Reliability and Clinical Utility of Machine Learning to Predict Stroke Prognosis: Comparison with Logistic Regression.
Ontology highlight
ABSTRACT:
SUBMITTER: Jang SK
PROVIDER: S-EPMC7568985 | biostudies-literature | 2020 Sep
REPOSITORIES: biostudies-literature
Publications
Reliability and Clinical Utility of Machine Learning to Predict Stroke Prognosis: Comparison with Logistic Regression.
Jang Su-Kyeong SK Chang Jun Young JY Lee Ji Sung JS Lee Eun-Jae EJ Kim Yong-Hwan YH Han Jung Hoon JH Chang Dae-Il DI Cho Han Jin HJ Cha Jae-Kwan JK Yu Kyung Ho KH Jung Jin-Man JM Ahn Seong Hwan SH Kim Dong-Eog DE Sohn Sung-Il SI Lee Ju Hun JH Park Kyung-Pil KP Kwon Sun U SU Kim Jong S JS Kang Dong-Wha DW
Journal of stroke 20200929 3
Similar Datasets
Project description:This study investigated whether machine learning (ML) has better predictive accuracy than logistic regression analysis (LR) for gait independence at discharge in subacute stroke patients (n = 843) who could not walk independently at admission. We developed prediction models using LR and five ML algorithms-specifically, the decision tree (DT), support vector machine, artificial neural network, ensemble learning, and k-nearest neighbor methods. Functional Independence Measure sub-items were used to evaluate the ability to walk independently. Model predictive accuracies were evaluated using areas under receiver operating characteristic curves (AUCs) as well as accuracy, precision, recall, F1 score, and specificity. The AUC for DT (0.812) was significantly lower than those for the other algorithms (p < 0.01); however, the AUC for LR (0.895) did not differ significantly from those for the other models (0.893-0.903). Other performance metrics showed no substantial differences between LR and ML algorithms. In conclusion, the DT algorithm had significantly low predictive accuracy, and LR showed no significant difference in predictive accuracy compared with the other ML algorithms. As its predictive accuracy is similar to that of ML, LR can continue to be used for predicting the prognosis of gait independence, with additional advantages of being easily understandable and manually computable.
| S-EPMC11390880 | biostudies-literature
Project description:BackgroundSepsis is a life-threatening disease associated with a high mortality rate, emphasizing the need for the exploration of novel models to predict the prognosis of this patient population. This study compared the performance of traditional logistic regression and machine learning models in predicting adult sepsis mortality.ObjectiveTo develop an optimum model for predicting the mortality of adult sepsis patients based on comparing traditional logistic regression and machine learning methodology.MethodsRetrospective analysis was conducted on 606 adult sepsis inpatients at our medical center between January 2020 and December 2022, who were randomly divided into training and validation sets in a 7:3 ratio. Traditional logistic regression and machine learning methods were employed to assess the predictive ability of mortality in adult sepsis. Univariate analysis identified independent risk factors for the logistic regression model, while Least Absolute Shrinkage and Selection Operator (LASSO) regression facilitated variable shrinkage and selection for the machine learning model. Among various machine learning models, which included Bagged Tree, Boost Tree, Decision Tree, LightGBM, Naïve Bayes, Nearest Neighbors, Support Vector Machine (SVM), and Random Forest (RF), the one with the maximum area under the curve (AUC) was chosen for model construction. Model validation and comparison with the Sequential Organ Failure Assessment (SOFA) and the Acute Physiology and Chronic Health Evaluation (APACHE) scores were performed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) curves in the validation set.ResultsUnivariate analysis was employed to assess 17 variables, namely gender, history of coronary heart disease (CHD), systolic pressure, white