Association of COVID-19 and the prevalence of in-person vs telehealth primary care visits and subsequent impacts on tobacco use assessment and referral for cessation assistance.

INTRODUCTION: The COVID-19 pandemic dramatically altered patterns of health care delivery. Smoking remains an important risk factor for multiple chronic conditions and may exacerbate more severe symptoms of COVID-19. Thus, it is important to understand how pandemic-induced changes in primary care practice patterns affected smoking assessment and cessation assistance. METHODS: Electronic health record (EHR) data from 8 community health centers were examined from March 1, 2019 to February 28, 2022. Data include both telehealth (phone and video) and in-person office visits and represent 310,388 visits by adult patients. Rates of smoking assessment, provision of referral to counseling and orders for smoking cessation medications were calculated. Comparisons by visit mode and time period were examined using generalized estimating equations and logistic regression. RESULTS: The proportion of telehealth visits was <0.1% one year prior to COVID-19 onset and, 54.5% and 34.1% 1 and 2 years after. The odds of asking about smoking status and offering a referral to smoking cessation counseling were significantly higher during in-person vs. telehealth visits; AOR (95% CI) = 15.0 (14.7 -15.4) and AOR (95% CI)= 6.5 (3.0 - 13.9), respectively. The interaction effect of visit type * time period was significant for ordering smoking cessation medications. CONCLUSION: Telehealth visits were significantly less likely to include smoking status assessment and referral to smoking cessation counseling compared to in-person visits. Given that smoking assessment and cessation assistance do not require face-to-face interactions with health care providers, continued efforts are needed to ensure provision at all visits, regardless of modality. IMPLICATIONS: The COVID-19 pandemic dramatically altered patterns of health care seeking and delivery with a considerable rise in telehealth visits. This study examined one year prior to the onset of COVID-19 and two years after to evaluate the assessment of tobacco use and assistance with tobacco cessation and differences during in-person vs telehealth visits. Tobacco assessment was 15 times more likely during in-person vs. telehealth visits in the two years post onset of COVID-19. Given that telehealth visits are likely to continue, ensuring that patients are regularly assessed for tobacco regardless of visit modality is an important concern for health systems.

Applying Machine Learning Techniques to Implementation Science.

Machine learning (ML) approaches could expand the usefulness and application of implementation science methods in clinical medicine and public health settings. The aim of this viewpoint is to introduce a roadmap for applying ML techniques to address implementation science questions, such as predicting what will work best, for whom, under what circumstances, and with what predicted level of support, and what and when adaptation or deimplementation are needed. We describe how ML approaches could be used and discuss challenges that implementation scientists and methodologists will need to consider when using ML throughout the stages of implementation.