Search

Background: Teachers often rely on the use of open‐ended questions to assess students' conceptual understanding of assigned content. Particularly in the context of mathematics; teachers use these types of questions to gain insight into the processes and strategies adopted by students in solving mathematical problems beyond what is possible through more close‐ended problem types. While these types of problems are valuable to teachers, the variation in student responses to these questions makes it difficult, and time‐consuming, to evaluate and provide directed feedback. It is a well‐studied concept that feedback, both in terms of a numeric score but more importantly in the form of teacher‐authored comments, can help guide students as to how to improve, leading to increased learning. It is for this reason that teachers need better support not only for assessing students' work but also in providing meaningful and directed feedback to students. Objectives: In this paper, we seek to develop, evaluate, and examine machine learning models that support automated open response assessment and feedback. Methods: We build upon the prior research in the automatic assessment of student responses to open‐ended problems and introduce a novel approach that leverages student log data combined with machine learning and natural language processing methods. Utilizing sentence‐level semantic representations of student responses to open‐ended questions, we propose a collaborative filtering‐based approach to both predict student scores as well as recommend appropriate feedback messages for teachers to send to their students. Results and Conclusion: We find that our method outperforms previously published benchmarks across three different metrics for the task of predicting student performance. Through an error analysis, we identify several areas where future works may be able to improve upon our approach. Lay Description: What is already known about this topic: Open‐ended questions are used by teachers in the domain of mathematics to assess their students understanding but automated support for these types of questions are limited in online learning platforms. Recent advancements in areas of machine learning and natural language processing have led to promising results in a range of domains and applications. What this paper adds: Emulating how teachers identify similar student answers can be used to build tools that support teachers in assessing and providing feedback to student open‐ended work. Implications for practice: Developing better automated supports can increase the amount of direct feedback students receive to guide their learning. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this study was to explore the concept of distrust of traditional banking institutions as a factor that can explain the choice to remain unbanked in a marketplace that is designed to be financially inclusive. Design/methodology/approach: Earning, spending, saving and borrowing data collected between May 2021 and February 2022 from 17,819 consumers living in the United States were used to examine the factors associated with distrust of banks. Using a conceptual framework borrowed from the health services profession, the study was conducted in two stages. At the first stage, distrust among the unbanked and banked was estimated using a Boruta-random forest algorithm. At the second stage of the analysis, a logit regression model was estimated to validate the variables identified in the Boruta-random forest analysis. Findings: Results from the analyses show that distrust of banks is multi-layered where being older, believing the country is heading in the wrong direction and being less confident in one's ability to obtain a personal loan in the amount of $1 to $999 are important factors related to distrust of banks among the unbanked. Research limitations/implications: This study shows how an ensemble machine learning technique based on a decision-tree methodology can be used to obtain unique insights into complicated data and large datasets within the bank marketing field. Originality/value: The paper provides a discussion about ways domains of trust and specific variables can be utilized to address the persistent problem of financial exclusion in the United States. Implications for bankers, researchers, educators and policymakers are provided. [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]

Suicide is the second leading cause of death among individuals aged 5 to 24 in the United States (US). However, the precursors to suicide often do not surface, making suicide prevention challenging. This study aims to develop a machine learning model for predicting suicide ideation (SI), suicide planning (SP), and suicide attempts (SA) among adolescents in the US during the coronavirus pandemic. We used the 2021 Adolescent Behaviors and Experiences Survey Data. Class imbalance was addressed using the proposed data augmentation method tailored for binary variables, Modified Synthetic Minority Over-Sampling Technique. Five different ML models were trained and compared. SHapley Additive exPlanations analysis was conducted for explainability. The Logistic Regression model, identified as the most effective, showed superior performance across all targets, achieving high scores in recall: 0.82, accuracy: 0.80, and area under the Receiver Operating Characteristic curve: 0.88. Variables such as sad feelings, hopelessness, sexual behavior, and being overweight were noted as the most important predictors. Our model holds promise in helping health policymakers design effective public health interventions. By identifying vulnerable sub-groups within regions, our model can guide the implementation of tailored interventions that facilitate early identification and referral to medical treatment. [ABSTRACT FROM AUTHOR]

Aim: To develop and validate models based on logistic regression and artificial intelligence for prognostic prediction of molar survival in periodontally affected patients. Materials and Methods: Clinical and radiographic data from four different centres across four continents (two in Europe, one in the United States, and one in China) including 515 patients and 3157 molars were collected and used to train and test different types of machine‐learning algorithms for their prognostic ability of molar loss over 10 years. The following models were trained: logistic regression, support vector machine, K‐nearest neighbours, decision tree, random forest, artificial neural network, gradient boosting, and naive Bayes. In addition, different models were aggregated by means of the ensembled stacking method. The primary outcome of the study was related to the prediction of overall molar loss (MLO) in patients after active periodontal treatment. Results: The general performance in the external validation settings (aggregating three cohorts) revealed that the ensembled model, which combined neural network and logistic regression, showed the best performance among the different models for the prediction of MLO with an area under the curve (AUC) = 0.726. The neural network model showed the best AUC of 0.724 for the prediction of periodontitis‐related molar loss. In addition, the ensembled model showed the best calibration performance. Conclusions: Through a multi‐centre collaboration, both prognostic models for the prediction of molar loss were developed and externally validated. The ensembled model showed the best performance in terms of both discrimination and validation, and it is made freely available to clinicians for widespread use in clinical practice. [ABSTRACT FROM AUTHOR]

