Predicting return visits to the emergency department for pediatric patients: Applying supervised learning techniques to the Taiwan National Health Insurance Research Database

Influence of demographic factors on prolonged length of stay in an emergency department

BACKGROUND

A prolonged length of stay in an emergency department is related to lower quality of care and adverse outcomes, which are often linked with overcrowding.

OBJECTIVE

Examine the influence of demographic factors on prolonged length of stay in the emergency department.

METHODS

This study used a cross-sectional design. It used secondary data for all patients admitted during the specific duration at the emergency department of a governmental hospital in Saudi Arabia. The independent variables were gender, age, disposition status, shift time, and clinical acuity (CTAS) level while the dependent variable was prolonged length of stay.

RESULTS

The study shows that 30% of patients stay at the emergency department for four hours or more. The results also show a significant association between demographic factors which are age, gender, disposition status, shift time, clinical acuity (CTAS) level and prolonged length of stay in an emergency department. Based on the results males are more likely to stay in the emergency department than females (OR = 1.20; 95% CI = 1.04 to 1.38). Patients aged 60 and older are less likely to stay in the emergency department than patients aged 29 or smaller (OR = 0.58; 95% CI = 0.39 to 0.84). According to disposition status discharged patients after examination stays in the emergency department more than admitted patients after the examination (OR = 2.78; 95% CI = 1.67 to 4.99). Patients who come to the night shift are less likely to stay in the emergency department than patients who come in the morning shift (OR = 0.67; 95% CI = 0.56 to 0.81). Patients who are classified in level three of CTAS are less likely to stay in the emergency department than patients who are classified in level one (OR = 0.28; 95% CI = 0.88 to 0.023).

CONCLUSION

Demographic factors such as age, gender, shift time, disposition status and clinical acuity (CTAS) were important factors that needed to be considered to reduce the length of stay of patients in the emergency department. it is possible to formulate a machine learning model to predict the anticipated length of stay in the hospital for each patient. This prediction with an accepted margin of uncertainty will help the clinicians to communicate the evidence-based anticipated length of stay with the patient's caregivers. In addition, hospital managers need to provide the emergency department with enough staff and materials to reduce the length of stay of patients.

An explainable machine learning approach for hospital emergency department visits forecasting using continuous training and multi-model regression

BACKGROUND AND OBJECTIVE

In the last years, the Emergency Department (ED) has become an important source of admissions for hospitals. Since late 90s, the number of ED visits has been steadily increasing, and since Covid19 pandemic this trend has been much stronger. Accurate prediction of ED visits, even for moderate forecasting time-horizons, can definitively improve operational efficiency, quality of care, and patient outcomes in hospitals.

METHODS

In this paper we propose two different interpretable approaches, based on Machine Learning algorithms, to accurately forecast hospital emergency visits. The proposed approaches involve a first step of data segmentation based on two different criteria, depending on the approach considered: first, a threshold-based strategy is adopted, where data is divided depending on the value of specific predictor variables. In a second approach, a cluster-based ensemble learning is proposed, in such a way that a clustering algorithm is applied to the training dataset, and ML models are then trained for each cluster.

RESULTS

The two proposed methodologies have been evaluated in real data from two hospital ED visits datasets in Spain. We have shown that the proposed approaches are able to obtain accurate ED visits forecasting, in short-term and also long-term prediction time-horizons up to one week, improving the efficiency of alternative prediction methods for this problem.

CONCLUSIONS

The proposed forecasting approaches have a strong emphasis on providing explainability to the problem. An analysis on which variables govern the problem and are pivotal for obtaining accurate predictions is finally carried out and included in the discussion of the paper.

Machine learning models for predicting unscheduled return visits to an emergency department: a scoping review

BACKGROUND

Unscheduled return visits (URVs) to emergency departments (EDs) are used to assess the quality of care in EDs. Machine learning (ML) models can incorporate a wide range of complex predictors to identify high-risk patients and reduce errors to save time and cost. However, the accuracy and practicality of such models are questionable. This review compares the predictive power of multiple ML models and examines the effects of multiple research factors on these models' performance in predicting URVs to EDs.

