Understanding healthy ageing in India: insights from multivariate regression trees.

BACKGROUND: Population ageing represents a significant global challenge, particularly pronounced in countries like India. AIMS: This study aims to explore how factors such as socio-economic status, behaviour, and health influence healthy ageing across the Indian older population. METHODS: In this study, we utilized the Longitudinal Ageing Study in India - wave 1 dataset for analysis purposes. Scores were generated for five dimensions of healthy aging, including physical, functional, mental, cognitive, and social aspects and these scores were treated as the target variables. Multivariate Regression Trees analysis was employed to identify the behavioural and socio-demographic factors associated with each dimension of healthy ageing. RESULTS: Years of education emerge as crucial across all dimensions, positively impacting cognitive health and mitigating age-related decline in healthy ageing. Marital status, engagement in household activities, spiritual practices, and living arrangements impacts the scores of different aspects of healthy ageing. Gender disparities in healthy aging are noticeable in the 60-74 age group, with women generally having lower scores. Safety of the living environment is a crucial determinant of the mental health of the elderly across all age groups.These findings highlight the complex interplay of factors in healthy ageing outcomes. CONCLUSION: Our study emphasizes the pivotal role of education in fostering healthy ageing in India. Factors such as environmental safety and social participation also influence well-being. Targeted interventions addressing education, gender equality, safety, and healthcare access are vital for enhancing the ageing experience and overall well-being of older adults.

Missing data imputation using classification and regression trees.

Background: Missing data are common when analyzing real data. One popular solution is to impute missing data so that one complete dataset can be obtained for subsequent data analysis. In the present study, we focus on missing data imputation using classification and regression trees (CART). Methods: We consider a new perspective on missing data in a CART imputation problem and realize the perspective through some resampling algorithms. Several existing missing data imputation methods using CART are compared through simulation studies, and we aim to investigate the methods with better imputation accuracy under various conditions. Some systematic findings are demonstrated and presented. These imputation methods are further applied to two real datasets: Hepatitis data and Credit approval data for illustration. Results: The method that performs the best strongly depends on the correlation between variables. For imputing missing ordinal categorical variables, the rpart package with surrogate variables is recommended under correlations larger than 0 with missing completely at random (MCAR) and missing at random (MAR) conditions. Under missing not at random (MNAR), chi-squared test methods and the rpart package with surrogate variables are suggested. For imputing missing quantitative variables, the iterative imputation method is most recommended under moderate correlation conditions.

Predicting plant disease epidemics using boosted regression trees.

Plant epidemics are often associated with weather-related variables. It is difficult to identify weather-related predictors for models predicting plant epidemics. In the article by Shah et al., to predict Fusarium head blight (FHB) epidemics of wheat, they explored a functional approach using scalar-on-function regression to model a binary outcome (FHB epidemic or non-epidemic) with respect to weather time series spanning 140 days relative to anthesis. The scalar-on-function models fit the data better than previously described logistic regression models. In this work, given the same dataset and models, we attempt to reproduce the article by Shah et al. using a different approach, boosted regression trees. After fitting, the classification accuracy and model statistics are surprisingly good.

Heterogeneous Distributed Lag Models to Estimate Personalized Effects of Maternal Exposures to Air Pollution.

Children's health studies support an association between maternal environmental exposures and children's birth outcomes. A common goal is to identify critical windows of susceptibility-periods during gestation with increased association between maternal exposures and a future outcome. The timing of the critical windows and magnitude of the associations are likely heterogeneous across different levels of individual, family, and neighborhood characteristics. Using an administrative Colorado birth cohort we estimate the individualized relationship between weekly exposures to fine particulate matter (PM 2.5) during gestation and birth weight. To achieve this goal, we propose a statistical learning method combining distributed lag models and Bayesian additive regression trees to estimate critical windows at the individual level and identify characteristics that induce heterogeneity from a high-dimensional set of potential modifying factors. We find evidence of heterogeneity in the PM 2.5 -birth weight relationship, with some mother-child dyads showing a 3 times larger decrease in birth weight for an IQR increase in exposure (5.9 to 8.5 PM 2.5 µg/m3) compared to the population average. Specifically, we find increased vulnerabilitity for non-Hispanic mothers who are either younger, have higher body mass index or lower educational attainment. Our case study is the first precision health study of critical windows.

