Search

Objectives.To evaluate the positive predictive value of machine learning algorithms for early assessment of adverse birth risk among pregnant women as a means of improving the allocation of social services. Methods. We used administrative data for 6457 women collected by the Illinois Department of Human Services from July 2014 to May 2015 to develop a machine learning model for adverse birth prediction and improve upon the existing paper-based risk assessment. We compared different models and determined the strongest predictors of adverse birth outcomes using positive predictive value as the metric for selection. Results. Machine learning algorithms performed similarly, outperforming the current paper-based risk assessment by up to 36%; a refined paper-based assessment outperformed the current assessment by up to 22%. We estimate that these improvements will allow 100 to 170 additional high-risk pregnant women screened for program eligibility each year to receive services that would have otherwise been unobtainable. Conclusions. Our analysis exhibits the potential for machine learning to move government agencies toward a more data-informed approach to evaluating risk and providing social services. Overall, such efforts will improve the efficiency of allocating resource-intensive interventions. [ABSTRACT FROM AUTHOR]

Algorithmic vision, the computational process of making meaning from digital images or visual information, has changed the relationship between the image and the human subject. In this paper, I explicate on the role of algorithmic vision as a technique of algorithmic governance, the organization of a population by algorithmic means. With its roots in the United States post-war cybernetic sciences, the ontological status of the computational image undergoes a shift, giving way to the hegemonic use of automated facial recognition technologies towards predatory policing and profiling practices. By way of example, I argue that algorithmic vision reconfigures the philosophical links between vision, image, and truth, paradigmatically changing the way a human subject is represented through imagistic data. With algorithmic vision, the relationship between subject and representation challenges the humanistic discourse around images, calling for a critical displacement of the human subject from the center of an analysis of how computational images make meaning. I will explore the relationship between the operative image, the image that acts but is not seen by human eyes, and what Louise Amoore calls an "emergent subject," a subject that is made visible through algorithmic techniques (2013). Algorithmic vision reveals subjects to power in a mode that requires a new approach towards analyzing the entanglement and invisiblization of the human in automated decision-making systems. [ABSTRACT FROM AUTHOR]

Purpose – This paper aims to analyze the relationship among measures of resource and service usage and other features of academic libraries in the USA and Canada. Design/methodology/approach – Through the use of a self-organizing map, academic library data were clustered and visualized. Analysis of the library data was conducted through the computation of a "library performance metric" that was applied to the resulting map. Findings – Two areas of high-performing academic libraries emerged on the map. One area included libraries with large numbers of resources, while another area included libraries that had low resources but gave greater numbers of presentations to groups, offered greater numbers of public service hours, and had greater numbers of staffed service points. Research limitations/implications – The metrics chosen as a measure of library performance offer only a partial picture of how libraries are being used. Future research might involve the use of a self-organizing map to cluster library data within certain parameters and the identification of high-performing libraries within these clusters. Practical implications – This study suggests that libraries can improve their performance not only by acquiring greater resources but also by putting greater emphasis on the services that they provide to their users. Originality/value – This paper demonstrates how a self-organizing map can be used in the analysis of large data sets to facilitate library comparisons. [ABSTRACT FROM AUTHOR]

This paper investigates the possibility of the implementation of Genetic Programming (GP) algorithm on a publicly available COVID-19 data set, in order to obtain mathematical models which could be used for estimation of confirmed, deceased, and recovered cases and the estimation of epidemiology curve for specific countries, with a high number of cases, such as China, Italy, Spain, and USA and as well as on the global scale. The conducted investigation shows that the best mathematical models produced for estimating confirmed and deceased cases achieved R2 scores of 0.999, while the models developed for estimation of recovered cases achieved the R2 score of 0.998. The equations generated for confirmed, deceased, and recovered cases were combined in order to estimate the epidemiology curve of specific countries and on the global scale. The estimated epidemiology curve for each country obtained from these equations is almost identical to the real data contained within the data set [ABSTRACT FROM AUTHOR]

The article offers a perspective on the main concepts of algorithmic fairness and how their application can improve the design of machine learning or artificial intelligence algorithms. Topics discussed include the increasing use of machine learning algorithms in decision making, interaction of algorithms with the existing ethical conflicts such as disparities and discrimination, and the impact of algorithm on health care in the U.S.

