scholarly journals Building Prediction Models for 30-Day Readmissions Among ICU Patients Using Both Structured and Unstructured Data in Electronic Health Records

2021 ◽  
Author(s):  
Alex Moerschbacher ◽  
Zhe He
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Poor Performance ◽  
Readmission Rates ◽  
Icu Patients ◽  
Increased Risk ◽  
Hospital Deaths ◽  
Poor Outcomes ◽  
Mimic Iii ◽  
Discharge Summaries

ICU readmissions are associated with poor outcomes for patients and poor performance of hospitals. Patients who are re-admitted have an increased risk of in-hospital deaths; hospitals with a higher readmission rate have reduced profitability, due to an increase in cost and reduced payments from Medicare and Medicaid programs. Predicting a patient's likelihood of being readmitted to the ICU can help reduce early discharges, the risk of in-hospital deaths, and help increase profitability. In this study, we built and evaluated multiple machine learning models to predict 30-day readmission rates of ICU patients in the MIMIC-III database. We used both the structured data including demographics, laboratory tests, comorbidities, and unstructured discharge summaries as the predictors and evaluated different combinations of features. The best performing model in this study Logistic Regression achieved an AUROC of 75.7%. This study shows the potential of leveraging machine learning and deep learning for predicting ICU readmissions.

scholarly journals Development and Validation of Unplanned Extubation Prediction Models Using Intensive Care Unit Data: Comparative Machine Learning Study (Preprint)

2020 ◽  
Author(s):  
Sujeong Hur ◽  
Ji Young Min ◽  
Junsang Yoo ◽  
Kyunga Kim ◽  
Chi Ryang Chung ◽  
...  
Keyword(s):  
Machine Learning ◽  
Intensive Care Unit ◽  
Patient Safety ◽  
Intensive Care ◽  
Predictive Value ◽  
Prediction Models ◽  
Support Vector ◽  
Unplanned Extubation ◽  
Electronic Health Record Data ◽  
Icu Patients

BACKGROUND Patient safety in the intensive care unit (ICU) is one of the most critical issues, and unplanned extubation (UE) is considered as the most adverse event for patient safety. Prevention and early detection of such an event is an essential but difficult component of quality care. OBJECTIVE This study aimed to develop and validate prediction models for UE in ICU patients using machine learning. METHODS This study was conducted an academic tertiary hospital in Seoul. The hospital had approximately 2,000 inpatient beds and 120 intensive care unit (ICU) beds. The number of patients, on daily basis, was approximately 9,000 for the out-patient. The number of annual ICU admission was approximately 10,000. We conducted a retrospective study between January 1, 2010 and December 31, 2018. A total of 6,914 extubation cases were included. We developed an unplanned extubation prediction model using machine learning algorithms, which included random forest (RF), logistic regression (LR), artificial neural network (ANN), and support vector machine (SVM). For evaluating the model’s performance, we used area under the receiver operator characteristic curve (AUROC). Sensitivity, specificity, positive predictive value negative predictive value, and F1-score were also determined for each model. For performance evaluation, we also used calibration curve, the Brier score, and the Hosmer-Lemeshow goodness-of-fit statistic. RESULTS Among the 6,914 extubation cases, 248 underwent UE. In the UE group, there were more males than females, higher use of physical restraints, and fewer surgeries. The incidence of UE was more likely to occur during the night shift compared to the planned extubation group. The rate of reintubation within 24 hours and hospital mortality was higher in the UE group. The UE prediction algorithm was developed, and the AUROC for RF was 0.787, for LR was 0.762, for ANN was 0.762, and for SVM was 0.740. CONCLUSIONS We successfully developed and validated machine learning-based prediction models to predict UE in ICU patients using electronic health record data. The best AUROC was 0.787, which was obtained using RF. CLINICALTRIAL N/A

scholarly journals Machine Learning Approach Using Routine Immediate Postoperative Laboratory Values for Predicting Postoperative Mortality

2021 ◽  
Vol 11 (12) ◽  
pp. 1271
Author(s):  
Jaehyeong Cho ◽  
Jimyung Park ◽  
Eugene Jeong ◽  
Jihye Shin ◽  
Sangjeong Ahn ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Prediction Models ◽  
External Validation ◽  
Model Development ◽  
Postoperative Mortality ◽  
Random Forest Model ◽  
Forest Model ◽  
Laboratory Values ◽  
Increased Risk

