Using random forest to identify longitudinal predictors of health in a 30-year cohort study

Predicting 24-Hour Blood Pressure Variability Post Thrombectomy Using Machine Learning for Patients with Ischemic Stroke from Anterior Circulation Large Vessel Occlusion

BACKGROUND

Mechanical thrombectomy is the standard of care for patients with ischemic stroke from large vessel occlusion. Blood pressure variability (BPV) in the post thrombectomy period is associated with poor functional outcomes. To determine predictive factors associated with increased BPV, a machine learning algorithm was used to identify factors that are linked with increased BPV indices at 24 hours post thrombectomy.

METHODS

This retrospective study examined all patients from a Comprehensive Stroke Center's registry who underwent mechanical thrombectomy between January 2016 and December 2019. The primary outcome was BPV between patients who had adequate reperfusion post thrombectomy (Thrombolysis in Cerebral Infarction [TICI] grading 2b+) and those who did not. The secondary outcomes were good functional status at 90 days (modified Rankin Scale ≤2) and reperfusion (TICI 2b+). Random forest analysis was leveraged to determine predictors for BPV with reported root mean square error and normalized root mean square error metrics. Multivariable regression analysis was used to determine factors significantly associated with secondary outcomes. P < 0.05 was the threshold for statistical significance.

RESULTS

A total of 395 patients (49%, n = 195 females and 51%, n = 200 males) were included in the final analysis with mean age (± standard deviation) of 65 (±15) years. TICI 2b+ was achieved in 322 (82%) patients. Median Alberta stroke program early CT score and National Institutes of Health Stroke Scale (NIHSS) were 9 and 18, respectively. Higher age, NIHSS, number of passes, and mechanical ventilation were significantly associated with lower likelihood of modified Rankin Scale ≤2 at 90 days in multivariable regression analysis.

CONCLUSIONS

This study identified the interval from last-known-well time-to-groin puncture, age, and NIHSS as factors significantly associated with increased 24-hour BPV in random forest analysis. These predisposing factors in our machine learning analysis allow clinicians to identify patients who are at risk of having increased BPV and opportunities to augment these patients' blood pressure control.

Global research trends on the human exposome: a bibliometric analysis (2005-2024)

Exposome represents one of the most pressing issues in the environmental science research field. However, a comprehensive summary of worldwide human exposome research is lacking. We aimed to explore the bibliometric characteristics of scientific publications on the human exposome. A bibliometric analysis of human exposome publications from 2005 to December 2024 was conducted using the Web of Science in accordance with PRISMA guidelines. Trends/hotspots were investigated with keyword frequency, co-occurrence, and thematic map. Sex disparities in terms of publications and citations were examined. From 2005 to 2024, 931 publications were published in 363 journals and written by 4529 authors from 72 countries. The number of publications tripled during the last 5 years. Publications written by females (51% as first authors and 34% as last authors) were cited fewer times (13,674) than publications written by males (22,361). Human exposome studies mainly focused on air pollution, metabolomics, chemicals (e.g., per- and polyfluoroalkyl substances (PFAS), endocrine-disrupting chemicals, pesticides), early-life exposure, biomarkers, microbiome, omics, cancer, and reproductive disorders. Social and built environment factors, occupational exposure, multi-exposure, digital exposure (e.g., screen use), climate change, and late-life exposure received less attention. Our results uncovered high-impact countries, institutions, journals, references, authors, and key human exposome research trends/hotspots. The use of digital exposome technologies (e.g., sensors, and wearables) and data science (e.g., artificial intelligence) has blossomed to overcome challenges and could provide valuable knowledge toward precision prevention. Exposome risk scores represent a promising research avenue.

Dengue dynamics, predictions, and future increase under changing monsoon climate in India

