Application of Machine Learning Techniques to Analyze Patient Returns to the Emergency Department

The study of the quality of hospital emergency services is based on analyzing a set of indicators such as the average time of first medical attention, the average time spent in the emergency department, degree of completion of the medical report and others. In this paper, an analysis is presented of one of the quality indicators: the rate of return of patients to the emergency service less than 72 h from their discharge. The objective of the analysis was to know the variables that influence the rate of return and which prediction model is the best. In order to do this, the data of the activity of the emergency service of a hospital of a reference population of 290,000 inhabitants were analyzed, and prediction models were created for the binary objective variable (rate of return to emergencies) using the logistic regression techniques, neural networks, random forest, gradient boosting and assembly models. Each of the models was analyzed and the result shows that the best model is achieved through a neural network with activation function tanh, algorithm levmar and three nodes in the hidden layer. This model obtains the lowest mean squared error (MSE) and the best area under the curve (AUC) with respect to the rest of the models used.

Download Full-text

Consent for Medical Services for Children and Adolescents

PEDIATRICS ◽

10.1542/peds.92.2.290 ◽

1993 ◽

Vol 92 (2) ◽

pp. 290-291

Author(s):

Keyword(s):

Emergency Department ◽

Emergency Services ◽

Routine Care ◽

Emergency Department Visits ◽

Medical Attention ◽

Unaccompanied Minors ◽

Sexually Transmitted ◽

Practical Guidelines ◽

Societal Changes ◽

Definition Of

Major societal changes affecting the provision of child health care have occurred over the last few decades. In the area of emergency services, consent for medical treatment is an important issue. The purpose of this statement is to outline major considerations involving consent and provide the physician with practical guidelines concerning this issue. Today fewer than one third of children live in two-parent families in which only the father works outside the home.1,2 Because of foster care placement, or temporary or permanent arrangements with relatives or friends, parents may not be available to give consent for treatment of their children.3-6 Unaccompanied minors may seek medical attention in any one of a number of locations. Some go to the emergency department, 14% of which have no policy regarding consent for the care of these patients.7 Unaccompanied minors younger than 18 years of age account for 3.4% of all emergency department visits.7 Twenty-two states and the District of Columbia now have laws concerning the "mture minor." Most other states have provisions in which competent minors may arrange for care involving contraceptives, pregnancy, abortion, sexually transmitted diseases, drug and alcohol abuse, and psychiatric disorders.8 The dilemma for emergency physicians and practicing pediatricians alike is whether to follow a strict interpretation of the law or to adopt a more practical approach. Clearly, consent is not required in life- or limb-threatening emergencies,8,9 although the definition of emergency varies from state to state. However, in most instances, only routine care, not emergency care, is needed. As a result, many physicians fear charges of battery or litigation should their judgement regarding treatment be questioned.8

Download Full-text

Clinical and Laboratory Predictors of In-hospital Mortality in Patients With Coronavirus Disease-2019: A Cohort Study in Wuhan, China

Clinical Infectious Diseases ◽

10.1093/cid/ciaa538 ◽

2020 ◽

Vol 71 (16) ◽

pp. 2079-2088 ◽

Cited By ~ 52

Author(s):

Kun Wang ◽

Peiyuan Zuo ◽

Yuwei Liu ◽

Meng Zhang ◽

Xiaofang Zhao ◽

...

Keyword(s):

