Machine learning to predict mortality after rehabilitation among patients with severe stroke.
Ontology highlight
ABSTRACT:
SUBMITTER: Scrutinio D
PROVIDER: S-EPMC7674405 | biostudies-literature | 2020 Nov
REPOSITORIES: biostudies-literature
Publications
Machine learning to predict mortality after rehabilitation among patients with severe stroke.
Scrutinio Domenico D Ricciardi Carlo C Donisi Leandro L Losavio Ernesto E Battista Petronilla P Guida Pietro P Cesarelli Mario M Pagano Gaetano G D'Addio Giovanni G
Scientific reports 20201118 1
Stroke is among the leading causes of death and disability worldwide. Approximately 20-25% of stroke survivors present severe disability, which is associated with increased mortality risk. Prognostication is inherent in the process of clinical decision-making. Machine learning (ML) methods have gained increasing popularity in the setting of biomedical research. The aim of this study was twofold: assessing the performance of ML tree-based algorithms for predicting three-year mortality model in 12 ...[more]
Similar Datasets
Project description:Age acceleration (Age-A) is a useful tool that is able to predict a broad range of health outcomes. It is necessary to determine DNA methylation levels to estimate it, and it is known that Age-A is influenced by environmental, lifestyle, and vascular risk factors (VRF). The aim of this study is to estimate the contribution of these easily measurable factors to Age-A in patients with cerebrovascular disease (CVD), using different machine learning (ML) approximations, and try to find a more accessible model able to predict Age-A. We studied a CVD cohort of 952 patients with information about VRF, lifestyle habits, and target organ damage. We estimated Age-A using Hannum's epigenetic clock, and trained six different models to predict Age-A: a conventional linear regression model, four ML models (elastic net regression (EN), K-Nearest neighbors, random forest, and support vector machine models), and one deep learning approximation (multilayer perceptron (MLP) model). The best-performing models were EN and MLP; although, the predictive capability was modest (R2 0.358 and 0.378, respectively). In conclusion, our results support the influence of these factors on Age-A; although, they were not enough to explain most of its variability.
| S-EPMC9917369 | biostudies-literature
Project description:Machine learning (ML), one aspect of artificial intelligence (AI), involves computer algorithms that train themselves. They have been widely applied in the healthcare domain. However, many trained ML algorithms operate as 'black boxes', producing a prediction from input data without a clear explanation of their workings. Non-transparent predictions are of limited utility in many clinical domains, where decisions must be justifiable. Here, we apply class-contrastive counterfactual reasoning to ML to demonstrate how specific changes in inputs lead to different predictions of mortality in people with severe mental illness (SMI), a major public health challenge. We produce predictions accompanied by visual and textual explanations as to how the prediction would have differed given specific changes to the input. We apply it to routinely collected data from a mental health secondary care provider in patients with schizophrenia. Using a data structuring framework informed by clinical knowledge, we captured information on physical health, mental health, and social predisposing factors. We then trained an ML algorithm and other statistical learning techniques to predict the risk of death. The ML algorithm predicted mortality with an area under receiver operating characteristic curve (AUROC) of 0.80 (95% confidence intervals [0.78, 0.82]). We used class-contrastive analysis to produce explanations for the model predictions. We outline the scenarios in which class-contrastive analysis is likely to be successful in producing explanations for model predictions. Our aim is not to advocate for a particular model but show an application of the class-contrastive analysis technique to electronic healthcare record data for a disease of public health significance. In patients with schizophrenia, our work suggests that use or prescription of medications like antidepressants was associated with lower risk of death. Abuse of alcohol/drugs and a diagnosis of delirium were associated with higher risk of death. Our ML models highlight the role of co-morbidities in determining mortality in patients with schizophrenia and the need to manage co-morbidities in these patients. We hope that some of these bio-social factors can be targeted therapeutically by either patient-level or service-level interventions. Our approach combines clinical knowledge, health data, and statistical learning, to make predictions interpretable to clinicians using class-contrastive reasoning. This is a step towards interpretable AI in the management of patients with schizophrenia and potentially other diseases.
