2016
Coelho, D.; Miranda, J.; Portela, F.; Machado, J.; Santos, M. F.; Abelha, A.
Towards of a Business Intelligence Platform to Portuguese Misericórdias Proceedings Article
Em: R., Cruz-Cunha M. M. Rijo R. Martinho (Ed.): pp. 762-767, Elsevier B.V., 2016, ISSN: 18770509, (cited By 12; Conference of Conference on ENTERprise Information Systems / International Conference on Project MANagement / Conference on Health and Social Care Information Systems and Technologies, CENTERIS / ProjMAN / HCist 2016 ; Conference Date: 5 October 2016 Through 7 October 2016; Conference Code:121650).
Resumo | Links | BibTeX | Etiquetas: Business Intelligence platform; Entity relationship diagrams; Healthcare industry; Resource management; Sustainable decision makings, Competitive intelligence; Data warehouses; Decision making; Health care; Information analysis; Information systems; Management science; Project management, Information management
@inproceedings{Coelho2016762,
title = {Towards of a Business Intelligence Platform to Portuguese Misericórdias},
author = {D. Coelho and J. Miranda and F. Portela and J. Machado and M. F. Santos and A. Abelha},
editor = {Cruz-Cunha M. M. Rijo R. Martinho R.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85006877786&doi=10.1016%2fj.procs.2016.09.222&partnerID=40&md5=0dbe6e7ab4e67743318c6f0a991e55f8},
doi = {10.1016/j.procs.2016.09.222},
issn = {18770509},
year = {2016},
date = {2016-01-01},
journal = {Procedia Computer Science},
volume = {100},
pages = {762-767},
publisher = {Elsevier B.V.},
abstract = {In the healthcare industry it is imperative the need to increase the efficiency of resource management and services. The increasing of Business Intelligence (BI) use in organizations and the demonstrated effectiveness of this type of solution, arises the desire to use BI in healthcare as in Misericórdias. So, in this work some concepts associated to the use of BI in Misericórdias were addressed and a BI architecture was designed. Furthermore, a survey was made in order to understand what are the tools used by Misericórdias every day and which ones have the BI components. Finally, a BI architecture was developed based on the organization's mission and their stakeholders. Through this work it was possible to identify the critical processes and designing the Entity Relationship Diagram as well as a set of indicators to meet the needs of a sustainable decision-making in Portuguese Misericórdias. © 2016 The Authors.},
note = {cited By 12; Conference of Conference on ENTERprise Information Systems / International Conference on Project MANagement / Conference on Health and Social Care Information Systems and Technologies, CENTERIS / ProjMAN / HCist 2016 ; Conference Date: 5 October 2016 Through 7 October 2016; Conference Code:121650},
keywords = {Business Intelligence platform; Entity relationship diagrams; Healthcare industry; Resource management; Sustainable decision makings, Competitive intelligence; Data warehouses; Decision making; Health care; Information analysis; Information systems; Management science; Project management, Information management},
pubstate = {published},
tppubtype = {inproceedings}
}
In the healthcare industry it is imperative the need to increase the efficiency of resource management and services. The increasing of Business Intelligence (BI) use in organizations and the demonstrated effectiveness of this type of solution, arises the desire to use BI in healthcare as in Misericórdias. So, in this work some concepts associated to the use of BI in Misericórdias were addressed and a BI architecture was designed. Furthermore, a survey was made in order to understand what are the tools used by Misericórdias every day and which ones have the BI components. Finally, a BI architecture was developed based on the organization's mission and their stakeholders. Through this work it was possible to identify the critical processes and designing the Entity Relationship Diagram as well as a set of indicators to meet the needs of a sustainable decision-making in Portuguese Misericórdias. © 2016 The Authors.
Foshch, T.; Portela, F.; Machado, J.; Maksimov, M.
Regression Models of the Nuclear Power Unit VVER-1000 Using Data Mining Techniques Proceedings Article
Em: R., Cruz-Cunha M. M. Rijo R. Martinho (Ed.): pp. 253-262, Elsevier B.V., 2016, ISSN: 18770509, (cited By 5; Conference of Conference on ENTERprise Information Systems / International Conference on Project MANagement / Conference on Health and Social Care Information Systems and Technologies, CENTERIS / ProjMAN / HCist 2016 ; Conference Date: 5 October 2016 Through 7 October 2016; Conference Code:121650).