Background: Several prediction models have been proposed for preoperative risk stratification for mortality. However, few studies have investigated postoperative risk factors, which have a significant influence on survival after surgery. This study aimed to develop prediction models using routine immediate postoperative laboratory values for predicting postoperative mortality. Methods: Two tertiary hospital databases were used in this research: one for model development and another for external validation of the resulting models. The following algorithms were utilized for model development: LASSO logistic regression, random forest, deep neural network, and XGBoost. We built the models on the lab values from immediate postoperative blood tests and compared them with the SASA scoring system to demonstrate their efficacy. Results: There were 3817 patients who had immediate postoperative blood test values. All models trained on immediate postoperative lab values outperformed the SASA model. Furthermore, the developed random forest model had the best AUROC of 0.82 and AUPRC of 0.13, and the phosphorus level contributed the most to the random forest model. Conclusions: Machine learning models trained on routine immediate postoperative laboratory values outperformed previously published approaches in predicting 30-day postoperative mortality, indicating that they may be beneficial in identifying patients at increased risk of postoperative death.

scholarly journals Role of Transitional Care Measures in the Prevention of Readmission After Critical Illness

2017 ◽  
Vol 37 (1) ◽  
pp. e10-e17 ◽  
Author(s):  
Jessica S. Peters
Keyword(s):  
Critical Care ◽  
Critical Illness ◽  
Critical Care Unit ◽  
Transitional Care ◽  
Discharge Planning ◽  
Surgical Care ◽  
Care Needs ◽  
Readmission Rates ◽  
Increased Risk ◽  
Poor Outcomes

Transitioning from the critical care unit to the medical-surgical care area is vital to patients’ recovery and resolution of critical illness. Such transitions are necessary to optimize use of available hospital resources to meet patient care needs. One in 10 patients discharged from the intensive care unit are readmitted to the unit during their hospitalization. Critical care readmission is associated with significant increases in illness acuity, overall length of stay, and health care costs as well as a potential 4-fold increased risk of mortality. Patients with complex illness, multiple comorbid conditions, and a prolonged initial stay in the critical care unit are at an increased risk of being readmitted to the critical care unit and experiencing poor outcomes. Implementing nurse-driven measures that support continuity of care and consistent communication practices such as critical care outreach services, transitional communication tools, discharge planning, and transitional care units improves transitions of patients from the critical care environment and reduces readmission rates.

Hyperchloremia is associated with aute kidney injury in critical ill patients: an analysis of the MIMIC-III database

2020 ◽  
Author(s):  
Jie Gu ◽  
Tingting Zuo ◽  
Qingqing Zhu ◽  
Hui Chen ◽  
Yanbin Chen ◽  
...  
Keyword(s):  
Intensive Care ◽  
Medical Information ◽  
Gastrointestinal Disease ◽  
Kidney Injury ◽  
Cerebral Disease ◽  
Icu Patients ◽  
Increased Risk ◽  
Critical Ill Patients ◽  
Mimic Iii ◽  
Critical Ill

Abstract Objective: Balanced fluid with no critical increase of chloride in serum was recommended in clinic. Whether hyperchloremia could make a difference for intensive care unit (ICU) patients with a higher acute kidney injury (AKI) occurrence remains controversial.Methods: The Medical Information Mart for Intensive Care III (MIMIC-III) database was searched to identify patients hyperchloremia or non-hyperchloremia, and relationship between level of chloride and AKI incidence was analyzed using the univariate and multivariate logistic regression. Patients were divided into four disease subgroups based on the diagnosis at admission: cardiac, cerebral, gastrointestinal, respiratory. The association between maximum chloride (chloride_max) and incidence of AKI in each subgroup was evaluated using the Lowess Smoothing technique. Receiver operating characteristic curves were applied to analyze the diagnostic value of hyperchloremia (chloride_max>110mmol/L) in these four subgroup patients.Results: A total of 34,617 patients were included in our study, of which 12667 patients (36.6%) was diagnosed with hyperchloremia. The risk of incidence of AKI was increased in the hyperchloremia group. As the higher level of hyperchlorimia, the bigger adjusted odds ratio (OR) presented in terms of AKI, with the OR increasing from 1.13 (95%CI 1.06-1.21; P<0.001) to 4.09 (95%CI 3.04-5.52; P<0.001). Normal level of chloride (95-110mmol/L) was associated with the lower incidence of AKI rate compared to the hypochloremia (<95mmol/L) or the hyperchloremia (>110mmol/L) in any subgroup of cerebral, cardiac, respiratory and gastrointestinal disease. The diagnostic performance was good for cerebral disease (AUC=0.617), cardiac disease (AUC=0.636), respiratory disease (AUC=0.623) and gastrointestinal disease (AUC=0.633). The optimal cut-off value in terms of chloride_max for diagnosing AKI was 116mmol/L for the subgroup of cerebral, respiratory and gastrointestinal diseases, and 115 mmol/L for cardiac patients.Conclusion: Hyperchloremia was associated with increased risk adjusted AKI incidence among critical ill patients. For ICU patients with cerebral, gastrointestinal and respiratory admission diagnose, the predictive threshold was at 116mmoL/L, and cardiac diagnose was at 115 mmol/L.

