RESUMEN
BACKGROUND: Postacute sequelae of COVID-19 (PASC), also known as long COVID, is a broad grouping of a range of long-term symptoms following acute COVID-19. These symptoms can occur across a range of biological systems, leading to challenges in determining risk factors for PASC and the causal etiology of this disorder. An understanding of characteristics that are predictive of future PASC is valuable, as this can inform the identification of high-risk individuals and future preventative efforts. However, current knowledge regarding PASC risk factors is limited. OBJECTIVE: Using a sample of 55,257 patients (at a ratio of 1 patient with PASC to 4 matched controls) from the National COVID Cohort Collaborative, as part of the National Institutes of Health Long COVID Computational Challenge, we sought to predict individual risk of PASC diagnosis from a curated set of clinically informed covariates. The National COVID Cohort Collaborative includes electronic health records for more than 22 million patients from 84 sites across the United States. METHODS: We predicted individual PASC status, given covariate information, using Super Learner (an ensemble machine learning algorithm also known as stacking) to learn the optimal combination of gradient boosting and random forest algorithms to maximize the area under the receiver operator curve. We evaluated variable importance (Shapley values) based on 3 levels: individual features, temporal windows, and clinical domains. We externally validated these findings using a holdout set of randomly selected study sites. RESULTS: We were able to predict individual PASC diagnoses accurately (area under the curve 0.874). The individual features of the length of observation period, number of health care interactions during acute COVID-19, and viral lower respiratory infection were the most predictive of subsequent PASC diagnosis. Temporally, we found that baseline characteristics were the most predictive of future PASC diagnosis, compared with characteristics immediately before, during, or after acute COVID-19. We found that the clinical domains of health care use, demographics or anthropometry, and respiratory factors were the most predictive of PASC diagnosis. CONCLUSIONS: The methods outlined here provide an open-source, applied example of using Super Learner to predict PASC status using electronic health record data, which can be replicated across a variety of settings. Across individual predictors and clinical domains, we consistently found that factors related to health care use were the strongest predictors of PASC diagnosis. This indicates that any observational studies using PASC diagnosis as a primary outcome must rigorously account for heterogeneous health care use. Our temporal findings support the hypothesis that clinicians may be able to accurately assess the risk of PASC in patients before acute COVID-19 diagnosis, which could improve early interventions and preventive care. Our findings also highlight the importance of respiratory characteristics in PASC risk assessment. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1101/2023.07.27.23293272.
Asunto(s)
COVID-19 , Síndrome Post Agudo de COVID-19 , Humanos , COVID-19/epidemiología , Estudios de Cohortes , Femenino , Masculino , Estados Unidos/epidemiología , Persona de Mediana Edad , Anciano , Adulto , Factores de Riesgo , Aprendizaje AutomáticoRESUMEN
BACKGROUND: Postpartum depression (PPD) poses a significant maternal health challenge. The current approach to detecting PPD relies on in-person postpartum visits, which contributes to underdiagnosis. Furthermore, recognizing PPD symptoms can be challenging. Therefore, we explored the potential of using digital biomarkers from consumer wearables for PPD recognition. OBJECTIVE: The main goal of this study was to showcase the viability of using machine learning (ML) and digital biomarkers related to heart rate, physical activity, and energy expenditure derived from consumer-grade wearables for the recognition of PPD. METHODS: Using the All of Us Research Program Registered Tier v6 data set, we performed computational phenotyping of women with and without PPD following childbirth. Intraindividual ML models were developed using digital biomarkers from Fitbit to discern between prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods. Models were built using generalized linear models, random forest, support vector machine, and k-nearest neighbor algorithms and evaluated using the κ statistic and multiclass area under the receiver operating characteristic curve (mAUC) to determine the algorithm with the best performance. The specificity of our individualized ML approach was confirmed in a cohort of women who gave birth and did not experience PPD. Moreover, we assessed the impact of a previous history of depression on model performance. We determined the variable importance for predicting the PPD period using Shapley additive explanations and confirmed the results using a permutation approach. Finally, we compared our individualized ML methodology against a traditional cohort-based ML model for PPD recognition and compared model performance using sensitivity, specificity, precision, recall, and F1-score. RESULTS: Patient cohorts of women with valid Fitbit data who gave birth included <20 with PPD and 39 without PPD. Our results demonstrated that intraindividual models using digital biomarkers discerned among prepregnancy, pregnancy, postpartum without depression, and postpartum with depression (ie, PPD diagnosis) periods, with random forest (mAUC=0.85; κ=0.80) models outperforming generalized linear models (mAUC=0.82; κ=0.74), support vector machine (mAUC=0.75; κ=0.72), and k-nearest neighbor (mAUC=0.74; κ=0.62). Model performance decreased in women without PPD, illustrating the method's specificity. Previous depression history did not impact the efficacy of the model for PPD recognition. Moreover, we found that the most predictive biomarker of PPD was calories burned during the basal metabolic rate. Finally, individualized models surpassed the performance of a conventional cohort-based model for PPD detection. CONCLUSIONS: This research establishes consumer wearables as a promising tool for PPD identification and highlights personalized ML approaches, which could transform early disease detection strategies.
