MBMichael Pinzka Berry

Michael Pinzka Berry

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Michael Pinzka Berry has a total of 65 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Comparing Large Language Model AI and Human-Generated Coaching Messages for Behavioral Weight Loss

    by Zhuoran Huang, Michael P. Berry, Christina Chwyl, Gary Hsieh, Jing Wei, Evan M. Forman

    Automated coaching messages for weight control can save time and costs, but their repetitive, generic nature may limit their effectiveness compared to human coaching. Large language model (LLM) based artificial intelligence (AI) chatbots, like ChatGPT, could offer more personalized and novel messages to address repetition with their data-processing abilities. While LLM AI demonstrates promise to encourage healthier lifestyles, studies have yet to examine the feasibility and acceptability of LLM-based BWL coaching. Eighty-seven adults in a weight-loss trial (BMI ≥ 27 kg/m 2 ) rated ten coaching messages’ helpfulness (five human-written, five ChatGPT-generated) using a 5-point Likert scale, providing additional open-ended feedback to justify their ratings. Participants also identified which messages they believed were AI-generated. The evaluation occurred in two phases: messages in Phase 1 were perceived as impersonal and negative, prompting revisions for messages in Phase 2. In Phase 1, AI-generated messages were rated less helpful than human-written ones, with 66% receiving a helpfulness rating of 3 or higher. However, in Phase 2, the AI messages matched the human-written ones regarding helpfulness, with 82% scoring three or above. Additionally, 50% were misidentified as human-written, suggesting AI’s sophistication in mimicking human-generated content. A thematic analysis of open-ended feedback revealed that participants appreciated AI’s empathy and personalized suggestions but found them more formulaic, less authentic, and too data-focused. This study reveals the preliminary feasibility and perceived helpfulness of LLM AIs, like ChatGPT, in crafting potentially effective weight control coaching messages. Our findings also underscore areas for future enhancement.


  • Open Access

    Automated Messaging Delivered Alongside Behavioral Treatment for Weight Loss: Qualitative Study

    by Michael Berry, Lauren Taylor, Zhuoran Huang, Christina Chwyl, Stephanie Kerrigan, Evan Forman

    Background: Mobile health interventions for weight loss frequently use automated messaging. However, this intervention modality appears to have limited weight loss efficacy. Furthermore, data on users’ subjective experiences while receiving automated messaging–based interventions for weight loss are scarce, especially for more advanced messaging systems providing users with individually tailored, data-informed feedback. Objective: The purpose of this study was to characterize the experiences of individuals with overweight or obesity who received automated messages for 6-12 months as part of a behavioral weight loss trial. Methods: Participants (n=40) provided Likert-scale ratings of messaging acceptability and completed a structured qualitative interview (n=39) focused on their experiences with the messaging system and generating suggestions for improvement. Interview data were analyzed using thematic analysis. Results: Participants found the messages most useful for summarizing goal progress and least useful for suggesting new behavioral strategies. Overall message acceptability was moderate (2.67 out of 5). From the interviews, 2 meta-themes emerged. Participants indicated that although the messages provided useful reminders of intervention goals and skills, they did not adequately capture their lived experiences while losing weight. Conclusions: Many participants found the automated messages insufficiently tailored to their personal weight loss experiences. Future studies should explore alternative methods for message tailoring (eg, allowing for a higher degree of participant input and interactivity) that may boost treatment engagement and efficacy. Trial Registration: ClinicalTrials.gov NCT05231824; https://clinicaltrials.gov/study/NCT05231824


  • A randomized pilot trial of a tailored, reduced-frequency approach to dietary self-monitoring for weight loss

    by Michael Pinzka Berry, Evan M. Forman

    Most lifestyle modification programs for weight loss require comprehensive and precise dietary self-monitoring (DSM). However, the high level of burden associated with these requirements may compromise DSM compliance and limit its utility for some individuals. Recent studies have identified potentially promising alternative DSM methods that reduce burden by simplifying DSM (e.g., requiring tracking of food categories rather than specific foods). Still, such methods may cause individuals to overlook important dietary contributors to excess weight. Another potential, untested strategy for reducing burden is to lower the comprehensiveness of self-monitoring and require DSM only during daily eating occasions most associated with excess caloric intake. The purpose of the current pilot trial was to evaluate this novel approach within a sample of individuals with overweight or obesity (N = 46) who received a 12-week lifestyle modification intervention. Participants were randomized at baseline to adhere to either standard DSM or a reduced-frequency DSM prescription limited to two eating occasions daily. Contrary to hypotheses, intent-to-treat weight loss was significantly lower in the reduced-frequency condition compared to the standard condition (1.4% vs. 3.2%, p = .03), and rates of DSM compliance were not meaningfully different between conditions (d = 0.23). Additionally, the effect of intervention condition on weight change was mediated by mean DSM frequency, but not DSM compliance. Overall, findings suggest that the reduced-frequency DSM prescription had poor short-term efficacy for weight loss and for improving DSM compliance, and thus other options for reducing DSM burden should continue to be explored.


  • Behavioral weight loss outcomes in individuals with binge‐eating disorder: A meta‐analysis

    by Evan M. Forman, Brittney C. Evans, Michael P. Berry, Elizabeth W. Lampe, Christina Chwyl, Fengqing Zhang

    Objective: Binge‐eating disorder (BED) is highly comorbid with obesity. Weight loss may benefit individuals with BED; however, these individuals are often excluded from behavioral weight loss interventions (BWLIs), and findings from BWLIs including participants with and without BED are mixed. To the authors' knowledge, this study represents the first meta‐analysis of weight loss outcomes of individuals with and without BED in BWLIs, while adjusting for weight‐influencing variables. Treatment dropout rates were also examined.Methods: Electronic search engines and grey literature search methods were used to identify manuscripts published through December 2022 related to BWLIs and BED. Thirty manuscripts (BED n = 1519; 25 non‐BED n = 6345) were included.Results: A meta‐regression found that individuals with BED lost less weight compared with individuals without BED (~1.4 kg; ~2.9 kg among studies without meal replacements), but they still lost ~8.1 kg at post‐treatment. A random‐effects model showed that BED diagnosis increased odds of treatment dropout by 50%.Conclusions: BWLIs produced robust weight loss in those with BED, but those with BED lost less weight and had higher risk of dropout compared with those without. Future research should aim to close the gap in weight loss outcomes and retention between those with and without BED.