scholarly journals Predicting 30-days mortality for MIMIC-III patients with sepsis-3: a machine learning approach using XGboost

2020 ◽  
Vol 18 (1) ◽  
Author(s):  
Nianzong Hou ◽  
Mingzhe Li ◽  
Lu He ◽  
Bing Xie ◽  
Lin Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Prediction Model ◽  
Prediction Models ◽  
Clinical Impact ◽  
Curve Analysis ◽  
Learning Approach ◽  
Decision Curve Analysis ◽  
Saps Ii Score ◽  
Machine Learning Approach ◽  
Mimic Iii

Abstract Background Sepsis is a significant cause of mortality in-hospital, especially in ICU patients. Early prediction of sepsis is essential, as prompt and appropriate treatment can improve survival outcomes. Machine learning methods are flexible prediction algorithms with potential advantages over conventional regression and scoring system. The aims of this study were to develop a machine learning approach using XGboost to predict the 30-days mortality for MIMIC-III Patients with sepsis-3 and to determine whether such model performs better than traditional prediction models. Methods Using the MIMIC-III v1.4, we identified patients with sepsis-3. The data was split into two groups based on death or survival within 30 days and variables, selected based on clinical significance and availability by stepwise analysis, were displayed and compared between groups. Three predictive models including conventional logistic regression model, SAPS-II score prediction model and XGBoost algorithm model were constructed by R software. Then, the performances of the three models were tested and compared by AUCs of the receiver operating characteristic curves and decision curve analysis. At last, nomogram and clinical impact curve were used to validate the model. Results A total of 4559 sepsis-3 patients are included in the study, in which, 889 patients were death and 3670 survival within 30 days, respectively. According to the results of AUCs (0.819 [95% CI 0.800–0.838], 0.797 [95% CI 0.781–0.813] and 0.857 [95% CI 0.839–0.876]) and decision curve analysis for the three models, the XGboost model performs best. The risk nomogram and clinical impact curve verify that the XGboost model possesses significant predictive value. Conclusions Using machine learning technique by XGboost, more significant prediction model can be built. This XGboost model may prove clinically useful and assist clinicians in tailoring precise management and therapy for the patients with sepsis-3.

scholarly journals A Hybrid Classification and Prediction Methodology for the Diagonosis of Osteoporosis

2019 ◽  
Vol 8 (10) ◽  
pp. 4648-4653
Keyword(s):  
Machine Learning ◽  
Prediction Model ◽  
Bone Disease ◽  
Prediction Models ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Mineral Density ◽  
Increased Risk ◽  
Textual Data ◽  
Prediction Approach

With the advent of technology medical science is growing very fast . Disease diagonosis using machine learning technique is quite cumbersome. But efforts are made by the innovative minds to develope an optimal and efficient prediction model for the prediction of the disease viz, bone disease . Bone disease prediction is also a broad area of research where machine learning techniques can be used. Better prediction and analysis can be helpful to cure such disease . Osteoporosis is an osteo- metabolic disease characterized by low bone mineral density (BMD) and deterioration of the micro- architecture of the bone tissues, causing an increase in bone fragility and consequently leading to an increased risk of fractures.. Machine learning algorithms play important role for predicting and analyzing such disease using available algorithms and by modifying them . There are many algorithms such as SVM (Support vector machine), Genetic Algorithm, Naive bayes classifier and other tree based classifiers which are proposed in traditional scenario for prediction of expected data from an image. The goal of this paper is to discuss about a proposed hybrid analysis and prediction approach for diagonosing osteoporosis. This paper also discuss about various prediction models viz, svm prediction model as the efficient one while processing the textual data for symptoms analysis. Here symptoms are called predictors . A comparison using the Accuracy and training time is performed. The approach shows the efficiency of proposed model over textual data as well as graphical image data analysis.

