Prescription Patterns of Adjuvant Pain Medications Following an Opioid Supply Restriction Law: An Interrupted Time Series Analysis.

BACKGROUND: Florida House Bill 21 (HB21) was implemented in July 2018 to limit prescriptions of Schedule II opioids for acute pain patients, but it is unclear whether such restrictions have a collateral influence on the utilization of commonly prescribed adjuvant pain medications. OBJECTIVE: The objective of this study was to assess whether this law was associated with a change in use patterns of gabapentinoids, benzodiazepines, and muscle relaxants. METHODS: We obtained prescription claims for medications dispensed from January 1, 2015, to June 31, 2019, from a health plan serving a large Florida employer. Interrupted time series analyses were conducted to compare pre-HB21 and post-HB21 implementation changes in the mean monthly number of users and prescriptions for gabapentinoids, benzodiazepines, and muscle relaxants. RESULTS: There was a 6% immediate increase (relative risk: 1.06; 95% confidence interval: 1.02, 1.11) in the monthly proportion of gabapentinoid users, and an 11% immediate increase in the monthly proportion of gabapentinoids prescriptions (relative risk: 1.11; 95% confidence interval: 1.04, 1.18) per 1000 patients following law implementation. However, after the law, we observed a significant reduction in trend for the monthly proportion of muscle relaxants and benzodiazepine users. CONCLUSIONS: An increased number of patients and prescriptions were observed for gabapentinoids, while fewer patients received benzodiazepines and muscle relaxants after HB21. In previous studies, opioid prescription restriction laws are shown to reduce opioids, but this work suggests that these laws may also have unintended consequences for the use of adjunctive medications that were not intended to be affected.

Changes in Prescribing by Provider Type Following a State Prescription Opioid Restriction Law.

BACKGROUND: Many states have implemented opioid days' supply restriction policies, leading to reductions in opioid prescribing. Although research within certain provider types exist, no study has evaluated a restriction policy by various provider types. OBJECTIVE: To evaluate changes in opioid utilization following a days' supply restriction policy stratified by provider type: surgery, emergency medicine, primary care, specialty care, and dentistry. DESIGN: Interrupted time series (ITS) PARTICIPANTS: Opioid prescription claims of patients in a private health plan serving a large Florida employer from 1/1/2015 to 3/31/2019. Provider types were determined using the Healthcare Provider Taxonomy Code associated with the national provider identifier (NPI). INTERVENTIONS: Florida's opioid restriction policy implemented on July 1, 2018. MAIN MEASURES: Changes in mean morphine milligram equivalent (MMEs), mean days' supply, and mean number of units dispensed per opioid prescription before and after policy implementation. KEY RESULTS: There were 10,583 opioid initial prescriptions dispensed. Treating providers were classified as surgery (16.4%; n = 1732), emergency care (14.3%; n = 1516), primary care (21.2%; n = 2241), specialty care (11.4%; n = 1207), and dentistry providers (23.7%; n = 2511). Significant reductions in mean days' supply were observed across most provider types ranging from 14% reduction for dentistry providers to 41% reduction for specialty care providers. Significant changes were observed for emergency care and specialty care providers with a 30% (p = 0.001)and 29% (p < 0.001) reduction in mean MME, respectively, and a 27% (p = 0.040) reduction in mean number of units dispensed in emergency care providers, after implementation. Pre-implementation trends in opioid prescribing varied by provider type impacting the effects of the opioid days' supply restriction policy. CONCLUSIONS: Pre-policy opioid prescribing varied by provider type with a differential impact on mean MMEs, mean days' supply, and mean number of units dispensed per prescription following implementation.

Co-utilization of opioids and nonbenzodiazepine hypnotic drugs in U.S. ambulatory care visits, 2006-2016.