Asunto(s)
Biomarcadores , Depresión Posparto , Dispositivos Electrónicos Vestibles , Humanos , Depresión Posparto/diagnóstico , Depresión Posparto/psicología , Femenino , Adulto , Biomarcadores/análisis , Estudios Transversales , Dispositivos Electrónicos Vestibles/estadística & datos numéricos , Dispositivos Electrónicos Vestibles/normas , Aprendizaje Automático/normas , Embarazo , Estados Unidos , Conjuntos de Datos como Asunto , Curva ROCRESUMEN
Background: Water, sanitation, hygiene (WSH), nutrition (N), and combined (N+WSH) interventions are often implemented by global health organizations, but WSH interventions may insufficiently reduce pathogen exposure, and nutrition interventions may be modified by environmental enteric dysfunction (EED), a condition of increased intestinal permeability and inflammation. This study investigated the heterogeneity of these treatments' effects based on individual pathogen and EED biomarker status with respect to child linear growth. Methods: We applied cross-validated targeted maximum likelihood estimation and super learner ensemble machine learning to assess the conditional treatment effects in subgroups defined by biomarker and pathogen status. We analyzed treatment (N+WSH, WSH, N, or control) randomly assigned in-utero, child pathogen and EED data at 14 months of age, and child LAZ at 28 months of age. We estimated the difference in mean child length for age Z-score (LAZ) under the treatment rule and the difference in stratified treatment effect (treatment effect difference) comparing children with high versus low pathogen/biomarker status while controlling for baseline covariates. Results: We analyzed data from 1,522 children, who had median LAZ of -1.56. We found that myeloperoxidase (N+WSH treatment effect difference 0.0007 LAZ, WSH treatment effect difference 0.1032 LAZ, N treatment effect difference 0.0037 LAZ) and Campylobacter infection (N+WSH treatment effect difference 0.0011 LAZ, WSH difference 0.0119 LAZ, N difference 0.0255 LAZ) were associated with greater effect of all interventions on growth. In other words, children with high myeloperoxidase or Campylobacter infection experienced a greater impact of the interventions on growth. We found that a treatment rule that assigned the N+WSH (LAZ difference 0.23, 95% CI (0.05, 0.41)) and WSH (LAZ difference 0.17, 95% CI (0.04, 0.30)) interventions based on EED biomarkers and pathogens increased predicted child growth compared to the randomly allocated intervention. Conclusions: These findings indicate that EED biomarker and pathogen status, particularly Campylobacter and myeloperoxidase (a measure of gut inflammation), may be related to impact of N+WSH, WSH, and N interventions on child linear growth.
RESUMEN
BACKGROUND: Hundreds of millions of children in low- and middle-income countries are exposed to chronic stressors, such as poverty, poor sanitation and hygiene, and sub-optimal nutrition. These stressors can have physiological consequences for children and may ultimately have detrimental effects on child development. This study explores associations between biological measures of chronic stress in early life and developmental outcomes in a large cohort of young children living in rural Bangladesh. METHODS: We assessed physiologic measures of stress in the first two years of life using measures of the hypothalamic-pituitary-adrenal (HPA) axis (salivary cortisol and glucocorticoid receptor gene methylation), the sympathetic-adrenal-medullary (SAM) system (salivary alpha-amylase, heart rate, and blood pressure), and oxidative status (F2-isoprostanes). We assessed child development in the first two years of life with the MacArthur-Bates Communicative Development Inventories (CDI), the WHO gross motor milestones, and the Extended Ages and Stages Questionnaire (EASQ). We compared development outcomes of children at the 75th and 25th percentiles of stress biomarker distributions while adjusting for potential confounders using generalized additive models, which are statistical models where the outcome is predicted by a potentially non-linear function of predictor variables. RESULTS: We analyzed data from 684 children (49% female) at both 14 and 28 months of age; we included an additional 765 children at 28 months of age. We detected a significant relationship between HPA axis activity and child development, where increased HPA axis activity was associated with poor development outcomes. Specifically, we found that cortisol reactivity (coefficient -0.15, 95% CI (-0.29, -0.01)) and post-stressor levels (coefficient -0.12, 95% CI (-0.24, -0.01)) were associated with CDI comprehension score, post-stressor cortisol was associated with combined EASQ score (coefficient -0.22, 95% CI (-0.41, -0.04), and overall glucocorticoid receptor methylation was associated with CDI expression score (coefficient -0.09, 95% CI (-0.17, -0.01)). We did not detect a significant relationship between SAM activity or oxidative status and child development. CONCLUSIONS: Our observations reveal associations between the physiological evidence of stress in the HPA axis with developmental status in early childhood. These findings add to the existing evidence exploring the developmental consequences of early life stress.
