Predicting in-hospital mortality of patients with febrile neutropenia using machine learning models.
Ontology highlight
ABSTRACT: Background
Febrile neutropenia (FN) has been associated with high mortality among adults with cancer. Current systems for early detection of inpatient FN mortality are based on scoring indexes that require intensive physicians' subjective evaluation.Objective
In this study, we leveraged machine learning techniques to build a FN mortality risk evaluation tool focused on FN admissions without physicians' subjective evaluation.Methods
We used the National Inpatient Sample and Nationwide Inpatient Sample (NIS) that included mortality data among adult inpatients who were diagnosed with FN during a hospital admission. Machine learning techniques that we compared included linear models (ridge logistic regression and linear support vector machine) and non-linear models (gradient boosting tree and neural network). The primary outcome for this study was death among individuals with a recorded FN admission. Model comparison was evaluated based on areas under the receiver operating characteristic curve (AUROC) and model performance was estimated using 30 % test set created via stratified split.Results
Our analysis detected 126,013 adult admissions within the NIS data that were diagnosed with FN, among which 5,856 were declared as deceased (4.6 %). Our machine learning results demonstrate linear models and non-linear models achieved areas under the receiver operating characteristic (AUROC) around 92 % in survival prediction.Conclusions
We developed machine learning models that do not require physicians' subjective evaluation for FN mortality risk prediction.
SUBMITTER: Du X
PROVIDER: S-EPMC7255942 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description: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.
| S-EPMC8484712 | biostudies-literature
Project description:The present work aims to identify the predictors of COVID-19 in-hospital mortality testing a set of Machine Learning Techniques (MLTs), comparing their ability to predict the outcome of interest. The model with the best performance will be used to identify in-hospital mortality predictors and to build an in-hospital mortality prediction tool. The study involved patients with COVID-19, proved by PCR test, admitted to the "Ospedali Riuniti Padova Sud" COVID-19 referral center in the Veneto region, Italy. The algorithms considered were the Recursive Partition Tree (RPART), the Support Vector Machine (SVM), the Gradient Boosting Machine (GBM), and Random Forest. The resampled performances were reported for each MLT, considering the sensitivity, specificity, and the Receiving Operative Characteristic (ROC) curve measures. The study enrolled 341 patients. The median age was 74 years, and the male gender was the most prevalent. The Random Forest algorithm outperformed the other MLTs in predicting in-hospital mortality, with a ROC of 0.84 (95% C.I. 0.78-0.9). Age, together with vital signs (oxygen saturation and the quick SOFA) and lab parameters (creatinine, AST, lymphocytes, platelets, and hemoglobin), were found to be the strongest predictors of in-hospital mortality. The present work provides insights for the prediction of in-hospital mortality of COVID-19 patients using a machine-learning algorithm.
| S-EPMC8147079 | biostudies-literature
Project description:BackgroundBesides the classic logistic regression analysis, non-parametric methods based on machine learning techniques such as random forest are presently used to generate predictive models. The aim of this study was to evaluate random forest mortality prediction models in haemodialysis patients.MethodsData were acquired from incident haemodialysis patients between 1995 and 2015. Prediction of mortality at 6 months, 1 year and 2 years of haemodialysis was calculated using random forest and the accuracy was compared with logistic regression. Baseline data were constructed with the information obtained during the initial period of regular haemodialysis. Aiming to increase accuracy concerning baseline information of each patient, the period of time used to collect data was set at 30, 60 and 90 days after the first haemodialysis session.ResultsThere were 1571 incident haemodialysis patients included. The mean age was 62.3 years and the average Charlson comorbidity index was 5.99. The mortality prediction models obtained by random forest appear to be adequate in terms of accuracy [area under the curve (AUC) 0.68-0.73] and superior to logistic regression models (ΔAUC 0.007-0.046). Results indicate that both random forest and logistic regression develop mortality prediction models using different variables.ConclusionsRandom forest is an adequate method, and superior to logistic regression, to generate mortality prediction models in haemodialysis patients.