Resumo | Links | BibTeX | Etiquetas: Combined control; Control program; Correlation coefficient; Data mining models; Nuclear power unit; Regression model; Simulink software; VVER-1000, Coolants; Data mining; Information systems; Nuclear energy; Nuclear fuels; Nuclear power plants; Project management; Regression analysis, Information management
@inproceedings{Foshch2016253,
title = {Regression Models of the Nuclear Power Unit VVER-1000 Using Data Mining Techniques},
author = {T. Foshch and F. Portela and J. Machado and M. Maksimov},
editor = {Cruz-Cunha M. M. Rijo R. Martinho R.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85006851408&doi=10.1016%2fj.procs.2016.09.151&partnerID=40&md5=3c09489c8dd1a99e4f8a73d5f0451ac3},
doi = {10.1016/j.procs.2016.09.151},
issn = {18770509},
year = {2016},
date = {2016-01-01},
journal = {Procedia Computer Science},
volume = {100},
pages = {253-262},
publisher = {Elsevier B.V.},
abstract = {Due to plenty of changes in many interrelated processes at nuclear power plants there is the need to show which values of some parameters of the nuclear power plant with VVER-1000 are better. In this task data mining techniques can be introduced. In order to obtain regression models of nuclear power plant with VVER-1000 algorithms such as the Linear Regression, REPTree, and M5P were selected and the datasets were obtained by simulating two control programs in Simulink software. The study focused on such targets as the average temperature of the coolant in the first circuit and the output power of the power generator. This study demonstrates the good results of the correlation coefficients and the root relative squared error metrics in case of the improved compromise-combined control program in comparison with the control program with the constant average temperature of the coolant in the reactor core. In terms of the results the root relative squared error metric is less than 2.8% and the correlation coefficients had values higher than 99,95%. The use of these models can contribute to improving the understanding of the internal processes because using the best regression data mining models allows to see advantages of the improved compromise-combined control program. © 2016 The Authors.},
note = {cited By 5; Conference of Conference on ENTERprise Information Systems / International Conference on Project MANagement / Conference on Health and Social Care Information Systems and Technologies, CENTERIS / ProjMAN / HCist 2016 ; Conference Date: 5 October 2016 Through 7 October 2016; Conference Code:121650},
keywords = {Combined control; Control program; Correlation coefficient; Data mining models; Nuclear power unit; Regression model; Simulink software; VVER-1000, Coolants; Data mining; Information systems; Nuclear energy; Nuclear fuels; Nuclear power plants; Project management; Regression analysis, Information management},
pubstate = {published},
tppubtype = {inproceedings}
}
Due to plenty of changes in many interrelated processes at nuclear power plants there is the need to show which values of some parameters of the nuclear power plant with VVER-1000 are better. In this task data mining techniques can be introduced. In order to obtain regression models of nuclear power plant with VVER-1000 algorithms such as the Linear Regression, REPTree, and M5P were selected and the datasets were obtained by simulating two control programs in Simulink software. The study focused on such targets as the average temperature of the coolant in the first circuit and the output power of the power generator. This study demonstrates the good results of the correlation coefficients and the root relative squared error metrics in case of the improved compromise-combined control program in comparison with the control program with the constant average temperature of the coolant in the reactor core. In terms of the results the root relative squared error metric is less than 2.8% and the correlation coefficients had values higher than 99,95%. The use of these models can contribute to improving the understanding of the internal processes because using the best regression data mining models allows to see advantages of the improved compromise-combined control program. © 2016 The Authors.
2015
Pereira, S.; Portela, F.; Santos, M. F.; Machado, J.; Abelha, A.
Predicting Type of Delivery by Identification of Obstetric Risk Factors through Data Mining Proceedings Article
Em: V.J., Cruz-Cunha M. M. Eduardo (Ed.): pp. 601-609, Elsevier B.V., 2015, ISSN: 18770509, (cited By 32; Conference of Conference on ENTERprise Information Systems/International Conference on Project MANagement/Conference on Health and Social Care Information Systems and Technologies, CENTERIS 2015 ; Conference Date: 7 October 2015 Through 9 October 2015; Conference Code:123098).