Artificial intelligence models represented in machine learning algorithms are promising tools for risk assessment used to guide clinical and other health care decisions. Machine learning algorithms, however, may house biases that propagate stereotypes, inequities, and discrimination that contribute to socioeconomic health care disparities. The biases include those related to some sociodemographic characteristics such as race, ethnicity, gender, age, insurance, and socioeconomic status from the use of erroneous electronic health record data. Additionally, there is concern that training data and algorithmic biases in large language models pose potential drawbacks. These biases affect the lives and livelihoods of a significant percentage of the population in the United States and globally. The social and economic consequences of the associated backlash cannot be underestimated. Here, we outline some of the sociodemographic, training data, and algorithmic biases that undermine sound health care risk assessment and medical decision-making that should be addressed in the health care system. We present a perspective and overview of these biases by gender, race, ethnicity, age, historically marginalized communities, algorithmic bias, biased evaluations, implicit bias, selection/sampling bias, socioeconomic status biases, biased data distributions, cultural biases and insurance status bias, conformation bias, information bias and anchoring biases and make recommendations to improve large language model training data, including de-biasing techniques such as counterfactual role-reversed sentences during knowledge distillation, fine-tuning, prefix attachment at training time, the use of toxicity classifiers, retrieval augmented generation and algorithmic modification to mitigate the biases moving forward. [ABSTRACT FROM AUTHOR]

The topic of algorithmic fairness is of increasing importance to the Human–Computer Interaction research community following accumulating concerns regarding the use and deployment of Artificial Intelligence-based systems. How we conduct research on algorithmic fairness directly influences our inferences and conclusions regarding algorithmic fairness. To better understand the methodological decisions of studies focused on people's perceptions of algorithmic fairness, we systematic analysed relevant papers from the CHI and FAccT conferences. We identified 200 relevant papers published between 1993 and 2022 and assessed their study design, participant sample, and geographical location of participants and authors. Our results highlight that studies are predominantly cross-sectional, cover a wide range of participant roles, and that both authors and participants are primarily from the United States. Based on these findings, we reflect on the potential pitfalls and shortcomings in how the community studies algorithmic fairness. • Mapping of CHI and FAccT papers on algorithmic fairness published 1993–2022. • Over one-third of papers miss details on participant locality and compensation. • Algorithmic fairness research largely restricted to US and other Western countries. • Limited cross-country collaboration, most study samples from a single country. • Remote studies are most common, longitudinal studies are relatively rare. [ABSTRACT FROM AUTHOR]

Racial disparities in hospice care are well documented for patients with cancer, but the existence, direction, and extent of disparity findings are contradictory across the literature. Current methods to identify racial disparities aggregate data to produce single-value quality measures that exclude important patient quality elements and, consequently, lack information to identify actionable equity improvement insights. Our goal was to develop an explainable machine learning approach that elucidates healthcare disparities and provides more actionable quality improvement information. We infused clinical information with engineering systems modeling and data science to develop a time-by-utilization profile per patient group at each hospital using US Medicare hospice utilization data for a cohort of patients with advanced (poor-prognosis) cancer that died April-December 2016. We calculated the difference between group profiles for people of color and white people to identify racial disparity signatures. Using machine learning, we clustered racial disparity signatures across hospitals and compared these clusters to classic quality measures and hospital characteristics. With 45,125 patients across 362 hospitals, we identified 7 clusters; 4 clusters (n = 190 hospitals) showed more hospice utilization by people of color than white people, 2 clusters (n = 106) showed more hospice utilization by white people than people of color, and 1 cluster (n = 66) showed no difference. Within-hospital racial disparity behaviors cannot be predicted from quality measures, showing how the true shape of disparities can be distorted through the lens of quality measures. This approach elucidates the shape of hospice racial disparities algorithmically from the same data used to calculate quality measures. [ABSTRACT FROM AUTHOR]