The global burden of dengue disease is escalating under the influence of climate change, with India contributing a third of the total. The non-linearity and regional heterogeneity inherent in the climate-dengue relationship and the lack of consistent data makes it difficult to make useful predictions for effective disease prevention. The current study investigates these non-linear climate-dengue links in Pune, a dengue hotspot region in India with a monsoonal climate and presents a model framework for predicting both the near-term and future dengue mortalities. Dengue mortality and meteorological conditions over a twelve-year period (2004-2015) are analyzed using statistical tools and machine learning methods. Our findings point to a significant influence of temperature, rainfall, and relative humidity on dengue mortality in Pune, at a time-lag of 2-5 months, providing sufficient lead time for an early warning targeted at curbing dengue outbreaks. We find that moderate rains spread over the summer monsoon season lead to an increase in dengue mortality, whereas heavy rains reduce it through the flushing effect, indicating the links between dengue and monsoon intraseasonal variability. Additionally, warm temperatures above 27°C and humidity levels between 60% and 78% elevate the risk of dengue. Based on these weather-dengue associations, we developed a machine-learning model utilizing the random forest regression algorithm. The dengue model yields a skillful forecast, achieving a statistically significant correlation coefficient of r = 0.77 and a relatively low Normalized Root Mean Squared Error score of 0.52 between actual and predicted dengue mortalities, at a lead time of two months. The model finds that the relative contributions of temperature, rainfall, and relative humidity to dengue mortality in Pune are 41%, 39%, and 20%, respectively. We use the dengue model in conjunction with the climate change simulations from the Coupled Model Intercomparison Project phase 6 for the future dengue mortality projections under a global warming scenario. In a changing climate, dengue-related mortality in Pune is projected to rise by 13% in the near future (2021-2040), 23-40% in the mid-century (2041-2060), and 30-112% in the late century (2081-2100) under low-to-high emission pathways in response to the associated increase in temperature and changes in monsoon rainfall patterns.

Medical Therapy Alone for Ommaya Reservoir-Associated Bacterial Meningitis: When It Works and When It Fails

BACKGROUND AND OBJECTIVES

Administration of intraventricular chemotherapy through Ommaya reservoir is indicated for certain forms of leptomeningeal disease. However, ventricular reservoirs carry a substantial risk of infection. The conventional approach to managing reservoir-associated infections involves removal of the reservoir and systemic antibiotic therapy, but this strategy necessitates additional procedures to remove and subsequently replace the device. We evaluated the success rate of standardized, multimodal medical therapy alone in treating reservoir-associated meningitis and factors associated with the need for device removal.

METHODS

We used the International Neoplastic Meningitis Academic Registry Consortium database to identify patients at our institution with reservoir-associated bacterial meningitis. A standardized antibiotic regimen of oral rifampin, intraventricular vancomycin, and another intravenous antibiotic based on the infecting organism was used to treat infections for 10 to 14 days. We evaluated the rate of infection clearance and factors associated with success of therapy without reservoir removal.

RESULTS

Forty-eight infections in 33 patients (5.79% of all patients) were identified. Before infection, reservoirs were accessed a median of 6 (1-14) times. Infections were eradicated without reservoir removal in 39 of 48 patients (81.3%). Cerebrospinal fluid (CSF) leak/local wound infection was the only factor associated with the need for reservoir removal (odds ratio = 18.3 [3.68-141], P < .001) on multivariate analysis, and 98.0% of patients without this characteristic were cured with medical therapy alone. Other characteristics such as age, myelosuppression, tumor histology, number of reservoir accesses, concurrent systemic chemotherapy, or infecting organism were not predictive of reservoir removal. Random forest and gradient boost machine learning models further confirmed CSF leak/local wound infection to be the most important predictor of removal.

CONCLUSION

Most patients who develop a reservoir-associated infection can be successfully treated with a standardized antibiotic regimen alone, without additional surgery for reservoir removal and subsequent replacement. However, CSF leak/reservoir site infection is strongly associated with failure of medical therapy and warrants early device removal.

Construction and Application of a Traditional Chinese Medicine Syndrome Differentiation Model for Dysmenorrhea Based on Machine Learning

BACKGROUND

Dysmenorrhea is one of the most common ailments affecting young and middle-aged women, significantly impacting their quality of life. Traditional Chinese Medicine (TCM) offers unique advantages in treating dysmenorrhea. However, an accurate diagnosis is essential to ensure correct treatment. This research integrates the age-old wisdom of TCM with modern Machine Learning (ML) techniques to enhance the precision and efficiency of dysmenorrhea syndrome differentiation, a pivotal process in TCM diagnostics and treatment planning.

METHODS

A total of 853 effective cases of dysmenorrhea were retrieved from the CNKI database, including patients' syndrome types, symptoms, and features, to establish the TCM information database of dysmenorrhea. Subsequently, 42 critical features were isolated from a potential set of 86 using a selection procedure augmented by Python's Scikit-Learn Library. Various machine learning models were employed, including Logistic Regression, Random Forest Classifier, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Artificial Neural Networks (ANN), each chosen for their potential to unearth complex patterns within the data.

RESULTS

Based on accuracy, precision, recall, and F1-score metrics, SVM emerged as the most effective model, showcasing an impressive precision of 98.29% and an accuracy of 98.24%. This model's analytical prowess not only highlighted the critical features pivotal to the syndrome differentiation process but also stands to significantly aid clinicians in formulating personalized treatment strategies by pinpointing nuanced symptoms with high precision.