METHODS

We conducted the present scoping review by searching eight databases for data from 2010 to 2023. The criteria focused on eligible articles that used ML to predict ED return visits. The primary outcome was the predictive performances of the ML models, and results were analyzed on the basis of intervals of return visits, patient population, and research scale.

RESULTS

A total of 582 articles were identified through the database search, with 14 articles selected for detailed analysis. Logistic regression was the most widely used method; however, eXtreme Gradient Boosting generally exhibited superior performance. Variations in visit interval, target group, and research scale did not significantly affect the predictive power of the models.

CONCLUSION

This is the first study to summarize the use of ML for predicting URVs in ED patients. The development of practical ML prediction models for ED URVs is feasible, but improving the accuracy of predicting ED URVs to beyond 0.75 remains a challenge. Including multiple data sources and dimensions is key for enabling ML models to achieve high accuracy; however, such inclusion could be challenging within a limited timeframe. The application of ML models for predicting ED URVs may improve patient safety and reduce medical costs by decreasing the frequency of URVs. Further research is necessary to explore the real-world efficacy of ML models.

Development and Internal Validation of a Multivariable Prediction Model to Predict Repeat Attendances in the Pediatric Emergency Department: A Retrospective Cohort Study

OBJECTIVE

Unplanned reattendances to the pediatric emergency department (PED) occur commonly in clinical practice. Multiple factors influence the decision to return to care, and understanding risk factors may allow for better design of clinical services. We developed a clinical prediction model to predict return to the PED within 72 hours from the index visit.

METHODS

We retrospectively reviewed all attendances to the PED of Royal Manchester Children's Hospital between 2009 and 2019. Attendances were excluded if they were admitted to hospital, aged older than 16 years or died in the PED. Variables were collected from Electronic Health Records reflecting triage codes. Data were split temporally into a training (80%) set for model development and a test (20%) set for internal validation. We developed the prediction model using LASSO penalized logistic regression.

RESULTS

A total of 308,573 attendances were included in the study. There were 14,276 (4.63%) returns within 72 hours of index visit. The final model had an area under the receiver operating characteristic curve of 0.64 (95% confidence interval, 0.63-0.65) on temporal validation. The calibration of the model was good, although with some evidence of miscalibration at the high extremes of the risk distribution. After-visit diagnoses codes reflecting a nonspecific problem ("unwell child") were more common in children who went on to reattend.

CONCLUSIONS

We developed and internally validated a clinical prediction model for unplanned reattendance to the PED using routinely collected clinical data, including markers of socioeconomic deprivation. This model allows for easy identification of children at the greatest risk of return to PED.

The application of artificial intelligence in health financing: a scoping review

INTRODUCTION

Artificial Intelligence (AI) represents a significant advancement in technology, and it is crucial for policymakers to incorporate AI thinking into policies and to fully explore, analyze and utilize massive data and conduct AI-related policies. AI has the potential to optimize healthcare financing systems. This study provides an overview of the AI application domains in healthcare financing.

METHOD

We conducted a scoping review in six steps: formulating research questions, identifying relevant studies by conducting a comprehensive literature search using appropriate keywords, screening titles and abstracts for relevance, reviewing full texts of relevant articles, charting extracted data, and compiling and summarizing findings. Specifically, the research question sought to identify the applications of artificial intelligence in health financing supported by the published literature and explore potential future applications. PubMed, Scopus, and Web of Science databases were searched between 2000 and 2023.

RESULTS

We discovered that AI has a significant impact on various aspects of health financing, such as governance, revenue raising, pooling, and strategic purchasing. We provide evidence-based recommendations for establishing and improving the health financing system based on AI.

CONCLUSIONS

To ensure that vulnerable groups face minimum challenges and benefit from improved health financing, we urge national and international institutions worldwide to use and adopt AI tools and applications.

Connections between Various Disorders: Combination Pattern Mining Using Apriori Algorithm Based on Diagnosis Information from Electronic Medical Records

Objective

Short-term or long-term connections between different diseases have not been fully acknowledged. This study was aimed at exploring the network association pattern between disorders that occurred in the same individual by using the association rule mining technique.

Methods

Raw data were extracted from the large-scale electronic medical record database of the affiliated hospital of Xuzhou Medical University. 1551732 pieces of diagnosis information from 144207 patients were collected from 2015 to 2020. Clinic diagnoses were categorized according to “International Classification of Diseases, 10th revision”. The Apriori algorithm was used to explore the association patterns among those diagnoses.

