Search

Homelessness has been a persistent social concern in the United States. A combination of political and economic events since the 1960s has driven increases in poverty that, by 1991, had surpassed 1928 depression era levels in some accounts. This paper explores how the emerging field of behavioral economics can use machine learning and data science methods to explore preventative responses to homelessness. In this study, machine learning data mining strategies, specifically K-means cluster analysis and later, decision trees, were used to understand how environmental factors and resultant behaviors can contribute to the experience of homelessness. Prevention of the first homeless event is especially important as studies show that if a person has experienced homelessness once, they are 2.6 times more likely to have another homeless episode. Study findings demonstrate that when someone is at risk for not being able to pay utility bills at the same time as they experience challenges with two or more of the other social determinants of health, the individual is statistically significantly more likely to have their first homeless event. Additionally, for men over 50 who are not in the workforce, have a health hardship, and experience two or more other social determinants of health hardships at the same time, the individual has a high statistically significant probability of experiencing homelessness for the first time. [ABSTRACT FROM AUTHOR]

Annual turnover of home care workers represents a huge loss of revenue and is a key source of inefficiency in the home health care industry. In this article, we propose a data-driven approach to monitor employee churn and to capture the evolution of employee intent to leave. Unlike most papers in the literature, we use machine learning techniques to analyze over 2 million visits in the US, Canada, and Australia between 2016 and 2019. Results show that the gap between the number of hours worked and in the contract is the most important factor to predict employee intent to leave, which means an employee should be given as many hours as requested in the contract to improve retention. Secondary results show that having diverse shift lengths and continuity in services and patients seem to be associated with less turnover. [ABSTRACT FROM AUTHOR]

Supplemental digital content is available in the text. Background: About 30% of home healthcare patients are hospitalized or visit an emergency department (ED) during a home healthcare (HHC) episode. Novel data science methods are increasingly used to improve identification of patients at risk for negative outcomes. Objectives: The aim of the study was to identify patients at heightened risk hospitalization or ED visits using HHC narrative data (clinical notes). Methods: This study used a large database of HHC visit notes (n = 727,676) documented for 112,237 HHC episodes (89,459 unique patients) by clinicians of the largest nonprofit HHC agency in the United States. Text mining and machine learning algorithms (Naïve Bayes, decision tree, random forest) were implemented to predict patient hospitalization or ED visits using the content of clinical notes. Risk factors associated with hospitalization or ED visits were identified using a feature selection technique (gain ratio attribute evaluation). Results: Best performing text mining method (random forest) achieved good predictive performance. Seven risk factors categories were identified, with clinical factors, coordination/communication, and service use being the most frequent categories. Discussion: This study was the first to explore the potential contribution of HHC clinical notes to identifying patients at risk for hospitalization or an ED visit. Our results suggest that HHC visit notes are highly informative and can contribute significantly to identification of patients at risk. Further studies are needed to explore ways to improve risk prediction by adding more data elements from additional data sources. [ABSTRACT FROM AUTHOR]

Flight on-time performance is one of the most important issues in the National Airspace System, a very complex and dynamic system. To avoid negative impacts to the aviation industry, the Federal Aviation Administration has set a long-term objective of understanding and mitigating flight delays. Building an effective and accurate prediction model of flight-delay incidents will help airport executives make the best decisions in delay scenarios. This article utilized two advanced prediction methods to predict the probability of a flight-delay incident--data mining using the decision tree and data mining using Bayesian inference. Prediction models were built using flight on-time performance data collected from different sources. The results indicated important airport-related factors and their effects on the flight on-time performance. [ABSTRACT FROM AUTHOR]

Purpose - The purpose of this paper is to demonstrate how the use of data mining (DM) analysis can be used to evaluate how well cameras that monitor red-light-signal controlled intersections improve traffic safety by reducing fatalities. Design/methodology/approach - The paper demonstrates several different data modeling techniques - decision trees, neural networks, market-basket analysis and K-means models. Decision trees build rule sets that can abet future decision making. Neural networks try to predict future outcomes by looking at the effects of historical inputs. Market-basket analysis shows the strength of the relationships between variables. K-means models weigh the impact of homogenous clusters on target variables. All of these models are demonstrated using real data gathered by the Department of Transportation from fatal accidents at red-light-signal controlled intersections in Maryland and Washington, IX: from the year 2000 through 2003. Findings - The results of the DM analysis will show predictable relationships between the demographic data of drivers and fatal accidents; the type of collision and fatal accidents and between the time of day and fatal accidents. Research limitations/implications - The limitations of missing or incomplete data sets are addressed in this paper. Practical implications - This paper can act as a guide to follow for red light camera program managers or local municipalities to conduct their own analysis. Originality/value - This paper builds upon prior research in DM and also extends the body of research that examines the effectiveness of red camera programs as they mature. [ABSTRACT FROM AUTHOR]

