Mitigating the Multicollinearity Problem and Its Machine Learning Approach: A Review

Exploring predictors of substance use disorder treatment engagement with machine learning: The impact of social determinants of health in the therapeutic landscape

BACKGROUND

Improved knowledge of factors that influence treatment engagement could help treatment providers and systems better engage patients. The present study used machine learning to explore associations between individual- and neighborhood-level factors, and SUD treatment engagement.

METHODS

This was a secondary analysis of the Global Appraisal of Individual Needs (GAIN) dataset and United States Census Bureau data utilizing random forest machine learning and generalized linear mixed modelling. Our sample (N = 15,873) included all people entering SUD treatment at GAIN sites from 2006 to 2012. Predictors included an array of demographic, psychosocial, treatment-specific, and clinical measures, as well as environment-level measures for the neighborhood in which patients received treatment.

RESULTS

Greater odds of treatment engagement were predicted by adolescent age and psychiatric comorbidity, and at the neighborhood-level, by low unemployment and high population density. Lower odds of treatment engagement were predicted by Black/African American race, and at the neighborhood-level by high rate of public assistance and high income inequality. Regardless of the degree of treatment engagement, individuals receiving treatment in areas with high unemployment, alcohol sale outlet concentration, and poverty had greater substance use and related problems at baseline. Although these differences reduced with treatment and over time, disparities remained.

CONCLUSIONS

Neighborhood-level factors appear to play an important role in SUD treatment engagement. Regardless of whether individuals engage with treatment, greater loading on social determinants of health such as unemployment, alcohol sale outlet density, and poverty in the therapeutic landscape are associated with worse SUD treatment outcomes.

Enhanced PM2.5 estimation across China: An AOD-independent two-stage approach incorporating improved spatiotemporal heterogeneity representations

In China, population growth and aging have partially negated the public health benefits of air pollution control measures, underscoring the ongoing need for precise PM2.5 monitoring and mapping. Despite its prevalence, the satellite-derived Aerosol Optical Depth (AOD) method for estimating PM2.5 concentrations often encounters significant spatial data gaps. Additionally, current research still needs better representation of PM2.5 spatiotemporal heterogeneity. Addressing these challenges, we developed a two-stage model employing the Extreme Gradient Boosting (XGBoost) algorithm. By incorporating improved spatiotemporal factors, we achieved high-precision and full-coverage daily 1-km PM2.5 mappings across China for the year 2020 without utilizing AOD products. Specifically, Model 1 develops improved temporal encodings and a terrain classification factor (DC), while Model 2 constructs an enhanced spatial autocorrelation term (Ps) by integrating observed and estimated values. Notably, Model 2 excelled in 10-fold sample-based cross-validation, achieving a coefficient of determination of 0.948, a mean absolute error of 3.792 μg/m³, a root mean square error of 7.144 μg/m³, and a mean relative error of 14.171%. Feature importance and Shapley Additive exPlanations (SHAP) analyses determined the relative importance of predictors in model training and outcome prediction, while correlation analysis identified strong links between improved temporal encodings, PM2.5 concentrations, and significant meteorological factors. Two-way Partial Dependence Plots (PDPs) further explored the interactions among these factors and their impact on PM2.5 levels. Compared to traditional methods, improved temporal encodings align more closely with seasonal variations and synergize more effectively with meteorological factors. Besides, the structured nature of DC aids in model training, while the improved Ps more effectively captures PM2.5's spatial autocorrelation, outperforming traditional Ps. Overall, this study effectively represents spatiotemporal information, thereby boosting model accuracy and enabling seamless large-scale PM2.5 estimations. It provides deep insights into variables and models, providing significant implications for future air pollution research.

Improved mapping of heavy metals in agricultural soils using machine learning augmented with spatial regionalization indices

The accurate spatial mapping of heavy metal levels in agricultural soils is crucial for environmental management and food security. However, the inherent limitations of traditional interpolation methods and emerging machine-learning techniques restrict their spatial prediction accuracy. This study aimed to refine the spatial prediction of heavy metal distributions in Guangxi, China, by integrating machine learning models and spatial regionalization indices (SRIs). The results demonstrated that random forest (RF) models incorporating SRIs outperformed artificial neural network and support vector regression models, achieving R2 values exceeding 0.96 for eight heavy metals on the test data. Hierarchical clustering for feature selection further improved the model performance. The optimized RF models accurately predicted the heavy metal distributions in agricultural soils across the province, revealing higher levels in the central-western regions and lower levels in the north and south. Notably, the models identified that 25.78 % of agricultural soils constitute hotspots with multiple co-occurring heavy metals, and over 6.41 million people are exposed to excessive soil heavy metal levels. Our findings provide valuable insights for the development of targeted strategies for soil pollution control and agricultural soil management to safeguard food security and public health.

Prediction of post-donation renal function using machine learning techniques and conventional regression models in living kidney donors

BACKGROUND

Accurate prediction of renal function following kidney donation and careful selection of living donors are essential for living-kidney donation programs. We aimed to develop a prediction model for post-donation renal function following living kidney donation using machine learning.

METHODS

This retrospective cohort study was conducted with 823 living kidney donors between 2009 and 2020. The dataset was randomly split into training (80%) and test sets (20%). The main outcome was the post-donation estimated glomerular filtration rate (eGFR) 12 months after nephrectomy. We compared the performance of machine learning techniques, traditional regression models, and models from previous studies. The best-performing model was selected based on the mean absolute error (MAE) and root mean square error (RMSE).

RESULTS

The mean age of the participants was 45.2 ± 12.3 years, and 48.4% were males. The mean pre-donation and post-donation eGFRs were 101.3 ± 13.0 and 68.8 ± 12.7 mL/min/1.73 m2, respectively. The XGBoost model with the eGFR, age, serum creatinine, 24-h urine creatinine, 24-h urine sodium, creatinine clearance, cystatin C, cystatin C-based eGFR, computed tomography volume of the remaining kidney/body weight, normalized GFR of the remaining kidney measured through a diethylenetriaminepentaacetic acid scan, and sex, showed the best performance with a mean absolute error of 6.23 and root mean square error of 8.06. An easy-to-use web application titled Kidney Donation with Nephrologic Intelligence (KDNI) was developed.

