André S. Fialho

Data mining using clinical physiology at discharge to predict ICU readmissions

Patient readmissions to intensive care units (ICUs) are associated with increased mortality, morbidity and costs. Current models for predicting ICU readmissions have moderate predictive value, and can utilize up to twelve variables that may be assessed at various points of the ICU inpatient stay. We postulate that greater predictive value can be achieved with fewer physiological variables, some of which can be assessed in the 24h before discharge. A data mining approach combining fuzzy modeling with tree search feature selection was applied to a large retrospectively collected ICU database (MIMIC II), representing data from four different ICUs at Beth Israel Deaconess Medical Center, Boston. The goal was to predict ICU readmission between 24 and 72h after ICU discharge. Fuzzy modeling combined with sequential forward selection was able to predict readmissions with an area under the receiver-operating curve (AUC) of 0.72+/-0.04, a sensitivity of 0.68+/-0.02 and a specificity of 0.73+/-0.03. Variables selected as having the highest predictive power include mean heart rate, mean temperature, mean platelets, mean non-invasive arterial blood pressure (mean), mean spO2, and mean lactic acid, during the last 24h before discharge. Collection of the six predictive variables selected is not complex in modern ICUs, and their assessment may help support the development of clinical management plans that potentially mitigate the risk of readmission.

Missing data in medical databases: Impute, delete or classify?

BACKGROUND The multiplicity of information sources for data acquisition in modern intensive care units (ICUs) makes the resulting databases particularly susceptible to missing data. Missing data can significantly affect the performance of predictive risk modeling, an important technique for developing medical guidelines. The two most commonly used strategies for managing missing data are to impute or delete values, and the former can cause bias, while the later can cause both bias and loss of statistical power. OBJECTIVES In this paper we present a new approach for managing missing data in ICU databases in order to improve overall modeling performance. METHODS We use a statistical classifier followed by fuzzy modeling to more accurately determine which missing data should be imputed and which should not. We firstly develop a simulation test bed to evaluate performance, and then translate that knowledge using exactly the same database as previously published work by [13]. RESULTS In this work, test beds resulted in datasets with missing data ranging 10-50%. Using this new approach to missing data we are able to significantly improve modeling performance parameters such as accuracy of classifications by an 11%, sensitivity by 13%, and specificity by 10%, including also area under the receiver-operator curve (AUC) improvement of up to 13%. CONCLUSIONS In this work, we improve modeling performance in a simulated test bed, and then confirm improved performance replicating previously published work by using the proposed approach for missing data classification. We offer this new method to other researchers who wish to improve predictive risk modeling performance in the ICU through advanced missing data management.

Predicting Outcomes of Septic Shock Patients Using Feature Selection Based on Soft Computing Techniques

This paper proposes the application of new knowledge based methods to a septic shock patient database. It uses wrapper methods (bottom-up tree search or ant feature selection) to reduce the number of features. Fuzzy and neural modeling are used for classification. The goal is to estimate, as accurately as possible, the outcome (survived or deceased) of these septic shock patients. Results show that the approaches presented outperform any previous solutions, specifically in terms of sensitivity.

Reducing unnecessary lab testing in the ICU with artificial intelligence

OBJECTIVES To reduce unnecessary lab testing by predicting when a proposed future lab test is likely to contribute information gain and thereby influence clinical management in patients with gastrointestinal bleeding. Recent studies have demonstrated that frequent laboratory testing does not necessarily relate to better outcomes. DESIGN Data preprocessing, feature selection, and classification were performed and an artificial intelligence tool, fuzzy modeling, was used to identify lab tests that do not contribute an information gain. There were 11 input variables in total. Ten of these were derived from bedside monitor trends heart rate, oxygen saturation, respiratory rate, temperature, blood pressure, and urine collections, as well as infusion products and transfusions. The final input variable was a previous value from one of the eight lab tests being predicted: calcium, PTT, hematocrit, fibrinogen, lactate, platelets, INR and hemoglobin. The outcome for each test was a binary framework defining whether a test result contributed information gain or not. PATIENTS Predictive modeling was applied to recognize unnecessary lab tests in a real world ICU database extract comprising 746 patients with gastrointestinal bleeding. MAIN RESULTS Classification accuracy of necessary and unnecessary lab tests of greater than 80% was achieved for all eight lab tests. Sensitivity and specificity were satisfactory for all the outcomes. An average reduction of 50% of the lab tests was obtained. This is an improvement from previously reported similar studies with average performance 37% by [1-3]. CONCLUSIONS Reducing frequent lab testing and the potential clinical and financial implications are an important issue in intensive care. In this work we present an artificial intelligence method to predict the benefit of proposed future laboratory tests. Using ICU data from 746 patients with gastrointestinal bleeding, and eleven measurements, we demonstrate high accuracy in predicting the likely information to be gained from proposed future lab testing for eight common GI related lab tests. Future work will explore applications of this approach to a range of underlying medical conditions and laboratory tests.