| S-EPMC8247746 | biostudies-literature
Project description:Whereas transcatheter aortic valve implantation (TAVI) has become the gold standard for aortic valve stenosis treatment in high-risk patients, it has recently been extended to include intermediate risk patients. However, the mortality rate at 5 years is still elevated. The aim of the present study was to develop a novel machine learning (ML) approach able to identify the best predictors of 5-year mortality after TAVI among several clinical and echocardiographic variables, which may improve the long-term prognosis. We retrospectively enrolled 471 patients undergoing TAVI. More than 80 pre-TAVI variables were collected and analyzed through different feature selection processes, which allowed for the identification of several variables with the highest predictive value of mortality. Different ML models were compared. Multilayer perceptron resulted in the best performance in predicting mortality at 5 years after TAVI, with an area under the curve, positive predictive value, and sensitivity of 0.79, 0.73, and 0.71, respectively. We presented an ML approach for the assessment of risk factors for long-term mortality after TAVI to improve clinical prognosis. Fourteen potential predictors were identified with the organic mitral regurgitation (myxomatous or calcific degeneration of the leaflets and/or annulus) which showed the highest impact on 5 years mortality.
| S-EPMC8072967 | biostudies-literature
Project description:ObjectiveTo predict hospital admission at the time of ED triage using patient history in addition to information collected at triage.MethodsThis retrospective study included all adult ED visits between March 2014 and July 2017 from one academic and two community emergency rooms that resulted in either admission or discharge. A total of 972 variables were extracted per patient visit. Samples were randomly partitioned into training (80%), validation (10%), and test (10%) sets. We trained a series of nine binary classifiers using logistic regression (LR), gradient boosting (XGBoost), and deep neural networks (DNN) on three dataset types: one using only triage information, one using only patient history, and one using the full set of variables. Next, we tested the potential benefit of additional training samples by training models on increasing fractions of our data. Lastly, variables of importance were identified using information gain as a metric to create a low-dimensional model.ResultsA total of 560,486 patient visits were included in the study, with an overall admission risk of 29.7%. Models trained on triage information yielded a test AUC of 0.87 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.88) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on patient history yielded an AUC of 0.86 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.87) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on the full set of variables yielded an AUC of 0.91 for LR (95% CI 0.91-0.91), 0.92 for XGBoost (95% CI 0.92-0.93) and 0.92 for DNN (95% CI 0.92-0.92). All algorithms reached maximum performance at 50% of the training set or less. A low-dimensional XGBoost model built on ESI level, outpatient medication counts, demographics, and hospital usage statistics yielded an AUC of 0.91 (95% CI 0.91-0.91).ConclusionMachine learning can robustly predict hospital admission using triage information and patient history. The addition of historical information improves predictive performance significantly compared to using triage information alone, highlighting the need to incorporate these variables into prediction models.
| S-EPMC6054406 | biostudies-literature
Project description:IntroductionHospital readmission rates are an indicator of the health care quality provided by hospitals. Applying machine learning (ML) to a hospital readmission database offers the potential to identify patients at the highest risk for readmission. However, few studies applied ML methods to predict hospital readmission. This study sought to assess ML as a tool to develop prediction models for all-cause 90-day hospital readmission for dental patients.MethodsUsing the 2013 Nationwide Readmissions Database (NRD), the study identified 9260 cases for all-cause 90-day index admission for dental patients. Five ML classification algorithms including decision tree, logistic regression, support vector machine, k-nearest neighbors, and artificial neural network (ANN) were implemented to build predictive models. The model performance was estimated and compared by using area under the receiver operating characteristic curve (AUC), and accuracy, sensitivity, specificity, and precision.ResultsHospital readmission within 90 days occurred in 1746 cases (18.9%). Total charges, number of diagnosis, age, number of chronic conditions, length of hospital stays, number of procedures, primary expected payer, and severity of illness emerged as the top eight important features in all-cause 90-day hospital readmission. All models had similar performance with ANN (AUC = 0.743) slightly outperforming the rest.ConclusionThis study demonstrates a potential annual saving of over $500 million if all of the 90-day readmission cases could be prevented for 21 states represented in the NRD. Among the methods used, the prediction model built by ANN exhibited the best performance. Further testing using ANN and other methods can help to assess important readmission risk factors and to target interventions to those at the greatest risk.
