Downloads provided by UsageCounts
pmid: 35282654
pmc: PMC8904175
Antes de que las vacunas para la enfermedad por coronavirus 2019 (COVID-19) estuvieran disponibles, un conjunto de comportamientos de prevención de infecciones constituían el principal medio para mitigar la propagación del virus. Nuestro estudio tuvo como objetivo identificar predictores importantes de este conjunto de comportamientos. Mientras que las teorías psicológicas sociales y de salud sugieren un conjunto limitado de predictores, los análisis de aprendizaje automático pueden identificar correlatos de un grupo más grande de predictores candidatos. Utilizamos bosques aleatorios para clasificar 115 candidatos correlacionados de comportamiento de prevención de infecciones en 56.072 participantes en 28 países, administrados de marzo a mayo de 2020. El modelo de aprendizaje automático predijo el 52% de la varianza en el comportamiento de prevención de infecciones en una muestra de prueba separada, superando el rendimiento de los modelos psicológicos de comportamiento de salud. Los resultados indicaron los dos predictores más importantes relacionados con las normas cautelares a nivel individual. Para ilustrar cómo los métodos basados en datos pueden complementar la teoría, algunos de los predictores más importantes no se derivaron de las teorías del comportamiento de la salud, y algunos predictores derivados teóricamente eran relativamente poco importantes.
Avant que les vaccins contre la maladie à coronavirus 2019 (COVID-19) ne soient disponibles, un ensemble de comportements de prévention des infections constituait le principal moyen d'atténuer la propagation du virus. Notre étude visait à identifier les prédicteurs importants de cet ensemble de comportements. Alors que les théories psychologiques sociales et de santé suggèrent un ensemble limité de prédicteurs, les analyses d'apprentissage automatique peuvent identifier des corrélats à partir d'un plus grand nombre de prédicteurs candidats. Nous avons utilisé des forêts aléatoires pour classer 115 corrélats candidats du comportement de prévention des infections chez 56 072 participants dans 28 pays, administrés de mars à mai 2020. Le modèle d'apprentissage automatique a prédit 52 % de la variance du comportement de prévention des infections dans un échantillon de test distinct, dépassant la performance des modèles psychologiques de comportement de santé. Les résultats ont indiqué les deux prédicteurs les plus importants liés aux normes injonctives au niveau individuel. Illustrant comment les méthodes basées sur les données peuvent compléter la théorie, certains des prédicteurs les plus importants n'ont pas été dérivés des théories du comportement en matière de santé - et certains prédicteurs théoriquement dérivés étaient relativement peu importants.
Before vaccines for coronavirus disease 2019 (COVID-19) became available, a set of infection-prevention behaviors constituted the primary means to mitigate the virus spread. Our study aimed to identify important predictors of this set of behaviors. Whereas social and health psychological theories suggest a limited set of predictors, machine-learning analyses can identify correlates from a larger pool of candidate predictors. We used random forests to rank 115 candidate correlates of infection-prevention behavior in 56,072 participants across 28 countries, administered in March to May 2020. The machine-learning model predicted 52% of the variance in infection-prevention behavior in a separate test sample-exceeding the performance of psychological models of health behavior. Results indicated the two most important predictors related to individual-level injunctive norms. Illustrating how data-driven methods can complement theory, some of the most important predictors were not derived from theories of health behavior-and some theoretically derived predictors were relatively unimportant.
قبل أن تصبح لقاحات مرض فيروس كورونا 2019 (COVID -19) متاحة، شكلت مجموعة من سلوكيات الوقاية من العدوى الوسيلة الأساسية للتخفيف من انتشار الفيروس. هدفت دراستنا إلى تحديد المؤشرات المهمة لهذه المجموعة من السلوكيات. في حين أن النظريات النفسية الاجتماعية والصحية تشير إلى مجموعة محدودة من التنبؤات، يمكن لتحليلات التعلم الآلي تحديد الارتباطات من مجموعة أكبر من التنبؤات المرشحة. استخدمنا الغابات العشوائية لتصنيف 115 من السلوكيات المرشحة للوقاية من العدوى في 56,072 مشاركًا في 28 دولة، والتي تم إجراؤها في مارس إلى مايو 2020. توقع نموذج التعلم الآلي 52 ٪ من التباين في سلوك الوقاية من العدوى في عينة اختبار منفصلة - متجاوزًا أداء النماذج النفسية للسلوك الصحي. أشارت النتائج إلى أهم مؤشرين يتعلقان بالمعايير الزجرية على المستوى الفردي. لتوضيح كيف يمكن للطرق القائمة على البيانات أن تكمل النظرية، لم تكن بعض أهم التنبؤات مستمدة من نظريات السلوك الصحي - وكانت بعض التنبؤات المستمدة نظريًا غير مهمة نسبيًا.
