Comparing Machine Learning Algorithms for Predicting Acute Kidney Injury

2019 ◽  
Vol 85 (7) ◽  
pp. 725-729 ◽  
Author(s):  
Joshua Parreco ◽  
Hahn Soe-Lin ◽  
Jonathan J. Parks ◽  
Saskya Byerly ◽  
Matthew Chatoor ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Learning Algorithms ◽  
Vital Signs ◽  
Kidney Injury ◽  
Machine Learning Algorithms ◽  
Laboratory Measurements ◽  
Icu Patients ◽  
Laboratory Values ◽  
F Measure

Prior studies have used vital signs and laboratory measurements with conventional modeling techniques to predict acute kidney injury (AKI). The purpose of this study was to use the trend in vital signs and laboratory measurements with machine learning algorithms for predicting AKI in ICU patients. The eICU Collaborative Research Database was queried for five consecutive days of laboratory measurements per patient. Patients with AKI were identified and trends in vital signs and laboratory values were determined by calculating the slope of the least-squares-fit linear equation using three days for each value. Different machine learning classifiers (gradient boosted trees [GBT], logistic regression, and deep learning) were trained to predict AKI using the laboratory values, vital signs, and slopes. There were 151,098 ICU stays identified and the rate of AKI was 5.6 per cent. The best performing algorithm was GBT with an AUC of 0.834 ± 0.006 and an F-measure of 42.96 per cent ± 1.26 per cent. Logistic regression performed with an AUC of 0.827 ± 0.004 and an F-measure of 28.29 per cent ± 1.01 per cent. Deep learning performed with an AUC of 0.817 ± 0.005 and an F-measure of 42.89 per cent ± 0.91 per cent. The most important variable for GBT was the slope of the minimum creatinine (30.32%). This study identifies the best performing machine learning algorithms for predicting AKI using trends in laboratory values in ICU patients. Early identification of these patients using readily available data indicates that incorporating machine learning predictive models into electronic medical record systems is an inevitable requisite for improving patient outcomes.

scholarly journals A comparative study of machine learning algorithms for predicting acute kidney injury after liver cancer resection

PeerJ ◽  
2020 ◽  
Vol 8 ◽  
pp. e8583 ◽  
Author(s):  
Lei Lei ◽  
Ying Wang ◽  
Qiong Xue ◽  
Jianhua Tong ◽  
Cheng-Mao Zhou ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Random Forest ◽  
Tumor Size ◽  
Learning Algorithms ◽  
Kidney Injury ◽  
Machine Learning Algorithms ◽  
Cancer Resection ◽  
Machine Learning Methods ◽  
Surgery Duration

Objective Machine learning methods may have better or comparable predictive ability than traditional analysis. We explore machine learning methods to predict the likelihood of acute kidney injury after liver cancer resection. Methods This is a secondary analysis cohort study. We reviewed data from patients who had undergone resection of primary hepatocellular carcinoma between January 2008 and October 2015. Results The analysis included 1,173 hepatectomy patients, 77 (6.6%) of whom had AKI and 1,096 (93.4%) who did not. The importance matrix for the Gbdt algorithm model shows that age, cholesterol, tumor size, surgery duration and PLT were the five most important parameters. Figure 1 shows that Age, tumor size and surgery duration had weak positive correlations with AKI. Cholesterol and PLT also had weak negative correlations with AKI. The models constructed by the four machine learning algorithms in the training group were compared. Among the four machine learning algorithms, random forest and gbm had the highest accuracy, 0.989 and 0.970 respectively. The precision of four of the five algorithms was 1, random forest being the exception. Among the test group, gbm had the highest accuracy (0.932). Random forest and gbm had the highest precision, both being 0.333. The AUC values for the four algorithms were: Gbdt (0.772), gbm (0.725), forest (0.662) and DecisionTree (0.628). Conclusions Machine learning technology can predict acute kidney injury after hepatectomy. Age, cholesterol, tumor size, surgery duration and PLT influence the likelihood and development of postoperative acute kidney injury.

scholarly journals Screening Key Indicators for Acute Kidney Injury Prediction Using Machine Learning

2021 ◽  
Vol 16 (3) ◽  
Author(s):  
Jiaming Wang ◽  
Bing Zhu ◽  
Pei Liu ◽  
Ruiqi Jia ◽  
Lijing Jia ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Decision Tree ◽  
Learning Algorithms ◽  
Screening Method ◽  
Kidney Injury ◽  
Machine Learning Algorithms ◽  
Key Indicator ◽  
Key Indicators ◽  
Mimic Iii