Development and application of a weighted change score to evaluate interventions for vasomotor symptoms in patients with breast cancer using regression trees: a cohort study.

PURPOSE: Vasomotor symptoms (VMS) are common among individuals with breast cancer (BC) and poorly managed symptoms are associated with reduced quality of life, treatment discontinuation, and poorer breast cancer outcomes. Direct comparisons among therapies are limited, as prior studies evaluating VMS interventions have utilized heterogeneous change measures which may not fully assess the perceived impact of change in VMS severity. METHODS: We performed a prospective study where BC patients chose one of four categories of interventions to manage VMS. Change in VMS severity at 6 weeks was assessed using the validated Hot Flush Rating Scale (HFRS). A novel weighted change score integrating baseline symptom severity and directionality of change was computed to maximize the correlation between the change score and a perceived treatment effectiveness score. Variables influencing change in VMS severity were included in a regression tree to model factors influencing the weighted change score. RESULTS: 100 baseline and follow-up questionnaires assessing VMS were completed by 88 patients. Correlations between treatment effectiveness and VMS outcomes strengthened following adjustment for baseline symptoms. Patients with low VMS severity at baseline did not perceive change in treatment effectiveness. Intervention category was predictive of change in HFRS at 6 weeks. CONCLUSION: Baseline symptom severity and the directionality of change (improvement or deterioration of symptoms) influenced the perception of clinically meaningful change in VMS severity. Future interventional studies utilizing the weighted change score should target moderate-high baseline severity patients.

Hybrid machine learning model based predictions for properties of poly(2-hydroxyethyl methacrylate)-poly(vinyl alcohol) composite cryogels embedded with bacterial cellulose.

Supermacroporous composite cryogels with enhanced adjustable functionality have received extensive interest in bioseparation, tissue engineering, and drug delivery. However, the variations in their components significantly impactfinal properties. This study presents a two-step hybrid machine learning approach for predicting the properties of innovative poly(2-hydroxyethyl methacrylate)-poly(vinyl alcohol) composite cryogels embedded with bacterial cellulose (pHEMA-PVA-BC) based on their compositions. By considering the ratios of HEMA (1.0-22.0 wt%), PVA (0.2-4.0 wt%), poly(ethylene glycol) diacrylate (1.0-4.5 wt%), BC (0.1-1.5 wt%), and water (68.0-96.0 wt%) as investigational variables, overlay sampling uniform design (OSUD) was employed to construct a high-quality dataset for model development. The random forest (RF) model was used to classify the preparation conditions. Then four models of artificial neural network, RF, gradient boosted regression trees (GBRT), and XGBoost were developed to predict the basic properties of the composite cryogels. The results showed that the RF model achieved an accurate three-class classification of preparation conditions. Among the four models, the GBRT model exhibited the best predictive performance of the basic properties, with the mean absolute percentage error of 16.04 %, 0.85 %, and 2.44 % for permeability, effective porosity, and height of theoretical plate (1.0 cm/min), respectively. Characterization results of the representative pHEMA-PVA-BC composite cryogel showed an effective porosity of 81.01 %, a permeability of 1.20 × 10-12 m2, and a range of height of theoretical plate between 0.40-0.49 cm at flow velocities of 0.5-3.0 cm/min. These indicate that the pHEMA-PVA-BC cryogel was an excellent material with supermacropores, low flow resistance and high mass transfer efficiency. Furthermore, the model output demonstrates that the alteration of the proportions of PVA (0.2-3.5 wt%) and BC (0.1-1.5 wt%) components in composite cryogels resulted in significant changes in the material basic properties. This work represents an attempt to efficiently design and prepare target composite cryogels using machine learning and providing valuable insights for the efficient development of polymers.

A novel data-driven model for prediction and adaptive control of pH in raceway reactor for microalgae cultivation.