Background and Objective: Computer-based neurocognitive tests are widely used in sport-related concussion management, but the performance of these tests is not well understood in the participant population with attention-deficit/hyperactivity disorder (ADHD) and/or learning disorder (LD). This research estimates the sensitivity and specificity performance of the Immediate Post-Concussion Assessment and Cognitive Testing (ImPACT) computer-based neurocognitive test in identifying concussion in this population. Methods: Study participants consisted of collegiate university athletes and military service academy cadets from the National Collegiate Athletic Association-Department of Defense CARE Consortium who completed the ImPACT test between 2014 and 2021. Participants who self-identified as belonging to one of the subgroups of interest (ADHD with or without LD [ADHD:LD+/−], LD with or without ADHD [LD:ADHD+/−], ADHD and/or LD [ADHD a/o LD]) and completed a baseline (1874 ADHD:LD+/−, 779 LD:ADHD+/−, 2338 ADHD a/o LD) or 24–48 h post-concussion (175 ADHD:LD+/−, 77 LD:ADHD+/−, 216 ADHD a/o LD) ImPACT assessment were included. Sensitivity and specificity were calculated using a normative data method and three machine learning classification methods: logistic regression, classification and regression tree, and random forest. Results: Using the four methods, participants with ADHD:LD+/− had sensitivities that ranged from 0.474 to 0.697, and specificities that ranged from 0.538 to 0.686. Participants with LD:ADHD+/− had sensitivities that ranged from 0.455 to 0.688, and specificities that ranged from 0.456 to 0.588. For participants with ADHD a/o LD, sensitivities ranged from 0.542 to 0.755, and specificities ranged from 0.451 to 0.724. Conclusions: For all subgroups and analytical methods, the results illustrate sensitivity and specificity values below typically accepted levels indicative of clinical utility. These findings support that using ImPACT alone may be insufficient to inform concussion diagnoses and encourages the use of a multi-dimensional concussion assessment. [ABSTRACT FROM AUTHOR]

Purpose: We sought to develop and validate an incident non-small cell lung cancer (NSCLC) algorithm for United States (US) healthcare claims data. Diagnoses and procedures, but not medications, were incorporated to support longer-term relevance and reliability. Methods: Patients with newly diagnosed NSCLC per Surveillance, Epidemiology, and End Results (SEER) served as cases. Controls included newly diagnosed small-cell lung cancer and other lung cancers, and two 5% random samples for other cancer and without cancer. Algorithms derived from logistic regression and machine learning methods used the entire sample (Approach A) or started with a previous algorithm for those with lung cancer (Approach B). Sensitivity, specificity, positive predictive values (PPV), negative predictive values, and F-scores (compared for 1000 bootstrap samples) were calculated. Misclassification was evaluated by calculating the odds of selection by the algorithm among true positives and true negatives. Results: The best performing algorithm utilized neural networks (Approach B). A 10-variable point-score algorithm was derived from logistic regression (Approach B); sensitivity was 77.69% and PPV = 67.61% (F-score = 72.30%). This algorithm was less sensitive for patients ≥ 80 years old, with Medicare follow-up time < 3 months, or missing SEER data on stage, laterality, or site and less specific for patients with SEER primary site of main bronchus, SEER summary stage 2000 regional by direct extension only, or pre-index chronic pulmonary disease. Conclusion: Our study developed and validated a practical, 10-variable, point-based algorithm for identifying incident NSCLC cases in a US claims database based on a previously validated incident lung cancer algorithm. [ABSTRACT FROM AUTHOR]

This paper investigated whether the commonly observed immigrant health advantage persists among undocumented immigrants in the U.S. and provides nationally representative evidence on the health of this vulnerable population. Data were derived from pooled cross-sections of the National Health Interview Survey (NHIS, 2000–2018). The legal status of foreign-born NHIS respondents is imputed using a non-parametric machine learning model built based on information from the 2004, 2008 and 2014 cohorts of the Survey of Income and Program Participation (SIPP). Multivariate logistic regression analysis indicated that, despite exposure to numerous additional risk factors, the undocumented population experienced a more pronounced Healthy Migrant Effect, with lower odds of reporting fair or poor self-rated health, any physician-diagnosed chronic conditions or being obese. The observed patterns in undocumented health outcomes may be related to the additional challenges and exclusionary policies associated with undocumented migration that could in turn lead to a more pronounced selection of healthy and resilient individuals. • Undocumented immigrants had 26% lower odds of reporting poor or fair health. • Undocumented immigrants had 23% lower odds of having been diagnosed with a chronic condition. • Undocumented immigrants had 8% lower odds of being obese. • Differences in health behaviors do not explain the health advantage of undocumented immigrants. • Residence in the US 5+ years is positively associated with worse health outcomes. [ABSTRACT FROM AUTHOR]

