Predictive Factors for Pneumonia Onset After Cardiac Surgery in Rio de Janeiro, Brazil

Objective.To develop a predictive system for the occurrence of nosocomial pneumonia in patients who had cardiac surgery performed.Design.Retrospective cohort study.Setting.Two cardiologic tertiary care hospitals in Rio de Janeiro, Brazil.Patients.Between June 2000 and August 2002, there were 1,158 consecutive patients who had complex heart surgery performed. Patients older than 18 years who survived the first 48 postoperative hours were included in the study. The occurrence of pneumonia was diagnosed through active surveillance by an infectious diseases specialist according to the following criteria: the presence of new infiltrate on a radiograph in association with purulent sputum and either fever or leukocytosis until day 10 after cardiac surgery. Predictive models were built on the basis of logistic regression analysis and classification and regression tree (CART) analysis. The original data set was divided randomly into 2 parts, one used to construct the models (ie, “test sample”) and the other used for validation (ie, “validation sample”).Results.The area under the receiver–operating characteristic (ROC) curve was 69% for the logistic regression model and 76% for the CART model. Considering a probability greater than 7% to be predictive of pneumonia for both models, sensitivity was higher for the logistic regression models, compared with the CART models (64% vs 56%). However, the CART models had a higher specificity (92% vs 70%) and global accuracy (90% vs 70%) than the logistic regression models. Both models showed good performance, based on the 2-graph ROC, considering that 84.6% and 84.3% of the predictions obtained by regression and CART analyses were regarded as valid.Conclusion.Although our findings are preliminary, the predictive models we created showed fairly good specificity and fair sensitivity.

Download Full-text

Association Between Opioid Use and Diabetes in Patients With Ankle Fracture Repair

Foot & Ankle International ◽

10.1177/10711007211058157 ◽

2021 ◽

pp. 107110072110581

Author(s):

Wenye Song ◽

Naohiro Shibuya ◽

Daniel C. Jupiter

Keyword(s):

Diabetes Mellitus ◽

Logistic Regression ◽

Ankle Fracture ◽

Regression Models ◽

Fracture Repair ◽

Opioid Use ◽

Data Set ◽

Opioid Prescription ◽

Logistic Regression Models ◽

Patients With Diabetes

Background: Ankle fractures in patients with diabetes mellitus have long been recognized as a challenge to practicing clinicians. Ankle fracture patients with diabetes may experience prolonged healing, higher risk of hardware failure, an increased risk of wound dehiscence and infection, and higher pain scores pre- and postoperatively, compared to patients without diabetes. However, the duration of opioid use among this patient cohort has not been previously evaluated. The purpose of this study is to retrospectively compare the time span of opioid utilization between ankle fracture patients with and without diabetes mellitus. Methods: We conducted a retrospective cohort study using our institution’s TriNetX database. A total of 640 ankle fracture patients were included in the analysis, of whom 73 had diabetes. All dates of opioid use for each patient were extracted from the data set, including the first and last date of opioid prescription. Descriptive analysis and logistic regression models were employed to explore the differences in opioid use between patients with and without diabetes after ankle fracture repair. A 2-tailed P value of .05 was set as the threshold for statistical significance. Results: Logistic regression models revealed that patients with diabetes are less likely to stop using opioids within 90 days, or within 180 days, after repair compared to patients without diabetes. Female sex, neuropathy, and prefracture opioid use are also associated with prolonged opioid use after ankle fracture repair. Conclusion: In our study cohort, ankle fracture patients with diabetes were more likely to require prolonged opioid use after fracture repair. Level of Evidence: Level III, prognostic.

Download Full-text

Predicting Fusarium Head Blight Epidemics with Boosted Regression Trees

Phytopathology ◽

10.1094/phyto-10-13-0273-r ◽

2014 ◽

Vol 104 (7) ◽

pp. 702-714 ◽

Cited By ~ 22

Author(s):

D. A. Shah ◽

E. D. De Wolf ◽

P. A. Paul ◽

L. V. Madden

Keyword(s):