scholarly journals Machine Learning Models for Predicting Neonatal Mortality: A Systematic Review

Neonatology ◽  
2021 ◽  
pp. 1-12
Author(s):  
Cheyenne Mangold ◽  
Sarah Zoretic ◽  
Keerthi Thallapureddy ◽  
Axel Moreira ◽  
Kevin Chorath ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neonatal Mortality ◽  
Sensitivity And Specificity ◽  
Health Care Providers ◽  
Prediction Models ◽  
Characteristic Curve ◽  
External Validation ◽  
Care Providers ◽  
Linear Discriminant ◽  
Increased Risk

<b><i>Introduction:</i></b> Approximately 7,000 newborns die every day, accounting for almost half of child deaths under 5 years of age. Deciphering which neonates are at increased risk for mortality can have an important global impact. As such, integrating high computational technology (e.g., artificial intelligence [AI]) may help identify the early and potentially modifiable predictors of neonatal mortality. Therefore, the objective of this study was to collate, critically appraise, and analyze neonatal prediction studies that included AI. <b><i>Methods:</i></b> A literature search was performed in PubMed, Cochrane, OVID, and Google Scholar. We included studies that used AI (e.g., machine learning (ML) and deep learning) to formulate prediction models for neonatal death. We excluded small studies (<i>n</i> &#x3c; 500 individuals) and studies using only antenatal factors to predict mortality. Two independent investigators screened all articles for inclusion. The data collection consisted of study design, number of models, features used per model, feature importance, internal and/or external validation, and calibration analysis. Our primary outcome was the average area under the receiving characteristic curve (AUC) or sensitivity and specificity for all models included in each study. <b><i>Results:</i></b> Of 434 articles, 11 studies were included. The total number of participants was 1.26 M with gestational ages ranging from 22 weeks to term. Number of features ranged from 3 to 66 with timing of prediction as early as 5 min of life to a maximum of 7 days of age. The average number of models per study was 4, with neural network, random forest, and logistic regression comprising the most used models (58.3%). Five studies (45.5%) reported calibration plots and 2 (18.2%) conducted external validation. Eight studies reported results by AUC and 5 studies reported the sensitivity and specificity. The AUC varied from 58.3% to 97.0%. The mean sensitivities ranged from 63% to 80% and specificities from 78% to 99%. The best overall model was linear discriminant analysis, but it also had a high number of features (<i>n</i> = 17). <b><i>Discussion/Conclusion:</i></b> ML models can accurately predict death in neonates. This analysis demonstrates the most commonly used predictors and metrics for AI prediction models for neonatal mortality. Future studies should focus on external validation, calibration, as well as deployment of applications that can be readily accessible to health-care providers.

scholarly journals Recommending System for Penny Stock Trading

2019 ◽  
Vol 9 (1S5) ◽  
pp. 85-91
Keyword(s):  
Machine Learning ◽  
Experimental Study ◽  
Reinforcement Learning ◽  
Test Data ◽  
Stock Price ◽  
Prediction Models ◽  
Poor Performance ◽  
Stock Trading ◽  
Financial Metrics ◽  
Penny Stocks

Penny stocks at times makes the investors wealthy by turning to be a multi-bagger stocks or erode the wealth of the investors with poor performance in volatile conditions. While there are many machine learning-based prediction models that are used for stock price evaluation, very few studies have focused on the dynamics to be considered in penny stock conditions. Though the pattern might remain the same for normal stocks and the penny stock classification, still some of the parameters to be evaluated in the process needs changes. The model discussed in this report is a comprehensive solution discussed as scope for evaluation of the penny stock pick, using trading and reporting financial metrics. Experimental study of the test data indicates that the model is potential and if can be used effectively with reinforcement learning pattern, it can turn to be sustainable solution.

scholarly journals Using Machine Learning Algorithms to Predict Candidaemia in ICU Patients With New-Onset Systemic Inflammatory Response Syndrome