Results

12889 rules were generated after running the algorithm at first. After threshold filtering and manual examination, 110 disease combinations (support ≥ 0.001, confidence ≥ 60%, lift > 1) with strong association strength were obtained eventually. Association rules about the circulatory system and metabolic diseases accounted for a significant part of the results.

Conclusion

This research elucidated the network associations between disorders from different body systems in the same individual and demonstrated the usefulness of the Apriori algorithm in comorbidity or multimorbidity studies. The mined combinations will be helpful in improving prevention strategies, early identification of high-risk populations, and reducing mortality.

Reduction of Waiting Times and Patients Leaving Without Being Seen in the Tertiary Pediatric Emergency Department: A Comparative Observational Study

OBJECTIVES

Analyze the effectiveness of an intervention to reduce waiting time and patients leaving without being seen in the pediatric emergency department.

METHODS

A comparative observational study was carried out from November 2018 to April 2019.Patients aged 3 months to 17 years were included. The new organizational model consisted of a dedicated outpatients' clinic for nonurgent codes and a fast track for traumatic and surgical emergency cases.

RESULTS

The comparative group included 14,822, and the intervention group included 15,585 patients. The new organizational model significantly reduced the numbers of patients who left the ED without being seen from 12.9% to 5.9%.

CONCLUSIONS

This new organizational model in the pediatric emergency department could be successfully used to reduce overcrowding, waiting time, and the numbers of patients leaving without being seen. However, more needs to be done by the pediatric services in the community to reduce nonurgent accesses to the emergency department.

Pediatric Emergency Department Return Visits Within 72 Hours: Caregivers' Motives and Analysis of Ethnic and Primary Language Disparities

OBJECTIVES

In the United States, approximately 2.2% to 5% of children discharged from the emergency department (ED) return within 72 hours. There is limited literature examining caregivers' reasons for return to the ED, and none among Hispanics and Spanish-speaking caregivers. We sought to examine why caregivers of pediatric patients return to the ED within 72 hours of a prior ED visit, and assess roles of ethnicity and primary language.

METHODS

A previously validated survey was prospectively administered to caregivers returning to the ED within 72 hours of discharge at a freestanding, tertiary care, children's hospital over a 7-month period. Reasons for return to the ED, previous ED discharge processes, and events since discharge were summarized according to Hispanic ethnicity, and English or Spanish language preference, and compared using the Fisher exact test.

RESULTS

Among 499 caregiver surveys analyzed, caregivers returned mostly because of no symptom improvement (57.5%) and worsening condition (35.5%), with no statistically significant differences between Hispanic/non-Hispanic ethnicity, or English/Spanish preference. Most (85.2%) caregivers recalled reasons to return to the ED. Recall of expected duration until symptom improvement was significantly higher among Hispanic (60.4%) versus non-Hispanic (52.1%) (P = 0.003), and for Spanish- (68.9%) versus English-speaking (54.6%) (P = 0.04), caregivers.

CONCLUSIONS

Most caregivers returned to the ED because their child's condition was not better or had worsened. Ethnicity and language were not associated with variations in reasons for return. Non-Hispanic and English-speaking caregivers were less likely to recall being informed of time to improvement and may require additional intervention.

A clinical prediction model to identify children at risk for revisits with serious illness to the emergency department: A prospective multicentre observational study

Background

To develop a clinical prediction model to identify children at risk for revisits with serious illness to the emergency department.