Logistic Regression ◽

Relative Humidity ◽

Fusarium Head Blight ◽

Regression Models ◽

Boosted Regression Trees ◽

Misclassification Rate ◽

Head Blight ◽

Data Set ◽

Logistic Regression Models ◽

Daily Relative Humidity

Predicting major Fusarium head blight (FHB) epidemics allows for the judicious use of fungicides in suppressing disease development. Our objectives were to investigate the utility of boosted regression trees (BRTs) for predictive modeling of FHB epidemics in the United States, and to compare the predictive performances of the BRT models with those of logistic regression models we had developed previously. The data included 527 FHB observations from 15 states over 26 years. BRTs were fit to a training data set of 369 FHB observations, in which FHB epidemics were classified as either major (severity ≥ 10%) or non-major (severity < 10%), linked to a predictor matrix consisting of 350 weather-based variables and categorical variables for wheat type (spring or winter), presence or absence of corn residue, and cultivar resistance. Predictive performance was estimated on a test (holdout) data set consisting of the remaining 158 observations. BRTs had a misclassification rate of 0.23 on the test data, which was 31% lower than the average misclassification rate over 15 logistic regression models we had presented earlier. The strongest predictors were generally one of mean daily relative humidity, mean daily temperature, and the number of hours in which the temperature was between 9 and 30°C and relative humidity ≥ 90% simultaneously. Moreover, the predicted risk of major epidemics increased substantially when mean daily relative humidity rose above 70%, which is a lower threshold than previously modeled for most plant pathosystems. BRTs led to novel insights into the weather–epidemic relationship.

Download Full-text

Cardiac Surgical Outcome Prediction by Blood Pressure Variability Indices Poincaré plot and Coefficient of Variation: an Observational Study

10.21203/rs.2.15887/v1 ◽

2019 ◽

Author(s):

Senthil Packiasabapathy K ◽

Varesh Prasad ◽

Valluvan Rangasamy ◽

David Popok ◽

Xinling Xu ◽

...

Keyword(s):

Blood Pressure ◽

Renal Failure ◽

Logistic Regression ◽

Cardiac Surgery ◽

Coefficient Of Variation ◽

Blood Pressure Variability ◽

Regression Models ◽

Outcome Prediction ◽

Prediction Ability ◽

Logistic Regression Models

Abstract Background Recent literature suggests a significant association between blood pressure variability (BPV) and postoperative outcomes after cardiac surgery. However, its outcome prediction ability remains unclear. Current prediction models use static preoperative patient factors. We aimed to test the performance of Poincaré plots and coefficient of variation (CV) independently by measuring intraoperative BP variability.Methods In this retrospective, observational, cohort study, 3687 adult patients undergoing cardiac surgery from 2008 to 2013 were included. Poincaré plots from BP data and descriptors SD1, SD2 by ellipse fitting technique were computed. The outcomes analyzed were the 30-day mortality and postoperative renal failure. Logistic regression models adjusted for preoperative and surgical factors were constructed to evaluate the association between BPV parameters and outcomes. C-statistics were used to analyse the predictive ability.Results Analysis found that, 99 (2.7%) patients died within 30 days and 105 (2.8%) patients suffered from in-hospital renal failure. Logistic regression models including BPV parameters (SD1, SD2 and CV) performed poorly in predicting postoperative 30-day mortality and renal failure. They did not add any significant value to the conventional prediction model.Conclusions We demonstrate the feasibility of applying Poincaré plots for BP variability analysis. Patient comorbid conditions and other preoperative factors are still the gold standard for outcome prediction. Future directions include analysis of dynamic parameters such as complexity of physiological signals in identifying high risk patients and tailoring management accordingly.

Download Full-text

Cardiac Surgical Outcome Prediction by Blood Pressure Variability Indices Poincaré plot and Coefficient of Variation: an Observational Study

10.21203/rs.2.15887/v3 ◽

2020 ◽

Author(s):

Senthil Packiasabapathy K ◽

Varesh Prasad ◽

Valluvan Rangasamy ◽

David Popok ◽

Xinling Xu ◽

...