CONCLUSION

The study paves the way for a synergistic approach in TCM diagnostics, merging ancient wisdom with computational acuity, potentially innovating the diagnosis and treatment mode of TCM. Despite the promising outcomes, further research is needed to validate these models in real-world settings and extend this approach to other diseases addressed by TCM.

Development of a deep learning model to predict smoking status in patients with chronic obstructive pulmonary disease: A secondary analysis of cross-sectional national survey

Objective

This study aims to develop and validate a deep learning model to predict smoking status in patients with chronic obstructive pulmonary disease (COPD) using data from a national survey.

Methods

Data from the Korea National Health and Nutrition Examination Survey (2007-2018) were used to extract 5466 COPD-eligible cases. The data collection involved demographic, behavioral, and clinical variables, including 21 predictors such as age, sex, and pulmonary function test results. The dependent variable, smoking status, was categorized as smoker or nonsmoker. A residual neural network (ResNN) model was developed and compared with five machine learning algorithms (random forest, decision tree, Gaussian Naive Bayes, K-nearest neighbor, and AdaBoost) and two deep learning models (multilayer perceptron and TabNet). Internal validation was performed using five-fold cross-validation, and model performance was evaluated using the area under the receiver operating characteristic (AUROC) curve, sensitivity, specificity, and F1-score.

Results

The ResNN achieved an AUROC, sensitivity, specificity, and F1-score of 0.73, 70.1%, 75.2%, and 0.67, respectively, outperforming previous machine learning and deep learning models in predicting smoking status in patients with COPD. Explainable artificial intelligence (Shapley additive explanations) identified key predictors, including sex, age, and perceived health status.

Conclusion

This deep learning model accurately predicts smoking status in patients with COPD, offering potential as a decision-support tool to detect high-risk persistent smokers for targeted interventions. Future studies should focus on external validation and incorporate additional behavioral and psychological variables to improve its generalizability and performance.

The Use of Artificial Intelligence to Analyze the Exposome in the Development of Chronic Diseases: A Review of the Current Literature

The “Exposome” is a concept that indicates the set of exposures to which a human is subjected during their lifetime. These factors influence the health state of individuals and can drive the development of Noncommunicable Diseases (NCDs). Artificial Intelligence (AI) allows one to analyze large amounts of data in a short time. As such, several authors have used AI to study the relationship between exposome and chronic diseases. Under such premises, this study reviews the use of AI in analyzing the exposome to understand its role in the development of chronic diseases, focusing on how AI can identify patterns in exposure-related data and support prevention strategies. To achieve this, we carried out a search on multiple databases, including PubMed, ScienceDirect, and SCOPUS, from 1 January 2019 to 31 May 2023, using the MeSH terms (exposome) and (‘Artificial Intelligence’ OR ‘Machine Learning’ OR ‘Deep Learning’) to identify relevant studies on this topic. After completing the identification, screening, and eligibility assessment, a total of 18 studies were included in this literature review. According to the search, most authors used supervised or unsupervised machine learning models to study multiple exposure factors’ role in the risk of developing cardiovascular, metabolic, and chronic respiratory diseases. In some more recent studies, authors also used deep learning. Furthermore, the exposome analysis is useful to study the risk of developing neuropsychiatric disorders or evaluating pregnancy outcomes and child growth. Understanding the role of the exposome is pivotal to overcome the classic concept of a single exposure/disease. The application of AI allows one to analyze multiple environmental risks and their combined effects on health conditions. In the future, AI could be helpful in the prevention of chronic diseases, providing new diagnostic, therapeutic, and follow-up strategies.

Using machine learning to predict the risk of developing hypertensive disorders of pregnancy using a contemporary nulliparous cohort

Background

Hypertensive disorders of pregnancy (HDP) are significant drivers of maternal and neonatal morbidity and mortality. Current management strategies include early identification and initiation of risk mitigating interventions facilitated by a rules-based checklist. Advanced analytic techniques, such as machine learning, can potentially offer improved and refined predictive capabilities.

Objective

To develop and internally validate a machine learning prediction model for hypertensive disorders of pregnancy (HDP) when initiating prenatal care.

Study Design

We developed a prediction model using data from the prospective multisite cohort Nulliparous Pregnancy Outcomes Study: Monitoring Mothers-to-Be (nuMoM2b) among low-risk individuals without a prior history of aspirin utilization for preeclampsia prevention. The primary outcome was the development of HDP. Random forest modeling was utilized to develop predictive models. Recursive feature elimination (RFE) was employed to create a reduced model for each outcome. Area under the curve (AUC), 95% confidence intervals (CI), and calibration curves were utilized to assess discrimination and accuracy. Sensitivity analyses were conducted to compare the sensitivity and specificity of the reduced model compared to existing risk factor-based algorithms.

