Mortality prediction of septic shock patients using probabilistic fuzzy systems
| Autor: | Federico Cismondi, Stan N. Finkelstein, André S. Fialho, Rui Jorge Almeida, Shane R. Reti, Uzay Kaymak, João M. C. Sousa, Susana M. Vieira |
|---|---|
| Přispěvatelé: | Information Systems IE&IS |
| Jazyk: | angličtina |
| Rok vydání: | 2016 |
| Předmět: |
Septic shock
Probabilistic fuzzy systems Sequential forward feature selection Area under the ROC curve Mortality prediction Retrospective cohort study 02 engineering and technology Fuzzy control system Logistic regression medicine.disease Fuzzy logic 03 medical and health sciences 0302 clinical medicine Statistics 0202 electrical engineering electronic engineering information engineering medicine 020201 artificial intelligence & image processing 030212 general & internal medicine Software Mathematics Interpretability Point of care |
| Zdroj: | Applied Soft Computing, 42, 194-203. Elsevier |
| ISSN: | 1568-4946 |
| DOI: | 10.1016/j.asoc.2016.01.005 |
| Popis: | Graphical abstractDisplay Omitted HighlightsProbabilistic fuzzy systems (PFS) are used to predict mortality of septic shock patients.PFS models are compared with Takagi-Sugeno fuzzy models and logistic regression models.The methods are tested using ICU patients with abdominal septic shock.PFS models increase the transparency of the learned system using fuzzy rules.By providing estimates for the mortality risk, PFS help clinical decision making. Mortality scores based on multiple regressions are common in critical care medicine for prognostic stratification of patients. However, to be used at the point of care, they need to be both accurate and easily interpretable. In this work, we propose the application of one existent type of rule base system using statistical information - probabilistic fuzzy systems (PFS) - to predict mortality of septic shock patients. To assess its accuracy and interpretability, these models are compared to methodologies previously proposed in this domain: Takagi-Sugeno fuzzy models and logistic regression models. The methods are tested using a retrospective cohort study including ICU patients with abdominal septic shock. Regarding accuracy, PFS models are comparable to fuzzy modeling and logistic regression. In terms of interpretability, results indicate that PFS models increase the transparency of the learned system (using fuzzy rules), but at the same time, provide additional means for validating the fuzzy classifier using expert knowledge (from physicians in this paper). By providing accurate and interpretable estimates for the mortality risk, results suggest the usefulness of PFS to develop scores for critical care medicine. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect