Search

Objective: Youths who start behavioral health treatment often stop before completing a therapeutic course of care. To increase treatment engagement and quality of care, the Evidence-Based Practice and Innovation Center in Philadelphia has incentivized use of evidence-based practices (EBPs) for mental health care of youths. The authors aimed to compare treatment outcomes between youths who received EBP care and those who did not. Methods: Using EBP-specific billing codes and propensity score matching, the authors compared treatment retention among youths who received trauma-focused cognitive-behavioral therapy (TF-CBT; N=413) or parent-child interaction therapy (PCIT; N=90) relative to matched samples of youths in standard outpatient therapy (N=503). Results: Youths with a minimum of one session of TF-CBT or PCIT attended a second session at higher rates than did youths in the matched control group (TF-CBT: 96% vs. 68%, p<0.01; PCIT: 94% vs. 69%, respectively, p<0.01). On average, these returning youths attended more sessions in the EBP groups than in the control group (TF-CBT: 15.9 vs. 11.5 sessions, p<0.01; PCIT: 11.2 vs. 6.9 sessions, p<0.01). Conclusions: These findings indicate that, in addition to improving quality of care, EBP implementation helps address the major challenge that most youths who engage with treatment are not retained long enough for care to have therapeutic effects. Future research should examine the mechanisms through which EBPs can improve treatment retention. [ABSTRACT FROM AUTHOR]

Background: Prediction models have demonstrated a range of applications across medicine, including using electronic health record (EHR) data to identify hospital readmission and mortality risk. Large language models (LLMs) can transform unstructured EHR text into structured features, which can then be integrated into statistical prediction models, ensuring that the results are both clinically meaningful and interpretable., Objective: This study aims to compare the classification decisions made by clinical experts with those generated by a state-of-the-art LLM, using terms extracted from a large EHR data set of individuals with mental health disorders seen in emergency departments (EDs)., Methods: Using a dataset from the EHR systems of more than 50 health care provider organizations in the United States from 2016 to 2021, we extracted all clinical terms that appeared in at least 1000 records of individuals admitted to the ED for a mental health-related problem from a source population of over 6 million ED episodes. Two experienced mental health clinicians (one medically trained psychiatrist and one clinical psychologist) reached consensus on the classification of EHR terms and diagnostic codes into categories. We evaluated an LLM's agreement with clinical judgment across three classification tasks as follows: (1) classify terms into "mental health" or "physical health", (2) classify mental health terms into 1 of 42 prespecified categories, and (3) classify physical health terms into 1 of 19 prespecified broad categories., Results: There was high agreement between the LLM and clinical experts when categorizing 4553 terms as "mental health" or "physical health" (κ=0.77, 95% CI 0.75-0.80). However, there was still considerable variability in LLM-clinician agreement on the classification of mental health terms (κ=0.62, 95% CI 0.59-0.66) and physical health terms (κ=0.69, 95% CI 0.67-0.70)., Conclusions: The LLM displayed high agreement with clinical experts when classifying EHR terms into certain mental health or physical health term categories. However, agreement with clinical experts varied considerably within both sets of mental and physical health term categories. Importantly, the use of LLMs presents an alternative to manual human coding, presenting great potential to create interpretable features for prediction models., (© Nicholas C Cardamone, Mark Olfson, Timothy Schmutte, Lyle Ungar, Tony Liu, Sara W Cullen, Nathaniel J Williams, Steven C Marcus. Originally published in JMIR Medical Informatics (https://medinform.jmir.org).)

Background: Medications for opioid use disorder (MOUD) are among the best tools we have to combat the opioid epidemic. Yet, use of MOUD among people with opioid use disorder (OUD) remains low. Interventions to increase MOUD access in the United States have largely focused on improving organizational capacity and addressing funding barriers, yet stigma toward MOUD may inhibit uptake even where MOUD is readily available. Substance use disorder (SUD) treatment counselors likely have considerable influence on a client's choice to initiate and adhere to MOUD, but beliefs that counselors convey about MOUD in interaction with clients are understudied. The current study explores what advantages and disadvantages that SUD treatment counselors communicate about buprenorphine, methadone, and naltrexone., Methods: From June to December 2021, we surveyed counselors from publicly-funded SUD treatment agencies under a municipality-wide mandate to offer MOUD to all clients with OUD. Counselors were asked to describe, in a free-response format, the most important advantages and disadvantages to communicate to their clients about taking buprenorphine, methadone, and naltrexone. Counselor responses were coded for one or more advantage and disadvantage., Results: A total of 271 SUD counselors from 29 agencies completed the survey, generating 1,995 advantages and disadvantages across three types of MOUD. The most frequently reported advantage across all three types of MOUD was their ability to reduce cravings and illicit drug use. The most frequently reported disadvantage related to the potential for some types of MOUD to develop long-term medication dependence., Conclusions: As the availability and variety of MOUD treatment options continue to expand, it is important that SUD counselors are equipped with evidence-based recommendations for OUD care. We identified misalignments with the MOUD-prescribing evidence base and stigmatizing language toward MOUD within counselors' responses, highlighting the potential to refine training materials for MOUD and mitigate stigmatizing beliefs., Competing Interests: Declarations Competing interests. The authors declare that there is no conflict of interest.