This work proposes a new data-driven model to estimate and predict pH dynamics in freshwater raceway photobioreactors. The resulting model is based purely on data measured from the reactor and divides the pH dynamics into two different behaviors. One behavior is described by the variation of pH due to the photosynthesis phenomena made by microalgae; and the other comes from the effect of CO2 injections into the medium for control purposes. Moreover, it was observed that the model parameters vary throughout the day depending on the weather conditions and reactor status. Thus, a decision tree algorithm is also developed to capture the parameter variation based on measured variables of the system, such as solar radiation, medium temperature, and medium level. The proposed model has been validated for a data set of more than 100 days during 10 months in a semi-industrial raceway reactor, covering a wide range of weather and system scenarios. Additionally, the proposed model was used to design an adaptive control algorithm which was also experimentally tested and compared with a classical fixed parameter control approach.

Enhancing Pulmonary Embolism Mortality Risk Stratification Using Machine Learning: The Role of the Neutrophil-to-Lymphocyte Ratio.

(1) Background: Acute pulmonary embolism (PE) is a significant public health concern that requires efficient risk estimation to optimize patient care and resource allocation. The purpose of this retrospective study was to show the correlation of NLR (neutrophil-to-lymphocyte ratio) and PESI (pulmonary embolism severity index)/sPESI (simplified PESI) in determining the risk of in-hospital mortality in patients with pulmonary thromboembolism. (2) Methods: A total of 160 patients admitted at the County Clinical Emergency Hospital of Sibiu from 2019 to 2022 were included and their hospital records were analyzed. (3) Results: Elevated NLR values were significantly correlated with increased in-hospital mortality. Furthermore, elevated NLR was associated with PESI and sPESI scores and their categories, as well as the individual components of these parameters, namely increasing age, hypotension, hypoxemia, and altered mental status. We leveraged the advantages of machine learning algorithms to integrate elevated NLR into PE risk stratification. Utilizing two-step cluster analysis and CART (classification and regression trees), several distinct patient subgroups emerged with varying in-hospital mortality rates based on combinations of previously validated score categories or their defining elements and elevated NLR, WBC (white blood cell) count, or the presence COVID-19 infection. (4) Conclusion: The findings suggest that integrating these parameters in risk stratification can aid in improving predictive accuracy of estimating the in-hospital mortality of PE patients.

Environmental Controls on Evapotranspiration and Its Components in a Qinghai Spruce Forest in the Qilian Mountains.

Qinghai spruce forests, found in the Qilian mountains, are a typical type of water conservation forest and play an important role in regulating the regional water balance and quantifying the changes and controlling factors for evapotranspiration (ET) and its components, namely, transpiration (T), evaporation (Es) and canopy interceptions (Ei), of the Qinghai spruce, which may provide rich information for improving water resource management. In this study, we partitioned ET based on the assumption that total ET equals the sum of T, Es and Ei, and then we analyzed the environmental controls on ET, T and Es. The results show that, during the main growing seasons of the Qinghai spruce (from May to September) in the Qilian mountains, the total ET values were 353.7 and 325.1 mm in 2019 and 2020, respectively. The monthly dynamics in the daily variations in T/ET and Es/ET showed that T/ET increased until July and gradually decreased afterwards, while Es/ET showed opposite trends and was mainly controlled by the amount of precipitation. Among all the ET components, T always occupied the largest part, while the contribution of Es to ET was minimal. Meanwhile, Ei must be considered when partitioning ET, as it accounts for a certain percentage (greater than one-third) of the total ET values. Combining Pearson's correlation analysis and the boosted regression trees method, we concluded that net radiation (Rn), soil temperature (Ts) and soil water content (SWC) were the main controlling factors for ET. T was mainly determined by the radiation and soil hydrothermic factors (Rn, photosynthetic active radiation (PAR) and TS30), while Es was mostly controlled by the vapor pressure deficit (VPD), atmospheric precipitation (Pa), throughfall (Pt) and air temperature (Ta). Our study may provide further theoretical support to improve our understanding of the responses of ET and its components to surrounding environments.

