scholarly journals A comparison of logistic regression models with alternative machine learning methods to predict the risk of in-hospital mortality in emergency medical admissions via external validation

2018 ◽  
Vol 26 (1) ◽  
pp. 34-44 ◽  
Author(s):  
Muhammad Faisal ◽  
Andy Scally ◽  
Robin Howes ◽  
Kevin Beatson ◽  
Donald Richardson ◽  
...  

We compare the performance of logistic regression with several alternative machine learning methods to estimate the risk of death for patients following an emergency admission to hospital based on the patients’ first blood test results and physiological measurements using an external validation approach. We trained and tested each model using data from one hospital ( n = 24,696) and compared the performance of these models in data from another hospital ( n = 13,477). We used two performance measures – the calibration slope and area under the receiver operating characteristic curve. The logistic model performed reasonably well – calibration slope: 0.90, area under the receiver operating characteristic curve: 0.847 compared to the other machine learning methods. Given the complexity of choosing tuning parameters of these methods, the performance of logistic regression with transformations for in-hospital mortality prediction was competitive with the best performing alternative machine learning methods with no evidence of overfitting.

2020 ◽  
Vol 31 (6) ◽  
pp. 1348-1357 ◽  
Author(s):  
Ibrahim Sandokji ◽  
Yu Yamamoto ◽  
Aditya Biswas ◽  
Tanima Arora ◽  
Ugochukwu Ugwuowo ◽  
...  

BackgroundTimely prediction of AKI in children can allow for targeted interventions, but the wealth of data in the electronic health record poses unique modeling challenges.MethodsWe retrospectively reviewed the electronic medical records of all children younger than 18 years old who had at least two creatinine values measured during a hospital admission from January 2014 through January 2018. We divided the study population into derivation, and internal and external validation cohorts, and used five feature selection techniques to select 10 of 720 potentially predictive variables from the electronic health records. Model performance was assessed by the area under the receiver operating characteristic curve in the validation cohorts. The primary outcome was development of AKI (per the Kidney Disease Improving Global Outcomes creatinine definition) within a moving 48-hour window. Secondary outcomes included severe AKI (stage 2 or 3), inpatient mortality, and length of stay.ResultsAmong 8473 encounters studied, AKI occurred in 516 (10.2%), 207 (9%), and 27 (2.5%) encounters in the derivation, and internal and external validation cohorts, respectively. The highest-performing model used a machine learning-based genetic algorithm, with an overall receiver operating characteristic curve in the internal validation cohort of 0.76 [95% confidence interval (CI), 0.72 to 0.79] for AKI, 0.79 (95% CI, 0.74 to 0.83) for severe AKI, and 0.81 (95% CI, 0.77 to 0.86) for neonatal AKI. To translate this prediction model into a clinical risk-stratification tool, we identified high- and low-risk threshold points.ConclusionsUsing various machine learning algorithms, we identified and validated a time-updated prediction model of ten readily available electronic health record variables to accurately predict imminent AKI in hospitalized children.


2018 ◽  
Vol 129 (4) ◽  
pp. 675-688 ◽  
Author(s):  
Samir Kendale ◽  
Prathamesh Kulkarni ◽  
Andrew D. Rosenberg ◽  
Jing Wang

AbstractEditor’s PerspectiveWhat We Already Know about This TopicWhat This Article Tells Us That Is NewBackgroundHypotension is a risk factor for adverse perioperative outcomes. Machine-learning methods allow large amounts of data for development of robust predictive analytics. The authors hypothesized that machine-learning methods can provide prediction for the risk of postinduction hypotension.MethodsData was extracted from the electronic health record of a single quaternary care center from November 2015 to May 2016 for patients over age 12 that underwent general anesthesia, without procedure exclusions. Multiple supervised machine-learning classification techniques were attempted, with postinduction hypotension (mean arterial pressure less than 55 mmHg within 10 min of induction by any measurement) as primary outcome, and preoperative medications, medical comorbidities, induction medications, and intraoperative vital signs as features. Discrimination was assessed using cross-validated area under the receiver operating characteristic curve. The best performing model was tuned and final performance assessed using split-set validation.ResultsOut of 13,323 cases, 1,185 (8.9%) experienced postinduction hypotension. Area under the receiver operating characteristic curve using logistic regression was 0.71 (95% CI, 0.70 to 0.72), support vector machines was 0.63 (95% CI, 0.58 to 0.60), naive Bayes was 0.69 (95% CI, 0.67 to 0.69), k-nearest neighbor was 0.64 (95% CI, 0.63 to 0.65), linear discriminant analysis was 0.72 (95% CI, 0.71 to 0.73), random forest was 0.74 (95% CI, 0.73 to 0.75), neural nets 0.71 (95% CI, 0.69 to 0.71), and gradient boosting machine 0.76 (95% CI, 0.75 to 0.77). Test set area for the gradient boosting machine was 0.74 (95% CI, 0.72 to 0.77).ConclusionsThe success of this technique in predicting postinduction hypotension demonstrates feasibility of machine-learning models for predictive analytics in the field of anesthesiology, with performance dependent on model selection and appropriate tuning.


