Screening Adolescents for Alcohol Use: Tracking Practice Trends of Massachusetts Pediatricians

Levy, Sharon; Ziemnik, Rosemary; Harris, Sion Kim; Rabinow, Lily; Breen, Leigh; Fluet, Christina; Strother, Heather; Straus, John H.

doi:10.1097/adm.0000000000000340

Cited by 20 publications

(19 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 16 The promising performance achieved by the ASUDS suggests potential for technology to support implementation of evidence-based screening without the need to modify clinician behavior around documentation, addressing a critical first barrier to the delivery of substance use prevention and intervention. 49 , 50 For instance, the computerized system could assemble a report of historic substance use information before an encounter, presenting both predictions regarding previous screening results and supportive evidence (eg, sentences mentioning substance use in notes, values of laboratory results) to facilitate clinician review, assist with determining change over time in substance use, and inform decisions about intervention during the encounter. Further, creation of such a system would improve secondary analysis of substance use information in EHRs, which could facilitate the dissemination of screening results to external institutions or to researchers interested in understanding substance use onset and risk.…”

Section: Discussionmentioning

confidence: 99%

Automated detection of substance use information from electronic health records for a pediatric population

Bachtel

Nause

et al. 2021

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

Objective Substance use screening in adolescence is unstandardized and often documented in clinical notes, rather than in structured electronic health records (EHRs). The objective of this study was to integrate logic rules with state-of-the-art natural language processing (NLP) and machine learning technologies to detect substance use information from both structured and unstructured EHR data. Materials and Methods Pediatric patients (10-20 years of age) with any encounter between July 1, 2012, and October 31, 2017, were included (n = 3890 patients; 19 478 encounters). EHR data were extracted at each encounter, manually reviewed for substance use (alcohol, tobacco, marijuana, opiate, any use), and coded as lifetime use, current use, or family use. Logic rules mapped structured EHR indicators to screening results. A knowledge-based NLP system and a deep learning model detected substance use information from unstructured clinical narratives. System performance was evaluated using positive predictive value, sensitivity, negative predictive value, specificity, and area under the receiver-operating characteristic curve (AUC). Results The dataset included 17 235 structured indicators and 27 141 clinical narratives. Manual review of clinical narratives captured 94.0% of positive screening results, while structured EHR data captured 22.0%. Logic rules detected screening results from structured data with 1.0 and 0.99 for sensitivity and specificity, respectively. The knowledge-based system detected substance use information from clinical narratives with 0.86, 0.79, and 0.88 for AUC, sensitivity, and specificity, respectively. The deep learning model further improved detection capacity, achieving 0.88, 0.81, and 0.85 for AUC, sensitivity, and specificity, respectively. Finally, integrating predictions from structured and unstructured data achieved high detection capacity across all cases (0.96, 0.85, and 0.87 for AUC, sensitivity, and specificity, respectively). Conclusions It is feasible to detect substance use screening and results among pediatric patients using logic rules, NLP, and machine learning technologies.

show abstract

Section: Discussionmentioning

confidence: 99%

Automated detection of substance use information from electronic health records for a pediatric population

Bachtel

Nause

et al. 2021

Journal of the American Medical Informatics Association

View full text Add to dashboard Cite

show abstract

“…Primary care well-child screening and prevention to reduce adolescent risky behaviors have been recommended by the American Academy of Pediatrics for decades, with increasing support and evidence in recent years (AAP, 2010;Babor et al, 2017;Levy & Kokotailo, 2011;Ozechowski et al, 2016;Sterling et al, 2012;Tanner-Smith & Lipsey, 2015). Yet, two historical barriers have precluded implementation of such services: lack of reimbursement and physician concerns regarding burdens on their staff time and costs, lack of training and referral networks, perception that screening tools have high false-positive rates, and fear that screening could alienate patients (Levy et al, 2017;Singh et al, 2017;Sterling et al, 2012;Van Hook et al, 2007).…”

Section: Historical Barriers and Facilitators To Primary Care Screening And Referral To Preventionmentioning

confidence: 99%

“…Perhaps superseding all other implementation factors in necessity for SRP is funding (an outer setting factor). As mentioned, cost-savings from prevention services may incentivize healthcare payor investment in efficacious SRP (Levy et al, 2017;Singh et al, 2017). Hence, as a first step toward evaluating potential cost savings to payors (e.g., Medicaid) from SRP-initiated prevention, we estimated healthcare costs arising from adolescent risky behavior.…”

Section: The Present Studiesmentioning

confidence: 99%

Addressing Barriers to Primary Care Screening and Referral to Prevention for Youth Risky Health Behaviors: Evidence Regarding Potential Cost-Savings and Provider Concerns

et al. 2021

View full text Add to dashboard Cite

“…Given the severe consequences of depression and SUD, routine monitoring of their co-occurrence is critical to inform prevention and intervention. 9 , 10 …”

Section: Introductionmentioning

confidence: 99%

Trends and Disparities in Treatment for Co-occurring Major Depression and Substance Use Disorders Among US Adolescents From 2011 to 2019

Muñoz‐Laboy

Sohler

et al. 2021

JAMA Netw Open

View full text Add to dashboard Cite

IMPORTANCEMajor depression and substance use disorders (SUD) commonly co-occur among adolescents, yet little is known about treatment use among adolescents with both conditions. Given the reciprocal influence of these conditions on each other and low prevalence of treatment overall, current information on quantification and trends in treatment of co-occurring depression and SUD is critical toward assessing how the field is performing in reaching youth in need of these services, and among youth with sociodemographic risk factors. OBJECTIVE To examine temporal trends and sociodemographic disparities in the treatment of co-occurring major depression and SUD among US adolescents. DESIGN, SETTING, AND PARTICIPANTS This survey study used publicly available data for adolescents aged 12 to 17 years from the annual cross-sectional surveys of the National Survey on Drug Use and Health from 2011 to 2019 to assess co-occurrence of major depressive episodes (MDE) and SUD through time and prevalence of treatment for either or both of these conditions. Data were analyzed between October 2020 and February 2021. EXPOSURES Survey years, adolescent age, gender, race and ethnicity, type of insurance, annual household income, family structure, and residential stability. MAIN OUTCOMES AND MEASURES Presence and treatment of co-occurring 12-month MDE and SUD.

show abstract

Screening Adolescents for Alcohol Use: Tracking Practice Trends of Massachusetts Pediatricians

Abstract: Our findings suggest that adolescent alcohol use screening practices among Massachusetts pediatricians have improved in recent years, during a time of national and statewide efforts to educate physicians. However, opportunities for practice improvement remain.

Cited by 20 publications

References 27 publications

Automated detection of substance use information from electronic health records for a pediatric population

Automated detection of substance use information from electronic health records for a pediatric population

Addressing Barriers to Primary Care Screening and Referral to Prevention for Youth Risky Health Behaviors: Evidence Regarding Potential Cost-Savings and Provider Concerns

Trends and Disparities in Treatment for Co-occurring Major Depression and Substance Use Disorders Among US Adolescents From 2011 to 2019

Contact Info

Product

Resources

About