Resumo | Links | BibTeX | Etiquetas: Data mining models; Delivery techniques; High quality service; Maternity Care; Pregnant; Real data;Obstetrics Care; Sensitivity and specificity; Type of delivery, Data mining; Forecasting; Information systems; Interoperability; Obstetrics; Project management, Information management
@inproceedings{Pereira2015601,
title = {Predicting Type of Delivery by Identification of Obstetric Risk Factors through Data Mining},
author = {S. Pereira and F. Portela and M. F. Santos and J. Machado and A. Abelha},
editor = {Cruz-Cunha M. M. Eduardo V.J.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84962855663&doi=10.1016%2fj.procs.2015.08.573&partnerID=40&md5=cc8176cfd884fad22b2f8f3993869258},
doi = {10.1016/j.procs.2015.08.573},
issn = {18770509},
year = {2015},
date = {2015-01-01},
journal = {Procedia Computer Science},
volume = {64},
pages = {601-609},
publisher = {Elsevier B.V.},
abstract = {In Maternity Care, a quick decision has to be made about the most suitable delivery type for the current patient. Guidelines are followed by physicians to support that decision; however, those practice recommendations are limited and underused. In the last years, caesarean delivery has been pursued in over 28% of pregnancies, and other operative techniques regarding specific problems have also been excessively employed. This study identifies obstetric and pregnancy factors that can be used to predict the most appropriate delivery technique, through the induction of data mining models using real data gathered in the perinatal and maternal care unit of Centro Hospitalar of Oporto (CHP). Predicting the type of birth envisions high-quality services, increased safety and effectiveness of specific practices to help guide maternity care decisions and facilitate optimal outcomes in mother and child. In this work was possible to acquire good results, achieving sensitivity and specificity values of 90.11% and 80.05%, respectively, providing the CHP with a model capable of correctly identify caesarean sections and vaginal deliveries. © 2015 The Authors. Published by Elsevier B.V.},
note = {cited By 32; Conference of Conference on ENTERprise Information Systems/International Conference on Project MANagement/Conference on Health and Social Care Information Systems and Technologies, CENTERIS 2015 ; Conference Date: 7 October 2015 Through 9 October 2015; Conference Code:123098},
keywords = {Data mining models; Delivery techniques; High quality service; Maternity Care; Pregnant; Real data;Obstetrics Care; Sensitivity and specificity; Type of delivery, Data mining; Forecasting; Information systems; Interoperability; Obstetrics; Project management, Information management},
pubstate = {published},
tppubtype = {inproceedings}
}
In Maternity Care, a quick decision has to be made about the most suitable delivery type for the current patient. Guidelines are followed by physicians to support that decision; however, those practice recommendations are limited and underused. In the last years, caesarean delivery has been pursued in over 28% of pregnancies, and other operative techniques regarding specific problems have also been excessively employed. This study identifies obstetric and pregnancy factors that can be used to predict the most appropriate delivery technique, through the induction of data mining models using real data gathered in the perinatal and maternal care unit of Centro Hospitalar of Oporto (CHP). Predicting the type of birth envisions high-quality services, increased safety and effectiveness of specific practices to help guide maternity care decisions and facilitate optimal outcomes in mother and child. In this work was possible to acquire good results, achieving sensitivity and specificity values of 90.11% and 80.05%, respectively, providing the CHP with a model capable of correctly identify caesarean sections and vaginal deliveries. © 2015 The Authors. Published by Elsevier B.V.
Braga, A.; Portela, F.; Santos, M. F.; Machado, J.; Abelha, A.; Silva, Á.; Rua, F.
Step Towards a Patient Timeline in Intensive Care Units Proceedings Article
Em: V.J., Cruz-Cunha M. M. Eduardo (Ed.): pp. 618-625, Elsevier B.V., 2015, ISSN: 18770509, (cited By 4; Conference of Conference on ENTERprise Information Systems/International Conference on Project MANagement/Conference on Health and Social Care Information Systems and Technologies, CENTERIS 2015 ; Conference Date: 7 October 2015 Through 9 October 2015; Conference Code:123098).