2021 ◽  
pp. 1-8
Author(s):  
Sydney R. Rooney ◽  
Evan L. Reynolds ◽  
Mousumi Banerjee ◽  
Sara K. Pasquali ◽  
John R. Charpie ◽  
...  

Abstract Background: Cardiac intensivists frequently assess patient readiness to wean off mechanical ventilation with an extubation readiness trial despite it being no more effective than clinician judgement alone. We evaluated the utility of high-frequency physiologic data and machine learning for improving the prediction of extubation failure in children with cardiovascular disease. Methods: This was a retrospective analysis of clinical registry data and streamed physiologic extubation readiness trial data from one paediatric cardiac ICU (12/2016-3/2018). We analysed patients’ final extubation readiness trial. Machine learning methods (classification and regression tree, Boosting, Random Forest) were performed using clinical/demographic data, physiologic data, and both datasets. Extubation failure was defined as reintubation within 48 hrs. Classifier performance was assessed on prediction accuracy and area under the receiver operating characteristic curve. Results: Of 178 episodes, 11.2% (N = 20) failed extubation. Using clinical/demographic data, our machine learning methods identified variables such as age, weight, height, and ventilation duration as being important in predicting extubation failure. Best classifier performance with this data was Boosting (prediction accuracy: 0.88; area under the receiver operating characteristic curve: 0.74). Using physiologic data, our machine learning methods found oxygen saturation extremes and descriptors of dynamic compliance, central venous pressure, and heart/respiratory rate to be of importance. The best classifier in this setting was Random Forest (prediction accuracy: 0.89; area under the receiver operating characteristic curve: 0.75). Combining both datasets produced classifiers highlighting the importance of physiologic variables in determining extubation failure, though predictive performance was not improved. Conclusion: Physiologic variables not routinely scrutinised during extubation readiness trials were identified as potential extubation failure predictors. Larger analyses are necessary to investigate whether these markers can improve clinical decision-making.


2021 ◽  
Vol 8 ◽  
Author(s):  
Tuo Guo ◽  
Zhuo Fang ◽  
Guifang Yang ◽  
Yang Zhou ◽  
Ning Ding ◽  
...  

Background: Acute aortic dissection is a potentially fatal cardiovascular disorder associated with high mortality. However, current predictive models show a limited ability to efficiently and flexibly detect this mortality risk, and have been unable to discover a relationship between the mortality rate and certain variables. Thus, this study takes an artificial intelligence approach, whereby clinical data-driven machine learning was utilized to predict the in-hospital mortality of acute aortic dissection.Methods: Patients diagnosed with acute aortic dissection between January 2015 to December 2018 were voluntarily enrolled from the Second Xiangya Hospital of Central South University in the study. The diagnosis was defined by magnetic resonance angiography or computed tomography angiography, with an onset time of the symptoms being within 14 days. The analytical variables included demographic characteristics, physical examination, symptoms, clinical condition, laboratory results, and treatment strategies. The machine learning algorithms included logistic regression, decision tree, K nearest neighbor, Gaussian naive bayes, and extreme gradient boost (XGBoost). Evaluation of the predictive performance of the models was mainly achieved using the area under the receiver operating characteristic curve. SHapley Additive exPlanation was also implemented to interpret the final prediction model.Results: A total of 1,344 acute aortic dissection patients were recruited, including 1,071 (79.7%) patients in the survivor group and 273 (20.3%) patients in non-survivor group. The extreme gradient boost model was found to be the most effective model with the greatest area under the receiver operating characteristic curve (0.927, 95% CI: 0.860–0.968). The three most significant aspects of the extreme gradient boost importance matrix plot were treatment, type of acute aortic dissection, and ischemia-modified albumin levels. In the SHapley Additive exPlanation summary plot, medical treatment, type A acute aortic dissection, and higher ischemia-modified albumin level were shown to increase the risk of hospital-based mortality.


