Haves and have-nots: socioeconomic position improves accuracy of machine learning algorithms for predicting high-impact chronic pain.

ABSTRACT: Lower socioeconomic position (SEP) is associated with increased risk of developing chronic pain, experiencing more severe pain, and suffering greater pain-related disability. However, SEP is a multidimensional construct; there is a dearth of research on which SEP features are most strongly associated with high-impact chronic pain, the relative importance of SEP predictive features compared to established chronic pain correlates, and whether the relative importance of SEP predictive features differs by race and sex. This study used 3 machine learning algorithms to address these questions among adults in the 2019 National Health Interview Survey. Gradient boosting decision trees achieved the highest accuracy and discriminatory power for high-impact chronic pain. Results suggest that distinct SEP dimensions, including material resources (eg, ratio of family income to poverty threshold) and employment (ie, working in the past week, number of working adults in the family), are highly relevant predictors of high-impact chronic pain. Subgroup analyses compared the relative importance of predictive features of high-impact chronic pain in non-Hispanic Black vs White adults and men vs women. Whereas the relative importance of body mass index and owning/renting a residence was higher for non-Hispanic Black adults, the relative importance of working adults in the family and housing stability was higher for non-Hispanic White adults. Anxiety symptom severity, body mass index, and cigarette smoking had higher relevance for women, while housing stability and frequency of anxiety and depression had higher relevance for men. Results highlight the potential for machine learning algorithms to advance health equity research.

Fair AI-powered orthopedic image segmentation: addressing bias and promoting equitable healthcare.

AI-powered segmentation of hip and knee bony anatomy has revolutionized orthopedics, transforming pre-operative planning and post-operative assessment. Despite the remarkable advancements in AI algorithms for medical imaging, the potential for biases inherent within these models remains largely unexplored. This study tackles these concerns by thoroughly re-examining AI-driven segmentation for hip and knee bony anatomy. While advanced imaging modalities like CT and MRI offer comprehensive views, plain radiographs (X-rays) predominate the standard initial clinical assessment due to their widespread availability, low cost, and rapid acquisition. Hence, we focused on plain radiographs to ensure the utilization of our contribution in diverse healthcare settings, including those with limited access to advanced imaging technologies. This work provides insights into the underlying causes of biases in AI-based knee and hip image segmentation through an extensive evaluation, presenting targeted mitigation strategies to alleviate biases related to sex, race, and age, using an automatic segmentation that is fair, impartial, and safe in the context of AI. Our contribution can enhance inclusivity, ethical practices, equity, and an unbiased healthcare environment with advanced clinical outcomes, aiding decision-making and osteoarthritis research. Furthermore, we have made all the codes and datasets publicly and freely accessible to promote open scientific research.

Predicting incident cardiovascular disease among African-American adults: A deep learning approach to evaluate social determinants of health in the Jackson heart study.

The present study sought to leverage machine learning approaches to determine whether social determinants of health improve prediction of incident cardiovascular disease (CVD). Participants in the Jackson Heart study with no history of CVD at baseline were followed over a 10-year period to determine first CVD events (i.e., coronary heart disease, stroke, heart failure). Three modeling algorithms (i.e., Deep Neural Network, Random Survival Forest, Penalized Cox Proportional Hazards) were used to evaluate three feature sets (i.e., demographics and standard/biobehavioral CVD risk factors [FS1], FS1 combined with psychosocial and socioeconomic CVD risk factors [FS2], and FS2 combined with environmental features [FS3]) as predictors of 10-year CVD risk. Contrary to hypothesis, overall predictive accuracy did not improve when adding social determinants of health. However, social determinants of health comprised eight of the top 15 predictors of first CVD events. The social determinates of health indicators included four socioeconomic factors (insurance status and types), one psychosocial factor (discrimination burden), and three environmental factors (density of outdoor physical activity resources, including instructional and water activities; modified retail food environment index excluding alcohol; and favorable food stores). Findings suggest that whereas understanding biological determinants may identify who is currently at risk for developing CVD and in need of secondary prevention, understanding upstream social determinants of CVD risk could guide primary prevention efforts by identifying where and how policy and community-level interventions could be targeted to facilitate changes in individual health behaviors.

Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach.

BACKGROUND: The COVID-19 pandemic has demonstrated the need for efficient and comprehensive, simultaneous assessment of multiple combined novel therapies for viral infection across the range of illness severity. Randomized Controlled Trials (RCT) are the gold standard by which efficacy of therapeutic agents is demonstrated. However, they rarely are designed to assess treatment combinations across all relevant subgroups. A big data approach to analyzing real-world impacts of therapies may confirm or supplement RCT evidence to further assess effectiveness of therapeutic options for rapidly evolving diseases such as COVID-19. METHODS: Gradient Boosted Decision Tree, Deep and Convolutional Neural Network classifiers were implemented and trained on the National COVID Cohort Collaborative (N3C) data repository to predict the patients' outcome of death or discharge. Models leveraged the patients' characteristics, the severity of COVID-19 at diagnosis, and the calculated proportion of days on different treatment combinations after diagnosis as features to predict the outcome. Then, the most accurate model is utilized by eXplainable Artificial Intelligence (XAI) algorithms to provide insights about the learned treatment combination impacts on the model's final outcome prediction. RESULTS: Gradient Boosted Decision Tree classifiers present the highest prediction accuracy in identifying patient outcomes with area under the receiver operator characteristic curve of 0.90 and accuracy of 0.81 for the outcomes of death or sufficient improvement to be discharged. The resulting model predicts the treatment combinations of anticoagulants and steroids are associated with the highest probability of improvement, followed by combined anticoagulants and targeted antivirals. In contrast, monotherapies of single drugs, including use of anticoagulants without steroid or antivirals are associated with poorer outcomes. CONCLUSIONS: This machine learning model by accurately predicting the mortality provides insights about the treatment combinations associated with clinical improvement in COVID-19 patients. Analysis of the model's components suggests benefit to treatment with combination of steroids, antivirals, and anticoagulant medication. The approach also provides a framework for simultaneously evaluating multiple real-world therapeutic combinations in future research studies.

Removal of chloride ion from drinking water using Ag NPs-Modified bentonite: Characterization and optimization of effective parameters by response surface methodology-central composite design.

The presence of chloride ion as an environmental pollutant is having a devastating and irreversible effect on aquatic and terrestrial ecosystems. To ensure safe and clean drinking water, it is vital to remove this substance using non-toxic and eco-friendly methods. This study presents a novel and highly efficient Ag NPs-modified bentonite adsorbent for removing chloride ion, a common environmental pollutant, from drinking water using a facile approach. The surface chemical properties and morphology of the pristine Na-bentonite and Ag NPs-Modified bentonite were characterized by field emission scanning electron microscopy (FESEM) and X-ray spectroscopy (EDX), X-Ray diffraction (XRD), Fourier transform infrared (FTIR), and zeta potential (ζ). To achieve maximum chloride ion removal, the effects of experimental parameters, including adsorbent dosage (1-9 g/L), chloride ion concentration (100-900 mg/L), and reaction time (5-25 h), were examined using the Response Surface Methodology (RSM). The chloride ion removal of 90% was obtained at optimum conditions (adsorbent dosage: 7 g/L, chloride ion concentration: 500 mg/L, and reaction time: 20 h). The adsorption isotherm and kinetics results indicated that the Langmuir isotherm model and pseudo-second-order kinetics were found suitable to chloride ion removal. Additionally, the regeneration and reusability of the Ag NPs-modified bentonite were further studied. In the regeneration and reusability study, the Ag NPs-modified bentonite has shown consistently ≥90% and ≥87% chloride ion removal even up to 2 repeated cycles, separately. Thus, the findings in this study provided convincing evidence for using Ag-NPs modified bentonite as a high-efficiency and promising adsorbent to remove chloride ion from drinking water.

Predicting temporal and spatial variability in flood vulnerability and risk of rural communities at the watershed scale.