blood cell (WBC), neutrophil count (NEUT), lymphocyte count (LYMP), lactic acid, neutrophil-to-lymphocyte ratio (NLR), red blood cell distribution width (RDW), interleukin-6 (IL-6), prothrombin time (PT), international normalized ratio (INR), fibrinogen (FBI), D-dimer, aspartate aminotransferase (AST), total bilirubin (Tbil), and lung infection. Significant differences (p < 0.05) between the survival and non-survival groups were observed for these variables. Utilizing stepwise regression with the "backward" method, independent risk factors, including systolic pressure, lactic acid, NLR, RDW, IL-6, PT, and Tbil, were identified. These factors were then incorporated into a logistic regression model, chosen based on the minimum Akaike Information Criterion (AIC) value (98.65). Machine learning techniques were also applied, and the RF model, demonstrating the maximum Area Under the Curve (AUC) of 0.999, was selected. LASSO regression, employing the lambda.1SE criteria, identified systolic pressure, lactic acid, NEUT, RDW, IL6, INR, and Tbil as variables for constructing the RF model, validated through ten-fold cross-validation. For model validation and comparison with traditional logistic models, SOFA, and APACHE scoring.ConclusionBased on deep machine learning principles, the RF model demonstrates advantages over traditional logistic regression models in predicting adult sepsis prognosis. The RF model holds significant potential for clinical surveillance and interventions to enhance outcomes for sepsis patients.
| S-EPMC11743956 | biostudies-literature
Project description:(1) Medical research has shown an increasing interest in machine learning, permitting massive multivariate data analysis. Thus, we developed drug intoxication mortality prediction models, and compared machine learning models and traditional logistic regression. (2) Categorized as drug intoxication, 8,937 samples were extracted from the Korea Centers for Disease Control and Prevention (2008-2017). We trained, validated, and tested each model through data and compared their performance using three measures: Brier score, calibration slope, and calibration-in-the-large. (3) A chi-square test demonstrated that mortality risk statistically significantly differed according to severity, intent, toxic substance, age, and sex. The multilayer perceptron model (MLP) had the highest area under the curve (AUC), and lowest Brier score in training and validation phases, while the logistic regression model (LR) showed the highest AUC (0.827) and lowest Brier score (0.0307) in the testing phase. MLP also had the second-highest AUC (0.816) and second-lowest Brier score (0.003258) in the testing phase, demonstrating better performance than the decision-making tree model. (4) Given the complexity of choosing tuning parameters, LR proved competitive when using medical datasets, which require strict accuracy.
| S-EPMC7037603 | biostudies-literature
Project description:Cell annotation is a crucial methodological component to interpreting single cell and spatial omics data. These approaches were developed for single cell analysis but are often biased, manually curated and yet unproven in spatial omics. Here we apply a stemness model for assessing oncogenic states to single cell and spatial omic cancer datasets. This one-class logistic regression machine learning algorithm is used to extract transcriptomic features from non-transformed stem cells to identify dedifferentiated cell states in tumors. We found this method identifies single cell states in metastatic tumor cell populations without the requirement of cell annotation. This machine learning model identified stem-like cell populations not identified in single cell or spatial transcriptomic analysis using existing methods. For the first time, we demonstrate the application of a ML tool across five emerging spatial transcriptomic and proteomic technologies to identify oncogenic stem-like cell types in the tumor microenvironment.