CONCLUSIONS

The prediction model using XGBoost accurately predicted the post-donation eGFR after living kidney donation. This model can be applied in clinical practice using KDNI, the developed web application.

Identifying the most crucial factors associated with depression based on interpretable machine learning: a case study from CHARLS

Background

Depression is one of the most common mental illnesses among middle-aged and older adults in China. It is of great importance to find the crucial factors that lead to depression and to effectively control and reduce the risk of depression. Currently, there are limited methods available to accurately predict the risk of depression and identify the crucial factors that influence it.

Methods

We collected data from 25,586 samples from the harmonized China Health and Retirement Longitudinal Study (CHARLS), and the latest records from 2018 were included in the current cross-sectional analysis. Ninety-three input variables in the survey were considered as potential influential features. Five machine learning (ML) models were utilized, including CatBoost and eXtreme Gradient Boosting (XGBoost), Gradient Boosting decision tree (GBDT), Random Forest (RF), Light Gradient Boosting Machine (LightGBM). The models were compared to the traditional multivariable Linear Regression (LR) model. Simultaneously, SHapley Additive exPlanations (SHAP) were used to identify key influencing factors at the global level and explain individual heterogeneity through instance-level analysis. To explore how different factors are non-linearly associated with the risk of depression, we employed the Accumulated Local Effects (ALE) approach to analyze the identified critical variables while controlling other covariates.

Results

CatBoost outperformed other machine learning models in terms of MAE, MSE, MedAE, and R2metrics. The top three crucial factors identified by the SHAP were r4satlife, r4slfmem, and r4shlta, representing life satisfaction, self-reported memory, and health status levels, respectively.

Conclusion

This study demonstrates that the CatBoost model is an appropriate choice for predicting depression among middle-aged and older adults in Harmonized CHARLS. The SHAP and ALE interpretable methods have identified crucial factors and the nonlinear relationship with depression, which require the attention of domain experts.

Enhancing genomic prediction with Stacking Ensemble Learning in Arabica Coffee

Coffee Breeding programs have traditionally relied on observing plant characteristics over years, a slow and costly process. Genomic selection (GS) offers a DNA-based alternative for faster selection of superior cultivars. Stacking Ensemble Learning (SEL) combines multiple models for potentially even more accurate selection. This study explores SEL potential in coffee breeding, aiming to improve prediction accuracy for important traits [yield (YL), total number of the fruits (NF), leaf miner infestation (LM), and cercosporiosis incidence (Cer)] in Coffea Arabica. We analyzed data from 195 individuals genotyped for 21,211 single-nucleotide polymorphism (SNP) markers. To comprehensively assess model performance, we employed a cross-validation (CV) scheme. Genomic Best Linear Unbiased Prediction (GBLUP), multivariate adaptive regression splines (MARS), Quantile Random Forest (QRF), and Random Forest (RF) served as base learners. For the meta-learner within the SEL framework, various options were explored, including Ridge Regression, RF, GBLUP, and Single Average. The SEL method was able to predict the predictive ability (PA) of important traits in Coffea Arabica. SEL presented higher PA compared with those obtained for all base learner methods. The gains in PA in relation to GBLUP were 87.44% (the ratio between the PA obtained from best Stacking model and the GBLUP), 37.83%, 199.82%, and 14.59% for YL, NF, LM and Cer, respectively. Overall, SEL presents a promising approach for GS. By combining predictions from multiple models, SEL can potentially enhance the PA of GS for complex traits.

Flood susceptibility mapping of Cheongju, South Korea based on the integration of environmental factors using various machine learning approaches

Floods are natural occurrences that pose serious risks to human life and the environment, including significant property and infrastructure damage and subsequent socioeconomic challenges. Recent floods in Cheongju County, South Korea have been linked to river overflow. In this study, we created flood susceptibility maps of Cheongju, South Korea using machine learning techniques including support vector regression (SVR), boosted tree (BOOST), and long short-term memory (LSTM) algorithms, based on environmental factors. Potentially influential variables were selected based on flood data gathered through field surveys; these included the slope, aspect, length-slope factor, wind exposition index, terrain wetness index, plan curvature, normalized difference water index, geology, soil drainage, soil depth, soil texture, land use type, and forest density. To improve the robustness of the flood susceptibility model, the most influential factors were identified using the frequency ratio method. Implementing machine learning techniques like SVR and BOOST produced encouraging outcomes, achieving the area under the curve (AUC) of 83.16% and 86.70% for training, and 81.65% and 86.43% for testing, respectively. While, the LSTM algorithm showed superior flood susceptibility mapping performance, with an AUC value of 87.01% for training and 86.91% for testing, demonstrating its robust performance and reliability in accurately assessing flood susceptibility. The results of this study enhance our understanding of flood susceptibility in South Korea and demonstrate the potential of the proposed approach for informing and guiding crucial regional policy decisions, contributing to a more resilient and prepared future.

Machine learning approach for predicting post-intubation hemodynamic instability (PIHI) index values: towards enhanced perioperative anesthesia quality and safety

BACKGROUND

Adequate preoperative evaluation of the post-intubation hemodynamic instability (PIHI) is crucial for accurate risk assessment and efficient anesthesia management. However, the incorporation of this evaluation within a predictive framework have been insufficiently addressed and executed. This study aims to developed a machine learning approach for preoperatively and precisely predicting the PIHI index values.

METHODS

In this retrospective study, the valid features were collected from 23,305 adult surgical patients at Peking Union Medical College Hospital between 2012 and 2020. Three hemodynamic response sequences including systolic pressure, diastolic pressure and heart rate, were utilized to design the post-intubation hemodynamic instability (PIHI) index by computing the integrated coefficient of variation (ICV) values. Different types of machine learning models were constructed to predict the ICV values, leveraging preoperative patient information and initiatory drug infusion. The models were trained and cross-validated based on balanced data using the SMOTETomek technique, and their performance was evaluated according to the mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE) and R-squared index (R2).