Abstract Owing to its recent advance, machine learning has spawned a large collection of solar forecasting works. In particular, machine learning is currently one of the most popular approaches for hourly solar forecasting. Nevertheless, there is evidently a myth on forecast accuracy—virtually all research papers claim superiority over others. Apparently, the "best" model can only be selected with hindsight, i.e., after empirical evaluation. For any new forecasting project, it is irrational for solar forecasters to bet on a single model from the start. In this article, the hourly forecasting performance of 68 machine learning algorithms is evaluated for 3 sky conditions, 7 locations, and 5 climate zones in the continental United States. To ensure a fair comparison, no hybrid model is considered, and only off-the-shelf implementations of these algorithms are used. Moreover, all models are trained using the automatic tuning algorithm available in the R caret package. It is found that tree-based methods consistently perform well in terms of two-year overall results, however, they rarely stand out during daily evaluation. Although no universal model can be found, some preferred ones for each sky and climate condition are advised. Highlights • Hourly solar forecasting is performed using 68 machine learning models. • Models are evaluated at 7 locations in 5 climate zones for 2 years. • Tree-based methods consistently perform well in terms of 2-year average metrics. • Daily best model cannot be identified, regime-switching approach is advised. [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]

Merging satellite products and ground-based measurements is often required for obtaining precipitation datasets that simultaneously cover large regions with high density and are more accurate than pure satellite precipitation products. Machine and statistical learning regression algorithms are regularly utilized in this endeavor. At the same time, tree-based ensemble algorithms are adopted in various fields for solving regression problems with high accuracy and low computational costs. Still, information on which tree-based ensemble algorithm to select for correcting satellite precipitation products for the contiguous United States (US) at the daily time scale is missing from the literature. In this study, we worked towards filling this methodological gap by conducting an extensive comparison between three algorithms of the category of interest, specifically between random forests, gradient boosting machines (gbm) and extreme gradient boosting (XGBoost). We used daily data from the PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks) and the IMERG (Integrated Multi-satellitE Retrievals for GPM) gridded datasets. We also used earth-observed precipitation data from the Global Historical Climatology Network daily (GHCNd) database. The experiments referred to the entire contiguous US and additionally included the application of the linear regression algorithm for benchmarking purposes. The results suggest that XGBoost is the best-performing tree-based ensemble algorithm among those compared. Indeed, the mean relative improvements that it provided with respect to linear regression (for the case that the latter algorithm was run with the same predictors as XGBoost) are equal to 52.66%, 56.26% and 64.55% (for three different predictor sets), while the respective values are 37.57%, 53.99% and 54.39% for random forests, and 34.72%, 47.99% and 62.61% for gbm. Lastly, the results suggest that IMERG is more useful than PERSIANN in the context investigated. [ABSTRACT FROM AUTHOR]

The past two decades have witnessed an increase in ethnicity-related peer aggression, driven by the intensification of the migration phenomenon and rise of information and communication technologies. The goal of the current study is to extend the scope of previous reviews on peer aggression to examine the emerging evidence on the role of technological tools in the prevention, detection, and handling of ethnicity-related peer aggression among young people. We have identified 14 relevant papers published between 2005 and 2020 that help us answer the following research questions: What forms of aggression among young ethnic minorities do these technological interventions try to address? What types of technological interventions are being used? The results indicate that the technological tools are being used to tackle both intergroup as well as intragroup peer aggression, in which ethnic minorities youth is involved (as a victim, perpetrator or bystander). Most studies have focused on adolescents and young adults in the US or in Europe. The technological tools reported on, include: online games, videos, social media, and chat-based programmes, or machine learning algorithms aimed at tackling online and offline peer aggression. They can be used either as stand - alone tools, or as part of intervention programmes (at the school, family or community level). These findings can be useful to improve and elaborate future digital technologies developed to address ethnicity-related peer aggression. • The review maps the existing literature on the role of technological tools in tackling ethnicity-related peer aggression. • All forms of peer aggression are considered in which ethnic minorities youth was involved. • Three groups of technological interventions are identified and categorized into intra- or intergroup ethnicity-related peer aggression. • The digital tools presented include: online games, video, social media, chat-based programmes, and machine learning algorithms. • Our study reveals some follow-up research questions needed to expand current knowledge on digital technologies. [ABSTRACT FROM AUTHOR]