Infection risk, /dk/atira/pure/subjectarea/asjc/1800; name=Decision Sciences(all), COVID-19, health behaviors, machine learning, public goods dilemma, random forest, social norms, Social Sciences, implemented, Economic burden, Infectious disease (medical specialty), 310, and tested for one domain/problem, Behavior Change Techniques, Machine learning ; COVID-19 ; Health Behaviors ; Social Norms ; Public Goods DilemmaJo, COVID-19; Health behaviors; Machine learning; Public goods dilemma; Random forest; Social norms, DSML2: Proof-of-concept: Data science output has been formulated, implemented, and tested for one domain/problem, Validation, Social Norms, Pathology, Psychology, Disease, Business, /dk/atira/pure/sustainabledevelopmentgoals/good_health_and_well_being; name=SDG 3 - Good Health and Well-being, Public goods dilemma, social norms, Applied Psychology, public goods dilemma, Q, Life Sciences, Public Goods Dilemma, COVID-19 (Enfermedad), Programming language, Social norms, health behaviors, FOS: Psychology, Clinical Psychology, machine learning, Environmental health, Health, Medicine, /dk/atira/pure/core/keywords/559092180; name=Health sciences, 330, Cognitive Neuroscience, Clinical psychology, 610, Set (abstract data type), Article, Validity, SDG 3 - Good Health and Well-being, Variance (accounting), Accounting, Machine learning, Collective action, Health behaviors, Health behavior, Theories of Behavior Change and Self-Regulation, Pandemic, COVID-19, Health Behaviors, Computer science, Rationale, Scale, Neuroscience of Moral Judgment and Disgust, Coronavirus disease 2019 (COVID-19), DSML2: Proof-of-concept: Data science output has been formulated, Impact of COVID-19 on Mental Health, machine learning; covid-19; health behaviors; social norms; public goods dilemma; random forest, random forest, Model, Random forest, Neuroscience
Infection risk, /dk/atira/pure/subjectarea/asjc/1800; name=Decision Sciences(all), COVID-19, health behaviors, machine learning, public goods dilemma, random forest, social norms, Social Sciences, implemented, Economic burden, Infectious disease (medical specialty), 310, and tested for one domain/problem, Behavior Change Techniques, Machine learning ; COVID-19 ; Health Behaviors ; Social Norms ; Public Goods DilemmaJo, COVID-19; Health behaviors; Machine learning; Public goods dilemma; Random forest; Social norms, DSML2: Proof-of-concept: Data science output has been formulated, implemented, and tested for one domain/problem, Validation, Social Norms, Pathology, Psychology, Disease, Business, /dk/atira/pure/sustainabledevelopmentgoals/good_health_and_well_being; name=SDG 3 - Good Health and Well-being, Public goods dilemma, social norms, Applied Psychology, public goods dilemma, Q, Life Sciences, Public Goods Dilemma, COVID-19 (Enfermedad), Programming language, Social norms, health behaviors, FOS: Psychology, Clinical Psychology, machine learning, Environmental health, Health, Medicine, /dk/atira/pure/core/keywords/559092180; name=Health sciences, 330, Cognitive Neuroscience, Clinical psychology, 610, Set (abstract data type), Article, Validity, SDG 3 - Good Health and Well-being, Variance (accounting), Accounting, Machine learning, Collective action, Health behaviors, Health behavior, Theories of Behavior Change and Self-Regulation, Pandemic, COVID-19, Health Behaviors, Computer science, Rationale, Scale, Neuroscience of Moral Judgment and Disgust, Coronavirus disease 2019 (COVID-19), DSML2: Proof-of-concept: Data science output has been formulated, Impact of COVID-19 on Mental Health, machine learning; covid-19; health behaviors; social norms; public goods dilemma; random forest, random forest, Model, Random forest, Neuroscience
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 19 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Top 10% | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Top 10% |
| views | 7 | |
| downloads | 14 |

Views provided by UsageCounts
Downloads provided by UsageCounts