Background Celiac disease (CD) is a difficult-to-diagnose condition because of its multiple clinical presentations and symptoms shared with other diseases. Gold-standard diagnostic confirmation of suspected CD is achieved by biopsying the small intestine. Objective To develop a clinical decision–support system (CDSS) integrated with an automated classifier to recognize CD cases, by selecting from experimental models developed using intelligence artificial techniques. Methods A web-based system was designed for constructing a retrospective database that included 178 clinical cases for training. Tests were run on 270 automated classifiers available in Weka 3.6.1 using five artificial intelligence techniques, namely decision trees, Bayesian inference, k-nearest neighbor algorithm, support vector machines and artificial neural networks. The parameters evaluated were accuracy, sensitivity, specificity and area under the ROC curve (AUC). AUC was used as a criterion for selecting the CDSS algorithm. A testing database was constructed including 38 clinical CD cases for CDSS evaluation. The diagnoses suggested by CDSS were compared with those made by physicians during patient consultations. Results The most accurate method during the training phase was the averaged one-dependence estimator (AODE) algorithm (a Bayesian classifier), which showed accuracy 80.0%, sensitivity 0.78, specificity 0.80 and AUC 0.84. This classifier was integrated into the web-based decision–support system. The gold-standard validation of CDSS achieved accuracy of 84.2% and k = 0.68 (p < 0.0001) with good agreement. The same accuracy was achieved in the comparison between the physician’s diagnostic impression and the gold standard k = 0. 64 (p < 0.0001). There was moderate agreement between the physician’s diagnostic impression and CDSS k = 0.46 (p = 0.0008). Conclusions The study results suggest that CDSS could be used to help in diagnosing CD, since the algorithm tested achieved excellent accuracy in differentiating possible positive from negative CD diagnoses. This study may contribute towards developing of a computer-assisted environment to support CD diagnosis.
suportar a implementação deste protocolo. Para a avaliação da usabilidade do sistema web, foi utilizado o questionário System Usability Scale (SUS). O SUS-score resultou em um valor médio de 83,5±10,0, o que indica que o sistema web foi considerado de fácil uso e de acordo com a satisfação do usuário. O sistema web implementou adequadamente o protocolo. A utilização do protocolo eletrônico mostrou-se válida para o atendimento e monitoramento do paciente com doença celíaca, pois manteve a especificidade dos dados clínicos e a rotina dos profissionais envolvidos.
Background: A large number of studies indicate that subanesthetic doses of ketamine induce a fast antidepressant effect. Limited studies have investigated the subcutaneous (SC) route, and it remains unclear for whom this treatment is most suitable. Aims: The aim of this study was to examine the effect on depressive symptoms of repeated subanesthetic doses of SC esketamine in unipolar and bipolar treatment-resistant depression (TRD) and clinical predictors of response. Methods: A retrospective analysis of 70 patients who received six SC esketamine doses weekly as an adjunctive treatment was carried out. Doses started at 0.5 mg/kg and it could be titrated up to 1 mg/kg, according to response. The primary outcome was reduction in depressive symptoms. Statistical analysis to investigate clinical predictors of effectiveness included logistic regression analysis using a dependent variable of a 50% reduction in rating scale scores at the end of treatment. Comparisons between groups were made through analysis of variance and treatment effects. Results: At baseline, our sample presented with severe treatment resistance in 65.7%, as assessed by the Maudsley Staging Method (MSM), and 47.1% had anxiety disorder comorbidity. The response rate was 50%. A better outcome was predicted by mild and moderate MSM scores (OR = 3.162, p = 0.041) and anxiety disorder comorbidity (OR = 3.149, p = 0.028). Conclusions: Our results suggest that higher levels of treatment resistance may be associated with a poor response to SC esketamine. Unlike traditional pharmacotherapies, it might benefit those with poor prognosis such as patients with depression and comorbid anxiety. Therefore, future research could investigate whether esketamine should receive a more prominent place in the treatment algorithm for TRD.
Objective: Identifying predictors of infection or colonization with resistant microorganisms. Methods: A quantitative study of prospective cohort was carried out. A descriptive analysis was performed in order to know the population of the study and a discriminant analysis was performed to identify the predictors. Results: In this study were included 85 patients with infections caused by resistant microorganisms: carbapenem-resistant Pseudomonas aeruginosas (24.7%); carbapenem-resistant Acinetobacter (21.2%); methicillin-resistant Staphylococcus aureus (25.9%), vancomycin-resistant Enterococcus spp (17.6%) and carbapenem-resistant Klebsiella pneumonia (10.6%). The discriminant analysis identified transfers from other hospitals and hospitalization in intensive care unit as predictors for the occurrence of infections by the following groups: S. aureus resistant to methicillin, Acinetobacter resistant to carbapenems and K. pneumoniae resistant to carbapenems. None of the studied variables was discriminant for vancomycin-resistant Enterococcus spp. and carbapenem-resistant P. aeruginosas. Conclusion: The predictors found were: ICU hospitalization and transfers from other hospitals. ResumoObjetivo: Identificar os fatores preditores de infecção ou colonização por micro-organismos resistentes. Métodos: Foi realizado estudo quantitativo de coorte prospectivo. Foram realizadas a análise descritiva, para conhecimento da população do estudo, e a análise discriminante, para identificação dos fatores preditores. Resultados: Foram incluídos 85 pacientes com infecções por micro-organismos resistentes: Pseudomonas aeruginosas resistente aos carbapenêmicos (24,7%), Acinetobacter resistente aos carbapenêmicos (21,2%), Staphylococcus aureus resistente à meticilina (25,9%), Enterococcus spp. resistente à vancomicina (17,6%) e Klebsiella pneumoniae resistente aos carbapenêmicos (10,6%). A análise discriminante identificou transferências de outros hospitais e internação na Unidade de Terapia Intensiva como fatores preditores para ocorrência de infecção pelos grupos S. aureus resistente à meticilina, Acinetobacter resistente aos carbapenêmicos e K. pneumoniae resistente aos carbapenêmicos. Nenhuma das variáveis estudadas foi discriminante para Enterococcus spp. resistente à vancomicina e P. aeruginosas resistente aos carbapenêmico. Conclusão: Os fatores preditores encontrados foram: internação na UTI e a transferências de outros hospitais.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.