OBJECTIVE(S): This study aimed to characterize the co-utilization of non-benzodiazepine sedative 'Z'-drugs with opioids at ambulatory care visits in the United States. DESIGN: A cross-sectional analysis of the National Ambulatory Medical Care Survey (NAMCS) from 2006 to 2016 was completed. SETTING AND PARTICIPANTS: Ambulatory care visits in the United States involving adult patients with an opioid prescription were included in the analysis. OUTCOME MEASURES: The primary outcome was initiation or continuation of a Z-drug (zolpidem, eszopiclone, or zaleplon) in a patient visit in conjunction with an opioid medication. RESULTS: The authors analyzed 564,090,296 visits (weighted from a sample of 28,773) with a reported opioid prescription. Co-utilization of opioids with Z-drugs fluctuated during the study period beginning at 4.0% in 2006 (95% CI 2.2%-5.7%), 6.3% in 2012 (3.7%-8.9%), and 4.7% in 2016 (2.8%-6.5%). Among all opioid visits in the study period, co-utilization with a Z-drug was not significantly different among female patients compared with male patients (5.26% vs. 4.63%, P = 0.26). Among visits with concomitant opioid and Z-drugs, 7.0% reported new initiation of both medications in the same visit. CONCLUSION: At ambulatory care visits between 2006 and 2016, co-utilization of opioids and Z-drugs fluctuated with some differences by sex. Major regulatory advisories and policy changes during this period may have contributed to these varying rates of utilization. Additional work is needed to identify predictors of co-utilization and downstream consequences more widely.

A Pharmacoepidemiologic Approach to Evaluate Real-world Effectiveness of Hormonal Contraceptives in the Presence of Drug-drug Interactions.

BACKGROUND: Accurate estimation of conception is critical in the assessment of the effects of drugs used during pregnancy or to prevent pregnancy. In a novel application, we studied the effectiveness of oral contraceptives (OCs), where misclassification of conception relative to OC exposure may obscure effect estimates. METHODS: We studied OC failure, in a large claims database, among women who used antiepileptic drugs with metabolizing enzyme-inducing properties (carbamazepine or oxcarbazepine), which reduce OC's effectiveness or enzyme-neutral properties (lamotrigine or levetiracetam), with no expected impact on OC effectiveness. We compared conception rates in women 12-48 years of age concomitantly using OCs and enzyme-inducing drugs with rates in concomitant users of OCs and enzyme-neutral drugs. We measured conception with a validated algorithm that estimates gestational age based on pregnancy endpoints. We estimated relative and attributable risk using generalized estimating equation models after standardized mortality ratio weighting. RESULTS: We identified 89,777 concomitant use episodes with adjusted contraceptive failure rates of 1.6 (95% confidence interval (CI) = 1.4, 1.8) per 100 person-years among users of enzyme-neutral drugs and 18,964 episodes with a rate of 2.3 (1.9, 2.8) among users of enzyme-inducing drugs. The relative risk of conception for enzyme-inducing group was 1.4 (1.1, 1.8), and the rate difference was 0.7 (0.2, 1.2). CONCLUSIONS: OCs in combination with antiepileptic drugs that interact with metabolic enzymes were associated with increased contraceptive failure rates. Measurement of conception in claims data had adequate accuracy to uncover a strong drug-drug interaction, offering promise for broader application in comparative effectiveness studies on hormonal contraceptives to inform clinical and regulatory decisionmaking.

Cannabis use assessment and documentation in healthcare: Priorities for closing the gap.

Several factors, including the lack of a systematic cannabis use assessment within healthcare systems, have led to significant under-documentation of cannabis use and its correlates in medical records, the unpreparedness of clinicians, and poor quality of cannabis-related electronic health record data, limiting its utilization in research. Multiple steps are required to overcome the existing knowledge gaps and accommodate the health needs implied by the increasing cannabis use prevalence. These steps include (1) enhancing clinician and patient education on the importance of cannabis use assessment and documentation, (2) implementing a standardized approach for comprehensive cannabis use assessment within and across healthcare systems, (3) improving documentation of cannabis use and its correlates in medical records and electronic health records by building in prompts, (4) developing and validating reliable computable phenotypes of cannabis use, (5) conducting research utilizing electronic health data to study a wide array of related health outcomes, (6) and establishing evidence-based guidelines to inform clinical practices and policies. Integrating comprehensive cannabis use assessment and documentation within healthcare systems is necessary to enhance patient care and improve the quality of electronic health databases. Employing electronic health record data in cannabis-related research is crucial to accelerate research in light of the existing knowledge gaps on a wide array of health outcomes. Thus, improving and modernizing cannabis use assessment and documentation in healthcare is an integral step on which research conduct and evidence generation primarily rely.