Objective. To identify variables correlated with a diagnosis of diabetic peripheral neuropathy (DPN) using random forest modeling applied to electronic health records. Design. Retrospective analysis. Setting. Humedica de-identified electronic health records database. Subjects. Subjects≥18 years old with type 2 diabetes from January 1, 2008-September 30, 2013 having continuous data for 1 year pre- and postindex with DPN (n535,050) and without DPN (n5288,328) were identified. Methods. Demographic, clinical, and health care resource utilization variables (e.g., inpatient and outpatient encounters, medications, and procedures) were input into a random forest model to identify the most important correlates of a DPN diagnosis. Random forest modeling is a computationally extensive, robust data mining technique that accommodates large sets of variables to identify associated factors using an ensemble of classifications trees. Accuracy of the model was evaluated using receiver operating characteristic curves (ROC). Results. The final random forest model consisted of the following variables (importance) associated with a DPN diagnosis: Charlson Comorbidity Index score (100%), age (37.1%), number of pre-index procedures and services (29.7%), number of pre-index outpatient prescriptions (24.2%), number of preindex outpatient visits (18.3%), number of pre-index laboratory visits (16.9%), number of pre-index outpatient office visits (12.1%), number of inpatient prescriptions (5.9%), and number of pain-related medication prescriptions (4.4%). ROC analysis confirmed model performance, with an area under the curve of 0.824 and accuracy of 89.6% (95% confidence interval 89.4%, 89.8%). Conclusions. Random forest modeling can determine likelihood of a DPN diagnosis. Further validation of the random forest model may help facilitate earlier diagnosis and enhance management strategies. [ABSTRACT FROM AUTHOR]

The major purpose of this paper is to find the financial and nonfinancial variables which would be useful in identifying companies with Sarbanes-Oxley Act internal control material weaknesses (MW). Recently, three research papers have been published on this topic based on different variables. Using the decision tree model of data mining, this paper examines the predictive power of the variables used in each paper in identifying MW companies and compares the predictive rates of the three sets of the variables used in these studies. In addition, an attempt is made to find the optimal set of the variables which gives the highest predictive rate. Our results have shown that each set of the variables is complementary to each other and strengthens the prediction accuracy. The findings from this study can provide valuable insights to external auditors in designing a cost-effective and high-quality audit decision support system to comply with the Sarbanes-Oxley Act. [ABSTRACT FROM AUTHOR]

Background: Pressure ulcers are associated with a nearly three-fold increase in in-hospital mortality. It is essential to investigate how other factors besides the Braden scale could enhance the prediction of pressure ulcers. Data mining modeling techniques can be beneficial to conduct this type of analysis. Data mining techniques have been applied extensively in health care, but are not widely used in nursing research. Purpose: To remedy this methodological gap, this paper will review, explain, and compare several data mining models to examine patient level factors associated with pressure ulcers based on a four year study from military hospitals in the United States. Methods: The variables included in the analysis are easily accessible demographic information and medical measurements. Logistic regression, decision trees, random forests, and multivariate adaptive regression splines were compared based on their performance and interpretability. Results: The random forests model had the highest accuracy (C-statistic) with the following variables, in order of importance, ranked highest in predicting pressure ulcers: days in the hospital, serum albumin, age, blood urea nitrogen, and total Braden score. Conclusion: Data mining, particularly, random forests are useful in predictive modeling. It is important for hospitals and health care systems to use their own data over time for pressure ulcer risk prediction, to develop risk models based upon more than the total Braden score, and specific to their patient population. [ABSTRACT FROM AUTHOR]

Data mining is the important field of computer science. Decision tree is important tool of data mining. All the tools of data mining is used to extract knowledge from huge amount of data base. In this paper after giving introduction of data mining, decision tree is discussed in detail, how it is constructed. The adult dataset is popular data set. In this there are more than thirty two thousand instances. Using Weka, an important data mining tool, the decision tree is constructed for country India in adult data set. Using that decision tree the knowledge can be extracted. [ABSTRACT FROM AUTHOR]

Abstract: The existing disparity in the healthcare coverage is a pressing issue in the United States. Unfortunately, many in the US do not have healthcare coverage and much research is needed to identify the factors leading to this phenomenon. Hence, this study aims to examine the healthcare coverage of individuals by applying popular machine learning techniques on a wide-variety of predictive factors. Twenty-three variables and 193,373 records were utilized from the 2004 behavioral risk factor surveillance system survey data for this study. The artificial neural networks and the decision tree models were developed and compared to each other for predictive ability. The sensitivity analysis and variable importance measures are calculated to analyze the importance of the predictive factors. The experimental results indicated that the most accurate classifier for this phenomenon was the multi-layer perceptron type artificial neural network model that had an overall classification accuracy of 78.45% on the holdout sample. The most important predictive factors came out as income, employment status, education, and marital status. Using two popular machine learning techniques, this study identified the factors that can be used to accurately classify those with and without healthcare coverage. The ability to identify and explain the reasoning of those likely to be without healthcare coverage through the application of accurate classification models can potentially be used in reducing the disparity in healthcare coverage. [Copyright &y& Elsevier]