| S-EPMC8654849 | biostudies-literature
Project description:Importance:Machine learning algorithms could identify patients with cancer who are at risk of short-term mortality. However, it is unclear how different machine learning algorithms compare and whether they could prompt clinicians to have timely conversations about treatment and end-of-life preferences. Objectives:To develop, validate, and compare machine learning algorithms that use structured electronic health record data before a clinic visit to predict mortality among patients with cancer. Design, Setting, and Participants:Cohort study of 26 525 adult patients who had outpatient oncology or hematology/oncology encounters at a large academic cancer center and 10 affiliated community practices between February 1, 2016, and July 1, 2016. Patients were not required to receive cancer-directed treatment. Patients were observed for up to 500 days after the encounter. Data analysis took place between October 1, 2018, and September 1, 2019. Exposures:Logistic regression, gradient boosting, and random forest algorithms. Main Outcomes and Measures:Primary outcome was 180-day mortality from the index encounter; secondary outcome was 500-day mortality from the index encounter. Results:Among 26 525 patients in the analysis, 1065 (4.0%) died within 180 days of the index encounter. Among those who died, the mean age was 67.3 (95% CI, 66.5-68.0) years, and 500 (47.0%) were women. Among those who were alive at 180 days, the mean age was 61.3 (95% CI, 61.1-61.5) years, and 15 922 (62.5%) were women. The population was randomly partitioned into training (18 567 [70.0%]) and validation (7958 [30.0%]) cohorts at the patient level, and a randomly selected encounter was included in either the training or validation set. At a prespecified alert rate of 0.02, positive predictive values were higher for the random forest (51.3%) and gradient boosting (49.4%) algorithms compared with the logistic regression algorithm (44.7%). There was no significant difference in discrimination among the random forest (area under the receiver operating characteristic curve [AUC], 0.88; 95% CI, 0.86-0.89), gradient boosting (AUC, 0.87; 95% CI, 0.85-0.89), and logistic regression (AUC, 0.86; 95% CI, 0.84-0.88) models (P for comparison = .02). In the random forest model, observed 180-day mortality was 51.3% (95% CI, 43.6%-58.8%) in the high-risk group vs 3.4% (95% CI, 3.0%-3.8%) in the low-risk group; at 500 days, observed mortality was 64.4% (95% CI, 56.7%-71.4%) in the high-risk group and 7.6% (7.0%-8.2%) in the low-risk group. In a survey of 15 oncology clinicians with a 52.1% response rate, 100 of 171 patients (58.8%) who had been flagged as having high risk by the gradient boosting algorithm were deemed appropriate for a conversation about treatment and end-of-life preferences in the upcoming week. Conclusions and Relevance:In this cohort study, machine learning algorithms based on structured electronic health record data accurately identified patients with cancer at risk of short-term mortality. When the gradient boosting algorithm was applied in real time, clinicians believed that most patients who had been identified as having high risk were appropriate for a timely conversation about treatment and end-of-life preferences.
| S-EPMC6822091 | biostudies-literature
Project description:Previous scoring models, such as the Acute Physiologic Assessment and Chronic Health Evaluation II (APACHE II) score, do not adequately predict the mortality of patients receiving mechanical ventilation in the intensive care unit. Therefore, this study aimed to apply machine learning algorithms to improve the prediction accuracy for 30-day mortality of mechanically ventilated patients. The data of 16,940 mechanically ventilated patients were divided into the training-validation (83%, n = 13,988) and test (17%, n = 2952) sets. Machine learning algorithms including balanced random forest, light gradient boosting machine, extreme gradient boost, multilayer perceptron, and logistic regression were used. We compared the area under the receiver operating characteristic curves (AUCs) of machine learning algorithms with those of the APACHE II and ProVent score results. The extreme gradient boost model showed the highest AUC (0.79 (0.77-0.80)) for the 30-day mortality prediction, followed by the balanced random forest model (0.78 (0.76-0.80)). The AUCs of these machine learning models as achieved by APACHE II and ProVent scores were higher than 0.67 (0.65-0.69), and 0.69 (0.67-0.71)), respectively. The most important variables in developing each machine learning model were APACHE II score, Charlson comorbidity index, and norepinephrine. The machine learning models have a higher AUC than conventional scoring systems, and can thus better predict the 30-day mortality of mechanically ventilated patients.
| S-EPMC8157228 | biostudies-literature
Project description:Machine learning (ML) and deep learning (DL) can successfully predict high prevalence events in very large databases (big data), but the value of this methodology for risk prediction in smaller cohorts with uncommon diseases and infrequent events is uncertain. The clinical course of spontaneous coronary artery dissection (SCAD) is variable, and no reliable methods are available to predict mortality. Based on the hypothesis that machine learning (ML) and deep learning (DL) techniques could enhance the identification of patients at risk, we applied a deep neural network to information available in electronic health records (EHR) to predict in-hospital mortality in patients with SCAD. We extracted patient data from the EHR of an extensive urban health system and applied several ML and DL models using candidate clinical variables potentially associated with mortality. We partitioned the data into training and evaluation sets with cross-validation. We estimated model performance based on the area under the receiver-operator characteristics curve (AUC) and balanced accuracy. As sensitivity analyses, we examined results limited to cases with complete clinical information available. We identified 375 SCAD patients of which mortality during the index hospitalization was 11.5%. The best-performing DL algorithm identified in-hospital mortality with AUC 0.98 (95% CI 0.97-0.99), compared to other ML models (P < 0.0001). For prediction of mortality using ML models in patients with SCAD, the AUC ranged from 0.50 with the random forest method (95% CI 0.41-0.58) to 0.95 with the AdaBoost model (95% CI 0.93-0.96), with intermediate performance using logistic regression, decision tree, support vector machine, K-nearest neighbors, and extreme gradient boosting methods. A deep neural network model was associated with higher predictive accuracy and discriminative power than logistic regression or ML models for identification of patients with ACS due to SCAD prone to early mortality.