Keyword(s):

Blood Pressure ◽

Renal Failure ◽

Logistic Regression ◽

Cardiac Surgery ◽

Coefficient Of Variation ◽

Blood Pressure Variability ◽

Regression Models ◽

Outcome Prediction ◽

Logistic Regression Models ◽

C Statistic

Abstract Background Recent literature suggests a significant association between blood pressure variability (BPV) and postoperative outcomes after cardiac surgery. However, its outcome prediction ability remains unclear. Current prediction models use static preoperative patient factors. We explored the ability of Poincaré plots and coefficient of variation (CV) by measuring intraoperative BPV in predicting adverse outcomes. Methods In this retrospective, observational, cohort study, 3687 adult patients (> 18 years) undergoing cardiac surgery requiring cardio-pulmonary bypass from 2008 to 2014 were included. Blood pressure variability was computed by Poincare plots and CV. Standard descriptors (SD) SD1, SD2 were measured with Poincare plots by ellipse fitting technique. The outcomes analyzed were the 30-day mortality and postoperative renal failure. Logistic regression models adjusted for preoperative and surgical factors were constructed to evaluate the association between BPV parameters and outcomes. C-statistics were used to analyse the predictive ability. Results Analysis found that, 99 (2.7%) patients died within 30 days and 105 (2.8%) patients suffered from in-hospital renal failure. Logistic regression models including BPV parameters (standard descriptors from Poincare plots and CV) performed poorly in predicting postoperative 30-day mortality and renal failure [Concordance(C)-Statistic around 0.5]. They did not add any significant value to the standard STS risk score [C-statistic: STS alone 0.7, STS + BPV parmeters 0.7]. Conclusions In conclusion, BP variability computed from Poincare plots and CV were not predictive of mortality and renal failure in cardiac surgical patients. Patient comorbid conditions and other preoperative factors are still the gold standard for outcome prediction. Future directions include analysis of dynamic parameters such as complexity of physiological signals in identifying high risk patients and tailoring management accordingly.

Download Full-text

A Model-Based Approach to Preplanting Risk Assessment for Gray Leaf Spot of Maize

Phytopathology ◽

10.1094/phyto.2004.94.12.1350 ◽

2004 ◽

Vol 94 (12) ◽

pp. 1350-1357 ◽

Cited By ~ 43

Author(s):

P. A. Paul ◽

G. P. Munkvold

Keyword(s):

Risk Assessment ◽

Logistic Regression ◽

Leaf Spot ◽

Regression Models ◽

Soil Surface ◽

Strong Relationship ◽

Gray Leaf Spot ◽

Classification And Regression Tree ◽

Management Decision ◽

Logistic Regression Models

Risk assessment models for gray leaf spot of maize, caused by Cercospora zeae-maydis, were developed using preplanting site and maize genotype data as predictors. Disease severity at the dough/dent plant growth stage was categorized into classes and used as the response variable. Logistic regression and classification and regression tree (CART) modeling approaches were used to predict severity classes as a function of planting date (PD), amount of maize soil surface residue (SR), cropping sequence, genotype maturity and gray leaf spot resistance (GLSR) ratings, and longitude (LON). Models were development using 332 cases collected between 1998 and 2001. Thirty cases collected in 2002 were used to validate the models. Preplanting data showed a strong relationship with late-season gray leaf spot severity classes. The most important predictors were SR, PD, GLSR, and LON. Logistic regression models correctly classified 60 to 70% of the validation cases, whereas the CART models correctly classified 57 to 77% of these cases. Cases misclassified by the CART models were mostly due to overestimation, whereas the logistic regression models tended to misclassify cases by underestimation. Both the CART and logistic regression models have potential as management decision-making tools. Early quantitative assessment of gray leaf spot risk would allow for more sound management decisions being made when warranted.

Download Full-text

Is Greater Than 0.5 MAC Inhalational Agent Use Post-Bypass Related to Need for Inotropic and/or Vasoconstrictor Support?

Hearts ◽

10.3390/hearts2020017 ◽

2021 ◽

Vol 2 (2) ◽

pp. 213-223

Author(s):

Tara A. Lenk ◽

Carlos E. Guerra-Londono ◽

Thomas E. Graul ◽

Marc A. Murinson ◽

Prabhdeep K. Hehar ◽

...

Keyword(s):