A cluster model incorporating heterogeneous dose distribution within the parotid gland was developed and validated retrospectively for radiotherapy (RT) induced xerostomia prediction with machine learning (ML) techniques. Sixty clusters were obtained at 1 Gy step size with threshold doses ranging from 1 to 60 Gy, for each of the enrolled 155 patients with HNC from three institutions. Feature clusters were selected with the neighborhood component analysis (NCA) and subsequently fed into four supervised ML models for xerostomia prediction comparison: support vector machines (SVM), k-nearest neighbor (kNN), naïve Bayes (NB), and random forest (RF). The predictive performance of each model was evaluated using cross validation resampling with the area-under-the-curves (AUC) of the receiver-operating-characteristic (ROC). The xerostomia predicting capacity using testing data was assessed with accuracy, sensitivity, and specificity for these models and three cluster connectivity choices. Mean dose based logistic regression served as the benchmark for evaluation. Feature clusters identified by NCA fell in three threshold dose ranges: 5–15Gy, 25–35Gy, and 45–50Gy. Mean dose predictive power was 15% lower than that of the cluster model using the logistic regression classifier. Model validation demonstrated that kNN model outperformed slightly other three models but no substantial difference was observed. Applying the fine-tuned models to testing data yielded that the mean accuracy from SVM, kNN and NB models were between 0.68 and 0.7 while that of RF was ∼0.6. SVM model yielded the best sensitivity (0.76) and kNN model delivered consistent sensitivity and specificity. This is consistent with cross validation. Clusters calculated with three connectivity choices exhibited minimally different predictions. Compared to mean dose, the proposed cluster model has shown its improvement as the xerostomia predictor. When combining with ML techniques, it could provide a clinically useful tool for xerostomia prediction and facilitate decision making during radiotherapy planning for patients with HNC. [ABSTRACT FROM AUTHOR]

• Proposing an interpretable utility-based framework for dynamic activity pattern estimation. • Mapping from individual trip chains to aggregated activity location types. • Estimating traveler behavior with the support of multiple data sources. • Integrating machine learning tools, nested logit model and transportation domain knowledge. • Testing the proposed framework using 2017 national household survey and Google mobility dataset. During the coronavirus disease 2019 pandemic, the activity engagement and travel behavior of city residents have been impacted by government restrictions, such as temporary city-wide lockdowns, the closure of public areas and public transport suspension. Based on multiple heterogeneous data sources, which include aggregated mobility change reports and household survey data, this paper proposes a machine learning approach for dynamic activity chain pattern estimation with improved interpretability for examining behavioral pattern adjustments. Based on historical household survey samples, we first establish a computational graph-based discrete choice model to estimate the baseline travel tour parameters before the pandemic. To further capture structural deviations of activity chain patterns from day-by-day time series, we define the activity-oriented deviation parameters within an interpretable utility-based nested logit model framework, which are further estimated through a constrained optimization problem. By incorporating the long short-term memory method as the explainable module to capture the complex periodic and trend information before and after interventions, we predict day-to-day activity chain patterns with more accuracy. The performance of our model is examined based on publicly available datasets such as the 2017 National Household Travel Survey in the United States and the Google Global Mobility Dataset throughout the epidemic period. Our model could shed more light on transportation planning, policy adaptation and management decisions during the pandemic and post-pandemic phases. [ABSTRACT FROM AUTHOR]

It has been recognized that wildfire, followed by large precipitation events, triggers both flooding and debris flows in mountainous regions. The ability to predict and mitigate these hazards is crucial in protecting public safety and infrastructure. A need for advanced modeling techniques was highlighted by re-evaluating existing prediction models from the literature. Data from 15 individual burn basins in the intermountain western United States, which contained 388 instances and 26 variables, were obtained from the United States Geological Survey (USGS). After randomly selecting a subset of the data to serve as a validation set, advanced predictive modeling techniques, using machine learning, were implemented using the remaining training data. Tenfold cross-validation was applied to the training data to ensure nearly unbiased error estimation and also to avoid model over-fitting. Linear, nonlinear, and rule-based predictive models including naïve Bayes, mixture discriminant analysis, classification trees, and logistic regression models were developed and tested on the validation dataset. Results for the new non-linear approaches were nearly twice as successful as those for the linear models, previously published in debris flow prediction literature. The new prediction models advance the current state-of-the-art of debris flow prediction and improve the ability to accurately predict debris flow events in wildfire-prone intermountain western United States. [ABSTRACT FROM AUTHOR]