Resumo | Links | BibTeX | Etiquetas: Clinical history; INTCare; Medical history; Medical information; Patient Timeline; Patient-centered; Patients' conditions; Presenting informations, Information management, Information systems; Information use; Intensive care units; Project management
@inproceedings{Braga2015618,
title = {Step Towards a Patient Timeline in Intensive Care Units},
author = {A. Braga and F. Portela and M. F. Santos and J. Machado and A. Abelha and Á. Silva and F. Rua},
editor = {Cruz-Cunha M. M. Eduardo V.J.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84962786835&doi=10.1016%2fj.procs.2015.08.575&partnerID=40&md5=de7870befb4e0ea572d09fd2c91f020e},
doi = {10.1016/j.procs.2015.08.575},
issn = {18770509},
year = {2015},
date = {2015-01-01},
journal = {Procedia Computer Science},
volume = {64},
pages = {618-625},
publisher = {Elsevier B.V.},
abstract = {In Intensive Medicine, the presentation of medical information is done in many ways, depending on the type of data collected and stored. The way in which the information is presented can make it difficult for intensivists to quickly understand the patient's condition. When there is the need to cross between several types of clinical data sources the situation is even worse. This research seeks to explore a new way of presenting information about patients, based on the timeframe in which events occur. By developing an interactive Patient Timeline, intensivists will have access to a new environment in real-time where they can consult the patient clinical history and the data collected until the moment. The medical history will be available from the moment in which patients is admitted in the ICU until discharge, allowing intensivist to examine data regarding vital signs, medication, exams, among others. This timeline also intends to, through the use of information and models produced by the INTCare system, combine several clinical data in order to help diagnose the future patients' conditions. This platform will help intensivists to make more accurate decision. This paper presents the first approach of the solution designed. © 2015 The Authors. Published by Elsevier B.V.},
note = {cited By 4; Conference of Conference on ENTERprise Information Systems/International Conference on Project MANagement/Conference on Health and Social Care Information Systems and Technologies, CENTERIS 2015 ; Conference Date: 7 October 2015 Through 9 October 2015; Conference Code:123098},
keywords = {Clinical history; INTCare; Medical history; Medical information; Patient Timeline; Patient-centered; Patients' conditions; Presenting informations, Information management, Information systems; Information use; Intensive care units; Project management},
pubstate = {published},
tppubtype = {inproceedings}
}
In Intensive Medicine, the presentation of medical information is done in many ways, depending on the type of data collected and stored. The way in which the information is presented can make it difficult for intensivists to quickly understand the patient's condition. When there is the need to cross between several types of clinical data sources the situation is even worse. This research seeks to explore a new way of presenting information about patients, based on the timeframe in which events occur. By developing an interactive Patient Timeline, intensivists will have access to a new environment in real-time where they can consult the patient clinical history and the data collected until the moment. The medical history will be available from the moment in which patients is admitted in the ICU until discharge, allowing intensivist to examine data regarding vital signs, medication, exams, among others. This timeline also intends to, through the use of information and models produced by the INTCare system, combine several clinical data in order to help diagnose the future patients' conditions. This platform will help intensivists to make more accurate decision. This paper presents the first approach of the solution designed. © 2015 The Authors. Published by Elsevier B.V.
2014
Peixoto, H.; Abelha, A.; Santos, M.; Machado, J.
A preventive action management platform in healthcare information systems Book Chapter
Em: vol. 1-4, pp. 447-460, IGI Global, 2014, ISBN: 9781466672314; 1466672307; 9781466672307, (cited By 0).
Resumo | Links | BibTeX | Etiquetas: Administrative staff; Clinical application; Financial impacts; Health care information system; Health-care system; Management platforms; Open source platforms; Web-based interface, Health care; Information systems; Medical computing; Multimedia systems, Information management
@inbook{Peixoto2014447,
title = {A preventive action management platform in healthcare information systems},
author = {H. Peixoto and A. Abelha and M. Santos and J. Machado},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84956829257&doi=10.4018%2f978-1-4666-7230-7.ch026&partnerID=40&md5=c7f8b067202c5b5139d5871127d5cdc8},
doi = {10.4018/978-1-4666-7230-7.ch026},
isbn = {9781466672314; 1466672307; 9781466672307},
year = {2014},
date = {2014-01-01},
journal = {Open Source Technology: Concepts, Methodologies, Tools, and Applications},
volume = {1-4},
pages = {447-460},
publisher = {IGI Global},
abstract = {Preventive actions management plays a crucial role in clinical applications, not only for those who depend on data to make decisions, but also for those who monitor the operational and financial impact of the systems. This paper presents an open-source platform, named ScheduleIT, capable of managing preventive routines. The platform is based on an estimation model that determines the optimal time interval for interventions, according to the criticality of the system and the number of non-programmed faults, among others. ScheduleIT has a web-based interface available to a different area end-user, ranging from IT technicians to administrative staff. At this point, the platform covers around 75% of the healthcare systems and it is fully accepted by its main users as a reliable and effective preventive tool. © 2015, IGI Global. All rights reserved.},
note = {cited By 0},
keywords = {Administrative staff; Clinical application; Financial impacts; Health care information system; Health-care system; Management platforms; Open source platforms; Web-based interface, Health care; Information systems; Medical computing; Multimedia systems, Information management},
pubstate = {published},
tppubtype = {inbook}
}
Preventive actions management plays a crucial role in clinical applications, not only for those who depend on data to make decisions, but also for those who monitor the operational and financial impact of the systems. This paper presents an open-source platform, named ScheduleIT, capable of managing preventive routines. The platform is based on an estimation model that determines the optimal time interval for interventions, according to the criticality of the system and the number of non-programmed faults, among others. ScheduleIT has a web-based interface available to a different area end-user, ranging from IT technicians to administrative staff. At this point, the platform covers around 75% of the healthcare systems and it is fully accepted by its main users as a reliable and effective preventive tool. © 2015, IGI Global. All rights reserved.