Methods and findings

A secondary analysis of a prospective multicentre observational study in five European EDs (the TRIAGE study), including consecutive children aged <16 years who were discharged following their initial ED visit (‘index’ visit), in 2012–2015. Standardised data on patient characteristics, Manchester Triage System urgency classification, vital signs, clinical interventions and procedures were collected. The outcome measure was serious illness defined as hospital admission or PICU admission or death in ED after an unplanned revisit within 7 days of the index visit. Prediction models were developed using multivariable logistic regression using characteristics of the index visit to predict the likelihood of a revisit with a serious illness. The clinical model included day and time of presentation, season, age, gender, presenting problem, triage urgency, and vital signs. An extended model added laboratory investigations, imaging, and intravenous medications. Cross validation between the five sites was performed, and discrimination and calibration were assessed using random effects models. A digital calculator was constructed for clinical implementation. 7,891 children out of 98,561 children had a revisit to the ED (8.0%), of whom 1,026 children (1.0%) returned to the ED with a serious illness. Rates of revisits with serious illness varied between the hospitals (range 0.7–2.2%). The clinical model had a summary Area under the operating curve (AUC) of 0.70 (95% CI 0.65–0.74) and summary calibration slope of 0.83 (95% CI 0.67–0.99). 4,433 children (5%) had a risk of > = 3%, which was useful for ruling in a revisit with serious illness, with positive likelihood ratio 4.41 (95% CI 3.87–5.01) and specificity 0.96 (95% CI 0.95–0.96). 37,546 (39%) had a risk <0.5%, which was useful for ruling out a revisit with serious illness (negative likelihood ratio 0.30 (95% CI 0.25–0.35), sensitivity 0.88 (95% CI 0.86–0.90)). The extended model had an improved summary AUC of 0.71 (95% CI 0.68–0.75) and summary calibration slope of 0.84 (95% CI 0.71–0.97). As study limitations, variables on ethnicity and social deprivation could not be included, and only return visits to the original hospital and not to those of surrounding hospitals were recorded.

Conclusion

We developed a prediction model and a digital calculator which can aid physicians identifying those children at highest and lowest risks for developing a serious illness after initial discharge from the ED, allowing for more targeted safety netting advice and follow-up.

Characteristics and outcomes of patients with an unscheduled return visit within 72 hours to the Paediatric Emergency Centre at a Private Tertiary Referral Hospital in Kenya

Introduction

Patients’ unscheduled return visits (URVs) to the paediatric emergency Centre (PEC) contribute to overcrowding and affect health service delivery and overall quality of care. This study assessed the characteristics and outcomes of paediatric patients with URVs (within 72 hours) to the PEC at a private tertiary hospital in Kenya.

Methods

We conducted a retrospective chart review of all URVs within 72 hours among paediatric patients aged ≤15 years between 1 July and 31 December 2018 at the tertiary hospital in Nairobi, Kenya.

Results

During the study period, 1.6% (n=172) of patients who visited the PEC returned within 72 hours, with 4.7% revisiting the PEC more than once. Patients’ median age was 36 months (interquartile range: 42 months); over half were male (51.7%), 55.8% were ambulatory and 84.3% were insured. In addition, 21% (n=36) had chronic diseases and 7% (n=12) had drug allergies. Respiratory (59.5%) and gastrointestinal (21.5%) tract infections were the most common diagnoses. Compared with the first visit, more patients with URVs were classified as urgent (1.7% vs. 5.2%) and were non-ambulatory (44.2% vs. 49.5%, p=<0.001); 18% of these patients were admitted. Of these 58% were male, 83.9% were aged 0–5 years, 12.9% were classified as urgent, 64.5% had respiratory tract infections and 16.1% had gastrointestinal tract infections. Being admitted was associated with patient acuity (p=0.004), laboratory tests (p=<0.001) and ambulatory status (p=0.041).

Conclusion

The URV rate is low in our setting. Patients who returned to the PEC within 72 hours tended to be male, under 5 years old and insured. Many were non-urgent cases with diagnoses of respiratory and gastrointestinal tract infections. The findings suggest that some URVs were necessary and may have contributed to better care and improved outcomes while others highlight a need for effective patient education and comprehensive initial assessment.

Machine learning for predictive data analytics in medicine: A review illustrated by cardiovascular and nuclear medicine examples

The evidence-based medicine allows the physician to evaluate the risk-benefit ratio of a treatment through setting and data. Risk-based choices can be done by the doctor using different information. With the emergence of new technologies, a large amount of data is recorded offering interesting perspectives with machine learning for predictive data analytics. Machine learning is an ensemble of methods that process data to model a learning problem. Supervised machine learning algorithms consist in using annotated data to construct the model. This category allows to solve prediction data analytics problems. In this paper, we detail the use of supervised machine learning algorithms for predictive data analytics problems in medicine. In the medical field, data can be split into two categories: medical images and other data. For brevity, our review deals with any kind of medical data excluding images. In this article, we offer a discussion around four supervised machine learning approaches: information-based, similarity-based, probability-based and error-based approaches. Each method is illustrated with detailed cardiovascular and nuclear medicine examples. Our review shows that model ensemble (ME) and support vector machine (SVM) methods are the most popular. SVM, ME and artificial neural networks often lead to better results than those given by other algorithms. In the coming years, more studies, more data, more tools and more methods will, for sure, be proposed.