RESULTS

The ICV values were proved to be consistent with the anesthetists' ratings with Spearman correlation coefficient of 0.877 (P < 0.001), affirming its capability to effectively capture the PIHI variations. The extra tree regression model outperformed the other models in predicting the ICV values with the smallest MAE (0.0512, 95% CI: 0.0511-0.0513), RMSE (0.0792, 95% CI: 0.0790-0.0794), and MAPE (0.2086, 95% CI: 0.2077-0.2095) and the largest R2 (0.9047, 95% CI: 0.9043-0.9052). It was found that the features of age and preoperative hemodynamic status were the most important features for accurately predicting the ICV values.

CONCLUSIONS

Our results demonstrate the potential of the machine learning approach in predicting PIHI index values, thereby preoperatively informing anesthetists the possible anesthetic risk and enabling the implementation of individualized and precise anesthesia interventions.

Development and validation of a machine learning model to predict time to renal replacement therapy in patients with chronic kidney disease

BACKGROUND

Predicting time to renal replacement therapy (RRT) is important in patients at high risk for end-stage kidney disease. We developed and validated machine learning models for predicting the time to RRT and compared its accuracy with conventional prediction methods that uses the rate of estimated glomerular filtration rate (eGFR) decline.

METHODS

Data of adult chronic kidney disease (CKD) patients who underwent hemodialysis at Oita University Hospital from April 2016 to March 2021 were extracted from electronic medical records (N = 135). A new machine learning predictor was compared with the established prediction method that uses the eGFR decline rate and the accuracy of the prediction models was determined using the coefficient of determination (R2). The data were preprocessed and split into training and validation datasets. We created multiple machine learning models using the training data and evaluated their accuracy using validation data. Furthermore, we predicted the time to RRT using a conventional prediction method that uses the eGFR decline rate for patients who had measured eGFR three or more times in two years and evaluated its accuracy.

RESULTS

The least absolute shrinkage and selection operator regression model exhibited moderate accuracy with an R2 of 0.60. By contrast, the conventional prediction method was found to be extremely low with an R2 of -17.1.

CONCLUSIONS

The significance of this study is that it shows that machine learning can predict time to RRT moderately well with continuous values from data at a single time point. This approach outperforms the conventional prediction method that uses eGFR time series data and presents new avenues for CKD treatment.

Predicting effluent quality parameters for wastewater treatment plant: A machine learning-based methodology

Wastewater Treatment Plants (WWTPs) present complex biochemical processes of high variability and difficult prediction. This study presents an innovative approach using Machine Learning (ML) models to predict wastewater quality parameters. In particular, the models are applied to datasets from both a simulated wastewater treatment plant (WWTP), using DHI WEST software (WEST WWTP), and a real-world WWTP database from Santa Catarina Brewery AMBEV, located in Lages/SC - Brazil (AMBEV WWTP). A distinctive aspect is the evaluation of predictive performance in continuous data scenarios and the impact of changes in WWTP operations on predictive model performance, including changes in plant layout. For both plants, three different scenarios were addressed, and the quality of predictions by random forest (RF), support vector machine (SVM), and multilayer perceptron (MLP) models were evaluated. The prediction quality by the MLP model reached an R2 of 0.72 for TN prediction in the WEST WWTP output, and the RF model better adapted to the real data of the AMBEV WWTP, despite the significant discrepancy observed between the real and the predicted data. Techniques such as Partial Dependence Plots (PDP) and Permutation Importance (PI) were used to assess the importance of features, particularly in the simulated WEST tool scenario, showing a strong correlation of prediction results with influent parameters related to nitrogen content. The results of this study highlight the importance of collecting and storing high-quality data and the need for information on changes in WWTP operation for predictive model performance. These contributions advance the understanding of predictive modeling for wastewater quality and provide valuable insights for future practice in wastewater treatment.

Engineering Features from Raw Sensor Data to Analyse Player Movements during Competition

Research in field sports often involves analysis of running performance profiles of players during competitive games with individual, per-position, and time-related descriptive statistics. Data are acquired through wearable technologies, which generally capture simple data points, which in the case of many team-based sports are times, latitudes, and longitudes. While the data capture is simple and in relatively high volumes, the raw data are unsuited to any form of analysis or machine learning functions. The main goal of this research is to develop a multistep feature engineering framework that delivers the transformation of sequential data into feature sets more suited to machine learning applications.

Selecting, optimizing and externally validating a preexisting machine-learning regression algorithm for estimating waist circumference

Obesity, typically defined by the body mass index (BMI), has well known negative health effects. However, the BMI has serious deficiencies in predicting the adverse risks associated to obesity. Waist circumference (WC) is an alternative to define obesity and a better disease predictor according to the literature. However, old databases often lack this information, it is inaccurate (collected via self-report) or it is incomplete. Thus, this study accurately assesses WC using machine learning. The novel approaches are: 1) predictor variables (weight, height, age and sex) likely to appear in most data sets are used. 2) Publicly available data (including non-adults) and algorithms are used. 3) Systematic methods for data cleanup, model selection, hyperparameter optimization and external validation are performed. DATA ARE CLEANED: one variable per column, no special codes, missing values or outliers. Preexisting regression algorithms are gaged by cross-validation, using one data set. The hyperparameters of the best performing algorithm are optimized. The tuned algorithm is externally validated with other data sets by cross-validation. In spite of the limited number of features, the tuned algorithm outperforms prior WC approximations, using the same or similar predictor variables. The tuned algorithm enables using data where WC is not measured, is incomplete or is unreliable. A similar approach would be useful to estimate other variables of interest.

Machine learning and deep learning-based approach in smart healthcare: Recent advances, applications, challenges and opportunities

In recent years, machine learning (ML) and deep learning (DL) have been the leading approaches to solving various challenges, such as disease predictions, drug discovery, medical image analysis, etc., in intelligent healthcare applications. Further, given the current progress in the fields of ML and DL, there exists the promising potential for both to provide support in the realm of healthcare. This study offered an exhaustive survey on ML and DL for the healthcare system, concentrating on vital state of the art features, integration benefits, applications, prospects and future guidelines. To conduct the research, we found the most prominent journal and conference databases using distinct keywords to discover scholarly consequences. First, we furnished the most current along with cutting-edge progress in ML-DL-based analysis in smart healthcare in a compendious manner. Next, we integrated the advancement of various services for ML and DL, including ML-healthcare, DL-healthcare, and ML-DL-healthcare. We then offered ML and DL-based applications in the healthcare industry. Eventually, we emphasized the research disputes and recommendations for further studies based on our observations.