Background Obstructive sleep apnea (OSA) is a highly prevalent sleep disorder associated with daytime sleepiness, fatigue, and increased all-cause mortality risk in patients with cancer. Existing screening tools for OSA do not account for the interaction of cancer-related features that may increase OSA risk. Study Design and Methods This is a retrospective study of patients with cancer at a single tertiary cancer institution who underwent a home sleep apnea test (HSAT) to evaluate for OSA. Unsupervised machine learning (ML) was used to reduce the dimensions and extract significant features associated with OSA. ML classifiers were applied to principal components and model hyperparameters were optimized using k-fold cross-validation. Training models for OSA were subsequently tested and compared with the STOP-Bang questionnaire on a prospective unseen test set of patients who underwent an HSAT. Results From a training dataset of 249 patients, kernel principal component analysis (PCA) extracted eight components through dimension reduction to explain the maximum variance with OSA at 98%. Predictors of OSA were smoking, asthma, chronic kidney disease, STOP-Bang score, race, diabetes, radiation to head/neck/thorax (RT-HNT), type of cancer, and cancer metastases. Of the ML models, PCA + RF had the highest sensitivity (96.8%), specificity (92.3%), negative predictive value (92%), F1 score (0.93), and ROC-AUC score (0.88). The PCA + RF screening algorithm also performed better than the STOP-Bang questionnaire alone when tested on a prospective unseen test set. Conclusions The PCA + RF ML model had the highest accuracy in screening for OSA in patients with cancer. History of RT-HNT, cancer metastases, and type of cancer were identified as cancer-related risk factors for OSA. [ABSTRACT FROM AUTHOR]

Early childhood is an important development period for establishing healthy physical activity (PA) habits. The objective of this study was to evaluate PA levels in a representative sample of U.S. preschool-aged children. The study sample included 301 participants (149 girls, 3–5 years of age) in the 2012 U.S. National Health and Examination Survey National Youth Fitness Survey. Participants were asked to wear an ActiGraph accelerometer on their wrist for 7 days. A machine learning random forest classification algorithm was applied to accelerometer data to estimate daily time spent in moderate- and vigorous-intensity PA (MVPA; the sum of minutes spent in running, walking, and other moderate- and vigorous-intensity PA) and total PA (the sum of MVPA and light-intensity PA). We estimated that U.S. preschool-aged children engaged in 28 min/day of MVPA and 361 min/day of total PA, on average. MVPA and total PA levels were not significantly different between males and females. This study revealed that U.S. preschool-aged children engage in lower levels of MVPA and higher levels of total PA than the minimum recommended by the World Health Organization. [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]

Autism spectrum disorder (ASD) can be reliably diagnosed at 18 months, yet significant diagnostic delays persist in the United States. This double-blinded, multi-site, prospective, active comparator cohort study tested the accuracy of an artificial intelligence-based Software as a Medical Device designed to aid primary care healthcare providers (HCPs) in diagnosing ASD. The Device combines behavioral features from three distinct inputs (a caregiver questionnaire, analysis of two short home videos, and an HCP questionnaire) in a gradient boosted decision tree machine learning algorithm to produce either an ASD positive, ASD negative, or indeterminate output. This study compared Device outputs to diagnostic agreement by two or more independent specialists in a cohort of 18–72-month-olds with developmental delay concerns (425 study completers, 36% female, 29% ASD prevalence). Device output PPV for all study completers was 80.8% (95% confidence intervals (CI), 70.3%–88.8%) and NPV was 98.3% (90.6%–100%). For the 31.8% of participants who received a determinate output (ASD positive or negative) Device sensitivity was 98.4% (91.6%–100%) and specificity was 78.9% (67.6%–87.7%). The Device's indeterminate output acts as a risk control measure when inputs are insufficiently granular to make a determinate recommendation with confidence. If this risk control measure were removed, the sensitivity for all study completers would fall to 51.6% (63/122) (95% CI 42.4%, 60.8%), and specificity would fall to 18.5% (56/303) (95% CI 14.3%, 23.3%). Among participants for whom the Device abstained from providing a result, specialists identified that 91% had one or more complex neurodevelopmental disorders. No significant differences in Device performance were found across participants' sex, race/ethnicity, income, or education level. For nearly a third of this primary care sample, the Device enabled timely diagnostic evaluation with a high degree of accuracy. The Device shows promise to significantly increase the number of children able to be diagnosed with ASD in a primary care setting, potentially facilitating earlier intervention and more efficient use of specialist resources. [ABSTRACT FROM AUTHOR]