| S-EPMC10683105 | biostudies-literature
Project description:BackgroundOverweight or obesity is a primary health concern that leads to a significant burden of noncommunicable disease and threatens national productivity and economic growth. Given the complexity of the etiology of overweight or obesity, machine learning (ML) algorithms offer a promising alternative approach in disentangling interdependent factors for predicting overweight or obesity status.ObjectiveThis study examined the performance of 3 ML algorithms in comparison with logistic regression (LR) to predict overweight or obesity status among working adults in Malaysia.MethodsUsing data from 16,860 participants (mean age 34.2, SD 9.0 years; n=6904, 41% male; n=7048, 41.8% with overweight or obesity) in the Malaysia's Healthiest Workplace by AIA Vitality 2019 survey, predictor variables, including sociodemographic characteristics, job characteristics, health and weight perceptions, and lifestyle-related factors, were modeled using the extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM) algorithms, as well as LR, to predict overweight or obesity status based on a BMI cutoff of 25 kg/m2.ResultsThe area under the receiver operating characteristic curve was 0.81 (95% CI 0.79-0.82), 0.80 (95% CI 0.79-0.81), 0.80 (95% CI 0.78-0.81), and 0.78 (95% CI 0.77-0.80) for the XGBoost, RF, SVM, and LR models, respectively. Weight satisfaction was the top predictor, and ethnicity, age, and gender were also consistent predictor variables of overweight or obesity status in all models.ConclusionsBased on multi-domain online workplace survey data, this study produced predictive models that identified overweight or obesity status with moderate to high accuracy. The performance of both ML-based and logistic regression models were comparable when predicting obesity among working adults in Malaysia.
| S-EPMC9773027 | biostudies-literature
Project description:AimsTo compare the performance of logistic regression and machine learning methods in predicting postoperative delirium (POD) in elderly patients.MethodThis was a retrospective study of perioperative medical data from patients undergoing non-cardiac and non-neurology surgery over 65 years old from January 2014 to August 2019. Forty-six perioperative variables were used to predict POD. A traditional logistic regression and five machine learning models (Random Forest, GBM, AdaBoost, XGBoost, and a stacking ensemble model) were compared by the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, and precision.ResultsIn total, 29,756 patients were enrolled, and the incidence of POD was 3.22% after variable screening. AUCs were 0.783 (0.765-0.8) for the logistic regression method, 0.78 for random forest, 0.76 for GBM, 0.74 for AdaBoost, 0.73 for XGBoost, and 0.77 for the stacking ensemble model. The respective sensitivities for the 6 aforementioned models were 74.2%, 72.2%, 76.8%, 63.6%, 71.6%, and 67.4%. The respective specificities for the 6 aforementioned models were 70.7%, 99.8%, 96.5%, 98.8%, 96.5%, and 96.1%. The respective precision values for the 6 aforementioned models were 7.8%, 52.3%, 55.6%, 57%, 54.5%, and 56.4%.ConclusionsThe optimal application of the logistic regression model could provide quick and convenient POD risk identification to help improve the perioperative management of surgical patients because of its better sensitivity, fewer variables, and easier interpretability than the machine learning model.
| S-EPMC9804041 | biostudies-literature
Project description:[This corrects the article DOI: 10.1371/journal.pone.0221911.].
| S-EPMC6786577 | biostudies-literature
Project description:BackgroundIschemic Stroke (IS) stands as a leading cause of mortality and disability globally, with an anticipated increase in IS-related fatalities by 2030. Despite therapeutic advancements, many patients still lack effective interventions, underscoring the need for improved prognostic assessment tools. Machine Learning (ML) models have emerged as promising tools for predicting stroke prognosis, surpassing traditional methods in accuracy and speed.ObjectiveThe aim of this study was to develop and validate ML algorithms for predicting the 6-month prognosis of patients with Acute Cerebral Infarction, using clinical data from two medical centers in China, and to assess the feasibility of implementing Explainable ML in clinical settings.MethodsA retrospective observational cohort study was conducted involving 398 patients diagnosed with Acute Cerebral Infarction from January 2023 to February 2024. The dataset included demographic information, medical histories, clinical evaluations, and laboratory results. Six ML models were constructed: Logistic Regression, Naive Bayes, Support Vector Machine (SVM), Random Forest, XGBoost, and AdaBoost. Model performance was evaluated using the Area Under the Receiver Operating Characteristic curve (AUC), sensitivity, specificity, predictive values, and F1 score, with five-fold cross-validation to ensure robustness.ResultsThe training set, identified key variables associated with stroke prognosis, including hypertension, diabetes, and smoking history. The SVM model demonstrated exceptional performance, with an AUC of 0.9453 on the training set and 0.9213 on the validation set. A Nomogram based on Logistic Regression was developed for visualizing prognostic risk, incorporating factors such as the National Institutes of Health Stroke Scale (NIHSS) score, Barthel Index (BI), Watanabe Drinking Test (KWST) score, Platelet Distribution Width (PDW), and others. Our models showed high predictive accuracy and stability across both datasets.ConclusionThis study presents a robust ML approach for predicting stroke prognosis, with the SVM model and Nomogram providing valuable tools for clinical decision-making. By incorporating advanced ML techniques, we enhance the precision of prognostic assessments and offer a theoretical and practical framework for clinical application.
