Recall bias does impact on retrospective reports of quit attempts: response to Messer and Pierce

Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors

Major Depressive Disorder (MDD) and Generalized Anxiety Disorder (GAD) pose significant burdens on individuals and society, necessitating accurate prediction methods. Machine learning (ML) algorithms utilizing electronic health records and survey data offer promising tools for forecasting these conditions. However, potential bias and inaccuracies inherent in subjective survey responses can undermine the precision of such predictions. This research investigates the reliability of five prominent ML algorithms-a Convolutional Neural Network (CNN), Random Forest, XGBoost, Logistic Regression, and Naive Bayes-in predicting MDD and GAD. A dataset rich in biomedical, demographic, and self-reported survey information is used to assess the algorithms' performance under different levels of subjective response inaccuracies. These inaccuracies simulate scenarios with potential memory recall bias and subjective interpretations. While all algorithms demonstrate commendable accuracy with high-quality survey data, their performance diverges significantly when encountering erroneous or biased responses. Notably, the CNN exhibits superior resilience in this context, maintaining performance and even achieving enhanced accuracy, Cohen's kappa score, and positive precision for both MDD and GAD. This highlights the CNN's superior ability to handle data unreliability, making it a potentially advantageous choice for predicting mental health conditions based on self-reported data. These findings underscore the critical importance of algorithmic resilience in mental health prediction, particularly when relying on subjective data. They emphasize the need for careful algorithm selection in such contexts, with the CNN emerging as a promising candidate due to its robustness and improved performance under data uncertainties.

Being serious about quitting: a qualitative analysis of Australian ex-smokers' explanations of their quitting success

BACKGROUND

The process of successful quitting, and the personal and social conditions required to support it, remain poorly understood.

METHODS

This qualitative grounded theory study used in-depth interviews with 37 Australian adult ex-smokers (24-68 years; 15 men and 22 women) who quit in the past 6-24 months to explore how ex-smokers explain their quitting success.

FINDINGS

This analysis provides a framework for understanding the personal, social and structural factors critical to successful quitting. The key analytic finding was the core concept 'being serious'. Three factors contributed to 'being serious': (1) prior experiences of quitting; (2) an identity (or existential) threat; and (3) timing and circumstances. The analysis indicated that the concept 'being serious' rather than the oft-cited psychological constructs motivation and willpower more accurately captures how participants talked about and explained their quitting success, how they accounted for their success when previous apparently similar attempts had failed, and the advice they would offer would-be quitters about achieving quitting success. An explanation is provided for why some participants battled with quitting for years, while others quit unexpectedly, even effortlessly. The social and structural factors that made the state of 'being serious' easier or harder for the participant to attain are also discussed.

CONCLUSION

'Being serious' was a term that resonated with participants. Participants' accounts of quitting indicate that quitting is a complex and gradual process and that social and structural influences have a key role in determining how easy or difficult it was to become serious about quitting.

Nicotine Metabolite Ratio (NMR) Prospectively Predicts Smoking Relapse: Longitudinal Findings From ITC Surveys in Five Countries

INTRODUCTION

The ratio of trans 3'-hydroxycotinine (3HC) to cotinine (nicotine metabolite ratio [NMR]) is a biomarker of the rate of nicotine metabolism, with higher NMR indicating faster metabolism. Higher NMR has been found to be associated with higher daily cigarette consumption and less success stopping smoking in cessation trials. This study examines differences in NMR among population-based samples of smokers in the five countries and explores the relationship between NMR and smoking abstinence.

METHODS

Participants (N = 874) provided saliva samples during International Tobacco Control (ITC) surveys in the United States, United Kingdom, Mauritius, Mexico, and Thailand conducted in 2010/2011 with follow-up surveys in 2012/2013. When all samples were received, they were sent to a common laboratory for analysis using liquid chromatography and tandem mass spectroscopy.

RESULTS

There was significant variation in NMR across countries (F = 15.49, p < .001). Those who reported smoking at follow-up had a mean NMR of 0.32, compared to a mean NMR of 0.42 in participants who reported that they had stopped (F = 8.93; p = .003). Higher mean NMR values were also associated with longer quit duration (p = .007). There was no substantial difference in NMR between current smokers who made a failed quit attempt and those who made no attempt-both had significantly lower NMR compared to those who quit and remained abstinent. Smokers with a higher NMR were more likely to report that they stopped smoking compared to those with a lower NMR (odds ratio = 2.67; 95% confidence interval: 1.25 to 5.68).

CONCLUSIONS

These results suggest faster nicotine metabolizers may be less likely to relapse following a quit attempt. This finding differs from results of clinical trials testing stop smoking medications, where slower metabolizers have been found to be more likely to maintain abstinence from smoking.

IMPLICATIONS

Results of this study suggest faster nicotine metabolizers may be less likely to relapse following a quit attempt. This finding differs from results of clinical trials testing stop smoking medications, where slower metabolizers have been found to be more likely to maintain abstinence from smoking.