Hospital Mortality ◽

Prediction Models ◽

Area Under The Curve ◽

Mortality Prediction ◽

Gradient Boosting ◽

Laboratory Model ◽

Training Cohort ◽

Clinical Model ◽

Extreme Gradient Boosting ◽

Mortality Prediction Models

Abstract Background This study aimed to develop mortality-prediction models for patients with coronavirus disease-2019 (COVID-19). Methods The training cohort included consecutive COVID-19 patients at the First People’s Hospital of Jiangxia District in Wuhan, China, from 7 January 2020 to 11 February 2020. We selected baseline data through the stepwise Akaike information criterion and ensemble XGBoost (extreme gradient boosting) model to build mortality-prediction models. We then validated these models by randomly collected COVID-19 patients in Union Hospital, Wuhan, from 1 January 2020 to 20 February 2020. Results A total of 296 COVID-19 patients were enrolled in the training cohort; 19 died during hospitalization and 277 discharged from the hospital. The clinical model developed using age, history of hypertension, and coronary heart disease showed area under the curve (AUC), 0.88 (95% confidence interval [CI], .80–.95); threshold, −2.6551; sensitivity, 92.31%; specificity, 77.44%; and negative predictive value (NPV), 99.34%. The laboratory model developed using age, high-sensitivity C-reactive protein, peripheral capillary oxygen saturation, neutrophil and lymphocyte count, d-dimer, aspartate aminotransferase, and glomerular filtration rate had a significantly stronger discriminatory power than the clinical model (P = .0157), with AUC, 0.98 (95% CI, .92–.99); threshold, −2.998; sensitivity, 100.00%; specificity, 92.82%; and NPV, 100.00%. In the subsequent validation cohort (N = 44), the AUC (95% CI) was 0.83 (.68–.93) and 0.88 (.75–.96) for the clinical model and laboratory model, respectively. Conclusions We developed 2 predictive models for the in-hospital mortality of patients with COVID-19 in Wuhan that were validated in patients from another center.

Download Full-text

Machine Learning for Emergency Department Management

International Journal of Information Systems in the Service Sector ◽

10.4018/ijisss.2019070102 ◽

2019 ◽

Vol 11 (3) ◽

pp. 19-36 ◽

Cited By ~ 1

Author(s):

Sofia Benbelkacem ◽

Farid Kadri ◽

Baghdad Atmani ◽

Sondès Chaabane

Keyword(s):

Machine Learning ◽

Emergency Department ◽

Length Of Stay ◽

Prediction Models ◽

Pediatric Emergency ◽

Machine Learning Techniques ◽

Learning Techniques ◽

Emergency Department Management ◽

Increasing Demand ◽

Set Up

Nowadays, emergency department services are confronted to an increasing demand. This situation causes emergency department overcrowding which often increases the length of stay of patients and leads to strain situations. To overcome this issue, emergency department managers must predict the length of stay. In this work, the researchers propose to use machine learning techniques to set up a methodology that supports the management of emergency departments (EDs). The target of this work is to predict the length of stay of patients in the ED in order to prevent strain situations. The experiments were carried out on a real database collected from the pediatric emergency department (PED) in Lille regional hospital center, France. Different machine learning techniques have been used to build the best prediction models. The results seem better with Naive Bayes, C4.5 and SVM methods. In addition, the models based on a subset of attributes proved to be more efficient than models based on the set of attributes.

Download Full-text

Predicting mortality in hemodialysis patients using machine learning analysis

Clinical Kidney Journal ◽

10.1093/ckj/sfaa126 ◽

2020 ◽

Author(s):

Victoria Garcia-Montemayor ◽

Alejandro Martin-Malo ◽

Carlo Barbieri ◽

Francesco Bellocchio ◽

Sagrario Soriano ◽

...

Keyword(s):

Machine Learning ◽

Logistic Regression ◽

Random Forest ◽

Prediction Models ◽

Initial Period ◽

Area Under The Curve ◽

Mortality Prediction ◽

Machine Learning Techniques ◽

Prediction Of Mortality ◽

Mortality Prediction Models

Abstract Background Besides 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. Methods Data 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. Results There 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. Conclusions Random forest is an adequate method, and superior to logistic regression, to generate mortality prediction models in haemodialysis patients.