2021 ◽  
Vol 8 ◽  
Author(s):  
Siyi Yuan ◽  
Yunbo Sun ◽  
Xiongjian Xiao ◽  
Yun Long ◽  
Huaiwu He
Keyword(s):  
Machine Learning ◽  
Systemic Inflammatory Response Syndrome ◽  
Inflammatory Response ◽  
Prediction Models ◽  
Learning Algorithms ◽  
Systemic Inflammatory Response ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Icu Patients ◽  
New Onset

Background: Distinguishing ICU patients with candidaemia can help with the precise prescription of antifungal drugs to create personalized guidelines. Previous prediction models of candidaemia have primarily used traditional logistic models and had some limitations. In this study, we developed a machine learning algorithm trained to predict candidaemia in patients with new-onset systemic inflammatory response syndrome (SIRS).Methods: This retrospective, observational study used clinical information collected between January 2013 and December 2017 from three hospitals. The ICU patient data were used to train 4 machine learning algorithms–XGBoost, Support Vector Machine (SVM), Random Forest (RF), ExtraTrees (ET)–and a logistic regression (LR) model to predict patients with candidaemia.Results: Of the 8,002 cases of new-onset SIRS (in 7,932 patients) included in the analysis, 137 new-onset SIRS cases (in 137 patients) were blood culture positive for candidaemia. Risk factors, such as fungal colonization, diabetes, acute kidney injury, the total number of parenteral nutrition days and renal replacement therapy, were important predictors of candidaemia. The XGBoost machine learning model outperformed the other models in distinguishing patients with candidaemia [XGBoost vs. SVM vs. RF vs. ET vs. LR; area under the curve (AUC): 0.92 vs. 0.86 vs. 0.91 vs. 0.90 vs. 0.52, respectively]. The XGBoost model had a sensitivity of 84%, specificity of 89% and negative predictive value of 99.6% at the best cut-off value.Conclusions: Machine learning algorithms can potentially predict candidaemia in the ICU and have better efficiency than previous models. These prediction models can be used to guide antifungal treatment for ICU patients when SIRS occurs.

scholarly journals Development and validation of a novel blending machine learning model for hospital mortality prediction in ICU patients with Sepsis

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Zhixuan Zeng ◽  
Shuo Yao ◽  
Jianfei Zheng ◽  
Xun Gong
Keyword(s):  
Machine Learning ◽  
Hospital Mortality ◽  
Mortality Prediction ◽  
Research Database ◽  
Training Set ◽  
Icu Patients ◽  
Test Set ◽  
Saps Ii ◽  
Severity Scores ◽  
Mimic Iii

Abstract Background Early prediction of hospital mortality is crucial for ICU patients with sepsis. This study aimed to develop a novel blending machine learning (ML) model for hospital mortality prediction in ICU patients with sepsis. Methods Two ICU databases were employed: eICU Collaborative Research Database (eICU-CRD) and Medical Information Mart for Intensive Care III (MIMIC-III). All adult patients who fulfilled Sepsis-3 criteria were identified. Samples from eICU-CRD constituted training set and samples from MIMIC-III constituted test set. Stepwise logistic regression model was used for predictor selection. Blending ML model which integrated nine sorts of basic ML models was developed for hospital mortality prediction in ICU patients with sepsis. Model performance was evaluated by various measures related to discrimination or calibration. Results Twelve thousand five hundred fifty-eight patients from eICU-CRD were included as the training set, and 12,095 patients from MIMIC-III were included as the test set. Both the training set and the test set showed a hospital mortality of 17.9%. Maximum and minimum lactate, maximum and minimum albumin, minimum PaO2/FiO2 and age were important predictors identified by both random forest and extreme gradient boosting algorithm. Blending ML models based on corresponding set of predictors presented better discrimination than SAPS II (AUROC, 0.806 vs. 0.771; AUPRC 0.515 vs. 0.429) and SOFA (AUROC, 0.742 vs. 0.706; AUPRC 0.428 vs. 0.381) on the test set. In addition, calibration curves showed that blending ML models had better calibration than SAPS II. Conclusions The blending ML model is capable of integrating different sorts of basic ML models efficiently, and outperforms conventional severity scores in predicting hospital mortality among septic patients in ICU.

Sign in / Sign up

Export Citation Format

Share Document