Prioritizing determinants of cognitive function in healthy middle-aged and older adults: insights from a machine learning regression approach in the Canadian longitudinal study on aging

Introduction

The preservation of healthy cognitive function is a crucial step toward reducing the growing burden of cognitive decline and impairment. Our study aims to identify the characteristics of an individual that play the greatest roles in determining healthy cognitive function in mid to late life.

Methods

Data on the characteristics of an individual that influence their health, also known as determinants of health, were extracted from the baseline cohort of the Canadian Longitudinal Study of Aging (2015). Cognitive function was a normalized latent construct score summarizing eight cognitive tests administered as a neuropsychological battery by CLSA staff. A higher cognitive function score indicated better functioning. A penalized regression model was used to select and order determinants based on their strength of association with cognitive function. Forty determinants (40) were entered into the model including demographic and socioeconomic factors, lifestyle and health behaviors, clinical measures, chronic diseases, mental health status, social support and the living environment.

Results

The study sample consisted mainly of White, married, men and women aged 45-64 years residing in urban Canada. Mean overall cognitive function score for the study sample was 99.5, with scores ranging from 36.6 to 169.2 (lowest to highest cognitive function). Thirty-five (35) determinants were retained in the final model as significantly associated with healthy cognitive functioning. The determinants demonstrating the strongest associations with healthy cognitive function, were race, immigrant status, nutritional risk, community belongingness, and satisfaction with life. The determinants demonstrating the weakest associations with healthy cognitive function, were physical activity, greenness and neighborhood deprivation.

Conclusion

Greater prioritization and integration of demographic and socioeconomic factors and lifestyle and health behaviors, such greater access to healthy foods and enhancing aid programs for low-income and immigrant families, into future health interventions and policies can produce the greatest gains in preserving healthy cognitive function in mid to late life.

Identifying subgroups of childhood obesity by using multiplatform metabotyping

Introduction: Obesity results from an interplay between genetic predisposition and environmental factors such as diet, physical activity, culture, and socioeconomic status. Personalized treatments for obesity would be optimal, thus necessitating the identification of individual characteristics to improve the effectiveness of therapies. For example, genetic impairment of the leptin-melanocortin pathway can result in rare cases of severe early-onset obesity. Metabolomics has the potential to distinguish between a healthy and obese status; however, differentiating subsets of individuals within the obesity spectrum remains challenging. Factor analysis can integrate patient features from diverse sources, allowing an accurate subclassification of individuals. Methods: This study presents a workflow to identify metabotypes, particularly when routine clinical studies fail in patient categorization. 110 children with obesity (BMI > +2 SDS) genotyped for nine genes involved in the leptin-melanocortin pathway (CPE, MC3R, MC4R, MRAP2, NCOA1, PCSK1, POMC, SH2B1, and SIM1) and two glutamate receptor genes (GRM7 and GRIK1) were studied; 55 harboring heterozygous rare sequence variants and 55 with no variants. Anthropometric and routine clinical laboratory data were collected, and serum samples processed for untargeted metabolomic analysis using GC-q-MS and CE-TOF-MS and reversed-phase U(H)PLC-QTOF-MS/MS in positive and negative ionization modes. Following signal processing and multialignment, multivariate and univariate statistical analyses were applied to evaluate the genetic trait association with metabolomics data and clinical and routine laboratory features. Results and Discussion: Neither the presence of a heterozygous rare sequence variant nor clinical/routine laboratory features determined subgroups in the metabolomics data. To identify metabolomic subtypes, we applied Factor Analysis, by constructing a composite matrix from the five analytical platforms. Six factors were discovered and three different metabotypes. Subtle but neat differences in the circulating lipids, as well as in insulin sensitivity could be established, which opens the possibility to personalize the treatment according to the patients categorization into such obesity subtypes. Metabotyping in clinical contexts poses challenges due to the influence of various uncontrolled variables on metabolic phenotypes. However, this strategy reveals the potential to identify subsets of patients with similar clinical diagnoses but different metabolic conditions. This approach underscores the broader applicability of Factor Analysis in metabotyping across diverse clinical scenarios.

Machine learning approach for the detection of vitamin D level: a comparative study

BACKGROUND

After the World Health Organization declared the COVID-19 pandemic, the role of Vitamin D has become even more critical for people worldwide. The most accurate way to define vitamin D level is 25-hydroxy vitamin D(25-OH-D) blood test. However, this blood test is not always feasible. Most data sets used in health science research usually contain highly correlated features, which is referred to as multicollinearity problem. This problem can lead to misleading results and overfitting problems in the ML training process. Therefore, the proposed study aims to determine a clinically acceptable ML model for the detection of the vitamin D status of the North Cyprus adult participants accurately, without the need to determine 25-OH-D level, taking into account the multicollinearity problem.

METHOD

The study was conducted with 481 observations who applied voluntarily to Internal Medicine Department at NEU Hospital. The classification performance of four conventional supervised ML models, namely, Ordinal logistic regression(OLR), Elastic-net ordinal regression(ENOR), Support Vector Machine(SVM), and Random Forest (RF) was compared. The comparative analysis is performed regarding the model's sensitivity to the participant's metabolic syndrome(MtS)'positive status, hyper-parameter tuning, sensitivities to the size of training data, and the classification performance of the models.

RESULTS

Due to the presence of multicollinearity, the findings showed that the performance of the SVM(RBF) is obviously negatively affected when the test is examined. Moreover, it can be obviously detected that RF is more robust than other models when the variations in the size of training data are examined. This experiment's result showed that the selected RF and ENOR showed better performances than the other two models when the size of training samples was reduced. Since the multicollinearity is more severe in the small samples, it can be concluded that RF and ENOR are not affected by the presence of the multicollinearity problem. The comparative analysis revealed that the RF classifier performed better and was more robust than the other proposed models in terms of accuracy (0.94), specificity (0.96), sensitivity or recall (0.94), precision (0.95), F1-score (0.95), and Cohen's kappa (0.90).