2020 ◽  
Vol 58 (6) ◽  
pp. 1130-1136
Author(s):  
Umberto Benedetto ◽  
Shubhra Sinha ◽  
Matt Lyon ◽  
Arnaldo Dimagli ◽  
Tom R Gaunt ◽  
...  

Abstract OBJECTIVES Interest in the clinical usefulness of machine learning for risk prediction has bloomed recently. Cardiac surgery patients are at high risk of complications and therefore presurgical risk assessment is of crucial relevance. We aimed to compare the performance of machine learning algorithms over traditional logistic regression (LR) model to predict in-hospital mortality following cardiac surgery. METHODS A single-centre data set of prospectively collected information from patients undergoing adult cardiac surgery from 1996 to 2017 was split into 70% training set and 30% testing set. Prediction models were developed using neural network, random forest, naive Bayes and retrained LR based on features included in the EuroSCORE. Discrimination was assessed using area under the receiver operating characteristic curve, and calibration analysis was undertaken using the calibration belt method. Model calibration drift was assessed by comparing Goodness of fit χ2 statistics observed in 2 equal bins from the testing sample ordered by procedure date. RESULTS A total of 28 761 cardiac procedures were performed during the study period. The in-hospital mortality rate was 2.7%. Retrained LR [area under the receiver operating characteristic curve 0.80; 95% confidence interval (CI) 0.77–0.83] and random forest model (0.80; 95% CI 0.76–0.83) showed the best discrimination. All models showed significant miscalibration. Retrained LR proved to have the weakest calibration drift. CONCLUSIONS Our findings do not support the hypothesis that machine learning methods provide advantage over LR model in predicting operative mortality after cardiac surgery.


2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Yang Mi ◽  
Pengfei Qu ◽  
Na Guo ◽  
Ruimiao Bai ◽  
Jiayi Gao ◽  
...  

Abstract Background For most women who have had a previous cesarean section, vaginal birth after cesarean section (VBAC) is a reasonable and safe choice, but which will increase the risk of adverse outcomes such as uterine rupture. In order to reduce the risk, we evaluated the factors that may affect VBAC and and established a model for predicting the success rate of trial of the labor after cesarean section (TOLAC). Methods All patients who gave birth at Northwest Women’s and Children’s Hospital from January 2016 to December 2018, had a history of cesarean section and voluntarily chose the TOLAC were recruited. Among them, 80% of the population was randomly assigned to the training set, while the remaining 20% were assigned to the external validation set. In the training set, univariate and multivariate logistic regression models were used to identify indicators related to successful TOLAC. A nomogram was constructed based on the results of multiple logistic regression analysis, and the selected variables included in the nomogram were used to predict the probability of successfully obtaining TOLAC. The area under the receiver operating characteristic curve was used to judge the predictive ability of the model. Results A total of 778 pregnant women were included in this study. Among them, 595 (76.48%) successfully underwent TOLAC, whereas 183 (23.52%) failed and switched to cesarean section. In multi-factor logistic regression, parity = 1, pre-pregnancy BMI < 24 kg/m2, cervical score ≥ 5, a history of previous vaginal delivery and neonatal birthweight < 3300 g were associated with the success of TOLAC. The area under the receiver operating characteristic curve in the prediction and validation models was 0.815 (95% CI: 0.762–0.854) and 0.730 (95% CI: 0.652–0.808), respectively, indicating that the nomogram prediction model had medium discriminative power. Conclusion The TOLAC was useful to reducing the cesarean section rate. Being primiparous, not overweight or obese, having a cervical score ≥ 5, a history of previous vaginal delivery or neonatal birthweight < 3300 g were protective indicators. In this study, the validated model had an approving predictive ability.


2020 ◽  
Author(s):  
Jun Ke ◽  
Yiwei Chen ◽  
Xiaoping Wang ◽  
Zhiyong Wu ◽  
qiongyao Zhang ◽  
...  