Acute kidney injury is a common critical disease with a high mortality. The large number of indicators in AKI patients makes it difficult for clinicians to quickly and accurately determine the patient’s condition. This study used machine learning methods to filter key indicators and use key indicator data to achieve advance prediction of AKI so that a small number of indicators could be measured to reliably predict AKI and provide auxiliary decision support for clinical staff. Sequential forward selection based on feature importance calculated by XGBoost was used to screen out 17 key indicators. Three machine learning algorithms were used to make predictions, namely, logistic regression (LR), decision tree, and XGBoost. To verify the validity of the method, data were extracted from the MIMIC III database and the eICU-CRD database for 1,009 and 1,327 AKI patients, respectively. The MIMIC III database was used for internal validation, and the eICU-CRD database was used for external validation. For all three machine learning algorithms, the prediction performance from using only the key indicator dataset was very close to that from using the full dataset. The XGBoost algorithm performed the best, and LR was the next best. The decision tree performed the worst. The key indicator screening method proposed in this study can achieve a good predictive performance while streamlining the number of indicators.

scholarly journals Performance Evaluation of Machine Learning Techniques for Identifying Forged and Phony Uniform Resource Locators (URLs)

2019 ◽  
Vol 16 (4) ◽  
pp. 155-169
Author(s):  
N. A. Azeez ◽  
A. A. Ajayi
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Financial Institutions ◽  
Traditional Approach ◽  
Learning Algorithms ◽  
Performance Comparison ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Reliable Solution ◽  
F Measure

Since the invention of Information and Communication Technology (ICT), there has been a great shift from the erstwhile traditional approach of handling information across the globe to the usage of this innovation. The application of this initiative cut across almost all areas of human endeavours. ICT is widely utilized in education and production sectors as well as in various financial institutions. It is of note that many people are using it genuinely to carry out their day to day activities while others are using it to perform nefarious activities at the detriment of other cyber users. According to several reports which are discussed in the introductory part of this work, millions of people have become victims of fake Uniform Resource Locators (URLs) sent to their mails by spammers. Financial institutions are not left out in the monumental loss recorded through this illicit act over the years. It is worth mentioning that, despite several approaches currently in place, none could confidently be confirmed to provide the best and reliable solution. According to several research findings reported in the literature, researchers have demonstrated how machine learning algorithms could be employed to verify and confirm compromised and fake URLs in the cyberspace. Inconsistencies have however been noticed in the researchers’ findings and also their corresponding results are not dependable based on the values obtained and conclusions drawn from them. Against this backdrop, the authors carried out a comparative analysis of three learning algorithms (Naïve Bayes, Decision Tree and Logistics Regression Model) for verification of compromised, suspicious and fake URLs and determine which is the best of all based on the metrics (F-Measure, Precision and Recall) used for evaluation. Based on the confusion metrics measurement, the result obtained shows that the Decision Tree (ID3) algorithm achieves the highest values for recall, precision and f-measure. It unarguably provides efficient and credible means of maximizing the detection of compromised and malicious URLs. Finally, for future work, authors are of the opinion that two or more supervised learning algorithms can be hybridized to form a single effective and more efficient algorithm for fake URLs verification.Keywords: Learning-algorithms, Forged-URL, Phoney-URL, performance-comparison

Comparative Study of Various Machine Learning Algorithms for Prediction of Insomnia

2019 ◽  
pp. 234-257 ◽  
Author(s):  
Ravinder Ahuja ◽  
Vishal Vivek ◽  
Manika Chandna ◽  
Shivani Virmani ◽  
Alisha Banga
Keyword(s):  
Machine Learning ◽  
Heart Diseases ◽  
False Positive Rate ◽  
Learning Algorithms ◽  
True Positive Rate ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Mobility Problem ◽  
Positive Rate ◽  
F Measure

An early diagnosis of insomnia can prevent further medical aids such as anger issues, heart diseases, anxiety, depression, and hypertension. Fifteen machine learning algorithms have been applied and 14 leading factors have been taken into consideration for predicting insomnia. Seven performance parameters (accuracy, kappa, the true positive rate, false positive rate, precision, f-measure, and AUC) are used and for implementation. The authors have used python language. The support vector machine is giving higher performance out of all algorithms giving accuracy 91.6%, f-measure is 92.13, and kappa is 0.83. Further, SVM is applied on another dataset of 100 patients and giving accuracy 92%. In addition, an analysis of the variable importance of CART, C5.0, decision tree, random forest, adaptive boost, and XG boost is calculated. The analysis shows that insomnia primarily depends on the factors, which are the vision problem, mobility problem, and sleep disorder. This chapter mainly finds the usages and effectiveness of machine learning algorithms in Insomnia diseases prediction.