CONCLUSION

It is evident that the RF achieved better than the SVM(RBF), ENOR, and OLR. These comparison findings will be applied to develop a Vitamin D level intelligent detection system for being used in routine clinical, biochemical tests, and lifestyle characteristics of individuals to decrease the cost and time of vitamin D level detection.

A Critical Review of Data Science Applications in Resource Recovery and Carbon Capture from Organic Waste

Municipal and agricultural organic waste can be treated to recover energy, nutrients, and carbon through resource recovery and carbon capture (RRCC) technologies such as anaerobic digestion, struvite precipitation, and pyrolysis. Data science could benefit such technologies by improving their efficiency through data-driven process modeling along with reducing environmental and economic burdens via life cycle assessment (LCA) and techno-economic analysis (TEA), respectively. We critically reviewed 616 peer-reviewed articles on the use of data science in RRCC published during 2002-2022. Although applications of machine learning (ML) methods have drastically increased over time for modeling RRCC technologies, the reviewed studies exhibited significant knowledge gaps at various model development stages. In terms of sustainability, an increasing number of studies included LCA with TEA to quantify both environmental and economic impacts of RRCC. Integration of ML methods with LCA and TEA has the potential to cost-effectively investigate the trade-off between efficiency and sustainability of RRCC, although the literature lacked such integration of techniques. Therefore, we propose an integrated data science framework to inform efficient and sustainable RRCC from organic waste based on the review. Overall, the findings from this review can inform practitioners about the effective utilization of various data science methods for real-world implementation of RRCC technologies.

Validation of Risk Stratification for Cardiac Events in Pregnant Women With Valvular Heart Disease

BACKGROUND

Most risk stratification tools for pregnant patients with heart disease were developed in high-income countries and in populations with predominantly congenital heart disease, and therefore, may not be generalizable to those with valvular heart disease (VHD).

OBJECTIVES

The purpose of this study was to validate and establish the clinical utility of 2 risk stratification tools-DEVI (VHD-specific tool) and CARPREG-II-for predicting adverse cardiac events in pregnant patients with VHD.

METHODS

We conducted a cohort study involving consecutive pregnancies complicated with VHD admitted to a tertiary center in a middle-income setting from January 2019 to April 2022. Individual risk for adverse composite cardiac events was calculated using DEVI and CARPREG-II models. Performance was assessed through discrimination and calibration characteristics. Clinical utility was evaluated with Decision Curve Analysis.

RESULTS

Of 577 eligible pregnancies, 69 (12.1%) experienced a component of the composite outcome. A majority (94.7%) had rheumatic etiology, with mitral regurgitation as the predominant lesion (48.2%). The area under the receiver-operating characteristic curve was 0.884 (95% CI: 0.844-0.923) for the DEVI and 0.808 (95% CI: 0.753-0.863) for the CARPREG-II models. Calibration plots suggested that DEVI score overestimates risk at higher probabilities, whereas CARPREG-II score overestimates risk at both extremes and underestimates risk at middle probabilities. Decision curve analysis demonstrated that both models were useful across predicted probability thresholds between 10% and 50%.

CONCLUSIONS

In pregnant patients with VHD, DEVI and CARPREG-II scores showed good discriminative ability and clinical utility across a range of probabilities. The DEVI score showed better agreement between predicted probabilities and observed events.

Using Machine Learning to Predict Nonachievement of Clinically Significant Outcomes After Rotator Cuff Repair

Background

Although some evidence suggests that machine learning algorithms may outperform classical statistical methods in prognosis prediction for several orthopaedic surgeries, to our knowledge, no study has yet used machine learning to predict patient-reported outcome measures after rotator cuff repair.

Purpose

To determine whether machine learning algorithms using preoperative data can predict the nonachievement of the minimal clinically important difference (MCID) of disability at 2 years after rotator cuff surgical repair with a similar performance to that of other machine learning studies in the orthopaedic surgery literature.

Study Design

Case-control study; Level of evidence, 3.

Methods

We evaluated 474 patients (n = 500 shoulders) with rotator cuff tears who underwent arthroscopic rotator cuff repair between January 2013 and April 2019. The study outcome was the difference between the preoperative and 24-month postoperative American Shoulder and Elbow Surgeons (ASES) score. A cutoff score was calculated based on the established MCID of 15.2 points to separate success (higher than the cutoff) from failure (lower than the cutoff). Routinely collected imaging, clinical, and demographic data were used to train 8 machine learning algorithms (random forest classifier; light gradient boosting machine [LightGBM]; decision tree classifier; extra trees classifier; logistic regression; extreme gradient boosting [XGBoost]; k-nearest neighbors [KNN] classifier; and CatBoost classifier). We used a random sample of 70% of patients to train the algorithms, and 30% were left for performance assessment, simulating new data. The performance of the models was evaluated with the area under the receiver operating characteristic curve (AUC).

Results

The AUCs for all algorithms ranged from 0.58 to 0.68. The random forest classifier and LightGBM presented the highest AUC values (0.68 [95% CI, 0.48-0.79] and 0.67 [95% CI, 0.43-0.75], respectively) of the 8 machine learning algorithms. Most of the machine learning algorithms outperformed logistic regression (AUC, 0.59 [95% CI, 0.48-0.81]); nonetheless, their performance was lower than that of other machine learning studies in the orthopaedic surgery literature.

Conclusion

Machine learning algorithms demonstrated some ability to predict the nonachievement of the MCID on the ASES 2 years after rotator cuff repair surgery.