Abstract BackgroundThe purpose of this study is to identify the risk factors of in-hospital mortality in patients with acute coronary syndrome (ACS) and to evaluate the performance of traditional regression and machine learning prediction models.MethodsThe data of ACS patients who entered the emergency department of Fujian Provincial Hospital from January 1, 2017 to March 31, 2020 for chest pain were retrospectively collected. The study used univariate and multivariate logistic regression analysis to identify risk factors for in-hospital mortality of ACS patients. The traditional regression and machine learning algorithms were used to develop predictive models, and the sensitivity, specificity, and receiver operating characteristic curve were used to evaluate the performance of each model.ResultsA total of 7810 ACS patients were included in the study, and the in-hospital mortality rate was 1.75%. Multivariate logistic regression analysis found that age and levels of D-dimer, cardiac troponin I, N-terminal pro-B-type natriuretic peptide (NT-proBNP), lactate dehydrogenase (LDH), high-density lipoprotein (HDL) cholesterol, and calcium channel blockers were independent predictors of in-hospital mortality. The study found that the area under the receiver operating characteristic curve of the models developed by logistic regression, gradient boosting decision tree (GBDT), random forest, and support vector machine (SVM) for predicting the risk of in-hospital mortality were 0.963, 0.960, 0.963, and 0.959, respectively. Feature importance evaluation found that NT-proBNP, LDH, and HDL cholesterol were top three variables that contribute the most to the prediction performance of the GBDT model and random forest model.ConclusionsThe predictive model developed using logistic regression, GBDT, random forest, and SVM algorithms can be used to predict the risk of in-hospital death of ACS patients. Based on our findings, we recommend that clinicians focus on monitoring the changes of NT-proBNP, LDH, and HDL cholesterol, as this may improve the clinical outcomes of ACS patients.


2021 ◽  
Vol 9 (B) ◽  
pp. 1561-1564
Author(s):  
Ngakan Ketut Wira Suastika ◽  
Ketut Suega

Introduction: Coronavirus disease 2019 (Covid-19) can cause coagulation parameters abnormalities such as an increase of D-dimer levels especially in severe cases. The purpose of this study is to determine the differences of D-dimer levels in severe cases of Covid-19 who survived and non-survived and determine the optimal cut-off value of D-dimer levels to predict in-hospital mortality. Method: Data were obtained from confirmed Covid-19 patients who were treated from June to September 2020. The Mann-Whitney U test was used to determine differences of D-dimer levels in surviving and non-surviving patients. The optimal cut-off value and area under the curve (AUC) of the D-dimer level in predicting mortality were obtained by the receiver operating characteristic curve (ROC) method. Results: A total of 80 patients were recruited in this study. Levels of D-dimer were significantly higher in non-surviving patients (median 3.346 mg/ml; minimum – maximum: 0.939 – 50.000 mg/ml) compared to surviving patients (median 1.201 mg/ml; minimum – maximum: 0.302 – 29.425 mg/ml), p = 0.012. D-dimer levels higher than 1.500 mg/ml are the optimal cut-off value for predicting mortality in severe cases of Covid-19 with a sensitivity of 80.0%; specificity of 64.3%; and area under the curve of 0.754 (95% CI 0.586 - 0.921; p = 0.010). Conclusions: D-dimer levels can be used as a predictor of mortality in severe cases of Covid-19.


2021 ◽  
Author(s):  
Tao Zhong ◽  
Zian Zhuang ◽  
Xiaoli Dong ◽  
Ka Hing Wong ◽  
Wing Tak Wong ◽  
...  

BACKGROUND Tuberculosis (TB) is a pandemic, being one of the top 10 causes of death and the main cause of death from a single source of infection. Drug-induced liver injury (DILI) is the most common and serious side effect during the treatment of TB. OBJECTIVE We aim to predict the status of liver injury in patients with TB at the clinical treatment stage. METHODS We designed an interpretable prediction model based on the XGBoost algorithm and identified the most robust and meaningful predictors of the risk of TB-DILI on the basis of clinical data extracted from the Hospital Information System of Shenzhen Nanshan Center for Chronic Disease Control from 2014 to 2019. RESULTS In total, 757 patients were included, and 287 (38%) had developed TB-DILI. Based on values of relative importance and area under the receiver operating characteristic curve, machine learning tools selected patients’ most recent alanine transaminase levels, average rate of change of patients’ last 2 measures of alanine transaminase levels, cumulative dose of pyrazinamide, and cumulative dose of ethambutol as the best predictors for assessing the risk of TB-DILI. In the validation data set, the model had a precision of 90%, recall of 74%, classification accuracy of 76%, and balanced error rate of 77% in predicting cases of TB-DILI. The area under the receiver operating characteristic curve score upon 10-fold cross-validation was 0.912 (95% CI 0.890-0.935). In addition, the model provided warnings of high risk for patients in advance of DILI onset for a median of 15 (IQR 7.3-27.5) days. CONCLUSIONS Our model shows high accuracy and interpretability in predicting cases of TB-DILI, which can provide useful information to clinicians to adjust the medication regimen and avoid more serious liver injury in patients.


Sign in / Sign up

Export Citation Format

Share Document