Oliveira, S.; Portela, F.; Santos, M. F.; Machado, J.; Abelha, A.
Predictive models for hospital bed management using data mining techniques Proceedings Article
Em: pp. 407-416, Springer Verlag, Madeira, 2014, ISSN: 21945357, (cited By 6; Conference of 2014 World Conference on Information Systems and Technologies, WorldCIST 2014 ; Conference Date: 15 April 2014 Through 18 April 2014; Conference Code:104563).
Resumo | Links | BibTeX | Etiquetas: Classification tasks; CRISP-DM; Cross industry; Hospital management; Patient discharge; Predictive models; Real environments; Resources management, Data mining; Decision trees; Forecasting; Hospital beds; Hospitals; Information systems; Patient monitoring; Support vector machines, Information management
@inproceedings{Oliveira2014407,
title = {Predictive models for hospital bed management using data mining techniques},
author = {S. Oliveira and F. Portela and M. F. Santos and J. Machado and A. Abelha},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84898611818&doi=10.1007%2f978-3-319-05948-8_39&partnerID=40&md5=3faf01ae721a500d77e3cfe0b5a19b89},
doi = {10.1007/978-3-319-05948-8_39},
issn = {21945357},
year = {2014},
date = {2014-01-01},
journal = {Advances in Intelligent Systems and Computing},
volume = {276 VOLUME 2},
pages = {407-416},
publisher = {Springer Verlag},
address = {Madeira},
abstract = {It is clear that the failures found in hospital management are usually related to the lack of information and insufficient resources management. The use of Data Mining (DM) can contribute to overcome these limitations in order to identify relevant data on patient's management and providing important information for managers to support their decisions. Throughout this study, were induced DM models capable to make predictions in a real environment using real data. For this, was adopted the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology. Three distinct techniques were considered: Decision Trees (DT), Naïve Bayes (NB) and Support Vector Machine (SVM) to perform classification tasks. This work explored the possibility to predict the number of patient discharges using only the number of discharges veirifed in the past. The models developed are able to predict the number of patient discharges per week with acuity values ranging from ≈82.69% to ≈94.23%. The use of these models can improve the efficiency of the administration of hospital beds. An accurate forecasting of discharges allows a better estimate of the beds available for the coming weeks. © Springer International Publishing Switzerland 2014.},
note = {cited By 6; Conference of 2014 World Conference on Information Systems and Technologies, WorldCIST 2014 ; Conference Date: 15 April 2014 Through 18 April 2014; Conference Code:104563},
keywords = {Classification tasks; CRISP-DM; Cross industry; Hospital management; Patient discharge; Predictive models; Real environments; Resources management, Data mining; Decision trees; Forecasting; Hospital beds; Hospitals; Information systems; Patient monitoring; Support vector machines, Information management},
pubstate = {published},
tppubtype = {inproceedings}
}
It is clear that the failures found in hospital management are usually related to the lack of information and insufficient resources management. The use of Data Mining (DM) can contribute to overcome these limitations in order to identify relevant data on patient's management and providing important information for managers to support their decisions. Throughout this study, were induced DM models capable to make predictions in a real environment using real data. For this, was adopted the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology. Three distinct techniques were considered: Decision Trees (DT), Naïve Bayes (NB) and Support Vector Machine (SVM) to perform classification tasks. This work explored the possibility to predict the number of patient discharges using only the number of discharges veirifed in the past. The models developed are able to predict the number of patient discharges per week with acuity values ranging from ≈82.69% to ≈94.23%. The use of these models can improve the efficiency of the administration of hospital beds. An accurate forecasting of discharges allows a better estimate of the beds available for the coming weeks. © Springer International Publishing Switzerland 2014.