What influence farmers' relative poverty in China: A global analysis based on statistical and interpretable machine learning methods

Poverty eradication has always been a major challenge to global development and governance, which received widespread attention from each country. With the completion poverty alleviation task in 2020, relative poverty governance becomes an important issue to be solved in China urgently. Because of a large population, poor infrastructures, insufficient resources, and long-term uneven development raising the living standard of farmers in rural areas is critical to China's success in realizing moderate prosperity. Therefore, identifying the poor farmers, exploring the influence factors to relative poverty, and clarifying its effect mechanism in rural areas are significant for the subsequent poverty governance. Most of the previous studies adopted the method of apriori assuming the factor system and verifying the hypothesis. We innovatively constructed a relative poverty index system consistent with China's actual conditions, selecting all the possible variables that could affect relative poverty based on the existing literature, including individual characteristics, psychological endowment, and geographical environment, and rebuilt an experimental database. Then, through data processing and data analysis, the main factors influencing the relative poverty of farmers were systematically sorted out based on the machine learning method. Finally, 25 chosen influencing factors were discussed in detail. Research findings show that: 1) Machine learning algorithm is proved it could be well applied in relative poverty fields, especially XGBoost, which achieves 81.9% accuracy and the score of ROC_AUC reaches 0.819. 2) This study sheds light on many new research directions in applying machine learning for relative poverty research, besides, the paper offers an integral framework and beneficial reference for target identification using machine learning algorithms. 3) In addition, by utilizing the interpretable tools, the "black-box" of ML become transparent through PDP and SHAP explanation, it also reveals that machine learning models can readily handle the non-linear association relationship.

The Diagnostic Accuracy of Artificial Intelligence in Radiological Markers of Normal-Pressure Hydrocephalus (NPH) on Non-Contrast CT Scans of the Brain

Diagnosing normal-pressure hydrocephalus (NPH) via non-contrast computed tomography (CT) brain scans is presently a formidable task due to the lack of universally agreed-upon standards for radiographic parameter measurement. A variety of radiological parameters, such as Evans' index, narrow sulci at high parietal convexity, Sylvian fissures' dilation, focally enlarged sulci, and more, are currently measured by radiologists. This study aimed to enhance NPH diagnosis by comparing the accuracy, sensitivity, specificity, and predictive values of radiological parameters, as evaluated by radiologists and AI methods, utilizing cerebrospinal fluid volumetry. Results revealed a sensitivity of 77.14% for radiologists and 99.05% for AI, with specificities of 98.21% and 57.14%, respectively, in diagnosing NPH. Radiologists demonstrated NPV, PPV, and an accuracy of 82.09%, 97.59%, and 88.02%, while AI reported 98.46%, 68.42%, and 77.42%, respectively. ROC curves exhibited an area under the curve of 0.954 for radiologists and 0.784 for AI, signifying the diagnostic index for NPH. In conclusion, although radiologists exhibited superior sensitivity, specificity, and accuracy in diagnosing NPH, AI served as an effective initial screening mechanism for potential NPH cases, potentially easing the radiologists' burden. Given the ongoing AI advancements, it is plausible that AI could eventually match or exceed radiologists' diagnostic prowess in identifying hydrocephalus.

Machine learning and statistical models for analyzing multilevel patent data

A recent surge of patent applications among public hospitals in China has aroused significant research interest. A country's healthcare innovation capacity can be measured by its number of patents. This paper explores the link between the number of patents and ten independent variables. Multicollinearity was carefully detected and removed by using the variable selection method and LASSO regression, respectively. The Poisson model and the negative binomial model were proposed to analyze the patent data. Three goodness of fit tests, the Pearson test, the deviance test, and the DHARMa non-parametric dispersion test, were conducted to investigate if the model has a good fit. After discovering four clusters by conducting agglomerative hierarchical clustering, these two models were replaced by the negative binomial mixed model. The likelihood ratio test was used to determine which model is more appropriate and the results reveal that the negative binomial mixed model outperforms both the Poisson model and the negative binomial model. Three variables, number of health technicians per 10,000 people, financial expenditure on science and technology as well as number of patent applications per 10,000 health personnel, have a significantly positive relationship with the number of patents in Chinese tertiary public hospitals.

Nexus between FinTech, renewable energy resource consumption, and carbon emissions

An increase in energy crises and environmental degradation has pushed countries to adopt more sustainable practices. In this situation, financial technology has played an important role to lower carbon emissions by integrating renewable energy resources that can help increase renewable energy resource consumption (REC) and lower carbon emissions (CE). To better understand this transmission mechanism, this study has collected a panel dataset of 26 Morgan Stanley Capital International (MSCI) developing countries for the 2011-2021 period. Furthermore, a proxy indicator for financial technology (FinTech) was developed by extracting relevant data from CrunchBase. Pooled ordinary least square and robust fixed effects technique was adopted to analyse the influence of FinTech on renewable energy and carbon emissions for robustness. Results of the study show that FinTech development promotes renewable energy resource consumption (REC) and discourages carbon emissions (CE), moreover, economic growth positively impacts, and carbon emissions (CE). This research emphasizes the importance of adopting financial technology as an important deterrent of further environmental damage. Additionally, in line with the results of this study, policymakers should design and implement an industrial policy which promotes sustainable economic growth which can pave the path for a circular economy model in the future.

What is the impact of national public expenditure and its allocation on neonatal and child mortality? A machine learning analysis

BACKGROUND

Understanding the impact of national public expenditure and its allocation on child mortality may help governments move towards target 3.2 proposed in the 2030 Agenda. The objective of this study was to estimate the impacts of governmental expenditures, total, on health, and on other sectors, on neonatal mortality and mortality of children aged between 28 days and five years.

METHODS

This study has an ecological design with a population of 147 countries, with data between 2012 and 2019. Two steps were used: first, the Generalized Propensity Score of public spending was calculated; afterward, the Generalized Propensity Score was used to estimate the expenditures' association with mortality rates. The primary outcomes were neonatal mortality rates (NeoRt) and mortality rates in children between 28 days and 5 years (NeoU5Rt).

RESULTS

The 1% variation in Int$ Purchasing Power Parity (Int$ PPP) per capita in total public expenditures, expenditure in health, and in other sectors were associated with a variation of -0.635 (95% CI -1.176, -0.095), -2.17 (95% CI -3.051, -1.289) -0.632 (95% CI -1.169, -0.095) in NeoRt, respectively The same variation in public expenditures in sectors other than health, was associates with a variation of -1.772 (95% CI -6.219, -1.459) on NeoU5Rt. The results regarding the impact of total and health public spending on NeoU5Rt were not consistent.

CONCLUSION

Public investments impact mortality in children under 5 years of age. Likely, the allocation of expenditures between the health sector and the other social sectors will have different impacts on mortality between the NeoRt and the NeoU5Rt.