| S-EPMC7822935 | biostudies-literature
Project description:Bone is the most common site of distant metastasis from malignant tumors, with the highest prevalence observed in breast and prostate cancers. Such bone metastases (BM) cause many painful skeletal-related events, such as severe bone pain, pathological fractures, spinal cord compression, and hypercalcemia, with adverse effects on life quality. Many bone-targeting agents developed based on the current understanding of BM onset's molecular mechanisms dull these adverse effects. However, only a few studies investigated potential predictors of high risk for developing BM, despite such knowledge being critical for early interventions to prevent or delay BM. This work proposes a computational network-based pipeline that incorporates a ML/DL component to predict BM development. Based on the proposed pipeline we constructed several machine learning models. The deep neural network (DNN) model exhibited the highest prediction accuracy (AUC of 92.11%) using the top 34 featured genes ranked by betweenness centrality scores. We further used an entirely separate, "external" TCGA dataset to evaluate the robustness of this DNN model and achieved sensitivity of 85%, specificity of 80%, positive predictive value of 78.10%, negative predictive value of 80%, and AUC of 85.78%. The result shows the models' way of learning allowed it to zoom in on the featured genes that provide the added benefit of the model displaying generic capabilities, that is, to predict BM for samples from different primary sites. Furthermore, existing experimental evidence provides confidence that about 50% of the 34 hub genes have BM-related functionality, which suggests that these common genetic markers provide vital insight about BM drivers. These findings may prompt the transformation of such a method into an artificial intelligence (AI) diagnostic tool and direct us towards mechanisms that underlie metastasis to bone events.
| S-EPMC8631472 | biostudies-literature
Project description:Objective The goal of this study was to evaluate the efficacy of machine learning (ML) techniques in predicting survival for chordoma patients in comparison with the standard Cox proportional hazards (CoxPH) model. Methods Using a Surveillance, Epidemiology, and End Results database of consecutive newly diagnosed chordoma cases between January 2000 and December 2018, we created and validated three ML survival models as well as a traditional CoxPH model in this population-based cohort study. Randomly, the dataset was divided into training and validation datasets. Tuning hyperparameters on the training dataset involved a 1000-iteration random search with fivefold cross-validation. Concordance index (C-index), Brier score, and integrated Brier score were used to evaluate the performance of the model. The receiver operating characteristic (ROC) curves, calibration curves, and area under the ROC curves (AUC) were used to assess the reliability of the models by predicting 5- and 10-year survival probabilities. Results A total of 724 chordoma patients were divided into training (n = 508) and validation (n = 216) cohorts. Cox regression identified nine significant prognostic factors (p < 0.05). ML models showed superior performance over CoxPH model, with DeepSurv having the highest C-index (0.795) and the best discrimination for 5- and 10-year survival (AUC 0.84 and 0.88). Calibration curves revealed strong correlation between DeepSurv predictions and actual survival. Risk stratification by DeepSurv model effectively discriminated high- and low-risk groups (p < 0.01). The optimized DeepSurv model was implemented into a web application for clinical use that can be found at https://hust-chengp-ml-chordoma-app-19rjyr.streamlitapp.com/. Conclusion ML algorithms based on time-to-event results are effective in chordoma prediction, with DeepSurv having the best discrimination performance and calibration. Supplementary Information The online version contains supplementary material available at 10.1186/s13018-023-04105-9.