| S-EPMC8076284 | biostudies-literature
Project description:BACKGROUND:Previous scoring models such as the Acute Physiologic Assessment and Chronic Health Evaluation II (APACHE II) and the Sequential Organ Failure Assessment (SOFA) scoring systems do not adequately predict mortality of patients undergoing continuous renal replacement therapy (CRRT) for severe acute kidney injury. Accordingly, the present study applies machine learning algorithms to improve prediction accuracy for this patient subset. METHODS:We randomly divided a total of 1571 adult patients who started CRRT for acute kidney injury into training (70%, n = 1094) and test (30%, n = 477) sets. The primary output consisted of the probability of mortality during admission to the intensive care unit (ICU) or hospital. We compared the area under the receiver operating characteristic curves (AUCs) of several machine learning algorithms with that of the APACHE II, SOFA, and the new abbreviated mortality scoring system for acute kidney injury with CRRT (MOSAIC model) results. RESULTS:For the ICU mortality, the random forest model showed the highest AUC (0.784 [0.744-0.825]), and the artificial neural network and extreme gradient boost models demonstrated the next best results (0.776 [0.735-0.818]). The AUC of the random forest model was higher than 0.611 (0.583-0.640), 0.677 (0.651-0.703), and 0.722 (0.677-0.767), as achieved by APACHE II, SOFA, and MOSAIC, respectively. The machine learning models also predicted in-hospital mortality better than APACHE II, SOFA, and MOSAIC. CONCLUSION:Machine learning algorithms increase the accuracy of mortality prediction for patients undergoing CRRT for acute kidney injury compared with previous scoring models.
| S-EPMC7006166 | biostudies-literature
Project description:BackgroundSepsis is a leading cause of morbidity and mortality in hospitalized patients. Up to now, there are no well-established longitudinal networks from molecular mechanisms to clinical phenotypes in sepsis. Adding to the problem, about one of the five patients presented with diabetes. For this subgroup, management is difficult, and prognosis is difficult to evaluate.MethodsFrom the three databases, a total of 7,001 patients were enrolled on the basis of sepsis-3 standard and diabetes diagnosis. Input variable selection is based on the result of correlation analysis in a handpicking way, and 53 variables were left. A total of 5,727 records were collected from Medical Information Mart for Intensive Care database and randomly split into a training set and an internal validation set at a ratio of 7:3. Then, logistic regression with lasso regularization, Bayes logistic regression, decision tree, random forest, and XGBoost were conducted to build the predictive model by using training set. Then, the models were tested by the internal validation set. The data from eICU Collaborative Research Database (n = 815) and dtChina critical care database (n = 459) were used to test the model performance as the external validation set.ResultsIn the internal validation set, the accuracy values of logistic regression with lasso regularization, Bayes logistic regression, decision tree, random forest, and XGBoost were 0.878, 0.883, 0.865, 0.883, and 0.882, respectively. Likewise, in the external validation set 1, lasso regularization = 0.879, Bayes logistic regression = 0.877, decision tree = 0.865, random forest = 0.886, and XGBoost = 0.875. In the external validation set 2, lasso regularization = 0.715, Bayes logistic regression = 0.745, decision tree = 0.763, random forest = 0.760, and XGBoost = 0.699.ConclusionThe top three models for internal validation set were Bayes logistic regression, random forest, and XGBoost, whereas the top three models for external validation set 1 were random forest, logistic regression, and Bayes logistic regression. In addition, the top three models for the external validation set 2 were decision tree, random forest, and Bayes logistic regression. Random forest model performed well with the training and three validation sets. The most important features are age, albumin, and lactate.