| S-EPMC11913711 | biostudies-literature
Project description:Bronchopulmonary dysplasia (BPD) is the most prevalent and clinically significant complication of prematurity. Accurate identification of at-risk infants would enable ongoing intervention to improve outcomes. Although postnatal exposures are known to affect an infant's likelihood of developing BPD, most existing BPD prediction models do not allow risk to be evaluated at different time points, and/or are not suitable for use in ethno-diverse populations. A comprehensive approach to developing clinical prediction models avoids assumptions as to which method will yield the optimal results by testing multiple algorithms/models. We compared the performance of machine learning and logistic regression models in predicting BPD/death. Our main cohort included infants <33 weeks' gestational age (GA) admitted to a Canadian Neonatal Network site from 2016 to 2018 (n = 9,006) with all analyses repeated for the <29 weeks' GA subcohort (n = 4,246). Models were developed to predict, on days 1, 7, and 14 of admission to neonatal intensive care, the composite outcome of BPD/death prior to discharge. Ten-fold cross-validation and a 20% hold-out sample were used to measure area under the curve (AUC). Calibration intercepts and slopes were estimated by regressing the outcome on the log-odds of the predicted probabilities. The model AUCs ranged from 0.811 to 0.886. Model discrimination was lower in the <29 weeks' GA subcohort (AUCs 0.699-0.790). Several machine learning models had a suboptimal calibration intercept and/or slope (k-nearest neighbor, random forest, artificial neural network, stacking neural network ensemble). The top-performing algorithms will be used to develop multinomial models and an online risk estimator for predicting BPD severity and death that does not require information on ethnicity.
| S-EPMC8688959 | biostudies-literature
Project description:BackgroundWhile there is increasing interest in identifying pregnancies at risk for adverse outcome, existing prediction models have not adequately assessed population-based risks, and have been based on conventional regression methods. The objective of the current study was to identify predictors of fetal growth abnormalities using logistic regression and machine learning methods, and compare diagnostic properties in a population-based sample of infants.MethodsData for 30,705 singleton infants born between 2009 and 2014 to mothers resident in Nova Scotia, Canada was obtained from the Nova Scotia Atlee Perinatal Database. Primary outcomes were small (SGA) and large for gestational age (LGA). Maternal characteristics pre-pregnancy and at 26 weeks were studied as predictors. Logistic regression and select machine learning methods were used to build the models, stratified by parity. Area under the curve was used to compare the models; relative importance of predictors was compared qualitatively.Results7.9% and 13.5% of infants were SGA and LGA, respectively; 48.6% of births were to primiparous women and 51.4% were to multiparous women. Prediction of SGA and LGA was poor to fair (area under the curve 60-75%) and improved with increasing parity and pregnancy information. Smoking, previous low birthweight infant, and gestational weight gain were important predictors for SGA; pre-pregnancy body mass index, gestational weight gain, and previous macrosomic infant were the strongest predictors for LGA.ConclusionsThe machine learning methods used in this study did not offer any advantage over logistic regression in the prediction of fetal growth abnormalities. Prediction accuracy for SGA and LGA based on maternal information is poor for primiparous women and fair for multiparous women.
| S-EPMC6094446 | biostudies-literature