The article focuses on debates on access to medical products and disability bioethics that claims challenges and mentions appealing work on cognitive biases and theoretical work on problems of partial representation. Topics include optimism concerning sharing insights across experimental gaps, concerns raised by bioethics community on approaches weakening regulatory authority of U.S. Food & Drug Administration (FDA), and providing access on evidence to patients to interfere with trials.

Knowledge embedded within artificial neural networks (ANNs) is distributed over the connections and weights of neurons. So, the user considers ANN as a black box system. There are many researches investigating the area of rule extraction by ANNs. In this paper, a dynamic cell structure (DCS) neural network and a modified version of LERX algorithm are used for rule extraction. On the other hand, intrusion detection system (IDS) is known as a critical technology to secure computer networks. So, the proposed algorithm is used to develop IDS and classify the patterns of intrusion. To compare the performance of the proposed system with other machine learning algorithms, multi-layer perceptron (MLP) with output weight optimization-hidden weight optimization (OWO-HWO) training algorithm is employed with selected inputs based on the results of a feature relevance analysis. Empirical results show the superior performance of the IDS based on rule extraction from DCS, in recognizing hard-detectable attack categories, e.g. userto- root (U2R) and also offering competitive false alarm rate (FAR). Although, MLP with 25 selected input features, instead of 41 standard features introduced by knowledge discovery and data mining group (KDD), performs better in terms of detection rate (DR) and cost per example (CPE) when compared with some other machine learning methods, as well. [ABSTRACT FROM AUTHOR]

This study uses machine-learning methods, specifically the random-forests (RF) method, on a radar-based mesoscale convective system (MCS) tracking dataset to classify the five types of linear MCS morphology in the contiguous United States during the period 2004–16. The algorithm is trained using radar- and satellite-derived spatial and morphological parameters, along with reanalysis environmental information from a 5-yr manually identified nonlinear mode and five linear MCS modes. The algorithm is then used to automate the classification of linear MCSs over 8 years with high accuracy, providing a systematic, long-term climatology of linear MCSs. Results reveal that nearly 40% of MCSs are classified as linear MCSs, of which one-half of the linear events belong to the type of system having a leading convective line. The occurrence of linear MCSs shows large annual and seasonal variations. On average, 113 linear MCSs occur annually during the warm season (March–October), with most of these events clustered from May through August in the central eastern Great Plains. MCS characteristics, including duration, propagation speed, orientation, and system cloud size, have large variability among the different linear modes. The systems having a trailing convective line and the systems having a back-building area of convection typically move more slowly and have higher precipitation rate, and thus they have higher potential for producing extreme rainfall and flash flooding. Analysis of the environmental conditions associated with linear MCSs show that the storm-relative flow is of most importance in determining the organization mode of linear MCSs. [ABSTRACT FROM AUTHOR]