Download Full-text

Threshold benchmarking for feature ranking techniques

Bulletin of Electrical Engineering and Informatics ◽

10.11591/eei.v10i2.2752 ◽

2021 ◽

Vol 10 (2) ◽

pp. 1063-1070

Author(s):

Ruchika Malhotra ◽

Anjali Sharma

Keyword(s):

Prediction Models ◽

Area Under The Curve ◽

Threshold Value ◽

Performance Measure ◽

Machine Learning Techniques ◽

Feature Ranking ◽

Ranking Algorithms ◽

Learning Techniques ◽

Defect Prediction Models ◽

Necessary And Sufficient

In prediction modeling, the choice of features chosen from the original feature set is crucial for accuracy and model interpretability. Feature ranking techniques rank the features by its importance but there is no consensus on the number of features to be cut-off. Thus, it becomes important to identify a threshold value or range, so as to remove the redundant features. In this work, an empirical study is conducted for identification of the threshold benchmark for feature ranking algorithms. Experiments are conducted on Apache Click dataset with six popularly used ranker techniques and six machine learning techniques, to deduce a relationship between the total number of input features (N) to the threshold range. The area under the curve analysis shows that ≃ 33-50% of the features are necessary and sufficient to yield a reasonable performance measure, with a variance of 2%, in defect prediction models. Further, we also find that the log2(N) as the ranker threshold value represents the lower limit of the range.

Download Full-text

Patient-Level Cancer Prediction Models From a Nationwide Patient Cohort: Model Development and Validation (Preprint)

10.2196/preprints.29807 ◽

2021 ◽

Author(s):

Eunsaem Lee ◽

Se Young Jung ◽

Hyung Ju Hwang ◽

Jaewoo Jung

Keyword(s):

Prediction Models ◽

Area Under The Curve ◽

Claim Data ◽

Gradient Boosting ◽

Health Checkup ◽

Cancer Prediction ◽

Patient Level ◽

Light Gradient ◽

Precision Recall Curve ◽

Recall Curve

BACKGROUND Nationwide population-based cohorts provide a new opportunity to build automated risk prediction models at the patient level, and claim data are one of the more useful resources to this end. To avoid unnecessary diagnostic intervention after cancer screening tests, patient-level prediction models should be developed. OBJECTIVE We aimed to develop cancer prediction models using nationwide claim databases with machine learning algorithms, which are explainable and easily applicable in real-world environments. METHODS As source data, we used the Korean National Insurance System Database. Every Korean in ≥40 years old undergoes a national health checkup every 2 years. We gathered all variables from the database including demographic information, basic laboratory values, anthropometric values, and previous medical history. We applied conventional logistic regression methods, light gradient boosting methods, neural networks, survival analysis, and one-class embedding classifier methods to effectively analyze high dimension data based on deep learning–based anomaly detection. Performance was measured with area under the curve and area under precision recall curve. We validated our models externally with a health checkup database from a tertiary hospital. RESULTS The one-class embedding classifier model received the highest area under the curve scores with values of 0.868, 0.849, 0.798, 0.746, 0.800, 0.749, and 0.790 for liver, lung, colorectal, pancreatic, gastric, breast, and cervical cancers, respectively. For area under precision recall curve, the light gradient boosting models had the highest score with values of 0.383, 0.401, 0.387, 0.300, 0.385, 0.357, and 0.296 for liver, lung, colorectal, pancreatic, gastric, breast, and cervical cancers, respectively. CONCLUSIONS Our results show that it is possible to easily develop applicable cancer prediction models with nationwide claim data using machine learning. The 7 models showed acceptable performances and explainability, and thus can be distributed easily in real-world environments.

Download Full-text

Predicting Stand Attributes of Loblolly Pine in West Gulf Coastal Plain Using Gradient Boosting and Random Forests

Canadian Journal of Forest Research ◽

10.1139/cjfr-2020-0330 ◽

2020 ◽

Author(s):

Xiongwei Lou ◽

Yuhui Weng ◽

Luming Fang ◽

HL Gao ◽

Jason Grogan ◽

...