Logistic Regression ◽

Cardiac Surgery ◽

Propensity Score ◽

Regression Models ◽

Independent Predictor ◽

Care Hospital ◽

Elective Cardiac Surgery ◽

Logistic Regression Models ◽

Adjusted Analysis ◽

Inhalational Agent

Background and Aims: We hypothesized that maintaining a patient on moderate–high doses of potent inhalational agent for greater than 30 min during the post-bypass period would be an independent predictor of initiation and usage of either inotropic and/or vasopressor infusions. Setting and Design: This study is a retrospective design and approved by the institutional review board. The setting was a single-center, academic tertiary care hospital in Detroit, Michigan. Materials and Methods: Three-hundred, ninety-seven elective cardiac surgery patients were identified for chart review. Electronic medical records were reviewed to collect demographics and perioperative data. Statistics used include a propensity score regression adjusted analysis utilizing logistic regression models and a multivariable model. Results: A propensity score regression adjusted analysis was performed and then applied in both univariate and multivariate logistic regression models with a p value of <0.05 reaching statistical significance. Fifty-six percent of the participants had an exposure of greater than 30 min of a minimum alveolar concentration of isoflurane greater than 0.5 (ETISO ≥ 0.5MAC, 30 min) in the post-bypass period. After adjusting for propensity score, this was found to be a significant predictor of inotrope and/or vasoconstrictor use post-bypass (OR 2.49, 95% CI 1.15–5.38, p = 0.021). In the multivariate model, pulmonary hypertension (OR 5.9; 95% CI 1.33–26.28; p = 0.02), Euroscore II (2.73; 95% CI 1.35–5.5; p = 0.005), and cardiopulmonary bypass hours (OR 1.86; 95% CI 1.02–3.4; p = 0.042) emerged as significant. Conclusions: This study showed that an ETISO ≥ 0.5MAC, 30 min exposure during the immediate post-bypass period during elective cardiac surgery was an independent predictor of a patient being started on inotrope or vasoconstrictor infusions. Further research should consider a prospective design and examine depth of anesthesia during the post-bypass period.

Download Full-text

Bootstrap internal validation command for predictive logistic regression models

The Stata Journal Promoting communications on statistics and Stata ◽

10.1177/1536867x211025836 ◽

2021 ◽

Vol 21 (2) ◽

pp. 498-509

Author(s):

B. M. Fernandez-Felix ◽

E. García-Esquinas ◽

A. Muriel ◽

A. Royuela ◽

J. Zamora

Keyword(s):

Logistic Regression ◽

Regression Model ◽

Predictive Model ◽

Performance Measures ◽

Predictive Models ◽

Regression Models ◽

Logistic Regression Model ◽

Model Performance ◽

Internal Validation ◽

Logistic Regression Models

Overfitting is a common problem in the development of predictive models. It leads to an optimistic estimation of apparent model performance. Internal validation using bootstrapping techniques allows one to quantify the optimism of a predictive model and provide a more realistic estimate of its performance measures. Our objective is to build an easy-to-use command, bsvalidation, aimed to perform a bootstrap internal validation of a logistic regression model.

Download Full-text

Some Evidence On The Secondary Market Trading Of Syndicated Loans

Journal of Business & Economics Research (JBER) ◽

10.19030/jber.v8i5.717 ◽

2010 ◽

Vol 8 (5) ◽

Author(s):

Peter J. Nigro ◽

Jonathan D. Jones ◽

Murat Aydogdu

Keyword(s):

Logistic Regression ◽

Regression Models ◽

Stock Exchange ◽

Secondary Market ◽

Syndicated Loans ◽

Leveraged Buyouts ◽

Font Size ◽

Data Set ◽

Logistic Regression Models ◽

Normal Text

An important recent development in U. S. capital markets is the tremendous growth in the secondary market trading of syndicated loans. This paper uses a unique trading data set for syndicated loans over the period 1997 to 2003 to empirically investigate two major issues. First, we present a statistical overview of the recent growth in the secondary market trading of syndicated loans. Second, we examine the determinants of which syndicated loans are most likely to be traded in the secondary market using binomial logistic regression models. We find that syndicated loans that are larger, have longer maturities, are underwritten by larger syndicates, and are used for debt repayment, takeovers, and leveraged buyouts are more likely to be traded. Lender reputation plays an important role as well, with loans originated by very active lenders more likely to be traded.  We also find that syndicated loans made to borrowers with only senior debt ratings are more likely to be traded in the secondary market than loans made to borrowers with both a debt rating and equity that trades in a stock exchange. This result most likely reflects the growing demand of institutional investors for the higher yields of levered and highly levered syndicated loans made to riskier opaque borrowers with less available market information.

Download Full-text

Using self-supervised feature learning to improve the use of pulse oximeter signals to predict paediatric hospitalization

Wellcome Open Research ◽

10.12688/wellcomeopenres.17148.1 ◽

2021 ◽

Vol 6 ◽

pp. 248

Author(s):

Paul Mwaniki ◽

Timothy Kamanu ◽

Samuel Akech ◽

Dustin Dunsmuir ◽

J. Mark Ansermino ◽

...

