed using a real case in order to prove the tool viability.

Business information visualization intellectual contributions: An integrative framework of visualization capabilities and dimensions of visual intelligence

Modern organizations treat data as an IT infrastructure based upon which business processes and strategy can not only be informed but shaped. One important step in this process deals with the way users consume data through visual display and how those visualization-reliant technologies could impact decision making. Motivated by business information visualization's (BIV) practical relevance and disjointed nature of academic literature, this research summarizes relevant BIV research landscape; by explicating and clarifying visualization terminology and definitions, and condensing relevant literature using a framework that describes and links essential visual elements of business intelligence (BI) platforms to the dimensions of the well-known visual intelligence quotient (IQ) dimensions. The paper identifies gaps and suggests future research opportunities.

Large scale opinion mining for social, news and blog data

A business intelligence platform with social basis.Real-time data filtering in the source.Summarization of historical content.Statistics computation over sliding windows. Companies that collect and analyze data from social media, news and other data streams are faced with several challenges that concern storage and processing of huge amounts of data. When they want to serve the processed information to their customers and moreover, when they want to cover different information needs for each customer, they need solutions that process data in near real time in order to gain insights on the data in motion. The volume and volatility of opinionated data that is published in social media, in combination with the variety of data sources has created a demanding ecosystem for stream processing. Although, there are several solutions that can handle information of static nature and small volume quite efficiently, they usually do not scale up properly because of their high complexity. Moreover, such solutions have been designed to run once or to run in a fixed dataset and they are not sufficient for processing huge volumes of streamed data. To address this problem, a platform for real-time opinion mining is proposed. Based on prior research and real application services that have been developed, a new platform called PaloPro is presented to cover the needs for brand monitoring.

How a BI-wise Responsible Integrated Management System May Support Food Traceability

Food manufacturers are required to meet certain traceability specifications. This research aims at underscoring the relevant needs and expectations of various stakeholders across the entire food supply chain. In this context, firms' decisions on resource allocation and risk mitigation overlap several domains, such as quality, safety, environment, social responsibility and information. Business Intelligence (BI) platforms are specifically conceived to support analytical decision making by providing a centralised view on multiple distributed data sources. However, BI solutions are usually deployed within a single organization, whilst traceability involves multiple actors with potentially divergent interests and diverse levels of willingness to participate. Along this line of thought, integration of management systems within a company and throughout the overall supply chain is suggested to meet the emerging managerial challenges. After a detailed survey of integrated management systems (IMSs) in food traceability contexts, this research proposes a BI-wise solution using the IMS overarching approach and investigates its success conditions.