Results

Of 9,124 assessed low risk nulliparous individuals, 21% (n=1,927) developed HDP. The prediction model for HDP had satisfactory discrimination with an AUC of 0.73 (95% CI: 0.70, 0.75). After RFE, a parsimonious reduced model with 30 features was created with an AUC of 0.71 (95% CI: 0.68, 0.74). Variables included in the model after RFE included body mass index at the first study visit, pre-pregnancy weight, first trimester complete blood count results, and maximum systolic blood pressure at the first visit. Calibration curves for all models revealed relatively stable agreement between predicted and observed probabilities. Sensitivity analysis noted superior sensitivity (AUC 0.80 vs 0.65) and specificity (0.65 vs 0.53) of the model compared to traditional risk factor-based algorithms.

Conclusion

In cohort of low-risk nulliparous pregnant individuals, a prediction model may accurately predict HDP diagnosis at the time of initiating prenatal care and aid employment of close interval monitoring and prophylactic measures earlier in pregnancy.

Exploring Clinical Practices of Critical Alarm Settings in Intensive Care Units: A Retrospective Study of 60,000 Patient Stays from the MIMIC-IV Database

In Intensive Care Unit (ICU), the settings of the critical alarms should be sensitive and patient-specific to detect signs of deteriorating health without ringing continuously, but alarm thresholds are not always calibrated to operate this way. An assessment of the connection between critical alarm threshold settings and the patient-specific variables in ICU would deepen our understanding of the issue. The aim of this retrospective descriptive and exploratory study was to assess this relationship using a large cohort of ICU patient stays. A retrospective study was conducted on some 70,000 ICU stays taken from the MIMIC-IV database. Critical alarm threshold values and threshold modification frequencies were examined. The link between these alarm threshold settings and 30 patient variables was then explored by computing the Shapley values of a Random Tree Forest model, fitted with patient variables and alarm settings. The study included 57,667 ICU patient stays. Alarm threshold values and alarm threshold modification frequencies exhibited the same trend: they were influenced by the vital sign monitored, but almost never by the patient's overall health status. This exploratory study also placed patients' vital signs as the most important variables, far ahead of medication. In conclusion, alarm settings were rigid and mechanical and were rarely adapted to the evolution of the patient. The management of alarms in ICU appears to be imperfect, and a different approach could result in better patient care and improved quality of life at work for staff.

Microbial-Derived Exerkines Prevent Skeletal Muscle Atrophy

Regular exercise yields a multitude of systemic benefits, many of which may be mediated through the gut microbiome. Here, we report that cecal microbial transplants (CMTs) from exercise-trained vs. sedentary mice have modest benefits in reducing skeletal muscle atrophy using a mouse model of unilaterally hindlimb-immobilization. Direct administration of top microbial-derived exerkines from an exercise-trained gut microbiome preserved muscle function and prevented skeletal muscle atrophy.

Ensemble technique of intrusion detection for IoT-edge platform

Internet of Things (IoT) technology has revolutionized modern industrial sectors. Moreover, IoT technology has been incorporated within several vital domains of applicability. However, security is overlooked due to the limited resources of IoT devices. Intrusion detection methods are crucial for detecting attacks and responding adequately to every IoT attack. Conspicuously, the current study outlines a two-stage procedure for the determination and identification of intrusions. In the first stage, a binary classifier termed an Extra Tree (E-Tree) is used to analyze the flow of IoT data traffic within the network. In the second stage, an Ensemble Technique (ET) comprising of E-Tree, Deep Neural Network (DNN), and Random Forest (RF) examines the invasive events that have been identified. The proposed approach is validated for performance analysis. Specifically, Bot-IoT, CICIDS2018, NSL-KDD, and IoTID20 dataset were used for an in-depth performance assessment. Experimental results showed that the suggested strategy was more effective than existing machine learning methods. Specifically, the proposed technique registered enhanced statistical measures of accuracy, normalized accuracy, recall measure, and stability.

Patterns of human and bots behaviour on Twitter conversations about sustainability

Sustainability is an issue of worldwide concern. Twitter is one of the most popular social networks, which makes it particularly interesting for exploring opinions and characteristics related to issues of social preoccupation. This paper aims to gain a better understanding of the activity related to sustainability that takes place on twitter. In addition to building a mathematical model to identify account typologies (bot and human users), different behavioural patterns were detected using clustering analysis mainly in the mechanisms of posting tweets and retweets). The model took as explanatory variables, certain characteristics of the user's profile and her/his activity. A lexicon-based sentiment analysis in the period from 2006 to 2022 was also carried out in conjunction with a keyword study based on centrality metrics. We found that, in both bot and human users, messages showed mostly a positive sentiment. Bots had a higher percentage of neutral messages than human users. With respect to the used keywords certain commonalities but also slight differences between humans and bots were identified.

Past or Present; Which Exposures Predict Metabolomic Aging Better? The Doetinchem Cohort Study

People age differently. Differences in aging might be reflected by metabolites, also known as metabolomic aging. Predicting metabolomic aging is of interest in public health research. However, the added value of longitudinal over cross-sectional predictors of metabolomic aging is unknown. We studied exposome-related exposures as potential predictors of metabolomic aging, both cross-sectionally and longitudinally in men and women. We used data from 4 459 participants, aged 36-75 of Round 4 (2003-2008) of the long-running Doetinchem Cohort Study (DCS). Metabolomic age was calculated with the MetaboHealth algorithm. Cross-sectional exposures were demographic, biological, lifestyle, and environmental at Round 4. Longitudinal exposures were based on the average exposure over 15 years (Round 1 [1987-1991] to 4), and trend in these exposure over time. Random Forest was performed to identify model performance and important predictors. Prediction performances were similar for cross-sectional and longitudinal exposures in both men (R2 6.8 and 5.8, respectively) and women (R2 14.8 and 14.4, respectively). Biological and diet exposures were most predictive for metabolomic aging in both men and women. Other important predictors were smoking behavior for men and contraceptive use and menopausal status for women. Taking into account history of exposure levels (longitudinal) had no added value over cross-sectionally measured exposures in predicting metabolomic aging in the current study. However, the prediction performances of both models were rather low. The most important predictors for metabolomic aging were from the biological and lifestyle domain and differed slightly between men and women.

Protocol of an individual participant data meta-analysis to quantify the impact of high ambient temperatures on maternal and child health in Africa (HE2AT IPD)

INTRODUCTION

Globally, recognition is growing of the harmful impacts of high ambient temperatures (heat) on health in pregnant women and children. There remain, however, major evidence gaps on the extent to which heat increases the risks for adverse health outcomes, and how this varies between settings. Evidence gaps are especially large in Africa. We will conduct an individual participant data (IPD) meta-analysis to quantify the impacts of heat on maternal and child health in sub-Saharan Africa. A detailed understanding and quantification of linkages between heat, and maternal and child health is essential for developing solutions to this critical research and policy area.

METHODS AND ANALYSIS

We will use IPD from existing, large, longitudinal trial and cohort studies, on pregnant women and children from sub-Saharan Africa. We will systematically identify eligible studies through a mapping review, searching data repositories, and suggestions from experts. IPD will be acquired from data repositories, or through collaboration with data providers. Existing satellite imagery, climate reanalysis data, and station-based weather observations will be used to quantify weather and environmental exposures. IPD will be recoded and harmonised before being linked with climate, environmental, and socioeconomic data by location and time. Adopting a one-stage and two-stage meta-analysis method, analytical models such as time-to-event analysis, generalised additive models, and machine learning approaches will be employed to quantify associations between exposure to heat and adverse maternal and child health outcomes.

ETHICS AND DISSEMINATION

The study has been approved by ethics committees. There is minimal risk to study participants. Participant privacy is protected through the anonymisation of data for analysis, secure data transfer and restricted access. Findings will be disseminated through conferences, journal publications, related policy and research fora, and data may be shared in accordance with data sharing policies of the National Institutes of Health.

PROSPERO REGISTRATION NUMBER

CRD42022346068.

Gaining Biological Insights through Supervised Data Visualization

Dimensionality reduction-based data visualization is pivotal in comprehending complex biological data. The most common methods, such as PHATE, t-SNE, and UMAP, are unsupervised and therefore reflect the dominant structure in the data, which may be independent of expert-provided labels. Here we introduce a supervised data visualization method called RF-PHATE, which integrates expert knowledge for further exploration of the data. RF-PHATE leverages random forests to capture intricate featurelabel relationships. Extracting information from the forest, RF-PHATE generates low-dimensional visualizations that highlight relevant data relationships while disregarding extraneous features. This approach scales to large datasets and applies to classification and regression. We illustrate RF-PHATE's prowess through three case studies. In a multiple sclerosis study using longitudinal clinical and imaging data, RF-PHATE unveils a sub-group of patients with non-benign relapsingremitting Multiple Sclerosis, demonstrating its aptitude for time-series data. In the context of Raman spectral data, RF-PHATE effectively showcases the impact of antioxidants on diesel exhaust-exposed lung cells, highlighting its proficiency in noisy environments. Furthermore, RF-PHATE aligns established geometric structures with COVID-19 patient outcomes, enriching interpretability in a hierarchical manner. RF-PHATE bridges expert insights and visualizations, promising knowledge generation. Its adaptability, scalability, and noise tolerance underscore its potential for widespread adoption.

Quality of life and socio-demographic factors associated with nutritional risk in Brazilian community-dwelling individuals aged 80 and over: cluster analysis and ensemble methods

Introduction

The aim of the present study was to use cluster analysis and ensemble methods to evaluate the association between quality of life, socio-demographic factors to predict nutritional risk in community-dwelling Brazilians aged 80 and over.

Methods

This cross-sectional study included 104 individuals, both sexes, from different community locations. Firstly, the participants answered the sociodemographic questionnaire, and were sampled for anthropometric data. Subsequently, the Mini-Mental State Examination (MMSE) was applied, and Mini Nutritional Assessment Questionnaire (MAN) was used to evaluate their nutritional status. Finally, quality of life (QoL) was assessed by a brief version of World Health Organizations' Quality of Life (WHOQOL-BREF) questionnaire and its older adults' version (WHOQOL-OLD).

Results

The K-means algorithm was used to identify clusters of individuals regarding quality-of-life characteristics. In addition, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) algorithms were used to predict nutritional risk. Four major clusters were derived. Although there was a higher proportion of individuals aged 80 and over with nutritional risk in cluster 2 and a lower proportion in cluster 3, there was no statistically significant association. Cluster 1 showed the highest scores for psychological, social, and environmental domains, while cluster 4 exhibited the worst scores for the social and environmental domains of WHOQOL-BREF and for autonomy, past, present, and future activities, and intimacy of WHOQOL-OLD.

Conclusion

Handgrip, household income, and MMSE were the most important predictors of nutritional. On the other hand, sex, self-reported health, and number of teeth showed the lowest levels of influence in the construction of models to evaluate nutritional risk. Taken together, there was no association between clusters based on quality-of-life domains and nutritional risk, however, predictive models can be used as a complementary tool to evaluate nutritional risk in individuals aged 80 and over.

Different volatile organic compounds in local point source air pollution pose distinctive elevated risks for respiratory disease-associated emergency room visits

Air pollution increases risk of respiratory disease but prior research has focused on particulate matter and criteria air pollutants, and there are few studies on respiratory effects of volatile organic compounds (VOC). We examined zip code level relationships between emergency room (ER) visits for respiratory illness and VOC pollution in New York State from 2010 to 2018. Detailed information on VOC pollution was derived from the National Emissions Inventory, which provides point source information on VOC emissions at the zip code level. We considered four respiratory diseases: asthma, acute upper respiratory infections, chronic obstructive pulmonary disease (COPD), and lower respiratory disease, using mixed effects regression with a random intercept to account for county level variability in single pollutant models, and Random Forest Regression (RFR) to assess relative importance of VOC exposures when considered together in multipollutant models. Single pollutant models show associations between respiratory-related ER visits with all pollutants of interest across all study years, even after adjusting for poverty and smoking by zip code. The largest relative single pollutant effect sizes considered included benzene, ethylbenzene, and total (summed) VOCs. Results from RFR including all VOC exposures indicate that ethylbenzene has the greatest variable importance for asthma, acute upper respiratory infections, and COPD, with toluene and benzene most important for lower respiratory ailments. RFR results also demonstrate presence of pairwise interactive effects between VOC pollutants. Our findings show that local VOC pollution may offer a significant contribution to the risk of respiratory disease-related ER visits, and that effects vary by illness and by VOC compound. ER visit rates for respiratory illness were elevated in high poverty zip codes, although this may be attributable to the fact that the poor lack basic access to health care and use ERs more frequently for routine care.

Strong Effect of Demographic Changes on Tuberculosis Susceptibility in South Africa

South Africa is among the world's top eight TB burden countries, and despite a focus on HIV-TB co-infection, most of the population living with TB are not HIV co-infected. The disease is endemic across the country with 80-90% exposure by adulthood. We investigated epidemiological risk factors for tuberculosis (TB) in the Northern Cape Province, South Africa: an understudied TB endemic region with extreme TB incidence (645/100,000) and the lowest provincial population density. We leveraged the population's high TB incidence and community transmission to design a case-control study with population-based controls, reflecting similar mechanisms of exposure between the groups. We recruited 1,126 participants with suspected TB from 12 community health clinics, and generated a cohort of 878 individuals (cases =374, controls =504) after implementing our enrollment criteria. All participants were GeneXpert Ultra tested for active TB by a local clinic. We assessed important risk factors for active TB using logistic regression and random forest modeling. Additionally, a subset of individuals were genotyped to determine genome-wide ancestry components. Male gender had the strongest effect on TB risk (OR: 2.87 [95% CI: 2.1-3.8]); smoking and alcohol consumption did not significantly increase TB risk. We identified two interactions: age by socioeconomic status (SES) and birthplace by residence locality on TB risk (OR = 3.05, p = 0.016) - where rural birthplace but town residence was the highest risk category. Finally, participants had a majority Khoe-San ancestry, typically greater than 50%. Epidemiological risk factors for this cohort differ from other global populations. The significant interaction effects reflect rapid changes in SES and mobility over recent generations and strongly impact TB risk in the Northern Cape of South Africa. Our models show that such risk factors combined explain 16% of the variance (r2) in case/control status.