Asunto(s)
Desarrollo Infantil , Hidrocortisona , Niño , Humanos , Preescolar , Femenino , Masculino , Hidrocortisona/metabolismo , Sistema Hipotálamo-Hipofisario/metabolismo , Receptores de Glucocorticoides/metabolismo , Bangladesh , Sistema Hipófiso-Suprarrenal/metabolismo , Biomarcadores/metabolismo , Saliva/metabolismo , Estrés Psicológico/metabolismoRESUMEN
Postpartum depression (PPD), afflicting one in seven women, poses a major challenge in maternal health. Existing approaches to detect PPD heavily depend on in-person postpartum visits, leading to cases of the condition being overlooked and untreated. We explored the potential of consumer wearable-derived digital biomarkers for PPD recognition to address this gap. Our study demonstrated that intra-individual machine learning (ML) models developed using these digital biomarkers can discern between pre-pregnancy, pregnancy, postpartum without depression, and postpartum with depression time periods (i.e., PPD diagnosis). When evaluating variable importance, calories burned from the basal metabolic rate (calories BMR) emerged as the digital biomarker most predictive of PPD. To confirm the specificity of our method, we demonstrated that models developed in women without PPD could not accurately classify the PPD-equivalent phase. Prior depression history did not alter model efficacy for PPD recognition. Furthermore, the individualized models demonstrated superior performance compared to a conventional cohort-based model for the detection of PPD, underscoring the effectiveness of our individualized ML approach. This work establishes consumer wearables as a promising avenue for PPD identification. More importantly, it also emphasizes the utility of individualized ML model methodology, potentially transforming early disease detection strategies.
RESUMEN
Background: Hundreds of millions of children in low- and middle-income countries are exposed to chronic stressors, such as poverty, poor sanitation and hygiene, and sub-optimal nutrition. These stressors can have physiological consequences for children and may ultimately have detrimental effects on child development. This study explores associations between biological measures of chronic stress in early life and developmental outcomes in a large cohort of young children living in rural Bangladesh. Methods: We assessed physiologic measures of stress in the first two years of life using measures of the hypothalamic-pituitary-adrenal (HPA) axis (salivary cortisol and glucocorticoid receptor gene methylation), the sympathetic-adrenal-medullary (SAM) system (salivary alpha-amylase, heart rate, and blood pressure), and oxidative status (F2-isoprostanes). We assessed child development in the first two years of life with the MacArthur-Bates Communicative Development Inventories (CDI), the WHO gross motor milestones, and the Extended Ages and Stages Questionnaire (EASQ). We compared development outcomes of children at the 75th and 25th percentiles of stress biomarker distributions while adjusting for potential confounders (hereafter referred to as contrasts) using generalized additive models, which are statistical models where the outcome is predicted by a potentially non-linear function of predictor variables. Results: We analyzed data from 684 children (49% female) at both 14 and 28 months of age; we included an additional 765 children at 28 months of age. We observed 135 primary contrasts of the differences in child development outcomes at the 75th and 25th percentiles of stress biomarkers, where we detected significant relationships in 5 out of 30 contrasts (17%) of HPA axis activity, 1 out of 30 contrasts (3%) of SAM activity, and 3 out of 75 contrasts (4%) of oxidative status. These findings revealed that measures of HPA axis activity were associated with poor development outcomes. We did not find consistent evidence that markers of SAM system activity or oxidative status were associated with developmental status. Conclusions: Our observations reveal associations between the physiological evidence of stress in the HPA axis with developmental status in early childhood. These findings add to the existing evidence exploring the developmental consequences of early life stress.
RESUMEN
In trials of infectious disease interventions, rare outcomes and unpredictable spatiotemporal variation can introduce bias, reduce statistical power, and prevent conclusive inferences. Spillover effects can complicate inference if individual randomization is used to gain efficiency. Ring trials are a type of cluster-randomized trial that may increase efficiency and minimize bias, particularly in emergency and elimination settings with strong clustering of infection. They can be used to evaluate ring interventions, which are delivered to individuals in proximity to or contact with index cases. We conducted a systematic review of ring trials, compare them with other trial designs for evaluating ring interventions, and describe strengths and weaknesses of each design. Of 849 articles and 322 protocols screened, we identified 26 ring trials, 15 cluster-randomized trials, 5 trials that randomized households or individuals within rings, and 1 individually randomized trial. The most common interventions were postexposure prophylaxis (n = 23) and focal mass drug administration and screening and treatment (n = 7). Ring trials require robust surveillance systems and contact tracing for directly transmitted diseases. For rare diseases with strong spatiotemporal clustering, they may have higher efficiency and internal validity than cluster-randomized designs, in part because they ensure that no clusters are excluded from analysis due to zero cluster incidence. Though more research is needed to compare them with other types of trials, ring trials hold promise as a design that can increase trial speed and efficiency while reducing bias.