Domperidone prescribing patterns in pediatric patients before and after safety warning in South Korea.

OBJECTIVE: In 2014, the Korean Ministry of Food and Drug Safety (MFDS) issued a safety warning to carefully consider adverse cardiac effects when prescribing domperidone for children. We conducted this study to compare the trends of domperidone prescription in pediatrics before and after the MFDS safety warning. MATERIALS: This study included patients < 18 years old who used national health insurance services within the year 2011 and the year 2016, sampled from Health Insurance Review Agency data. METHODS: We analyzed domperidone prescribing patterns including prescribed daily dosage, maximum period of continuous prescription, and number and types of co-prescribed medications and compared two different years pre and post safety warning. RESULTS: A total of 16,614 pediatric patients (1.74%) received domperidone prescriptions in 2011, and 11,317 patients (1.23%) in 2016. The probability of receiving at least one prescription in 2016 has been reduced by 30% compared to 2011. Gastritis was the most common indication in both years. The number of prescriptions containing a maximum daily dosage of over 30 mg was significantly lower in 2016. In the same time period, the number of cases with a maximum continuous prescription period of more than 7 days significantly decreased (p < 0.001). In addition, from 2011 to 2016, comorbid diseases of domperidone-treated patients were similar, but the number of co-prescriptions of interacting medication to domperidone decreased (p < 0.001). CONCLUSION: After the 2014 safety letter was released, the pattern of prescribing domperidone in pediatrics has enhanced drug safety for children in terms of frequency of prescriptions, maximum duration of domperidone use, and the prescription of drugs interacting with domperidone.

Impact of an on-site perinatal mood disorders clinic in the diagnosis and management of perinatal mood disorders.

Objectives To assess change in Edinburgh Postnatal Depression Scale (EPDS) scores in women treated at the Perinatal Mood Disorders Clinic (PMDC) as a measure of improvement in perinatal mood disorders (primary outcome), and treatment disposition at final visit. Methods Chart review was performed for all PMDC patients between March 1, 2017 and June 1, 2018 (n=120), as a self-controlled case series design. Two-tailed t-tests compared initial and final EPDS scores for all patients with >1 visit (n=64), where EPDS score of ≥13 indicated a positive screen for depression. A multivariable linear regression model with robust standard errors estimated the relationship between patient characteristics and final EPDS scores. Results Of 120 patients, n=56 had one visit and n=64 had >1 visit. Of these 64, mean final score (11.04) was lower than mean initial score (16.54; p<0.001). Additionally, certain patient characteristics were associated with higher final EPDS score, including history of mood disorder and treatment with both pharmacotherapy and psychotherapy. Conclusions Women treated at the PMDC showed improved EPDS scores when receiving at least two separate care visits. Therefore, the clinic may be filling a gap in access to timely care for women with perinatal mood disorders.

Assessing the utility of the Healthy Start Screen to predict an elevated Edinburgh Postnatal Depression Scale score.

Objective To examine the utility of the Healthy Start Screen (HSS), which is an assessment of health, environment, and behavioral risk factors offered to all pregnant women in the state of Florida, in identifying women at risk for developing postpartum depression (PPD). Methods The sample for this Institutional Review Board (IRB)-approved, retrospective study consisted of patients who presented to a women's clinic for a new prenatal visit. Those patients who completed both the HSS at their prenatal visit and the Edinburgh Postnatal Depression Scale (EPDS) at their postpartum visit were included. We focused on items 1-10 of the HSS, where patients could respond with either "yes" or "no", and identified a positive EPDS as any score greater than or equal to 12. Results Women who identified as feeling down, depressed or hopeless, feeling alone when facing problems, to having ever received mental health services, or to having any trouble paying bills were more likely to have an EPDS score greater than or equal to 12. Conclusion The HSS, currently mandated by the state of Florida to be offered to all pregnant women, is a useful tool for identifying women at increased risk of developing PPD.