Toward New Assessment of Knee Cartilage Degeneration

OBJECTIVE

Assessment of human joint cartilage is a crucial tool to detect and diagnose pathological conditions. This exploratory study developed a workflow for 3D modeling of cartilage and bone based on multimodal imaging. New evaluation metrics were created and, a unique set of data was gathered from healthy controls and patients with clinically evaluated degeneration or trauma.

DESIGN

We present a novel methodology to evaluate knee bone and cartilage based on features extracted from magnetic resonance imaging (MRI) and computed tomography (CT) data. We developed patient specific 3D models of the tibial, femoral, and patellar bones and cartilages. Forty-seven subjects with a history of degenerative disease, traumatic events, or no symptoms or trauma (control group) were recruited in this study. Ninety-six different measurements were extracted from each knee, 78 2D and 18 3D measurements. We compare the sensitivity of different metrics to classify the cartilage condition and evaluate degeneration.

RESULTS

Selected features extracted show significant difference between the 3 groups. We created a cumulative index of bone properties that demonstrated the importance of bone condition to assess cartilage quality, obtaining the greatest sensitivity on femur within medial and femoropatellar compartments. We were able to classify degeneration with a maximum recall value of 95.9 where feature importance analysis showed a significant contribution of the 3D parameters.

CONCLUSION

The present work demonstrates the potential for improving sensitivity in cartilage assessment. Indeed, current trends in cartilage research point toward improving treatments and therefore our contribution is a first step toward sensitive and personalized evaluation of cartilage condition.

The Comparative Effectiveness of Monotherapy and Combination Therapies: Impact of Angiotensin Receptor Blockers on the Onset of Alzheimer's Disease

Background

The criteria for use of Alzheimer's disease (AD) drug Leqembi recommended by the Department of Veterans Affairs (VA) include patients aged 65 years or older with mild cognitive impairment (MCI) or mild AD. Comorbidities that include hypertension, hyperlipidemia, and diabetes are common among these patients.

Objectives

Our objective is to investigate the comparative effectiveness of the administration of one, two, or three medications belonging to the categories of angiotensin receptor blockers (ARBs), angiotensin-converting enzyme inhibitors (ACEIs), Beta Blockers, Statins, and Metformin, for their potential to delay the clinical onset of AD and provide a window of opportunity for therapeutic intervention.

Design

Retrospective matched case-control study.

Setting

Data from the Department of Veterans Affairs national corporate data warehouse.

Participants

We conducted an analysis of 122,351 participants (13,611 with AD and 108,740 without AD), aged 65-89, who began at least one of the prescribed medication classes under investigation between October 1998 and April 2018.

Measurements

We utilized Cox proportional hazard regressions, both with and without propensity score weighting, to estimate hazard ratios (HR) associated with the use of different medication combinations for the pre-symptomatic survival time of AD onset. Additionally, we employed a supervised machine learning algorithm (random forest) to assess the relative importance of various therapies in predicting the occurrence of AD.

Result

Adding Metformin to the combination of ACEI+Beta Blocker (HR = 0.56, 95% CI (0.41, 0.77)) reduced the risk of AD onset compared to ACEI monotherapy alone (HR = 0.91, (0.85, 0.98)), Beta Blocker monotherapy (HR = 0.86, 95% CI (0.80, 0.92)), or combined ACEI+Beta Blocker (HR=0.85, 95%CI (0.77, 0.94)), when statin prescribers were used as a reference. Prescriptions of ARB alone or the combination of ARB with Beta Blocker showed an association with a lower risk of AD onset.

Conclusion

Selected medications for the treatment of multiple chronic conditions among elderly individuals with hypertension, hyperlipidemia, and diabetes as monotherapy or combination therapies lengthen the pre-symptomatic period before the onset of AD.

Predicting self-perceived general health status using machine learning: an external exposome study

BACKGROUND

Self-perceived general health (SPGH) is a general health indicator commonly used in epidemiological research and is associated with a wide range of exposures from different domains. However, most studies on SPGH only investigated a limited set of exposures and did not take the entire external exposome into account. We aimed to develop predictive models for SPGH based on exposome datasets using machine learning techniques and identify the most important predictors of poor SPGH status.