  • Open Access

    Automated Messaging Delivered Alongside Behavioral Treatment for Weight Loss: Qualitative Study (Preprint)

    by Michael Berry, Lauren Taylor, Zhuoran Huang, Christina Chwyl, Stephanie Kerrigan, Evan Forman

    BACKGROUND Mobile health interventions for weight loss frequently use automated messaging. However, this intervention modality appears to have limited weight loss efficacy. Furthermore, data on users’ subjective experiences while receiving automated messaging–based interventions for weight loss are scarce, especially for more advanced messaging systems providing users with individually tailored, data-informed feedback. OBJECTIVE The purpose of this study was to characterize the experiences of individuals with overweight or obesity who received automated messages for 6-12 months as part of a behavioral weight loss trial. METHODS Participants (n=40) provided Likert-scale ratings of messaging acceptability and completed a structured qualitative interview (n=39) focused on their experiences with the messaging system and generating suggestions for improvement. Interview data were analyzed using thematic analysis. RESULTS Participants found the messages most useful for summarizing goal progress and least useful for suggesting new behavioral strategies. Overall message acceptability was moderate (2.67 out of 5). From the interviews, 2 meta-themes emerged. Participants indicated that although the messages provided useful reminders of intervention goals and skills, they did not adequately capture their lived experiences while losing weight. CONCLUSIONS Many participants found the automated messages insufficiently tailored to their personal weight loss experiences. Future studies should explore alternative methods for message tailoring (eg, allowing for a higher degree of participant input and interactivity) that may boost treatment engagement and efficacy. CLINICALTRIAL ClinicalTrials.gov NCT05231824; https://clinicaltrials.gov/study/NCT05231824

  • Using artificial intelligence to optimize delivery of weight loss treatment: Protocol for an efficacy and cost-effectiveness trial

    by Evan M. Forman, Michael P. Berry, Meghan L. Butryn, Charlotte J. Hagerman, Zhuoran Huang, Adrienne S. Juarascio, Erica M. LaFata, Santiago Ontañón, J. Mick Tilford, Fengqing Zhang


  • Associations between behaviour change technique clusters and weight loss outcomes of automated digital interventions: a systematic review and meta-regression

    by Michael P. Berry, Christina Chwyl, Abigail L. Metzler, Jasmine H. Sun, Hannah Dart, Evan M. Forman

    Automated digital interventions for weight loss represent a highly scalable and potentially cost-effective approach to treat obesity. However, current understanding of the active components of automated digital interventions is limited, hindering efforts to improve efficacy. Thus, the current systematic review and meta-analysis (preregistration: PROSPERO 2021-CRD42021238878) examined relationships between utilization of behavior change techniques (BCTs) and the efficacy of automated digital interventions for producing weight loss. Electronic database searches (December 2020 to March 2021) were used to identify trials of automated digital interventions reporting weight loss as an outcome. BCT clusters were coded using Michie’s 93-item BCT taxonomy. Mixed-effects meta-regression was used to examine moderating effects of BCT clusters and techniques on both within-group and between-group measures of weight change. One hundred and eight conditions across sixty-six trials met inclusion criteria (13,672 participants). Random-effects meta-analysis revealed a small mean post-intervention weight loss of -1.37 kg (95% CI, -1.75 to -1.00) relative to control groups. Interventions utilized a median of five BCT clusters, with goal-setting, feedback and providing instruction on behavior being most common. Use of Reward and Threat techniques, and specifically social incentive/reward BCTs, was associated with a higher between-group difference in efficacy, although results were not robust to sensitivity analyses.


  • Efficacy and mechanisms of a brief adaptive goal-setting intervention for physical activity: A randomised pilot trial

    by Michael P. Berry, Marc A. Adams, Meghan L. Butryn, Stephanie Kerrigan, Evan M. Forman

    Adaptive goal-setting (AGS) interventions, which tailor physical activity (PA) goals to changing individual capability over time, have previously shown efficacy for improving physical activity compared with more standard, static goal-setting (SGS). However, trials to date have been fully automated, which negatively impacts generalisability to more traditional coaching interventions providing human coach support. Furthermore, data on underlying mechanisms of action of AGS are lacking. The purpose of the current pilot trial was to address these two research gaps by preliminarily evaluating both efficacy and change in putative underlying mechanisms of AGS during a 6-week, coach-supplemented PA intervention. 38 sedentary adults (89.5% female) engaging in d = 0.14). However, the AGS group also showed a small (d = 0.01), unexpected, subsequent decrease in PA that was greater than under SGS. A non-significant trend towards greater improvement in implicit attitudes towards PA following AGS was also observed (d = 0.62) but change in implicit attitudes did not mediate intervention effects on PA. Findings suggest that a brief, coach-supplemented AGS intervention was not superior to SGS for increasing PA, but also highlight that implicit attitude variables may warrant further study as potential mechanisms of AGS. Trial registration: ClinicalTrials.gov identifier: NCT04505241.


  • Rethinking emotional eating: Retrospective and momentary indices of emotional eating represent distinct constructs

    by Christina Chwyl, Michael P. Berry, Stephanie M. Manasse, Evan M. Forman