Machine Learning Approaches to Define Candidates for Ambulatory Single Level Laminectomy Surgery

2021 ◽  
pp. 219256822097983
Author(s):  
Qiyi Li ◽  
Haoyan Zhong ◽  
Federico P. Girardi ◽  
Jashvant Poeran ◽  
Lauren A. Wilson ◽  
...  
Keyword(s):  
Machine Learning ◽  
Predictive Value ◽  
Learning Algorithms ◽  
White Blood Cells ◽  
Machine Learning Algorithms ◽  
Learning Approaches ◽  
Improvement Program ◽  
Single Level ◽  
Laboratory Values ◽  
Same Day Discharge

Study Design: retrospective cohort study. Objectives: To test and compare 2 machine learning algorithms to define characteristics associated with candidates for ambulatory same day laminectomy surgery. Methods: The American College of Surgeons National Surgical Quality Improvement Program database was queried for patients who underwent single level laminectomy in 2017 and 2018. The main outcome was ambulatory same day discharge. Study variables of interest included demographic information, comorbidities, preoperative laboratory values, and intra-operative information. Two machine learning predictive modeling algorithms, artificial neural network (ANN) and random forest, were trained to predict same day discharge. The quality of models was evaluated with area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) measures. Results: Among 35,644 patients, 13,230 (37.1%) were discharged on the day of surgery. Both ANN and RF demonstrated a satisfactory model quality in terms of AUC (0.77 and 0.77), accuracy (0.69 and 0.70), sensitivity (0.83 and 0.58), specificity (0.55 and 0.80), PPV (0.77 and 0.69), and NPV (0.64 and 0.70). Both models highlighted several important predictive variables, including age, duration of operation, body mass index and preoperative laboratory values including, hematocrit, platelets, white blood cells, and alkaline phosphatase. Conclusion: Machine learning approaches provide a promising tool to identify candidates for ambulatory laminectomy surgery. Both machine learning algorithms highlighted the as yet unrecognized importance of preoperative laboratory testing on patient pathway design.

scholarly journals Unsupervised Machine learning to subtype Sepsis-Associated Acute Kidney Injury

2018 ◽  
Author(s):  
Kumardeep Chaudhary ◽  
Aine Duffy ◽  
Priti Poojary ◽  
Aparna Saha ◽  
Kinsuk Chauhan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Tertiary Care ◽  
Vital Signs ◽  
Kidney Injury ◽  
Machine Learning Techniques ◽  
Care Hospital ◽  
Unsupervised Machine Learning ◽  
Laboratory Variables ◽  
Cluster 2

AbstractObjectiveAcute kidney injury (AKI) is highly prevalent in critically ill patients with sepsis. Sepsis-associated AKI is a heterogeneous clinical entity, and, like many complex syndromes, is composed of distinct subtypes. We aimed to agnostically identify AKI subphenotypes using machine learning techniques and routinely collected data in electronic health records (EHRs).DesignCohort study utilizing the MIMIC-III Database.SettingICUs from tertiary care hospital in the U.S.PatientsPatients older than 18 years with sepsis and who developed AKI within 48 hours of ICU admission.InterventionsUnsupervised machine learning utilizing all available vital signs and laboratory measurements.Measurements and Main ResultsWe identified 1,865 patients with sepsis-associated AKI. Ten vital signs and 691 unique laboratory results were identified. After data processing and feature selection, 59 features, of which 28 were measures of intra-patient variability, remained for inclusion into an unsupervised machine-learning algorithm. We utilized k-means clustering with k ranging from 2 – 10; k=2 had the highest silhouette score (0.62). Cluster 1 had 1,358 patients while Cluster 2 had 507 patients. There were no significant differences between clusters on age, race or gender. We found significant differences in comorbidities and small but significant differences in several laboratory variables (hematocrit, bicarbonate, albumin) and vital signs (systolic blood pressure and heart rate). In-hospital mortality was higher in cluster 2 patients, 25% vs. 20%, p=0.008. Features with the largest differences between clusters included variability in basophil and eosinophil counts, alanine aminotransferase levels and creatine kinase values.ConclusionsUtilizing routinely collected laboratory variables and vital signs in the EHR, we were able to identify two distinct subphenotypes of sepsis-associated AKI with different outcomes. Variability in laboratory variables, as opposed to their actual value, was more important for determination of subphenotypes. Our findings show the potential utility of unsupervised machine learning to better subtype AKI.

scholarly journals Entropy-Based Time Window Features Extraction for Machine Learning to Predict Acute Kidney Injury in ICU

2021 ◽  
Vol 11 (14) ◽  
pp. 6364
Author(s):  
Chun-Te Huang ◽  
Rong-Ching Chang ◽  
Yi-Lu Tsai ◽  
Kai-Chih Pai ◽  
Tsai-Jung Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Missing Data ◽  
Prediction Model ◽  
Kidney Injury ◽  
Machine Learning Algorithms ◽  
Data Availability ◽  
Supervised Machine Learning ◽  
Data Set ◽  
Clinical Scenarios