Keyword(s):

Loblolly Pine ◽

Random Forests ◽

Coastal Plain ◽

Mean Squared Error ◽

Pine Plantations ◽

Machine Learning Techniques ◽

Coefficient Of Determination ◽

Gradient Boosting ◽

Gulf Coastal Plain ◽

Intensively Managed

Two machine-learning techniques, gradient boosting (GB) and random forests (RF), were used to predict stand mean height (HT), trees per hectare (Tree ha-1) and basal area per hectare (BA ha-1) based on datasets collected from extensively- and intensively-managed loblolly pine plantations in the West Gulf Coastal Plain region. Models were evaluated using coefficient of determination (R2), bias and root mean squared error (RMSE) by applying models to independent dataset and then compared to the model (Coble et al. 2017) currently being used in the region. For extensively-managed plantations, the GB models had less bias, larger R2 and smaller RMSE than RF and HT model was the best, followed by those of Tree ha-1 and BA ha-1. Even for BA ha-1, the GB model had R2 over 0.83. GB and RF models outperformed the Coble et al. (2017); differences were notable for HT and Tree ha-1, but significant for BA ha-1. For intensively-managed plantations, GB and RF were similarly great in predicting HT and Tree ha-1, but GB outperformed RF in predicting BA ha-1. We recommend the use of GB models to predict quantitative information required for managing loblolly pine plantations in the region.

Download Full-text

Predicting Acute Kidney Injury: A Machine Learning Approach Using Electronic Health Records

Information ◽

10.3390/info11080386 ◽

2020 ◽

Vol 11 (8) ◽

pp. 386

Author(s):

Sheikh S. Abdullah ◽

Neda Rostamzadeh ◽

Kamran Sedig ◽

Amit X. Garg ◽

Eric McArthur

Keyword(s):

Machine Learning ◽

Emergency Department ◽

Acute Kidney Injury ◽

Electronic Health Records ◽

Prediction Models ◽

Kidney Injury ◽

Machine Learning Techniques ◽

Health Records ◽

Mortality And Morbidity ◽

Electronic Health

Acute kidney injury (AKI) is a common complication in hospitalized patients and can result in increased hospital stay, health-related costs, mortality and morbidity. A number of recent studies have shown that AKI is predictable and avoidable if early risk factors can be identified by analyzing Electronic Health Records (EHRs). In this study, we employ machine learning techniques to identify older patients who have a risk of readmission with AKI to the hospital or emergency department within 90 days after discharge. One million patients’ records are included in this study who visited the hospital or emergency department in Ontario between 2014 and 2016. The predictor variables include patient demographics, comorbid conditions, medications and diagnosis codes. We developed 31 prediction models based on different combinations of two sampling techniques, three ensemble methods, and eight classifiers. These models were evaluated through 10-fold cross-validation and compared based on the AUROC metric. The performances of these models were consistent, and the AUROC ranged between 0.61 and 0.88 for predicting AKI among 31 prediction models. In general, the performances of ensemble-based methods were higher than the cost-sensitive logistic regression. We also validated features that are most relevant in predicting AKI with a healthcare expert to improve the performance and reliability of the models. This study predicts the risk of AKI for a patient after being discharged, which provides healthcare providers enough time to intervene before the onset of AKI.

Download Full-text

Predicting poor outcome in patients with suspected COVID-19 presenting to the Emergency Department (COVERED) – Development, internal and external validation of a prediction model

Acute Medicine Journal ◽

10.52964/amja.0836 ◽

2021 ◽

Vol 20 (1) ◽

pp. 4-14

Author(s):

K. Azijli ◽

◽

A.W.E. Lieveld ◽

S.F.B. van der Horst ◽

N. de Graaf ◽

...

Keyword(s):