Computational intelligence methods for processing misaligned, unevenly sampled time series containing missing data

One consequence of the increasing amount of data stored during acquisition processes is that sampled time series are more prone to be collected in a misaligned uneven fashion and/or be partly lost or unavailable (missing data). Due to their severe impact on data mining techniques, this work proposes methods to (a) align misaligned unevenly sampled data, (b) differentiate absent values related to low sampling frequencies, compared to those resulting from missingness mechanisms, and (c) to classify recoverable and non-recoverable segments of missing data by using statistical and fuzzy modeling approaches. These methods were evaluated against randomly simulated test datasets containing different amounts of missing data. Results show that: (1) using the variable most frequently sampled as a template, combined with cubic interpolation, allowed to unshift misaligned uneven data without significant errors; (2) the differentiation of absent values due to low sampling frequencies from those truly missing, can be succesfully performed using 95% confidence intervals relative to the mean sampling time; (3) fuzzy modeling returned better classification results for recoverable segments, while the statistical approach performed better in classifying non-recoverable segments. All three methods proposed in this work decreased their performance when the amount of missing data was increased in the test datasets.

Multi-stage modeling using fuzzy multi-criteria feature selection to improve survival prediction of ICU septic shock patients

In many binary medical classification problems, the cost of misclassifying one category is higher than the other, and in these applications it is desirable to employ a classifier with selective sensitivity or specificity. This work explores the utility of a fuzzy multi-criteria function for performance evaluation during knowledge-based medical classification and prediction. The method presented here uses fuzzy optimization to combine the sensitivity, specificity, and accuracy of classification as goals in a single objective function. This approach is used to assign flexible goals, which can be used to maximize the outcome in terms of each one of the goals. The proposed approach significantly increases the sensitivity and the specificity while maintaining or increasing accuracy. The versatility of the method is further exploited in a multi-model approach, using individual structures of multi-objective optimization of sensitivity and specificity separately, and then combining their outcomes through a decision-making module. Among various medical benefits derived from applying this technique, the divergent feature sets selected by high sensitivity and specificity models lend insight into factors more integrally connected to what causes risk of death for patients.

Disease-based Modeling to Predict Fluid Response in Intensive Care Units

OBJECTIVE To compare general and disease-based modeling for fluid resuscitation and vasopressor use in intensive care units. METHODS Retrospective cohort study involving 2944 adult medical and surgical intensive care unit (ICU) patients receiving fluid resuscitation. Within this cohort there were two disease-based groups, 802 patients with a diagnosis of pneumonia, and 143 patients with a diagnosis of pancreatitis. Fluid resuscitation either progressing to subsequent vasopressor administration or not was used as the primary outcome variable to compare general and disease-based modeling. RESULTS Patients with pancreatitis, pneumonia and the general group all shared three common predictive features as core variables, arterial base excess, lactic acid and platelets. Patients with pneumonia also had non-invasive systolic blood pressure and white blood cells added to the core model, and pancreatitis patients additionally had temperature. Disease-based models had significantly higher values of AUC (p < 0.05) than the general group (0.82 ± 0.02 for pneumonia and 0.83 ± 0.03 for pancreatitis vs. 0.79 ± 0.02 for general patients). CONCLUSIONS Disease-based predictive modeling reveals a different set of predictive variables compared to general modeling and improved performance. Our findings add support to the growing body of evidence advantaging disease specific predictive modeling.

Mortality prediction of septic shock patients using probabilistic fuzzy systems

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.

Fuzzy modeling to predict administration of vasopressors in intensive care unit patients

Vasopressors belong to a powerful class of drugs used in the management of systemic shock in ill patients. The administration of a vasopressor involves the non-trivial process of inserting a central venous catheter. This procedure carries with it inherent risks which are increased when done under urgency such as in the case of unexpected systemic shock. The ability to predict the transition to vasopressor dependence could be expected to improve overall outcomes associated with the procedure. We use three different approaches combining fuzzy modeling with bottom-up (BU), top-town (TD) and ant feature selection (AFS), to classify requirements for vasopressors in shock. We observe that fuzzy models combined with BU feature selection return higher values of sensitivity; fuzzy models with no feature selection and fuzzy models with TD feature selection return higher values of AUC and specificity; features most commonly selected to classify impending use of vasopressores in pancreatitis patients include levels of Sodium and White Blood Cell counts, while for pneumonia patients include levels of Lactid Acid and White Blood Cell Count; and finally, fuzzy models combined with BU and fuzzy models combined with AFS demonstrate the lowest number of selected variables with no significant loss in accuracy.

Predicting intensive care unit readmissions using probabilistic fuzzy systems

We propose the application of probabilistic fuzzy systems (PFS) to model the prediction of early readmission in intensive care unit patients and compare it with the gold-standard method - logistic regression based on the APACHE II score. PFS are characterized by the combination of the linguistic description of the system with the statistical properties of data. On one hand, results point that PFS models perform comparably to the gold-standard method, with AUC values of 0.66±0.03. On the other hand, results also show that PFS models use a significant lower number of variables which, from the clinical practice point of view, suggests improved gains in terms of simplicity.