Gomes E.,Hospital Of Santo Antanio |
Antunes R.,Hospital Of Santo Antanio |
Dias C.,University of Porto |
Arajo R.,Hospital Of Santo Antanio |
Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine | Year: 2010
Background. Acute kidney injury (AKI) has been hard to assess due to the lack of standard definitions. Recently, the Risk, Injury, Failure, Loss and End-Stage Kidney (RIFLE) classification has been proposed to classify AKI in a number of clinical settings. This study aims to estimate the frequency and levels of severity of AKI and to study its association with patient mortality and length of stay (LOS) in a cohort of trauma patients needing intensive care. Methods. Between August 2001 and September 2007, 436 trauma patients consecutively admitted to a general intensive care unit (ICU), were assessed using the RIFLE criteria. Demographic data, characteristics of injury, and severity of trauma variables were also collected. Results. Half of all ICU trauma admissions had AKI, which corresponded to the group of patients with a significantly higher severity of trauma. Among patients with AKI, RIFLE class R (Risk) comprised 47%, while I (Injury) and F (Failure) were, 36% and 17%, respectively. None of these patients required renal replacement therapy. No significant differences were found among these three AKI classes in relation to patient's age, gender, type and mechanism of injury, severity of trauma or mortality. Nevertheless, increasing severity of acute renal injury was associated with a longer ICU stay. Conclusions. AKI is a common feature among trauma patients requiring intensive care. Although the development of AKI is associated with an increased LOS it does not appear to influence patient mortality. © 2010 Gomes et al; licensee BioMed Central Ltd.
Rebuge A.,University of Porto |
Lapao L.V.,CINTESIS |
Lapao L.V.,New University of Lisbon
Proceedings - IEEE Symposium on Computer-Based Medical Systems | Year: 2013
Process mining can be used to extract healthcare processes related information from event logs by performing analysis exploiting the information recorded in it. We report a process mining analysis made to an event log containing traces on user activity recorded by a Virtual Electronic Patient Record (VEPR) system of a Central Hospital. A set of technical analyses were performed. Results from the discovery and characterization of global behavior and from a time series analysis on observed user tasks are reported. Process mining was applied successfully to discover, characterize and analyze user behavior recorded from VEPR. Worth noting the execution of tasks profile observed after log out, revealing significant security problems. © 2013 IEEE.
Pereira C.,Telecommunications Institute of Portugal |
Pereira C.,University of Porto |
Frade S.,University of Porto |
Brandao P.,Telecommunications Institute of Portugal |
And 5 more authors.
2014 IEEE 16th International Conference on e-Health Networking, Applications and Services, Healthcom 2014 | Year: 2015
E-health has raised a great deal of expectations on improving the quality of health services while simultaneously enabling health services cost reductions. To advance towards those visions, it is imperative to gain the trust of the involved stakeholders, doctors and other medical personnel, patients, families, health care providers and regulators. Even though one critical requirement is interoperability among the various systems involved, currently existing solutions are still vertical silos to a large extent. In this paper, we present an E-health solution that results from the integration of components that comply with rising standards at the various levels of the ICT infrastructure: Machine-to-Machine (M2M) communications for interconnecting devices and services, Health Level 7 (HL7) for communicating with health platforms and openEHR for data semantics, storing and making data available. Concretely, we provide an interoperable and extensible e-health service following these three uprising standards and present the architecture design. We map the service to the various components of the infrastructure building blocks, thus demonstrating how the integration can be successfully accomplished. We are currently developing a prototype solution to be used in a pilot project with 15 elders. © 2014 IEEE.
Riaz F.,University of Porto |
Areia M.,Instituto Portugues Of Oncologia |
Silva F.B.,Karolinska Universitessjukhuse |
Dinis-Ribeiro M.,CINTESIS |
And 2 more authors.
Proceedings - International Symposium on Biomedical Imaging | Year: 2011
Automatic classification of cancer lesions for gastroenterology imaging scenarios poses novel challenges to computer assisted decision systems, owing to their distinct visual characteristics such as reduced color spaces or natural organic textures. In this paper, we explore the prospects of using Gabor filters in a texton framework for the classification of images from two distinct imaging modalities (chromoendoscopy and narrow-band imaging) into three different groups: normal, precancerous and cancerous. Results show that they produce consistent results for both imaging modalities, hinting on their possible generic use for the classification of in-body images. © 2011 IEEE.
Kikuste I.,University of Latvia |
Marques-Pereira R.,CINTESIS |
Monteiro-Soares M.,CINTESIS |
Pimentel-Nunes P.,Portuguese Oncology Institute |
And 4 more authors.
Scandinavian Journal of Gastroenterology | Year: 2013
Aim. The aim of the article is to systematically review the current evidence on the diagnostic use of narrow band imaging (NBI), flexible spectral imaging color enhancement (FICE) and endoscopic image enhancement technology i-scan endoscopies for gastric precancerous and cancerous lesions. Materials and methods. Original manuscripts were searched in PubMed until October 2012. Pertinent data were collected and pooled diagnostic accuracy measures were estimated when possible. Results. In total, 38 studies were evaluated. Thirty-one studies were included for NBI and 7 studies for FICE assessment in this systematic review. No article was found meeting inclusion criteria for i-scan endoscopy. The most defined and evaluated outcomes were cancer-related (n = 26). Quality Assessment of Diagnostic Accuracy Studies score varied from 9 to 12 (out of 14). Only few studies assessed the interobserver reliability. On a patient level analysis, NBI's pooled sensitivity, specificity and diagnostic odds ratio were 0.67 (95% CI: 0.61-0.73), 0.81 (95% CI: 0.76-0.85) and 22.71 (95% CI: 12.53-41.1), respectively for diagnosing normal mucosa; 0.86 (95% CI: 0.82-0.90), 0.77 (95% CI: 0.73-0.80) and 17.01 (95% CI: 1.4-207.2) for intestinal metaplasia and 0.90 (95% CI: 0.84-0.94), 0.83 (95% CI: 0.80-0.86) and 47.61 (95% CI: 4.61-491.34) for dysplasia. Owing to the insufficient data and different definitions, we could not aggregate the results for FICE. Conclusion. Gastric pattern descriptions have been proposed for NBI and FICE studies by gathering all descriptions in one single description. The classification systems varied between studies, a single description of gastric mucosal features with HR-scopes or at least per technology-will have to be agreed on. © 2013 Informa Healthcare.
Patriarca-Almeida J.H.,CINTESIS |
Santos B.,SPMS |
Proceedings of CBMS 2013 - 26th IEEE International Symposium on Computer-Based Medical Systems | Year: 2013
The OPTIM project aims to optimize the graphical user interface of an electronic health record (EHR) by predicting clinical documents' relevance and provide a ranked list of relevant documents for the given user at a certain time. In this paper we will describe part of the system architecture pertaining to report retrieval and relevance assignment, focusing on the optimization of an agent based report retrieval system (MAID) using the webservice layer of the OPTIM project. The prototype of MAID using the optimized retrieval was tested in a simulated environment. In the executed simulations the classifier was able to rate 10 reports per second. Including a report rating in the EHR interface based on clinical relevance calculated by mathematical models can potentially improve the usability of the EHR. © 2013 IEEE.
Areia M.,Portuguese Oncology Institute |
Soares M.,CINTESIS |
Dinis-Ribeiro M.,CINTESIS |
Dinis-Ribeiro M.,Portuguese Oncology InstitutePorto
Endoscopy | Year: 2010
Background and study aims: Many papers have been published in the field of diagnostic endoscopy in the last few years. However, there are no reports on their quality. The aim of this study was to evaluate quality in recently published endoscopic articles. Materials and methods: The study reviewed published articles on diagnostic endoscopy from 1998 to 2008. Quality was assessed and independently quantified by two observers using the STARD (STandards for the Reporting of Diagnostic accuracy studies) and CONSORT (Consolidated Standards for Reporting of Trials) statements. The interobserver proportion of agreement and coefficient were estimated. Results: A total of 120 articles comprising 10 randomized controlled trials and 110 diagnostic accuracy studies were evaluated. Most studies related to colonic polyp detection (30%) or evaluation of Barretts esophagus (29%). Chromoscopy (45%), fluorescence (21%), and narrow-band imaging (14%) were the technologies most often evaluated. The mean number of items (i.e. standard requirements) fulfilled by the randomized controlled trials was 15.72.2 out of 22 while for the diagnostic accuracy studies it was 12.23.6 out of 25. Reporting of study results was complete in 90% of the randomized controlled trials, but only 65% of the diagnostic accuracy studies presented a cross-table of results. The global proportion of agreement between observers was 97% in randomized controlled trials and 95% in diagnostic accuracy studies. Conclusions: Recent publications in diagnostic endoscopy achieve only medium quality according to the available statements. It seems that it would be useful for authors, reviewers, and editors to be familiar with and apply these statements. The development of a specific checklist for diagnostic endoscopy publications might be helpful toward achieving better quality reporting in the future. © 2010 Georg Thieme Verlag KG Stuttgart New York.
Kikuste I.,University of Latvia |
Kikuste I.,Digestive Diseases Center |
Stirna D.,Digestive Diseases Center |
Liepniece-Karele I.,Academic Histology Laboratory |
And 4 more authors.