Due to land-use and hydrology changes, people are constantly exposed to floods. The adverse impact of floods is greater on vulnerable populations that disproportionately inhabit flood-prone areas. This paper reports a comprehensive study on flood vulnerability of flood prone areas in residential areas of the Tajan watershed, Iran in two periods before 2006 and after 2006. Flood prone area were determined by the random forest (RF) and K-nearest neighbor (KNN) machine learning methods. To reduce time and cost, the vulnerability was assessed only in areas with very high flood hazard using 4 main criteria (social, policy, economic, infrastructure), 40 items, and 210 questionnaires across 40 villages. Independent t-test, Kruskal-Wallis, and paired t-test were used for statistical analysis of questionnaire data. The results of machine learning models (MLMs) showed that the RF model with AUC = 0.92% is more accurate in determining flood prone areas. The results of paired t-test showed that the three criteria of social (mean P1 = 2.97 and P2 = 3.35), infrastructure (mean P1 = 2.88 and P2 = 3.25), and policy (mean P1 = 3.02 and P2 = 3.50) had significant changes in both periods. The Kruskal-Wallis test also revealed the mean of all four criteria in both periods and all sub-watersheds, except three sub-watersheds 10 (Khalkhil village), 19 (Tellarem and Kerasp villages), and 23 (Dinehsar and Jafarabad), had a significant difference. The results of the t-test also showed a decrease in vulnerability in the second period (before 2006) compared to the first period (after 2006), so the number of sub-watersheds in the very high vulnerability class was more in the first period than in the second period. A vulnerability map was developed using three factors of risk zone area, area of each sub-watershed, and population of each sub-watershed.

An ordinal severity scale for COVID-19 retrospective studies using Electronic Health Record data.

Objectives: Although the World Health Organization (WHO) Clinical Progression Scale for COVID-19 is useful in prospective clinical trials, it cannot be effectively used with retrospective Electronic Health Record (EHR) datasets. Modifying the existing WHO Clinical Progression Scale, we developed an ordinal severity scale (OS) and assessed its usefulness in the analyses of COVID-19 patient outcomes using retrospective EHR data. Materials and Methods: An OS was developed to assign COVID-19 disease severity using the Observational Medical Outcomes Partnership common data model within the National COVID Cohort Collaborative (N3C) data enclave. We then evaluated usefulness of the developed OS using heterogenous EHR data from January 2020 to October 2021 submitted to N3C by 63 healthcare organizations across the United States. Principal component analysis (PCA) was employed to characterize changes in disease severity among patients during the 28-day period following COVID-19 diagnosis. Results: The data set used in this analysis consists of 2 880 456 patients. PCA of the day-to-day variation in OS levels over the totality of the 28-day period revealed contrasting patterns of variation in disease severity within the first and second 14 days and illustrated the importance of evaluation over the full 28-day period. Discussion: An OS with well-defined, robust features, based on discrete EHR data elements, is useful for assessments of COVID-19 patient outcomes, providing insights on the progression of COVID-19 disease severity over time. Conclusions: The OS provides a framework that can facilitate better understanding of the course of acute COVID-19, informing clinical decision-making and resource allocation.

Multi-objective design optimization of dental implant geometrical parameters.

In-silico investigations are becoming an integral part of the development of novel biomedical devices, including dental implants. Using computer simulations can streamline the process by tuning different geometrical and structural features, emphasizing the osseointegration of the implant design a priori, leading to the optimal designs in preparation for in-vivo trails. This research aims to elucidate the interrelationship between 12 geometrical variables that holistically define the shape of the implant. The approach to achieve optimality hinged on coupling the finite element analysis results with the fractional factorial design method. The latter was used to determine the most influential variables during the screening process, followed by the parameter optimization process using the response surface method, regarding four different objectives, namely: bone-implant contact area, volume of trabecular bone dead cells, volume of cortical bone dead cells, and axial displacement. This resulted in reducing the number of virtual experiments and substantially decreasing the computational cost without compromising the accuracy of the solution. It was found that the optimized values improved the performance significantly. The validity of all models was verified by comparing optimized responses with simulation results. A sensitivity analysis was performed on all five optimized models to address the effect of friction coefficient on the implant-bone joint interaction. It was shown that the mechanical behavior of implant-bone would be independent in higher friction coefficients. The significance of this study is demonstrated in determining the most effective and optimized values of all possible geometrical parameters considering their singular or interactive effects.