| S-EPMC10474690 | biostudies-literature
Project description:AimsThis study aimed to review the performance of machine learning (ML) methods compared with conventional statistical models (CSMs) for predicting readmission and mortality in patients with heart failure (HF) and to present an approach to formally evaluate the quality of studies using ML algorithms for prediction modelling.Methods and resultsFollowing Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we performed a systematic literature search using MEDLINE, EPUB, Cochrane CENTRAL, EMBASE, INSPEC, ACM Library, and Web of Science. Eligible studies included primary research articles published between January 2000 and July 2020 comparing ML and CSMs in mortality and readmission prognosis of initially hospitalized HF patients. Data were extracted and analysed by two independent reviewers. A modified CHARMS checklist was developed in consultation with ML and biostatistics experts for quality assessment and was utilized to evaluate studies for risk of bias. Of 4322 articles identified and screened by two independent reviewers, 172 were deemed eligible for a full-text review. The final set comprised 20 articles and 686 842 patients. ML methods included random forests (n = 11), decision trees (n = 5), regression trees (n = 3), support vector machines (n = 9), neural networks (n = 12), and Bayesian techniques (n = 3). CSMs included logistic regression (n = 16), Cox regression (n = 3), or Poisson regression (n = 3). In 15 studies, readmission was examined at multiple time points ranging from 30 to 180 day readmission, with the majority of studies (n = 12) presenting prediction models for 30 day readmission outcomes. Of a total of 21 time-point comparisons, ML-derived c-indices were higher than CSM-derived c-indices in 16 of the 21 comparisons. In seven studies, mortality was examined at 9 time points ranging from in-hospital mortality to 1 year survival; of these nine, seven reported higher c-indices using ML. Two of these seven studies reported survival analyses utilizing random survival forests in their ML prediction models. Both reported higher c-indices when using ML compared with CSMs. A limitation of studies using ML techniques was that the majority were not externally validated, and calibration was rarely assessed. In the only study that was externally validated in a separate dataset, ML was superior to CSMs (c-indices 0.913 vs. 0.835).ConclusionsML algorithms had better discrimination than CSMs in most studies aiming to predict risk of readmission and mortality in HF patients. Based on our review, there is a need for external validation of ML-based studies of prediction modelling. We suggest that ML-based studies should also be evaluated using clinical quality standards for prognosis research. Registration: PROSPERO CRD42020134867.
| S-EPMC7835549 | biostudies-literature
Project description:BackgroundClinical laboratories have traditionally used a single critical value for thrombocytopenic events. This system, however, could lead to inaccuracies and inefficiencies, causing alarm fatigue and compromised patient safety.ObjectivesThis study shows how machine learning (ML) models can provide auxiliary information for more accurate identification of critical thrombocytopenic patients when compared with the traditional notification system.Research designA total of 50,505 patients' platelet count and other 26 additional laboratory datasets of each thrombocytopenic event were used to build prediction models. Conventional logistic regression and ML methods, including random forest (RF), artificial neural network, stochastic gradient descent (SGD), naive Bayes, support vector machine, and decision tree, were applied to build different models and evaluated.ResultsModels using logistic regression [area under the curve (AUC)=0.842], RF (AUC=0.859), artificial neural network (AUC=0.867), or SGD (AUC=0.826) achieved the desired average AUC>0.80. The highest positive predictive value was obtained by the SGD model in the testing data (72.2%), whereas overall, the RF model showed higher sensitivity and total positive predictions in both the training and testing data and outperformed other models. The positive 2-day mortality predictive rate of RF methods is as high as 46.1%-significantly higher than using the traditional notification system at only 14.8% [χ2(1)=81.66, P<0.001].ConclusionsThis study demonstrates a data-driven ML approach showing a significantly more accurate 2-day mortality prediction after a critical thrombocytopenic event, which can reinforce the accuracy of the traditional notification system.
| S-EPMC7993911 | biostudies-literature