European Journal of Gastroenterology and Hepatology | Year: 2014
BACKGROUND: Targeting biopsies on the basis of visual recognition of mucosal changes in the stomach instead of the currently accepted random biopsy sampling may be attractive. AIM: The aim of this study was to evaluate the accuracy of endoscopic findings using flexible spectral imaging colour enhancement (FICE) for intestinal metaplasia (IM) in the gastric mucosa. METHODS: A consecutive cohort of 126 individuals aged over 50 years (27% men) was subjected to upper endoscopy using FICE. Histological assessment (per patient and per biopsy) was considered the gold standard to accuracy estimates. RESULTS: Histological assessment revealed IM in 50% of the individuals [OLGIM (operative link on gastric intestinal metaplasia assessment) stages I-IV]. Overall, endoscopy presented sensitivities, specificities, positive likelihood ratio, negative likelihood ratio and accuracies per patient of 60% [95% confidence interval (95% CI) 48-72], 87% (95% CI 79-95), 4.7 (95% CI 2.4-93), 0.45 (95% CI 0.33-0.62) and 74% (95% CI 0.66-0.82), respectively, for IM diagnosis and 71% (95% CI 37-100), 87% (95% CI 79-95), 5.6 (95% CI 2.5-12.5), 0.32 (95% CI 0.10-1.0) and 86% (95% CI 77-94), respectively, for selecting individuals with OLGIM (III-IV). The proportions of agreement (and κ values) for IM in the antrum and the corpus were 75% (0.37) and 81% (0.19), respectively. CONCLUSION: FICE endoscopy yielded favourable results in the endoscopic diagnosis of IM of the gastric mucosa, and this is a very practical and easy method to use in daily clinical practice for unselected patients. Our study demonstrated a good specificity for FICE endoscopy to detect IM in the stomach. Further improvement in disseminating and training of this assessment is required to improve the reliability. © 2014 Wolters Kluwer Health | Lippincott Williams & Wilkins.
Monteiro-Soares M.,CINTESIS |
Diabetologia | Year: 2010
Aims/hypothesis In 2006 a risk stratification model was developed by Boyko et al. to predict foot ulceration in patients with diabetes, using seven commonly available clinical variables. We sought to validate and optimise this clinical prediction rule in a different setting. Methods A retrospective cohort study was conducted on all patients with diabetes attending the podiatry section of a diabetic foot clinic at a tertiary hospital in Portugal (n=360). Assessment at baseline included variables evaluated in the previous study and other relevant variables. Results Type 2 diabetes was present in 98% of patients, 45% were men and (at baseline) the median age was 65 years. Median follow-up was 25 months (range 3-86), during which 94 patients (26%) developed a foot ulcer. Boyko's model had an area under the receiver operating curve of 0.83 (95% CI 0.78-0.88). The corresponding value for the optimised model, which included the footwear risk variable, was 0.88 (95% CI 0.84-0.91). Both models had high classification accuracy for prediction of foot ulceration. However, the optimised model tended to produce higher specificity and positive likelihood ratio values at all levels. Conclusions/interpretation This study confirmed that Boyko's proposed model has a high capacity to predict foot ulceration in diabetes patients of both sexes. Our results suggest that the inclusion of a further footwear variable could improve the model. Nevertheless, prospective validation in a larger population is still necessary. © Springer-Verlag 2010.
PubMed | CINTESIS
Type: Journal Article | Journal: Scandinavian journal of gastroenterology | Year: 2013
AIM. The aim of the article is to systematically review the current evidence on the diagnostic use of narrow band imaging (NBI), flexible spectral imaging color enhancement (FICE) and endoscopic image enhancement technology i-scan endoscopies for gastric precancerous and cancerous lesions. MATERIALS AND METHODS. Original manuscripts were searched in PubMed until October 2012. Pertinent data were collected and pooled diagnostic accuracy measures were estimated when possible. RESULTs. In total, 38 studies were evaluated. Thirty-one studies were included for NBI and 7 studies for FICE assessment in this systematic review. No article was found meeting inclusion criteria for i-scan endoscopy. The most defined and evaluated outcomes were cancer-related (n = 26). Quality Assessment of Diagnostic Accuracy Studies score varied from 9 to 12 (out of 14). Only few studies assessed the interobserver reliability. On a patient level analysis, NBIs pooled sensitivity, specificity and diagnostic odds ratio were 0.67 (95% CI: 0.61-0.73), 0.81 (95% CI: 0.76-0.85) and 22.71 (95% CI: 12.53-41.1), respectively for diagnosing normal mucosa; 0.86 (95% CI: 0.82-0.90), 0.77 (95% CI: 0.73-0.80) and 17.01 (95% CI: 1.4-207.2) for intestinal metaplasia and 0.90 (95% CI: 0.84-0.94), 0.83 (95% CI: 0.80-0.86) and 47.61 (95% CI: 4.61-491.34) for dysplasia. Owing to the insufficient data and different definitions, we could not aggregate the results for FICE. CONCLUSION. Gastric pattern descriptions have been proposed for NBI and FICE studies by gathering all descriptions in one single description. The classification systems varied between studies, a single description of gastric mucosal features with HR--scopes or at least per technology--will have to be agreed on.