Development of a smart spectral analysis method for the determination of mulberry (Morus alba var. nigra L.) juice quality parameters using FT-IR spectroscopy

Recently, the application of Fourier transform infrared (FT-IR) spectroscopy as a noninvasive technique combined with chemometric methods has been widely noted for quality evaluation of agricultural products. Mulberry (Morus alba var. nigra L.) is a native fruit of Iran and there is limited information about its quality characteristics. The present study aims at assessing a nondestructive optical method for determining the internal quality of mulberry juice. To do so, first, FT-IR spectra were acquired in the spectral range 1000-8333 nm. Then, the principal component analysis (PCA) was used to extract the principal components (PCs) which were given as inputs to three predictive models (support vector regression (SVR), partial least square (PLS), and artificial neural network (ANN)) to predict the internal parameters of the mulberry juice. The performance of predictive models showed that SVR got better results for the prediction of ascorbic acid (R 2 = .84, RMSE = 0.29), acidity (R 2 = .71, RMSE = 0.0004), phenol (R 2 = .35, RMSE = 0.19), total anthocyanin (R 2 = .93, RMSE = 5.85), and browning (R 2 = .89, RMSE = 0.062) compared to PLS and ANN. However, the ANN predicted the parameters TSS (R 2 = .98, RMSE = 0.003) and pH (R 2 = .99, RMSE = 0.0009) better than the other two models. The results indicated that a good prediction performance was obtained using the FT-IR technique along with SVR and this method could be easily adapted to detect the quality parameters of mulberry juice.

Bioelectrical Impedance Analysis Can Be an Effective Tool for Screening Fatty Liver in Patients with Suspected Liver Disease

Background and study aims: Although abdominal ultrasound (USG) or controlled attenuation parameter (CAP) score of transient elastography (TE) is recommended for the diagnosis of fatty liver, issues regarding cost and accessibility still exist. The aim of this study was to evaluate if bioelectrical impedance analysis (BIA) can be used as a reliable screening tool for fatty liver. Patients and methods: A total of 249 patients who underwent all three tests including TE, BIA, and USG were enrolled. The correlation between fat mass measured by BIA, CAP score of TE, and fatty liver grade measured by USG was analyzed. In addition, the cut-off value of BIA which can predict the fatty liver grade was calculated. Results: Fat mass index (FMI) assessed by BIA increased significantly along with the rise in fatty liver grade measured by USG (normal: 6.2 ± 2.4, Gr I: 8.0 ± 3.7, Gr II: 10.6 ± 3.5, Gr III: 10.7 ± 3.7 kg/m2, p < 0.001). In addition, a positive correlation was found between the CAP score of TE and the FMI of BIA. Additionally, a total body fat mass increase by 24.3% or 29.8% in men and 34.8% or 35.1% in women increased the possibility of developing any grade of fatty liver or significant fatty liver (≥Gr II fatty liver), respectively. Conclusion: The total fat or fat mass index of BIA was related to fatty liver as assessed by ultrasound or CAP score, and area under the receiver operating characteristic (AUROC) was about 0.8. Thus, BIA can be used as a screening tool for fatty liver in patients with suspected liver disease.

Using similar patients to predict complication in patients with diabetes, hypertension, and lipid disorder: a domain knowledge-infused convolutional neural network approach

OBJECTIVE

This study aims to develop a convolutional neural network-based learning framework called domain knowledge-infused convolutional neural network (DK-CNN) for retrieving clinically similar patient and to personalize the prediction of macrovascular complication using the retrieved patients.

MATERIALS AND METHODS

We use the electronic health records of 169 434 patients with diabetes, hypertension, and/or lipid disorder. Patients are partitioned into 7 subcohorts based on their comorbidities. DK-CNN integrates both domain knowledge and disease trajectory of patients over multiple visits to retrieve similar patients. We use normalized discounted cumulative gain (nDCG) and macrovascular complication prediction performance to evaluate the effectiveness of DK-CNN compared to state-of-the-art models. Ablation studies are conducted to compare DK-CNN with reduced models that do not use domain knowledge as well as models that do not consider short-term, medium-term, and long-term trajectory over multiple visits.

RESULTS

Key findings from this study are: (1) DK-CNN is able to retrieve clinically similar patients and achieves the highest nDCG values in all 7 subcohorts; (2) DK-CNN outperforms other state-of-the-art approaches in terms of complication prediction performance in all 7 subcohorts; and (3) the ablation studies show that the full model achieves the highest nDCG compared with other 2 reduced models.

DISCUSSION AND CONCLUSIONS

DK-CNN is a deep learning-based approach which incorporates domain knowledge and patient trajectory data to retrieve clinically similar patients. It can be used to assist physicians who may refer to the outcomes and past treatments of similar patients as a guide for choosing an effective treatment for patients.

Extubation in neurocritical care patients: the ENIO international prospective study

PURPOSE

Neurocritical care patients receive prolonged invasive mechanical ventilation (IMV), but there is poor specific information in this high-risk population about the liberation strategies of invasive mechanical ventilation.

METHODS

ENIO (NCT03400904) is an international, prospective observational study, in 73 intensive care units (ICUs) in 18 countries from 2018 to 2020. Neurocritical care patients with a Glasgow Coma Score (GCS) ≤ 12, receiving IMV ≥ 24 h, undergoing extubation attempt or tracheostomy were included. The primary endpoint was extubation failure by day 5. An extubation success prediction score was created, with 2/3 of patients randomly allocated to the training cohort and 1/3 to the validation cohort. Secondary endpoints were the duration of IMV and in-ICU mortality.

RESULTS

1512 patients were included. Among the 1193 (78.9%) patients who underwent an extubation attempt, 231 (19.4%) failures were recorded. The score for successful extubation prediction retained 20 variables as independent predictors. The area under the curve (AUC) in the training cohort was 0.79 95% confidence interval (CI₉₅) [0.71-0.87] and 0.71 CI₉₅ [0.61-0.81] in the validation cohort. Patients with extubation failure displayed a longer IMV duration (14 [7-21] vs 6 [3-11] days) and a higher in-ICU mortality rate (8.7% vs 2.4%). Three hundred and nineteen (21.1%) patients underwent tracheostomy without extubation attempt. Patients with direct tracheostomy displayed a longer duration of IMV and higher in-ICU mortality than patients with an extubation attempt (success and failure).