Objective: The Centers for Disease Control and Prevention (CDC) coordinates a labor-intensive process to measure the prevalence of autism spectrum disorder (ASD) among children in the United States. Random forests methods have shown promise in speeding up this process, but they lag behind human classification accuracy by about 5%. We explore whether more recently available document classification algorithms can close this gap. Materials and methods: Using data gathered from a single surveillance site, we applied 8 supervised learning algorithms to predict whether children meet the case definition for ASD based solely on the words in their evaluations. We compared the algorithms’ performance across 10 random train-test splits of the data, using classification accuracy, F1 score, and number of positive calls to evaluate their potential use for surveillance. Results: Across the 10 train-test cycles, the random forest and support vector machine with Naive Bayes features (NB-SVM) each achieved slightly more than 87% mean accuracy. The NB-SVM produced significantly more false negatives than false positives (P = 0.027), but the random forest did not, making its prevalence estimates very close to the true prevalence in the data. The best-performing neural network performed similarly to the random forest on both measures. Discussion: The random forest performed as well as more recently available models like the NB-SVM and the neural network, and it also produced good prevalence estimates. NB-SVM may not be a good candidate for use in a fully-automated surveillance workflow due to increased false negatives. More sophisticated algorithms, like hierarchical convolutional neural networks, may not be feasible to train due to characteristics of the data. Current algorithms might perform better if the data are abstracted and processed differently and if they take into account information about the children in addition to their evaluations. Conclusion: Deep learning models performed similarly to traditional machine learning methods at predicting the clinician-assigned case status for CDC’s autism surveillance system. While deep learning methods had limited benefit in this task, they may have applications in other surveillance systems. [ABSTRACT FROM AUTHOR]

Rising admissions from emergency departments (EDs) to hospitals are a primary concern for many healthcare systems. The issue of how to differentiate urgent admissions from non-urgent or even elective admissions is crucial. We aim to develop a model for classifying inpatient admissions based on a patient's primary diagnosis as either emergency care or elective care and predicting urgency as a numerical value. We use supervised machine learning techniques and train the model with physician-expert judgments. Our model is accurate (96%) and has a high area under the ROC curve (>.99). We provide the first comprehensive classification and urgency categorization for inpatient emergency and elective care. This model assigns urgency values to every relevant diagnosis in the ICD catalog, and these values are easily applicable to existing hospital data. Our findings may provide a basis for policy makers to create incentives for hospitals to reduce the number of inappropriate ED admissions. [ABSTRACT FROM AUTHOR]

Machine-learning algorithms are improving and automating important functions in medicine, transportation, and business. Government officials have also started to take notice of the accuracy and speed that such algorithms provide, increasingly relying on them to aid with consequential public-sector functions, including tax administration, regulatory oversight, and benefits administration. Despite machine-learning algorithms’ superior predictive power over conventional analytic tools, algorithmic forecasts are difficult to understand and explain. Machine learning’s “black box” nature has thus raised concern: Can algorithmic governance be squared with legal principles of governmental transparency? We analyze this question and conclude that machine-learning algorithms’ relative inscrutability does not pose a legal barrier to their responsible use by governmental authorities. We distinguish between principles of “fishbowl transparency” and “reasoned transparency,” explaining how both are implicated by algorithmic governance but also showing that neither conception compels anything close to total transparency. Although machine learning’s black-box features distinctively implicate notions of reasoned transparency, legal demands for reason-giving can be satisfied by explaining an algorithm’s purpose, design, and basic functioning. Furthermore, new technical advances will only make machine-learning algorithms increasingly more explainable. Algorithmic governance can meet both legal and public demands for transparency while still enhancing accuracy, efficiency, and even potentially legitimacy in government. [ABSTRACT FROM AUTHOR]