Acute kidney injury (AKI) refers to rapid decline of kidney function and is manifested by decreasing urine output or abnormal blood test (elevated serum creatinine). Electronic health records (EHRs) is fundamental for clinicians and machine learning algorithms to predict the clinical outcome of patients in the Intensive Care Unit (ICU). Early prediction of AKI could automatically warn the clinicians to review the possible risk factors and act in advance to prevent it. However, the enormous amount of patient data usually consists of a relatively incomplete data set and is very challenging for supervised machine learning process. In this paper, we propose an entropy-based feature engineering framework for vital signs based on their frequency of records. In particular, we address the missing at random (MAR) and missing not at random (MNAR) types of missing data according to different clinical scenarios. Regarding its applicability, we applied it to establish a prediction model for future AKI in ICU patients using 4278 ICU admissions from a tertiary hospital. Our result shows that the proposed entropy-based features are feasible to be used in the AKI prediction model and its performance improves as the data availability increases. In addition, we study the performance of AKI prediction model by comparing different time gaps and feature windows with the proposed vital sign entropy features. This work could be used as a guidance for feature windows selection and missing data processing during the development of a prediction model in ICU.

scholarly journals Artificial Intelligence Assisted Early Warning System for Acute Kidney Injury Driven by Multi-Center ICU Database

2020 ◽  
Author(s):  
Zhi Huang ◽  
Sai Huang ◽  
Li Chen ◽  
Wei-Hung Weng ◽  
Lili Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Acute Kidney Injury ◽  
Early Warning ◽  
Early Warning System ◽  
Data Extraction ◽  
Model Development ◽  
Warning System ◽  
Kidney Injury ◽  
Machine Learning Algorithms ◽  
Mimic Iii

AbstractBackgroundTo improve the performance of early acute kidney injury (AKI) prediction in intensive care unit (ICU), we developed and externally validated machine learning algorithms in two large ICU databases.MethodsUsing eICU® Collaborative Research Database (eICU) and MIMIC-III databases, we selected all adult patients (age ≥ 18). The detection of AKI was based on both the oliguric and serum creatinine criteria of the KDIGO (Kidney Disease Improving Global Outcomes). We developed an early warning system for forecasting the onset of AKI within the first week of ICU stay, by using 6- or 12-hours as the data extraction window and make a prediction within a 1-hour window after a gap window of 6- or 12-hours. We used 52 features which are routinely available ICU data as predictors. eICU was used for model development, and MIMIC-III was used for externally validation. We applied and experimented on eight machine learning algorithms for the prediction task.Results3,816 unique admissions in multi-center eICU database were selected for model development, and 5,975 unique admissions in single-center MIMIC-III database were selected for external validation. The incidence of AKI within the first week of ICU stay in eICU and MIMIC-III cohorts was 52.1% (n=1,988) and 31.3% (n=1,870), respectively. In eICU cohort, the performance of AKI prediction is better with shorter extraction window and gap window. We found that the AdaBoost algorithm yielded the highest AUC (0.8859) on the model with 6-hours data extraction window and 6-hours gap window (model 6-6) rather than other prediction models. In MIMIC-III cohort, AdaBoost also performed well.ConclusionsWe developed the machine learning-based early AKI prediction model, which considered clinical important features and has been validated in two datasets.

scholarly journals Machine Learning Based Algorithms to Impute PaO 2 from SpO2 Values and Development of an Online Calculator

2021 ◽  
Author(s):  
Shuangxia Ren ◽  
Jill A. Zupetic ◽  
Mohammadreza Tabary ◽  
Rebecca DeSensi ◽  
Mehdi Nouraie ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Clinical Variable ◽  
Learning Models ◽  
Icu Patients ◽  
Non Linear ◽  
Online Calculator ◽  
Machine Learning Models

Abstract We created an online calculator using machine learning algorithms to impute the partial pressure of oxygen (PaO2)/fraction of delivered oxygen (FiO2) ratio using the non-invasive peripheral saturation of oxygen (SpO2) and compared the accuracy of the machine learning models we developed to previously published equations. We generated three machine learning algorithms (neural network, regression, and kernel-based methods) using 7 clinical variable features (N=9,900 ICU events) and subsequently 3 features (N=20,198 ICU events) as input into the models. Data from mechanically ventilated ICU patients were obtained from the publicly available Medical Information Mart for Intensive Care (MIMIC III) database and used for analysis. Compared to seven features, three features (SpO2, FiO2 and PEEP) were sufficient to impute PaO2 from the SpO2. Any of the tested machine learning models enabled imputation of PaO2 from the SpO2 with lower error and showed greater accuracy in predicting PaO2/FiO2 < 150 compared to the previously published log-linear and non-linear equations. Imputation using data from an independent validation cohort of ICU patients (N = 133) from 2 hospitals within the University of Pittsburgh Medical Center (UPMC) showed greater accuracy with the neural network and kernel-based machine learning models compared to the previously published non-linear equation.

Sign in / Sign up

Export Citation Format

Share Document