Mass Casualty Shooting Venues, Types of Firearms, and Age of Perpetrators in the United States, 1982-2018.

OBJECTIVES: To evaluate the association between mass casualty shooting venues, types of firearms, and the age of perpetrators in the United States. METHODS: We analyzed data on mass casualty (≥ 3 fatalities) shootings for August 1982 through February 14, 2018. We describe data overall, specifically by school venues and the weapons used. We categorized perpetrators by ages of younger than 18 years, 18 to 20 years, and 21 years and older. We described the number of victims (fatalities plus injuries) by medians and average per event. RESULTS: Of 97 events, the median perpetrator age was 35 years and 21 years for school shootings. Four of 16 school events were committed by those aged 18 to 20 years, and all of those events included long guns. Victims of perpetrators aged 18 to 20 years made up 9.0% of all victims and 31.1% of victims of school shootings. CONCLUSIONS: Persons aged 18 to 20 years perpetrated about 1 in 8 shootings, accounting for about 1 in 3 victims of school shootings. Public Health Implications. Legislation to prevent mass casualty events must be multifaceted, including age restrictions, restrictions on certain types of firearms, and improved resources for mental health, with particular emphasis on mental health and firearm restrictions for young adults.

An investigation of factors predicting the type of bladder antimuscarinics initiated in Medicare nursing homes residents.

BACKGROUND: To examine factors predicting type of bladder antimuscarinics (BAM) initiated in nursing home (NH) residents. METHODS: Incident BAM initiators following NH admission were identified by constructing a retrospective cohort from Medicare files and Minimum Data Set (MDS). Participants included all residents 65 years and older admitted in Medicare-certified NH between January 1, 2007 and December 31, 2008 who were prescribed BAM and had continuous Medicare (Part A, B, and D) enrollment. Patient characteristics, medications, and comorbidities were derived from Medicare enrollment and claims. NH characteristics and health status were derived from MDS assessments. The outcome was defined as type of BAM initiated after admission (selective, non-selective extended release, non-selective immediate release). Multinomial logistic regression using generalized estimating equation methodology determined which factors predicted the type of BAM initiated. RESULTS: Twelve thousand eight hundred ninety-nine NH residents initiating BAM therapy were identified; 13.38% of new users were prescribed selective BAM, 45.56% non-selective extended release, and 41.07% non-selective immediate release medications. In both sexes, significant predictors of BAM included region of nursing home, body mass index, cognitive performance score, frailty measures, activities of daily living, and measures of bladder continence. In women, history of fracture and fall-related injuries were significant predictors of type of BAM use, while race and indicators of balance were significant predictors of type of BAM use in men. Non-pharmacological continence management strategies were not predictive of type of BAM initiation. CONCLUSIONS: Several factors are important in predicting type of BAM initiation in both women and men, but other factors are sex-specific. Some observed factors predicting the type of BAM initiated, such as other medications use, body mass index, or provider-related factors are potentially modifiable and could be used in targeted interventions to help optimize BAM use in this population. TRIAL REGISTRATION: Not applicable.

Online medical care: the current state of "eVisits" in acute primary care delivery.