Background: Risk prediction is crucial in many areas of medical practice, such as cardiac transplantation, but existing clinical risk-scoring methods have suboptimal performance. We develop a novel risk prediction algorithm and test its performance on the database of all patients who were registered for cardiac transplantation in the United States during 1985-2015. Methods and findings: We develop a new, interpretable, methodology (ToPs: Trees of Predictors) built on the principle that specific predictive (survival) models should be used for specific clusters within the patient population. ToPs discovers these specific clusters and the specific predictive model that performs best for each cluster. In comparison with existing clinical risk scoring methods and state-of-the-art machine learning methods, our method provides significant improvements in survival predictions, both post- and pre-cardiac transplantation. For instance: in terms of 3-month survival post-transplantation, our method achieves AUC of 0.660; the best clinical risk scoring method (RSS) achieves 0.587. In terms of 3-year survival/mortality predictions post-transplantation (in comparison to RSS), holding specificity at 80.0%, our algorithm correctly predicts survival for 2,442 (14.0%) more patients (of 17,441 who actually survived); holding sensitivity at 80.0%, our algorithm correctly predicts mortality for 694 (13.0%) more patients (of 5,339 who did not survive). ToPs achieves similar improvements for other time horizons and for predictions pre-transplantation. ToPs discovers the most relevant features (covariates), uses available features to best advantage, and can adapt to changes in clinical practice. Conclusions: We show that, in comparison with existing clinical risk-scoring methods and other machine learning methods, ToPs significantly improves survival predictions both post- and pre-cardiac transplantation. ToPs provides a more accurate, personalized approach to survival prediction that can benefit patients, clinicians, and policymakers in making clinical decisions and setting clinical policy. Because survival prediction is widely used in clinical decision-making across diseases and clinical specialties, the implications of our methods are far-reaching. [ABSTRACT FROM AUTHOR]

Electric water heaters represent 14% of the electricity consumption in residential buildings. An average household in the United States (U.S.) spends about USD 400–600 (0.45 ¢/L–0.68 ¢/L) on water heating every year. In this context, water heaters are often considered as a valuable asset for Demand Response (DR) and building energy management system (BEMS) applications. To this end, this study proposes a model-free deep reinforcement learning (RL) approach that aims to minimize the electricity cost of a water heater under a time-of-use (TOU) electricity pricing policy by only using standard DR commands. In this approach, a set of RL agents, with different look ahead periods, were trained using the deep Q-networks (DQN) algorithm and their performance was tested on an unseen pair of price and hot water usage profiles. The testing results showed that the RL agents can help save electricity cost in the range of 19% to 35% compared to the baseline operation without causing any discomfort to end users. Additionally, the RL agents outperformed rule-based and model predictive control (MPC)-based controllers and achieved comparable performance to optimization-based control. [ABSTRACT FROM AUTHOR]

Effective information systems require the existence of explicit process models. A completely specified process design needs to be developed in order to enact a given business process. This development is time consuming and often subjective and incomplete. We propose a method that constructs the process model from process log data, by determining the relations between process tasks. To predict these relations, we employ machine learning technique to induce rule sets. These rule sets are induced from simulated process log data generated by varying process characteristics such as noise and log size. Tests reveal that the induced rule sets have a high predictive accuracy on new data. The effects of noise and imbalance of execution priorities during the discovery of the relations between process tasks are also discussed. Knowing the causal, exclusive, and parallel relations, a process model expressed in the Petri net formalism can be built. We illustrate our approach with real world data in a case study. [ABSTRACT FROM AUTHOR]

Protein domains are the structural and functional units of proteins. The ability to parse protein chains into different domains is important for protein classification and for understanding protein structure, function, and evolution. Here we use machine learning algorithms, in the form of recursive neural networks, to develop a protein domain predictor called DOMpro. DOMpro predicts protein domains using a combination of evolutionary information in the form of profiles, predicted secondary structure, and predicted relative solvent accessibility. DOMpro is trained and tested on a curated dataset derived from the CATH database. DOMpro correctly predicts the number of domains for 69% of the combined dataset of single and multi-domain chains. DOMpro achieves a sensitivity of 76% and specificity of 85% with respect to the single-domain proteins and sensitivity of 59% and specificity of 38% with respect to the two-domain proteins. DOMpro also achieved a sensitivity and specificity of 71% and 71% respectively in the Critical Assessment of Fully Automated Structure Prediction 4 (CAFASP-4) (Fisher et al., 1999; Saini and Fischer, 2005) and was ranked among the top ab initio domain predictors. The DOMpro server, software, and dataset are available at http://www.igb.uci.edu/servers/psss.html. [ABSTRACT FROM AUTHOR]