Artificial intelligence in emergency medicine: A scoping review

INTRODUCTION

Despite the growing investment in and adoption of artificial intelligence (AI) in medicine, the applications of AI in an emergency setting remain unclear. This scoping review seeks to identify available literature regarding the applications of AI in emergency medicine.

METHODS

The scoping review was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for scoping reviews using Medline-OVID, EMBASE, CINAHL, and IEEE, with a double screening and extraction process. The search included articles published until February 28, 2020. Articles were excluded if they did not self-classify as studying an AI intervention, were not relevant to the emergency department (ED), or did not report outcomes or evaluation.

RESULTS

Of the 1483 original database citations, 395 were eligible for full-text evaluation. Of these articles, a total of 150 were included in the scoping review. The majority of included studies were retrospective in nature (n = 124, 82.7%), with only 3 (2.0%) prospective controlled trials. We found 37 (24.7%) interventions aimed at improving diagnosis within the ED. Among the 150 studies, 19 (12.7%) focused on diagnostic imaging within the ED. A total of 16 (10.7%) studies were conducted in the out-of-hospital environment (eg, emergency medical services, paramedics) with the remainder occurring either in the ED or the trauma bay. Of the 24 (16%) studies that had human comparators, there were 12 (8%) studies in which AI interventions outperformed clinicians in at least 1 measured outcome.

CONCLUSION

AI-related research is rapidly increasing in emergency medicine. There are several promising AI interventions that can improve emergency care, particularly for acute radiographic imaging and prediction-based diagnoses. Higher quality evidence is needed to further assess both short- and long-term clinical outcomes.

Analyzing Main and Interaction Effects of Length of Stay Determinants in Emergency Departments

BACKGROUND

Measuring and understanding main determinants of length of stay (LOS) in emergency departments (EDs) is critical from an operations perspective, since LOS is one of the main performance indicators of ED operations. Therefore, this study analyzes both the main and interaction effects of four widely-used independent determinants of ED-LOS.

METHODS

The analysis was conducted using secondary data from an ED of a large urban hospital in Izmir, Turkey. Between-subject factorial analysis of variance (ANOVA) was used to test the main and interaction effects of the corresponding factors. P values <.05 were considered statistically significant.

RESULTS

While the main effect of gender was insignificant, age, mode of arrival, and clinical acuity had significant effects, whereby ED-LOS was significantly higher for the elderly, those arriving by ambulance, and clinically-categorized high-acuity patients. Additionally, there was an interaction between the age and clinical acuity in that, while ED-LOS increased with age for high acuity patients, the opposite trend occurred for low acuity patients. When ED-LOS was modeled using gender, age, and mode of arrival, there was a significant interaction between age and mode of arrival. However, this interaction was not significant when the model included age, mode of arrival, and clinical acuity.

CONCLUSION

Significant interactions exist between commonly used ED-LOS determinants. Therefore, interaction effects should be considered in analyzing and modelling ED-LOS.

The likelihood of requiring a diagnostic test: Classifying emergency department patients with logistic regression

BACKGROUND

Emergency departments (EDs) play an important role in health systems since they are the front line for patients with emergency medical conditions who frequently require diagnostic tests and timely treatment.

OBJECTIVE

To improve decision-making and accelerate processes in EDs, this study proposes predictive models for classifying patients according to whether or not they are likely to require a diagnostic test based on referral diagnosis, age, gender, triage category and type of arrival.

METHOD

Retrospective data were categorised into four output patient groups: not requiring any diagnostic test (group A); requiring a radiology test (group B); requiring a laboratory test (group C); requiring both tests (group D). Multivariable logistic regression models were used, with the outcome classifications represented as a series of binary variables: test (1) or no test (0); in the case of group A, no test (1) or test (0).