BACKGROUND: Online technologies offer the promise of an efficient, improved healthcare system. Patients benefit from increased access to care, physicians are afforded greater flexibility in care delivery, and the health system itself benefits from lower costs to provide such care. One method of incorporating online care into clinical practice, called electronic office visits or "eVisits," allows physicians to provide a consultation with patients online. We performed an analysis of the current published literature on eVisits as well as present emerging research describing the use of mobile platforms as the delivery model. We focused on the role of eVisits in acute primary care practice. MATERIALS AND METHODS: A literature review was conducted using electronic databases with a variety of search terms related to the use of eVisits in primary care. RESULTS: Several advantages to eVisit utilization in the primary care setting were identified, namely, improvements in efficiency, continuity of care, quality of care, and access to care. Barriers to eVisit implementation were also identified, including challenges with incorporation into workflow, reimbursement, physician technological literacy, patient health literacy, overuse, security, confidentiality, and integration with existing medical technologies. CONCLUSIONS: Only one study of patient satisfaction with eVisit acute primary care services was identified, and this suggests that previous analyses of eVisit utilization are lacking this key component of healthcare service delivery evaluations. The delivery of primary care via eVisits on mobile platforms is still in adolescence, with few methodologically rigorous analyses of outcomes of efficiency, patient health, and satisfaction.

Kentucky pharmacists' opinions of the potential reclassification of pseudoephedrine as a legend drug.

OBJECTIVES: To collect and analyze Kentucky pharmacists' opinions of the effectiveness of current methamphetamine precursor controls, to analyze proposed legislation to make pseudoephedrine (PSE) a legend drug, and to analyze the potential impact of such legislation on pharmacy practice and patients. DESIGN: Descriptive, nonexperimental survey study. SETTING: Kentucky; June through October 2012. PARTICIPANTS: 431 Kentucky community pharmacists. INTERVENTION: Mailed survey. MAIN OUTCOME MEASURES: Perceived efficacy of current methamphetamine precursor controls, anticipated impact on individual pharmacy practices and patients of proposed legislation to make PSE available by prescription only, and current opinions about the proposed legislation. RESULTS: Analysis of 431 community pharmacists showed that approximately 77% believed proposed legislation to make PSE available by prescription only would be effective in reducing methamphetamine abuse and methamphetamine-related laboratory incidents, with 56.2% indicating support for the proposed legislation. Pharmacists practicing in chain pharmacies were 2.9 times more likely to support the legislation than pharmacists practicing in independent pharmacies. Additional factors influencing pharmacist support included Kentucky region of practice, anticipated impact on time spent on PSE activities, pharmacy profit, methamphetamine abuse, and methamphetamine-related laboratory incidents. Pharmacists practicing in regions of Kentucky associated with higher methamphetamine abuse appear to more strongly support the proposed legislation. CONCLUSION: Pharmacists are at the frontline of PSE distribution. Gaining a better understanding of issues surrounding the distribution of PSE will enhance the likelihood that future legislation may be crafted to reduce methamphetamine production, laboratory incidents, and abuse while minimizing inconvenience and cost.

An explainable machine learning framework for predicting the risk of buprenorphine treatment discontinuation for opioid use disorder among commercially insured individuals.

OBJECTIVES: Buprenorphine is an effective evidence-based medication for opioid use disorder (OUD). Yet premature discontinuation undermines treatment effectiveness, increasing the risk of mortality and overdose. We developed and evaluated a machine learning (ML) framework for predicting buprenorphine care discontinuity within 12 months following treatment initiation. METHODS: This retrospective study used United States (US) 2018-2021 MarketScan commercial claims data of insured individuals aged 18-64 who initiated buprenorphine between July 2018 and December 2020 with no buprenorphine prescriptions in the previous six months. We measured buprenorphine prescription discontinuation gaps of ≥30 days within 12 months of initiating treatment. We developed predictive models employing logistic regression, decision tree classifier, random forest, extreme gradient boosting, Adaboost, and random forest-extreme gradient boosting ensemble. We applied recursive feature elimination with cross-validation to reduce dimensionality and identify the most predictive features while maintaining model robustness. For model validation, we used several statistics to evaluate performance, such as C-statistics and precision-recall curves. We focused on two distinct treatment stages: at the time of treatment initiation and one and three months after treatment initiation. We employed SHapley Additive exPlanations (SHAP) analysis that helped us explain the contributions of different features in predicting buprenorphine discontinuation. We stratified patients into risk subgroups based on their predicted likelihood of treatment discontinuation, dividing them into decile subgroups. Additionally, we used a calibration plot to analyze the reliability of the models. RESULTS: A total of 30,373 patients initiated buprenorphine and 14.98% (4551) discontinued treatment. C-statistic varied between 0.56 and 0.76 for the first-stage models including patient-level demographic and clinical variables. Inclusion of proportion of days covered (PDC) measured after one month and three months following treatment initiation significantly increased the models' discriminative power (C-statistics: 0.60 to 0.82). Random forest (C-statistics: 0.76, 0.79 and 0.82 with baseline predictors, one-month PDC and three-months PDC, respectively) outperformed other ML models in discriminative performance in all stages (C-statistics: 0.56 to 0.77). Most influential risk factors of discontinuation included early stage medication adherence, age, and initial days of supply. CONCLUSION: ML algorithms demonstrated a good discriminative power in identifying patients at higher risk of buprenorphine care discontinuity. The proposed framework may help healthcare providers optimize treatment strategies and deliver targeted interventions to improve buprenorphine care continuity.