Spatio-temporal classification of land use and land cover and its changes in Kerala using remote sensing and machine learning approach.

Land use and land cover (LULC) analysis gives important information on how the region has evolved over time. Kerala, a land with an extensive and dynamic history of land-use changes, has, until now, lacked comprehensive investigations into this history. So the current study focuses on Kerala, one of the ecologically diverse states in India with complex topography, through Landsat images taken from 1990 to 2020 using two different machine learning classifications, random forest (RF) and classification and regression trees (CART) on Google Earth Engine (GEE) platform. RF and CART are versatile machine learning algorithms frequently employed for classification and regression, offering effective tools for predictive modelling across diverse domains due to their flexibility and data-handling capabilities. Normalised Difference Vegetation Index (NDVI), Normalised Differences Built-up Index (NDBI), Modified Normalised Difference Water Index (MNDWI), and Bare soil index (BSI) are integral indices utilised to enhance the precision of land use and land cover classification in satellite imagery, playing a crucial role by providing valuable insights into specific landscape attributes that may be challenging to identify using individual spectral bands alone. The results showed that the performance of RF is better than that of CART in all the years. Thus, RF algorithm outputs are used to infer the change in the LULC for three decades. The changes in the NDVI values point out the loss of vegetation for the urban area expansion during the study period. The increasing value of NDBI and BSI in the state indicates growth in high-density built-up areas and barren land. The slight reduction in the value of MNDWI indicates the shrinking water bodies in the state. The results of LULC showed the urban expansion (158.2%) and loss of agricultural area (15.52%) in the region during the study period. It was noted the area of the barren class, as well as the water class, decreased steadily from 1990 to 2020. The results of the current study will provide insight into the land-use planners, government, and non-governmental organizations (NGOs) for the necessary sustainable land-use practices.

Cross-validated tree-based models for multi-target learning.

Multi-target learning (MTL) is a popular machine learning technique which considers simultaneous prediction of multiple targets. MTL schemes utilize a variety of methods, from traditional linear models to more contemporary deep neural networks. In this work we introduce a novel, highly interpretable, tree-based MTL scheme which exploits the correlation between the targets to obtain improved prediction accuracy. Our suggested scheme applies cross-validated splitting criterion to identify correlated targets at every node of the tree. This allows us to benefit from the correlation among the targets while avoiding overfitting. We demonstrate the performance of our proposed scheme in a variety of synthetic and real-world experiments, showing a significant improvement over alternative methods. An implementation of the proposed method is publicly available at the first author's webpage.

A BAYESIAN MACHINE LEARNING APPROACH FOR ESTIMATING HETEROGENEOUS SURVIVOR CAUSAL EFFECTS: APPLICATIONS TO A CRITICAL CARE TRIAL.

Assessing heterogeneity in the effects of treatments has become increasingly popular in the field of causal inference and carries important implications for clinical decision-making. While extensive literature exists for studying treatment effect heterogeneity when outcomes are fully observed, there has been limited development in tools for estimating heterogeneous causal effects when patient-centered outcomes are truncated by a terminal event, such as death. Due to mortality occurring during study follow-up, the outcomes of interest are unobservable, undefined, or not fully observed for many participants in which case principal stratification is an appealing framework to draw valid causal conclusions. Motivated by the Acute Respiratory Distress Syndrome Network (ARDSNetwork) ARDS respiratory management (ARMA) trial, we developed a flexible Bayesian machine learning approach to estimate the average causal effect and heterogeneous causal effects among the always-survivors stratum when clinical outcomes are subject to truncation. We adopted Bayesian additive regression trees (BART) to flexibly specify separate mean models for the potential outcomes and latent stratum membership. In the analysis of the ARMA trial, we found that the low tidal volume treatment had an overall benefit for participants sustaining acute lung injuries on the outcome of time to returning home but substantial heterogeneity in treatment effects among the always-survivors, driven most strongly by biologic sex and the alveolar-arterial oxygen gradient at baseline (a physiologic measure of lung function and degree of hypoxemia). These findings illustrate how the proposed methodology could guide the prognostic enrichment of future trials in the field.