RESULTS

For all models, age, triage category, type of arrival and referral diagnosis were significant predictors whereas gender was not. The main referral diagnosis with high model coefficients varied by designed output groups (groups A, B, C and D). The overall accuracies of the logistic regression models for groups A, B, C and D were, respectively, 74.11%, 73.07%, 82.47% and 85.79%. Specificity metrics were higher than the sensitivities for groups B, C and D, meaning that these models were better able to predict negative outcomes.

IMPLICATIONS

These results provide guidance for ED triage staff, researchers and practitioners in making rapid decisions regarding patients' diagnostic test requirements based on specified variables in the predictive models. This is critical in ED operations planning as it potentially decreases waiting times, while increasing patient satisfaction and operational performance.

Medical research using governments' health claims databases: with or without patients' consent?

Taking advantage of its single-payer, universal insurance system, Taiwan has leveraged its exhaustive database of health claims data for research purposes. Researchers can apply to receive access to pseudonymized (coded) medical data about insured patients, notably their diagnoses, health status and treatments. In view of the strict safeguards implemented, the Taiwanese government considers that this research use does not require patients' consent (either in the form of an opt-in or in the form of an opt-out). A group of non-governmental organizations has challenged this view in the Taiwanese Courts, but to no avail. The present article reviews the arguments both against and in favor of patients' consent for re-use of their data in research. It concludes that offering patients an opt-out would be appropriate as it would best balance the important interests at issue.

Highlighting the rules between diagnosis types and laboratory diagnostic tests for patients of an emergency department: Use of association rule mining

Diagnostic tests are widely used in emergency departments to make detailed investigations on diagnosis and treat patients correctly. However, since these tests are expensive and time-consuming, ordering correct tests for patients is crucial for efficient use of hospital resources. Thus, understanding the relation between diagnosis and diagnostic test requirement becomes an important issue in emergency departments. Association rule mining was used to extract hidden patterns and relation between diagnosis and diagnostic test requirement in real-life medical data received from an emergency department. Apriori was used as an association rule mining algorithm. Diagnosis was grouped into 21 categories based on International Classification of Disease, and laboratory tests were grouped into four main categories (hemogram, biochemistry, cardiac enzyme, urine and human excrement related). Both positive and negative rules were discovered. Since the nature of the data had the dominance of negative values, higher number of negative rules with higher confidences were discovered compared to positive ones. The extracted rules were validated by emergency department experts and practitioners. It was concluded that understanding the association between patient’s diagnosis and diagnostic test requirement can improve decision-making and efficient use of resources in emergency departments. Association rules can also be used for supporting physicians to treat patients.

Prediction of Recurrence-associated Death from Localized Prostate Cancer with a Charlson Comorbidity Index-reinforced Machine Learning Model

Research has failed to resolve the dilemma experienced by localized prostate cancer patients who must choose between radical prostatectomy (RP) and external beam radiotherapy (RT). Because the Charlson Comorbidity Index (CCI) is a measurable factor that affects survival events, this research seeks to validate the potential of the CCI to improve the accuracy of various prediction models. Thus, we employed the Cox proportional hazard model and machine learning methods, including random forest (RF) and support vector machine (SVM), to model the data of medical records in the National Health Insurance Research Database (NHIRD). In total, 8581 individuals were enrolled, of whom 4879 had received RP and 3702 had received RT. Patients in the RT group were older and exhibited higher CCI scores and higher incidences of some CCI items. Moderate-to-severe liver disease, dementia, congestive heart failure, chronic pulmonary disease, and cerebrovascular disease all increase the risk of overall death in the Cox hazard model. The CCI-reinforced SVM and RF models are 85.18% and 81.76% accurate, respectively, whereas the SVM and RF models without the use of the CCI are relatively less accurate, at 75.81% and 74.83%, respectively. Therefore, CCI and some of its items are useful predictors of overall and prostate-cancer-specific survival and could constitute valuable features for machine-learning modeling.

Predicting 72-hour and 9-day return to the emergency department using machine learning

Objectives

To predict 72-h and 9-day emergency department (ED) return by using gradient boosting on an expansive set of clinical variables from the electronic health record.

