Objective: Amidst restrictions to reduce the spread of COVID-19, jokes have surfaced regarding weight gain during the pandemic. The current study documents perceived changes since COVID-19 and compares these to observed longitudinal changes in reported weight, BMI, and how college students described their weight from January to April 2020. Method: Undergraduates (N = 90; 88% female) completed on-line assessments before and after students were required to leave campus due to COVID-19. Time 1 and Time 2 surveys collected demographic information, height, weight, and a Likert-scale rating to describe perceived weight, ranging from 1 = very underweight to 5 = very overweight (weight description). Time 2 surveys added questions for perceived changes since COVID-19 in body weight, eating, physical activity, various forms of screen time, and concerns about weight, shape, and eating. Results: Time 2 surveys indicated perceived increases in body weight, eating, and screen time, and decreases in physical activity along with increased concerns about weight, shape and eating since COVID-19. Longitudinal data indicated no significant change in weight, body mass index (BMI), or BMI category, but how participants described their weight changed significantly from January to April 2020. Compared to longitudinal changes in BMI category, students' weight description was significantly more likely to fall into a higher category from Time 1 to Time 2. Discussion: Shifts in how body weight is experienced in the wake of COVID-19 that do not align with observed changes in reported weight may reflect cognitive distortions that could increase risk for disordered eating in some individuals. K E Y W O R D S body mass index, COVID-19, eating concerns, weight concerns, weight gain 1 | INTRODUCTION COVID-19 has severely disrupted daily life around the globe. In the United States, many universities abruptly shifted to on-line instruction during March 2020 and required students to leave campus to reduce the risk of infection. For many students, this meant returning home to live with families and adapting to various stages of community restrictions to "flatten the curve." A return to home, adhering to calls for social distancing, and the closing of bars, restaurants, retail stores, movie theaters, gyms, and more, dramatically altered college students' home, school, work, and social lives. Because grocery shopping was deemed "essential" in almost all communities, food and eating remained one of the few pleasurable activities that most people could pursue along with watching television,

Results support that even a 5% weight loss, combined with cognitive concerns, may produce a group with a clinically significant eating disorder. AAN was observed in both healthy weight and overweight/obese adults, highlighting the importance of screening for restrictive eating disorders at all weights.

Our findings suggest that, despite greater degree of weight loss and no difference in duration of illness, participants with a history of overweight/obesity are less likely to receive inpatient medical care.

Theoretically-driven models of suicide have long guided suicidology; however, an approach employing machine learning models has recently emerged in the field. Some have suggested that machine learning models yield improved prediction as compared to theoretical approaches, but to date, this has not been investigated in a systematic manner. The present work directly compares widely researched theories of suicide (i.e., BioSocial, Biological, Ideation-to-Action, and Hopelessness Theories) to machine learning models, comparing the accuracy between the two differing approaches. We conducted literature searches using PubMed, PsycINFO, and Google Scholar, gathering effect sizes from theoretically-relevant constructs and machine learning models. Eligible studies were longitudinal research articles that predicted suicide ideation, attempts, or death published prior to May 1, 2020. 124 studies met inclusion criteria, corresponding to 330 effect sizes. Theoretically-driven models demonstrated suboptimal prediction of ideation (wOR = 2.87; 95% CI, 2.65–3.09; k = 87), attempts (wOR = 1.43; 95% CI, 1.34–1.51; k = 98), and death (wOR = 1.08; 95% CI, 1.01–1.15; k = 78). Generally, Ideation-to-Action (wOR = 2.41, 95% CI = 2.21–2.64, k = 60) outperformed Hopelessness (wOR = 1.83, 95% CI 1.71–1.96, k = 98), Biological (wOR = 1.04; 95% CI .97–1.11, k = 100), and BioSocial (wOR = 1.32, 95% CI 1.11–1.58, k = 6) theories. Machine learning provided superior prediction of ideation (wOR = 13.84; 95% CI, 11.95–16.03; k = 33), attempts (wOR = 99.01; 95% CI, 68.10–142.54; k = 27), and death (wOR = 17.29; 95% CI, 12.85–23.27; k = 7). Findings from our study indicated that across all theoretically-driven models, prediction of suicide-related outcomes was suboptimal. Notably, among theories of suicide, theories within the Ideation-to-Action framework provided the most accurate prediction of suicide-related outcomes. When compared to theoretically-driven models, machine learning models provided superior prediction of suicide ideation, attempts, and death.