Extinction risk predictions for the world's flowering plants to support their conservation.

More than 70% of all vascular plants lack conservation status assessments. We aimed to address this shortfall in knowledge of species extinction risk by using the World Checklist of Vascular Plants to generate the first comprehensive set of predictions for a large clade: angiosperms (flowering plants, c. 330 000 species). We used Bayesian Additive Regression Trees (BART) to predict the extinction risk of all angiosperms using predictors relating to range size, human footprint, climate, and evolutionary history and applied a novel approach to estimate uncertainty of individual species-level predictions. From our model predictions, we estimate 45.1% of angiosperm species are potentially threatened with a lower bound of 44.5% and upper bound of 45.7%. Our species-level predictions, with associated uncertainty estimates, do not replace full global, or regional Red List assessments, but can be used to prioritise predicted threatened species for full Red List assessment and fast-track predicted non-threatened species for Least Concern assessments. Our predictions and uncertainty estimates can also guide fieldwork, inform systematic conservation planning and support global plant conservation efforts and targets.

When mind and measurement diverge; the interplay between subjective cognitive complaints (SCCs), objective cognition, age, and depression in autistic adults.

While the increased incidence of dementia and subjective cognitive complaints (SCCs) suggests that autistic adults may face cognitive challenges at older age, the extent to which SCCs predict (future) cognitive functioning remains uncertain. This uncertainty is complicated by associations with variables like depression. The current study aims to unravel the interplay of age, depression, cognitive performance, and SCCs in autism. Using a large cross-sectional cohort of autistic (n=202) and non-autistic adults (n=247), we analyzed associations of SCCs with age, depression, and cognitive performance across three domains (visual memory, verbal memory, and fluency). Results showed a strong significant association between depression and SCCs in both autistic and non-autistic adults. Cognitive performance was not significantly associated with SCCs, except for a (modest) association between visual memory performance and SCCs in autistic adults only. Follow-up regression tree analysis indicated that depression and being autistic were considerably more predictive of SCCs than objective cognitive performance. Age nor sex was significantly associated with SCCs. These findings indicate that self-reported cognitive functioning does not equal cognitive performance, and should be interpreted with care, especially in individuals with high rates of depression. Longitudinal investigations are needed to understand SCCs' role in dementia and cognitive health in autism.

Development and evaluation of regression tree models for predicting in-hospital mortality of a national registry of COVID-19 patients over six pandemic surges.

BACKGROUND: Objective prognostic information is essential for good clinical decision making. In case of unknown diseases, scarcity of evidence and limited tacit knowledge prevent obtaining this information. Prediction models can be useful, but need to be not only evaluated on how well they predict, but also how stable these models are under fast changing circumstances with respect to development of the disease and the corresponding clinical response. This study aims to provide interpretable and actionable insights, particularly for clinicians. We developed and evaluated two regression tree predictive models for in-hospital mortality of COVID-19 patient at admission and 24 hours (24 h) after admission, using a national registry. We performed a retrospective analysis of observational routinely collected data. METHODS: Two regression tree models were developed for admission and 24 h after admission. The complexity of the trees was managed via cross validation to prevent overfitting. The predictive ability of the model was assessed via bootstrapping using the Area under the Receiver-Operating-Characteristic curve, Brier score and calibration curves. The tree models were assessed on the stability of their probabilities and predictive ability, on the selected variables, and compared to a full-fledged logistic regression model that uses variable selection and variable transformations using splines. Participants included COVID-19 patients from all ICUs participating in the Dutch National Intensive Care Evaluation (NICE) registry, who were admitted at the ICU between February 27, 2020, and November 23, 2021. From the NICE registry, we included concerned demographic data, minimum and maximum values of physiological data in the first 24 h of ICU admission and diagnoses (reason for admission as well as comorbidities) for model development. The main outcome measure was in-hospital mortality. We additionally analysed the Length-of-Stay (LoS) per patient subgroup per survival status. RESULTS: A total of 13,369 confirmed COVID-19 patients from 70 ICUs were included (with mortality rate of 28%). The optimism-corrected AUROC of the admission tree (with seven paths) was 0.72 (95% CI: 0.71-0.74) and of the 24 h tree (with 11 paths) was 0.74 (0.74-0.77). Both regression trees yielded good calibration and variable selection for both trees was stable. Patient subgroups comprising the tree paths had comparable survival probabilities as the full-fledged logistic regression model, survival probabilities were stable over six COVID-19 surges, and subgroups were shown to have added predictive value over the individual patient variables. CONCLUSIONS: We developed and evaluated regression trees, which operate at par with a carefully crafted logistic regression model. The trees consist of homogenous subgroups of patients that are described by simple interpretable constraints on patient characteristics thereby facilitating shared decision-making.