Methods

This retrospective study included all adult discharges from a level 1 trauma center ED and a community hospital ED covering the period of March 2013 to July 2017. A total of 1500 variables were extracted for each visit, and samples split randomly into training, validation, and test sets (80%, 10%, and 10%). Gradient boosting models were fit on 3 selections of the data: administrative data (demographics, prior hospital usage, and comorbidity categories), data available at triage, and the full set of data available at discharge. A logistic regression (LR) model built on administrative data was used for baseline comparison. Finally, the top 20 most informative variables identified from the full gradient boosting models were used to build a reduced model for each outcome.

Results

A total of 330 631 discharges were available for analysis, with 29 058 discharges (8.8%) resulting in 72-h return and 52 748 discharges (16.0%) resulting in 9-day return to either ED. LR models using administrative data yielded test AUCs of 0.69 (95% confidence interval [CI] 0.68–0.70) and 0.71(95% CI 0.70–0.72), while gradient boosting models using administrative data yielded test AUCs of 0.73 (95% CI 0.72–0.74) and 0.74 (95% CI 0.73–0.74) for 72-h and 9-day return, respectively. Gradient boosting models using variables available at triage yielded test AUCs of 0.75 (95% CI 0.74–0.76) and 0.75 (95% CI 0.74–0.75), while those using the full set of variables yielded test AUCs of 0.76 (95% CI 0.75–0.77) and 0.75 (95% CI 0.75–0.76). Reduced models using the top 20 variables yielded test AUCs of 0.73 (95% CI 0.71–0.74) and 0.73 (95% CI 0.72–0.74).

Discussion and Conclusion

Gradient boosting models leveraging clinical data are superior to LR models built on administrative data at predicting 72-h and 9-day returns.

A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models

OBJECTIVES

The objective of this study was to compare performance of logistic regression (LR) with machine learning (ML) for clinical prediction modeling in the literature.

STUDY DESIGN AND SETTING

We conducted a Medline literature search (1/2016 to 8/2017) and extracted comparisons between LR and ML models for binary outcomes.

RESULTS

We included 71 of 927 studies. The median sample size was 1,250 (range 72-3,994,872), with 19 predictors considered (range 5-563) and eight events per predictor (range 0.3-6,697). The most common ML methods were classification trees, random forests, artificial neural networks, and support vector machines. In 48 (68%) studies, we observed potential bias in the validation procedures. Sixty-four (90%) studies used the area under the receiver operating characteristic curve (AUC) to assess discrimination. Calibration was not addressed in 56 (79%) studies. We identified 282 comparisons between an LR and ML model (AUC range, 0.52-0.99). For 145 comparisons at low risk of bias, the difference in logit(AUC) between LR and ML was 0.00 (95% confidence interval, -0.18 to 0.18). For 137 comparisons at high risk of bias, logit(AUC) was 0.34 (0.20-0.47) higher for ML.

CONCLUSION

We found no evidence of superior performance of ML over LR. Improvements in methodology and reporting are needed for studies that compare modeling algorithms.

Partnership between families of children with muscular dystrophy and healthcare professionals: From parents' perspective

PURPOSES

At present, there is still controversy between parents of children with muscular dystrophy (MD) and healthcare professionals on care issues. Partnerships can connect the affected children and their families to appropriate healthcare services, to jointly face the care environment together and thereby improve the quality of life of children with MD. Therefore, the objective of this study is to explore partnerships between families and healthcare professionals from the perspectives of parents of children with MD.

METHOD

Husserl's phenomenological research was applied to explore the basic structures of parents' descriptions of MD. Through purposive sampling, we conducted in-depth interviews with parents, and analyzed the data according to the theory of Giorgi. Nineteen parents (10 mothers, nine fathers) participated in this study. The precision of the research results was tested by applying the four standards of Lincoln and Guba.

RESULTS

This study identified five constituents: feasible resources and detailed care information; the provision of an integrated medical care across systems; family and home as key elements in critical care; respect and care for family care demands; and finally; feedback and support from families.

CONCLUSION

This study demonstrated that partnerships were established by healthcare professionals, enhancing the care capacity of the families, developing the preventive medicine of MD, and enhancing children's potential for self-care within the families. Hospital policies should include the promotion of family partnership care. The findings can help healthcare professionals recognize the life experiences of children with MD when providing medical care.