| S-EPMC9709414 | biostudies-literature
Project description:Abstract Aims The current guidelines recommend aortic valve intervention in patients with severe aortic regurgitation (AR) with the onset of symptoms, left ventricular enlargement, or systolic dysfunction. Recent studies have suggested that we might be missing the window of early intervention in a significant number of patients by following the guidelines. Methods and results The overarching goal was to determine if machine learning (ML)-based algorithms could be trained to identify patients at risk for death from AR independent of aortic valve replacement (AVR). Models were trained with five-fold cross-validation on a dataset of 1035 patients, and performance was reported on an independent dataset of 207 patients. Optimal predictive performance was observed with a conditional random survival forest model. A subset of 19/41 variables was selected for inclusion in the final model. Variable selection was performed with 10-fold cross-validation using random survival forest model. The top variables included were age, body surface area, body mass index, diastolic blood pressure, New York Heart Association class, AVR, comorbidities, ejection fraction, end-diastolic volume, and end-systolic dimension, and the relative variable importance averaged across five splits of cross-validation in each repeat were evaluated. The concordance index for predicting survival of the best-performing model was 0.84 at 1 year, 0.86 at 2 years, and 0.87 overall, respectively. Conclusion Using common echocardiographic parameters and patient characteristics, we successfully trained multiple ML models to predict survival in patients with severe AR. This technique could be applied to identify high-risk patients who would benefit from early intervention, thereby improving patient outcomes. Graphical Abstract Graphical Abstract Overview of the data collection, model processing, and validation [conditional survival forest plot shown for validation in test sample (20%)].
| S-EPMC10232267 | biostudies-literature
Project description:Here we recorded serum proteome profiles of 33 COVID-19 patients admitted to the ICU. We received, for most patients, blood samples just after admission and at two more later timepoints. We focused on serum proteins different in abundance between the group of survivors and non-survivors and observed that a rather small panel of about a dozen proteins were significantly different in abundance between these two groups. The four structurally and functionally related type-3 cystatins AHSG, FETUB, HRG and KNG1 were all more abundant in the survivors. The family of inter-α-trypsin inhibitors, ITIH1, ITIH2, ITIH3 and ITIH4, were all found to be differentially abundant in between survivors and non-survivors, whereby ITIH1 and ITIH2 were more abundant in the survivor group and ITIH3 and ITIH4 more abundant in the non-survivors. ITIH1/ITIH2 and ITIH3/ITIH4 also did show opposite trends in protein abundance during disease progression. This panel of eight proteins, complemented with a few more, may represent a panel for mortality risk assessment and eventually even for treatment, by administration of exogenous proteins possibly aiding survival. Such administration is not unprecedented, as administration of exogenous inter-α-trypsin inhibitors is already used in the treatment of patients with severe sepsis and Kawasaki disease. The mortality risk panel defined here is in excellent agreement with findings in two recent COVID-19 serum proteomics studies on independent cohorts, supporting our findings. This panel may not be unique for COVID-19, as some of the proteins here annotated as mortality risk factors have previously been annotated as mortality markers in aging and in other diseases caused by different pathogens, including bacteria.
2021-07-05 | PXD024707 | Pride
Project description:Objective: We sought to determine sex differences in outcomes in patients with severe stroke who had been admitted to inpatient rehabilitation. Methods: We studied 1,316 patients aged 18 to 99 (mean 72) classified as case-mix groups 0108, 0109, and 0110 of the Medicare case-mix classification system. These groups encompass the most severe strokes. Three outcomes were analyzed: (1) 3-year mortality from admission to rehabilitation; (2) combined outcome of transfer to acute care or death within 90 days from admission to rehabilitation; (3) functional outcome, including proportional recovery in motor functioning and good functional outcome as defined by achievement of a Functional Independence Measure (FIM)-motor score ≥65 points at discharge. Multivariable regression analyses were used to assess sex-difference in each outcome between women and men. The covariates examined included age, marital status, comorbidities, time from stroke onset to rehabilitation admission <30 days, ischemic stroke, dysphagia, neglect, motor FIM score at admission, and cognitive FIM score at admission. Results: Kaplan-Meier estimated 3-year mortality rate was 20.7% in women and 22.0% in men. The crude hazard ratio (HR) of death for women compared with men was 0.94 (95% CI 0.74-1.20). After adjustment for significant covariates, the HR of 3-year mortality was 0.73 (95% CIs 0.56-0.96; p = 0.025). Comorbidity, including diabetes, anemia, coronary artery disease, atrial fibrillation, and chronic obstructive pulmonary disease, significantly increased mortality risk by 49-88%. The incidence of the combined outcome was 8.3% in women and 8.4% in men. The crude HR of the combined end-point for women compared with men was 1.05 (95% CI 0.72-1.53). After adjustment for significant covariates, the HR was 0.95 (95% CIs 0.65-1.40; p = 0.810). Likewise, no significant difference in proportional recovery or in the rate of achievement of a good functional outcome between women and men was observed. Conclusion: Among patients admitted to inpatient rehabilitation after severe stroke, women and men had comparable crude mortality rates at 3 years. After multivariable adjustment, however, women had lower mortality risk. No sex-differences in the risk of being transferred to acute care or dying within 90 days from admission to rehabilitation or in responsiveness to rehabilitation were observed.
| S-EPMC7040356 | biostudies-literature