METHODS

Random forest (RF) was used on two datasets based on personal characteristics from the 2012 and 2016 editions of the Dutch national health survey, enriched with environmental and neighborhood characteristics. Model performance was determined using the area under the curve (AUC) score. The most important predictors were identified using a variable importance procedure and individual effects of exposures using partial dependence and accumulated local effect plots. The final 2012 dataset contained information on 199,840 individuals and 81 variables, whereas the final 2016 dataset had 244,557 individuals with 91 variables.

RESULTS

Our RF models had overall good predictive performance (2012: AUC = 0.864 (CI: 0.852-0.876); 2016: AUC = 0.890 (CI: 0.883-0.896)) and the most important predictors were "Control of own life", "Physical activity", "Loneliness" and "Making ends meet". Subjects who felt insufficiently in control of their own life, scored high on the De Jong-Gierveld loneliness scale or had difficulty in making ends meet were more likely to have poor SPGH status, whereas increased physical activity per week reduced the probability of poor SPGH. We observed associations between some neighborhood and environmental characteristics, but these variables did not contribute to the overall predictive strength of the models.

CONCLUSIONS

This study identified that within an external exposome dataset, the most important predictors for SPGH status are related to mental wellbeing, physical exercise, loneliness, and financial status.

Predictors of healthy physiological aging across generations in a 30-year population-based cohort study: the Doetinchem Cohort Study

BACKGROUND

Predicting healthy physiological aging is of major interest within public health research. However, longitudinal studies into predictors of healthy physiological aging that include numerous exposures from different domains (i.e. the exposome) are scarce. Our aim is to identify the most important exposome-related predictors of healthy physiological aging over the life course and across generations.

METHODS

Data were used from 2815 participants from four generations (generation 1960s/1950s/1940s/1930s aged respectively 20-29/30-39/40-49/50-59 years old at baseline, wave 1) of the Doetinchem Cohort Study who were measured every 5 years for 30 years. The Healthy Aging Index, a physiological aging index consisting of blood pressure, glucose, creatinine, lung function, and cognitive functioning, was measured at age 46-85 years (wave 6). The average exposure and trend of exposure over time of demographic, lifestyle, environmental, and biological exposures were included, resulting in 86 exposures. Random forest was used to identify important predictors.

RESULTS

The most important predictors of healthy physiological aging were overweight-related (BMI, waist circumference, waist/hip ratio) and cholesterol-related (using cholesterol lowering medication, HDL and total cholesterol) measures. Diet and educational level also ranked in the top of important exposures. No substantial differences were observed in the predictors of healthy physiological aging across generations. The final prediction model's performance was modest with an R² of 17%.

CONCLUSIONS

Taken together, our findings suggest that longitudinal cardiometabolic exposures (i.e. overweight- and cholesterol-related measures) are most important in predicting healthy physiological aging. This finding was similar across generations. More work is needed to confirm our findings in other study populations.

Cross-sectional analysis reveals autoantibody signatures associated with COVID-19 severity

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection is associated with increased levels of autoantibodies targeting immunological proteins such as cytokines and chemokines. Reports further indicate that COVID-19 patients may develop a broad spectrum of autoimmune diseases due to reasons not fully understood. Even so, the landscape of autoantibodies induced by SARS-CoV-2 infection remains uncharted territory. To gain more insight, we carried out a comprehensive assessment of autoantibodies known to be linked to diverse autoimmune diseases observed in COVID-19 patients in a cohort of 231 individuals, of which 161 were COVID-19 patients (72 with mild, 61 moderate, and 28 with severe disease) and 70 were healthy controls. Dysregulated IgG and IgA autoantibody signatures, characterized mainly by elevated concentrations, occurred predominantly in patients with moderate or severe COVID-19 infection. Autoantibody levels often accompanied anti-SARS-CoV-2 antibody concentrations while stratifying COVID-19 severity as indicated by random forest and principal component analyses. Furthermore, while young versus elderly COVID-19 patients showed only slight differences in autoantibody levels, elderly patients with severe disease presented higher IgG autoantibody concentrations than young individuals with severe COVID-19. This work maps the intersection of COVID-19 and autoimmunity by demonstrating the dysregulation of multiple autoantibodies triggered during SARS-CoV-2 infection. Thus, this cross-sectional study suggests that SARS-CoV-2 infection induces autoantibody signatures associated with COVID-19 severity and several autoantibodies that can be used as biomarkers of COVID-19 severity, indicating autoantibodies as potential therapeutical targets for these patients.