Spatial distribution and main drivers of soil selenium in Taihu Lake Basin, Southeast China.

Selenium (Se) is an essential micronutrient that is both hazardous and beneficial to living organisms. However, few studies have examined soil Se distribution and its driving mechanisms on a large basin scale. Thus, multivariate statistics, geostatistics, boosted regression trees, and structural equation models were used to investigate the spatial distribution, driving factors, and multivariate interactions of soil Se based on 1753 topsoil samples (0-20 cm) from the Taihu Lake Basin. The results indicated that the soil Se concentration ranged from 0.12 to 57.26 mg kg-1, with a mean value of 0.90 mg kg-1. Overall, the spatial pattern of soil Se gradually decreased from south to north with approximately 1.06% of the soil contaminated with Se. Moisture index (MI), soil moisture (SM), and ≥ 0 â„ƒ accumulative temperature (AAT0) were the main determinants of soil Se accumulation. Additionally, the substantial effect of SM∩AAT0 on soil Se concentrations demonstrated that climate-soil interactions largely governed the spatial pattern of soil Se. The Se-enriched and Se-contaminated soils occurred mainly in regions with high precipitation, MI, SM, AAT0, and soil organic matter. This study provides a theoretical basis and practical guidance for the remediation of soil Se contamination and the sustainable development of Se-enriched agriculture.

Strategic restoration planning for land birds in the Colorado River Delta, Mexico.

Ecological restoration is an essential strategy for mitigating the current biodiversity crisis, yet restoration actions are costly. We used systematic conservation planning principles to design an approach that prioritizes restoration sites for birds and tested it in a riparian forest restoration program in the Colorado River Delta. Restoration goals were to maximize the abundance and diversity of 15 priority birds with a variety of habitat preferences. We built abundance models for priority birds based on the current landscape, and predicted bird distributions and relative abundances under a scenario of complete riparian forest restoration throughout our study area. Then, we used Zonation conservation planning software to rank this restored landscape based on core areas for all priority birds. The locations with the highest ranks represented the highest priorities for restoration and were located throughout the river reach. We optimized how much of the available landscape to restore by simulating restoration of the top 10-90% of ranked sites in 10% intervals. We found that total diversity was maximized when 40% of the landscape was restored, and mean relative abundance was maximized when 80% of the landscape was restored. The results suggest that complete restoration is not optimal for this community of priority birds and restoration of approximately 60% of the landscape would provide a balance between maximum relative abundance and diversity. Subsequent planning efforts will combine our results with an assessment of restoration costs to provide further decision support for the restoration-siting process. Our approach can be applied to any landscape-scale restoration program to improve the return on investment of limited economic resources for restoration.

Evaluation of the efficiency and drivers of complemented cropland in Southwest China over the past 30 years from the perspective of cropland abandonment.