CONCLUSIONS

In neurocritical care patients, extubation failure is high and is associated with unfavourable outcomes. A score could predict extubation success in multiple settings. However, it will be mandatory to validate our findings in another prospective independent cohort.

Computational approaches for predicting variant impact: An overview from resources, principles to applications

One objective of human genetics is to unveil the variants that contribute to human diseases. With the rapid development and wide use of next-generation sequencing (NGS), massive genomic sequence data have been created, making personal genetic information available. Conventional experimental evidence is critical in establishing the relationship between sequence variants and phenotype but with low efficiency. Due to the lack of comprehensive databases and resources which present clinical and experimental evidence on genotype-phenotype relationship, as well as accumulating variants found from NGS, different computational tools that can predict the impact of the variants on phenotype have been greatly developed to bridge the gap. In this review, we present a brief introduction and discussion about the computational approaches for variant impact prediction. Following an innovative manner, we mainly focus on approaches for non-synonymous variants (nsSNVs) impact prediction and categorize them into six classes. Their underlying rationale and constraints, together with the concerns and remedies raised from comparative studies are discussed. We also present how the predictive approaches employed in different research. Although diverse constraints exist, the computational predictive approaches are indispensable in exploring genotype-phenotype relationship.

Machine learning can guide food security efforts when primary data are not available

Estimating how many people are food insecure and where they are is of fundamental importance for governments and humanitarian organizations to make informed and timely decisions on relevant policies and programmes. In this study, we propose a machine learning approach to predict the prevalence of people with insufficient food consumption and of people using crisis or above-crisis food-based coping when primary data are not available. Making use of a unique global dataset, the proposed models can explain up to 81% of the variation in insufficient food consumption and up to 73% of the variation in crisis or above food-based coping levels. We also show that the proposed models can nowcast the food security situation in near real time and propose a method to identify which variables are driving the changes observed in predicted trends-which is key to make predictions serviceable to decision-makers.

A Review of Sentiment, Semantic and Event-Extraction-Based Approaches in Stock Forecasting

Stock forecasting is a significant and challenging task. The recent development of web technologies has transformed the communication channel to allow the public to share information over the web such as news, social media contents, etc., thus causing exponential growth of web data. The massively available information might be the key to revealing the financial market’s unexplained variability and facilitating forecasting accuracy. However, this information is usually in unstructured natural language and consists of different inherent meanings. Although a human can easily interpret the inherent messages, it is still complicated to manually process such a massive amount of textual data due to the constraint of time, ability, energy, etc. Due to the different properties of text sources, it is crucial to understand various text processing approaches to optimize forecasting performance. This study attempted to summarize and discuss the current text-based financial forecasting approaches in the aspect of semantic-based, sentiment-based, event-extraction-based, and hybrid approaches. Afterward, the study discussed the strength and weakness of each approach, followed with their comparison and suitable application scenarios. Moreover, this study also highlighted the future research direction in text-based stock forecasting, where the overall discussion is expected to provide insightful analysis for future reference.

Systemic physiology augmented functional near-infrared spectroscopy: a powerful approach to study the embodied human brain

In this Outlook paper, we explain why an accurate physiological interpretation of functional near-infrared spectroscopy (fNIRS) neuroimaging signals is facilitated when systemic physiological activity (e.g., cardiorespiratory and autonomic activity) is measured simultaneously by employing systemic physiology augmented functional near-infrared spectroscopy (SPA-fNIRS). The rationale for SPA-fNIRS is twofold: (i) SPA-fNIRS enables a more complete interpretation and understanding of the fNIRS signals measured at the head since they contain components originating from neurovascular coupling and from systemic physiological sources. The systemic physiology signals measured with SPA-fNIRS can be used for regressing out physiological confounding components in fNIRS signals. Misinterpretations can thus be minimized. (ii) SPA-fNIRS enables to study the embodied brain by linking the brain with the physiological state of the entire body, allowing novel insights into their complex interplay. We envisage the SPA-fNIRS approach will become increasingly important in the future.

A Hybrid Deep Transfer Learning of CNN-Based LR-PCA for Breast Lesion Diagnosis via Medical Breast Mammograms

One of the most promising research areas in the healthcare industry and the scientific community is focusing on the AI-based applications for real medical challenges such as the building of computer-aided diagnosis (CAD) systems for breast cancer. Transfer learning is one of the recent emerging AI-based techniques that allow rapid learning progress and improve medical imaging diagnosis performance. Although deep learning classification for breast cancer has been widely covered, certain obstacles still remain to investigate the independency among the extracted high-level deep features. This work tackles two challenges that still exist when designing effective CAD systems for breast lesion classification from mammograms. The first challenge is to enrich the input information of the deep learning models by generating pseudo-colored images instead of only using the input original grayscale images. To achieve this goal two different image preprocessing techniques are parallel used: contrast-limited adaptive histogram equalization (CLAHE) and Pixel-wise intensity adjustment. The original image is preserved in the first channel, while the other two channels receive the processed images, respectively. The generated three-channel pseudo-colored images are fed directly into the input layer of the backbone CNNs to generate more powerful high-level deep features. The second challenge is to overcome the multicollinearity problem that occurs among the high correlated deep features generated from deep learning models. A new hybrid processing technique based on Logistic Regression (LR) as well as Principal Components Analysis (PCA) is presented and called LR-PCA. Such a process helps to select the significant principal components (PCs) to further use them for the classification purpose. The proposed CAD system has been examined using two different public benchmark datasets which are INbreast and mini-MAIS. The proposed CAD system could achieve the highest performance accuracies of 98.60% and 98.80% using INbreast and mini-MAIS datasets, respectively. Such a CAD system seems to be useful and reliable for breast cancer diagnosis.

A Review on Preparation and Photocatalytic Hydrogen Evolution of Core-shell Cu2O Composites

Abstract:Due to the appropriate bandgap, Cu2O has been widely studied in the field of photocatalytic hydrogen evolution. The core-shell structure is used to design the photocatalytic semiconductor material, so that...