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Deep Learning ◽

Pulse Oximeter ◽

Regression Models ◽

Data Sets ◽

Learning Models ◽

Data Set ◽

Logistic Regression Models ◽

End To End

Background: The success of many machine learning applications depends on knowledge about the relationship between the input data and the task of interest (output), hindering the application of machine learning to novel tasks. End-to-end deep learning, which does not require intermediate feature engineering, has been recommended to overcome this challenge but end-to-end deep learning models require large labelled training data sets often unavailable in many medical applications. In this study, we trained machine learning models to predict paediatric hospitalization given raw photoplethysmography (PPG) signals obtained from a pulse oximeter. We trained self-supervised learning (SSL) for automatic feature extraction from PPG signals and assessed the utility of SSL in initializing end-to-end deep learning models trained on a small labelled data set with the aim of predicting paediatric hospitalization.Methods: We compared logistic regression models fitted using features extracted using SSL with end-to-end deep learning models initialized either randomly or using weights from the SSL model. We also compared the performance of SSL models trained on labelled data alone (n=1,031) with SSL trained using both labelled and unlabelled signals (n=7,578). Results: The SSL model trained on both labelled and unlabelled PPG signals produced features that were more predictive of hospitalization compared to the SSL model trained on labelled PPG only (AUC of logistic regression model: 0.78 vs 0.74). The end-to-end deep learning model had an AUC of 0.80 when initialized using the SSL model trained on all PPG signals, 0.77 when initialized using SSL trained on labelled data only, and 0.73 when initialized randomly. Conclusions: This study shows that SSL can improve the classification of PPG signals by either extracting features required by logistic regression models or initializing end-to-end deep learning models. Furthermore, SSL can leverage larger unlabelled data sets to improve performance of models fitted using small labelled data sets.

Download Full-text

Cardiac Surgical Outcome Prediction by Blood Pressure Variability Indices Poincaré plot and Coefficient of Variation: an Observational Study

10.21203/rs.2.15887/v4 ◽

2020 ◽

Author(s):

Senthil Packiasabapathy K ◽

Varesh Prasad ◽

Valluvan Rangasamy ◽

David Popok ◽

Xinling Xu ◽

...

Keyword(s):

Blood Pressure ◽

Renal Failure ◽

Logistic Regression ◽

Cardiac Surgery ◽

Coefficient Of Variation ◽

Blood Pressure Variability ◽

Regression Models ◽

Outcome Prediction ◽

Logistic Regression Models ◽

C Statistic

Abstract Background Recent literature suggests a significant association between blood pressure variability (BPV) and postoperative outcomes after cardiac surgery. However, its outcome prediction ability remains unclear. Current prediction models use static preoperative patient factors. We explored the ability of Poincaré plots and coefficient of variation (CV) by measuring intraoperative BPV in predicting adverse outcomes. Methods In this retrospective, observational, cohort study, 3687 adult patients (> 18 years) undergoing cardiac surgery requiring cardio-pulmonary bypass from 2008 to 2014 were included. Blood pressure variability was computed by Poincare plots and CV. Standard descriptors (SD) SD1, SD2 were measured with Poincare plots by ellipse fitting technique. The outcomes analyzed were the 30-day mortality and postoperative renal failure. Logistic regression models adjusted for preoperative and surgical factors were constructed to evaluate the association between BPV parameters and outcomes. C-statistics were used to analyse the predictive ability. Results Analysis found that, 99 (2.7%) patients died within 30 days and 105 (2.8%) patients suffered from in-hospital renal failure. Logistic regression models including BPV parameters (standard descriptors from Poincare plots and CV) performed poorly in predicting postoperative 30-day mortality and renal failure [Concordance(C)-Statistic around 0.5]. They did not add any significant value to the standard STS risk score [C-statistic: STS alone 0.7, STS + BPV parmeters 0.7]. Conclusions In conclusion, BP variability computed from Poincare plots and CV were not predictive of mortality and renal failure in cardiac surgical patients. Patient comorbid conditions and other preoperative factors are still the gold standard for outcome prediction. Future directions include analysis of dynamic parameters such as complexity of physiological signals in identifying high risk patients and tailoring management accordingly.

Download Full-text