Pragmatic Model and Faculty Toolkit for PharmD Student Engagement in Social and Administrative Pharmacy Research.

OBJECTIVE: We aim to describe the development of a pharmacy student workgroup as an experiential education model to provide social and administrative pharmacy research opportunities and provide a toolkit for faculty seeking to increase student research engagement via this model. METHODS: Three pharmacy faculty with diverse training backgrounds but a common interest in opioid medications established a workgroup named the Opioid Research Workgroup. The workgroup consisted of first-year pharmacy students, research interns, and advanced graduate trainees. A hierarchical leadership model of supervision was implemented, whereby students reported progress on research tasks directly to an advanced graduate trainee leading a project team. To understand students' perspectives on the research experience and educational outcomes, students were asked to complete an anonymous voluntary survey after a year of participation. RESULTS: Since its establishment, the workgroup has published multiple conference abstracts, manuscripts, and grants. Students' overall satisfaction with the Workgroup on a scale of 1-5, 5 being very high, was 4.69. The successful scalability and longevity of this model are dependent on administrative support that protects faculty resources. The toolkit provided offers resources for those interested in adapting this model. CONCLUSION: Our experience with the pragmatic model of pharmacy student engagement in research proved successful in terms of research output and student training experience. Although the model can be applied across a variety of health science clinical and research topics, and faculty can leverage this approach to increase productivity in research output, faculty must ensure that resources are available to support this effort.

Incident mental health episodes after initiation of gabapentinoids vs. dopamine agonists for early-onset idiopathic restless legs syndrome.

Limited long-term safety information exists for gabapentinoid treatment of idiopathic restless legs syndrome (RLS). We estimated incident mental health-related emergency department visits and hospitalizations with a primary mental health diagnosis (primary outcome) among early-onset idiopathic RLS patients following first-line treatment initiation and examined outcome risk with gabapentinoids compared with dopamine agonists (DAs). A retrospective cohort study was conducted using administrative claims data from 2012 to 2019. Adults with early-onset (18-44 years) idiopathic RLS initiating either gabapentinoids or DAs within 60 days of new diagnosis were followed up to two years. Incidence rates were calculated and a log-binomial regression model with propensity score weighting estimated relative risk of the outcome and of substance use disorders (SUDs) as a secondary analysis with gabapentinoids. Among a cohort of 6,672 patients, 4,986 (74.7%) initiated DAs and 1,686 (25.3%) gabapentinoids. Incidence of the primary outcome (49.8 [95% CI 40.8-69.3] per 1,000 person-years) and SUDs (49.5 [95% CI 40.6-59.9] per 1,000 person-years) were higher in the gabapentinoid group compared with the DA group. A statistically significant risk of mental health diagnoses with gabapentinoids was not detected, but SUD risk was significant after covariate adjustment. High-risk mental health comorbidities (i.e., SUDs) should be considered when initiating RLS treatments.