Complemented croplands are a crucial component of cropland resources and play a significant role in ensuring national food security. In recent decades, to counter the loss of prime farmland caused by urban construction, the Chinese government introduced a requisition-compensation balance policy, leading to the substantial expansion of new croplands. Therefore, there is an urgent need to determine whether these complemented croplands can be effectively used. Taking Southwest China as a case study, we used high-precision long-term land-use data from 1990 to 2020 to reveal the dynamics of complemented cropland utilization, evaluate the efficiency of complemented cropland utilization from the perspective of abandoned farmland, and identify the factors driving complemented cropland use efficiency based on more than 13 million land parcels. The results showed that: (1) From 1990 to 2020, complemented cropland amounted to approximately 1170.07 × 104 hm2, accounting for 32.67% of the total arable land area in 1990. The potential grain production capacity of these complemented croplands was significantly lower than that of base croplands. (2) The abandonment of complemented croplands was more serious than that of base croplands, and 47.03% of the complemented croplands experienced abandonment at least once during the study period, and the average efficiency of the complemented croplands was 75.61%. (3) The labor population ratio, elevation, and land parcel size played pivotal roles in influencing the complemented cropland utilization efficiency; however, there was substantial variation among the different provinces. Labor replacement, overcoming farming difficulties brought by mountainous terrain, and improving farmers' income are the keys to alleviating cropland abandonment in mountainous areas and improving cropland utilization efficiency. This study provides novel insights into the efficiency assessment and exploration of the mechanisms driving complemented croplands and can provide references for cropland management.

Unsupervised item response theory models for assessing sample heterogeneity in patient-reported outcomes measures.

PURPOSE: Unsupervised item-response theory (IRT) models such as polytomous IRT based on recursive partitioning (IRTrees) and mixture IRT (MixIRT) models can be used to assess differential item functioning (DIF) in patient-reported outcome measures (PROMs) when the covariates associated with DIF are unknown a priori. This study examines the consistency of results for IRTrees and MixIRT models. METHODS: Data were from 4478 individuals in the Alberta Provincial Project on Outcome Assessment in Coronary Heart Disease registry who received cardiac angiography in Alberta, Canada, and completed the Hospital Anxiety and Depression Scale (HADS) depression subscale items. The partial credit model (PCM) based on recursive partitioning (PCTree) and mixture PCM (MixPCM) were used to identify covariates associated with differential response patterns to HADS depression subscale items. Model covariates included demographic and clinical characteristics. RESULTS: The median (interquartile range) age was 64.5(15.7) years, and 3522(78.5%) patients were male. The PCTree identified 4 terminal nodes (subgroups) defined by smoking status, age, and body mass index. A 3-class PCM fits the data well. The MixPCM latent classes were defined by age, disease indication, smoking status, comorbid diabetes, congestive heart failure, and chronic obstructive pulmonary disease. CONCLUSION: PCTree and MixPCM were not consistent in detecting covariates associated with differential interpretations of PROM items. Future research will use computer simulations to assess these models' Type I error and statistical power for identifying covariates associated with DIF.

Forecasting daily COVID-19 cases with gradient boosted regression trees and other methods: evidence from U.S. cities.

Introduction: There is a vast literature on the performance of different short-term forecasting models for country specific COVID-19 cases, but much less research with respect to city level cases. This paper employs daily case counts for 25 Metropolitan Statistical Areas (MSAs) in the U.S. to evaluate the efficacy of a variety of statistical forecasting models with respect to 7 and 28-day ahead predictions. Methods: This study employed Gradient Boosted Regression Trees (GBRT), Linear Mixed Effects (LME), Susceptible, Infectious, or Recovered (SIR), and Seasonal Autoregressive Integrated Moving Average (SARIMA) models to generate daily forecasts of COVID-19 cases from November 2020 to March 2021. Results: Consistent with other research that have employed Machine Learning (ML) based methods, we find that Median Absolute Percentage Error (MAPE) values for both 7-day ahead and 28-day ahead predictions from GBRTs are lower than corresponding values from SIR, Linear Mixed Effects (LME), and Seasonal Autoregressive Integrated Moving Average (SARIMA) specifications for the majority of MSAs during November-December 2020 and January 2021. GBRT and SARIMA models do not offer high-quality predictions for February 2021. However, SARIMA generated MAPE values for 28-day ahead predictions are slightly lower than corresponding GBRT estimates for March 2021. Discussion: The results of this research demonstrate that basic ML models can lead to relatively accurate forecasts at the local level, which is important for resource allocation decisions and epidemiological surveillance by policymakers.