Emergency Department ◽

Prediction Model ◽

Clinical Decision Making ◽

Prediction Models ◽

External Validation ◽

Model Performance ◽

Area Under The Curve ◽

Brier Score ◽

Multi Centre Study ◽

Poor Outcome

Background: A recent systematic review recommends against the use of any of the current COVID-19 prediction models in clinical practice. To enable clinicians to appropriately profile and treat suspected COVID-19 patients at the emergency department (ED), externally validated models that predict poor outcome are desperately needed. Objective: Our aims were to identify predictors of poor outcome, defined as mortality or ICU admission within 30 days, in patients presenting to the ED with a clinical suspicion of COVID-19, and to develop and externally validate a prediction model for poor outcome. Methods: In this prospective, multi-centre study, we enrolled suspected COVID-19 patients presenting at the EDs of two hospitals in the Netherlands. We used backward logistic regression to develop a prediction model. We used the area under the curve (AUC), Brier score and pseudo-R2 to assess model performance. The model was externally validated in an Italian cohort. Results: We included 1193 patients between March 12 and May 27 2020, of whom 196 (16.4%) had a poor outcome. We identified 10 predictors of poor outcome: current malignancy (OR 2.774; 95%CI 1.682-4.576), systolic blood pressure (OR 0.981; 95%CI 0.964-0.998), heart rate (OR 1.001; 95%CI 0.97-1.028), respiratory rate (OR 1.078; 95%CI 1.046-1.111), oxygen saturation (OR 0.899; 95%CI 0.850-0.952), body temperature (OR 0.505; 95%CI 0.359-0.710), serum urea (OR 1.404; 95%CI 1.198-1.645), C-reactive protein (OR 1.013; 95%CI 1.001-1.024), lactate dehydrogenase (OR 1.007; 95%CI 1.002-1.013) and SARS-CoV-2 PCR result (OR 2.456; 95%CI 1.526-3.953). The AUC was 0.86 (95%CI 0.83-0.89), with a Brier score of 0.32 and, and R2 of 0.41. The AUC in the external validation in 500 patients was 0.70 (95%CI 0.65-0.75). Conclusion: The COVERED risk score showed excellent discriminatory ability, also in external validation. It may aid clinical decision making, and improve triage at the ED in health care environments with high patient throughputs.

Download Full-text

Status and Patients Satisfaction Attended at Emergency Department of a Tertiary Level Hospital in Dhaka City

Journal of Current and Advance Medical Research ◽

10.3329/jcamr.v6i1.40786 ◽

2019 ◽

Vol 6 (1) ◽

pp. 53-58

Author(s):

Khursheda Akhtar ◽

Md Mamun Or Rashid ◽

Khodeza Akhtar ◽

Ayesha Siddika ◽

Syeda Subrina Siddika

Keyword(s):

Health Care ◽

Emergency Department ◽

Health Care Providers ◽

Emergency Services ◽

Medical Attention ◽

Care Providers ◽

Emergency Unit ◽

Cross Sectional ◽

Patients Satisfaction ◽

Mean Waiting Time

Background: Emergency department is one of the most important parts of a hospital which is the point of major public health interest. Objective: The purpose of the present study was to find out the existing facilities of emergency department, to assess the satisfaction of patients and health care providers on emergency services. Method: This cross-sectional study was carried out at emergency department of Mugda Medical College, Dhaka, Bangladesh from January 2017 to June 2017 for a period of six (06) months. Research instruments were semi structured questionnaire. Existing facilities at emergency department were assessed by check list which was adopted from Table of Equipment (TOE) by Directorate General of Health Service (DGHS) and satisfaction level was categorized as good and bad. Face to face interview was taken from emergency patients and health care providers attending in emergency unit. Result: A total of 75 samples of respondents were selected purposively. Most of the respondents (30.0%) were in 26 to 35 years age group. According to their education level, 24(48.0%) were illiterate. Most of the respondents (76.0%) were attended to emergency unit by walking; however 48(96.0%) respondents attended by health care providers immediately. Half of the patients (50.0%) buy drugs from local dispensary and investigation in hospital was also done by half of the patients. After reaching at emergency, maximum patients 25(50.0%) waited for 1 to 5 minutes for receiving medical attention and mean waiting time was 10.14 minutes. Overall satisfactory level at emergency unit was good 23(46.0%) and bad 27(54.0%) (p<0.0001). Conclusion: Numbers of potential barriers influence the patients’ satisfaction. Periodic patient satisfaction survey should be institutionalized to provide feedback for continuous quality improvement. Journal of Current and Advance Medical Research 2019;6(1):53-58

Download Full-text