Enhancing active learning of medication errors in the PharmD curriculum through a multi-perspective video-based experience.

INTRODUCTION: We created and assessed an immersive instructional series of video-based activities for pharmacy student evaluation of medication errors via root cause analysis (RCA). METHODS: A novel series of video vignettes showed a medication error from the perspectives of each healthcare team member involved. Students were engaged in a series of activities to guide them through RCA interspersed with the vignettes. A pre/post-assessment tool measured student-perceived skills and attitudes in medication error prevention and handling. Per item pre/post-mean scores were compared using Mann-Whitney U tests with Bonferroni correction. RESULTS: From N = 270 students, 231 and 163 completed the anonymous pre- and post-assessment, respectively. Most students positively endorsed attitude items at both assessment intervals, with no significant changes in mean for "learning how to improve patient safety is an appropriate use of time in pharmacy school" (pre-assessment = 4.26; post-assessment = 4.23). However, there were significant improvements in the skills items "I am confident in my ability to analyze a case to find the root causes of an error" (pre = 3.44; post = 3.85) and "I can identify the key factors in systems and processes that could lead to a medication error" (pre = 3.55; post = 3.88). CONCLUSIONS: Pharmacy students reported significantly improved self-perceived skills in handling and preventing medication errors, but not in attitudes, following the immersive instructional activity. There are opportunities to expand such an immersive instructional series in an interprofessional setting, which may yield different findings.

Proceedings of the 2023 Cannabis Clinical Outcomes Research Conference.

The Consortium for Medical Marijuana Clinical Outcomes Research, a multi-university collaboration established by the state of Florida in the USA, hosted its third annual Cannabis Clinical Outcomes Research Conference (CCORC) in May 2023. CCORC was held as a hybrid conference, with a scientific program consisting of in-person sessions, with some sessions livestreamed to virtual attendees. CCORC facilitated and promoted up-to-date research on the clinical effects of medical cannabis, fostering collaboration and active involvement among scientists, policymakers, industry professionals, clinicians, and other stakeholders. Three themes emerged from conference sessions and speaker presentations: (1) disentangling conflicting evidence for the effects of medical cannabis on public health, (2) seeking solutions to address barriers faced when conducting clinical cannabis research - especially with medical cannabis use in special populations such as those who are pregnant, and (3) unpacking the data behind cannabis use and mental health outcomes. The fourth annual CCORC is planned for the summer of 2024 in Florida, USA.

A Natural Language Processing Algorithm for Classifying Suicidal Behaviors in Alzheimer's Disease and Related Dementia Patients: Development and Validation Using Electronic Health Records Data.

This study aimed to develop a natural language processing algorithm (NLP) using machine learning (ML) and Deep Learning (DL) techniques to identify and classify documentation of suicidal behaviors in patients with Alzheimer's disease and related dementia (ADRD). We utilized MIMIC-III and MIMIC-IV datasets and identified ADRD patients and subsequently those with suicide ideation using relevant International Classification of Diseases (ICD) codes. We used cosine similarity with ScAN (Suicide Attempt and Ideation Events Dataset) to calculate semantic similarity scores of ScAN with extracted notes from MIMIC for the clinical notes. The notes were sorted based on these scores, and manual review and categorization into eight suicidal behavior categories were performed. The data were further analyzed using conventional ML and DL models, with manual annotation as a reference. The tested classifiers achieved classification results close to human performance with up to 98% precision and 98% recall of suicidal ideation in the ADRD patient population. Our NLP model effectively reproduced human annotation of suicidal ideation within the MIMIC dataset. These results establish a foundation for identifying and categorizing documentation related to suicidal ideation within ADRD population, contributing to the advancement of NLP techniques in healthcare for extracting and classifying clinical concepts, particularly focusing on suicidal ideation among patients with ADRD. Our study showcased the capability of a robust NLP algorithm to accurately identify and classify documentation of suicidal behaviors in ADRD patients.