Asunto(s)
Enfermedades Transmisibles , Humanos , Enfermedades Transmisibles/terapiaRESUMEN
BACKGROUND: Antibiotics are increasingly used throughout the world in food animal production for controlling and preventing disease and for promoting growth. But this trend also has the potential for promoting antibiotic resistance, which represents a threat to human, animal, and environmental health. The use of antibiotics and the potential effects of antibiotic dependence has often been associated with large-scale food animal production. But rural households also engage in small-scale production, often operating literally in backyards. While some small-scale producers use veterinary antibiotics, many do not. This paper examines knowledge, attitudes, beliefs, and agricultural practices (KAP) that represent an alternative to dependence on antibiotics. METHODS: Qualitative field research was based on four focus group discussions (FGDs) with non-indigenous backyard food animal producers in four communities near Quito, Ecuador and two FGDs with veterinarians. FGDs were supplemented by structured observations and key informant interviews. They were recorded with digital audio devices and transcriptions were analyzed independently by two researchers using a three-stage coding procedure. Open coding identifies underlying concepts, while axial coding develops categories and properties, and selective coding integrates the information in order to identify the key dimensions of the collective qualitative data. RESULTS: Backyard food animal producers in the Ecuadorian highlands generally do not use antibiotics while rearing small batches of animals and poultry for predominantly non-commercial household consumption. Instead, they rely on low cost traditional veterinary remedies. These practices are informed by their Andean history of agriculture and a belief system whereby physical activity is a holistic lifestyle through which people maintain their health by participating in the physical and spiritual environment. CONCLUSIONS: Backyard food animal producers in the Ecuadorian highlands implement complex strategies based on both economic calculations and sociocultural underpinnings that shape perceptions, attitudes, and practices. They use traditional veterinary remedies in lieu of antibiotics in most cases because limited production of food animals in small spaces contributes to a predictable household food supply, while at the same time conforming to traditional concepts of human and environmental health.
Asunto(s)
Antibacterianos , Abastecimiento de Alimentos , Crianza de Animales Domésticos/métodos , Animales , Antibacterianos/uso terapéutico , Ecuador , Conocimientos, Actitudes y Práctica en Salud , Humanos , Investigación Cualitativa , Población RuralRESUMEN
Small-scale food animal production has been celebrated as a means of economic mobility and improved food security but the use of veterinary antibiotics among these producers may be contributing to the spread of antibiotic resistance in animals and humans. In order to improve antibiotic stewardship in this sector, it is critical to identify the drivers of producers' antibiotic use. This study assessed the determinants of antibiotic use in small-scale food animal production through simulated client visits to veterinary supply stores and surveys with households that owned food animals (n = 117) in Ecuador. Eighty percent of households with food animals owned chickens and 78% of those with chickens owned fewer than 10 birds. Among the households with small-scale food animals, 21% reported giving antibiotics to their food animals within the last six months. Simulated client visits indicated that veterinary sales agents frequently recommended inappropriate antibiotic use, as 66% of sales agents recommended growth promoting antibiotics, and 48% of sales agents recommended an antibiotic that was an inappropriate class for disease treatment. In contrast, few sales agents (3%) were willing to sell colistin, an antibiotic banned for veterinary use in Ecuador as of January 2020, which supports the effectiveness of government regulation in antibiotic stewardship. The cumulative evidence provided by this study indicates that veterinary sales agents play an active role in promoting indiscriminate and inappropriate use of antibiotics in small-scale food animal production.
RESUMEN
OBJECTIVE: To examine differences in waking to bedtime cortisol production between children who remained with birth parents vs children placed in foster care following involvement of Child Protective Services (CPS). DESIGN: Between-subject comparison of cortisol patterns among 2 groups of children. SETTING: Children referred from the child welfare system. PARTICIPANTS: Three hundred thirty-nine children aged 2.9 to 31.4 months who were living with birth parents (n = 155) or placed in foster care (n = 184) following CPS involvement as well as 96 unmatched children from low-risk environments. Main Exposures Involvement by CPS and foster care. Main Outcome Measure Salivary cortisol samples obtained at waking and bedtime for children on 2 days. RESULTS: Child Protective Services-involved children who continued to live with birth parents and CPS-involved children placed in foster care differed in cortisol production, with children living with their birth parents showing flatter slopes in waking to bedtime values. CONCLUSIONS: Continuing to live with birth parents following involvement of CPS is associated with greater perturbation to the diurnal pattern of cortisol production than living with foster parents. Foster care may have a regulating influence on children's cortisol among children who have experienced maltreatment.