Number Of Benzodiazepine Prescriptions Research Articles

Predicting benzodiazepine prescriptions: A proof-of-concept machine learning approach.

Benzodiazepines are the most commonly prescribed psychotropic medications, but they may place users at risk of serious adverse effects. Developing a method to predict benzodiazepine prescriptions could assist in prevention efforts. The present study applies machine learning methods to de-identified electronic health record data, in order to develop algorithms for predicting benzodiazepine prescription receipt (yes/no) and number of benzodiazepine prescriptions (0, 1, 2+) at a given encounter. Support-vector machine (SVM) and random forest (RF) approaches were applied to outpatient psychiatry, family medicine, and geriatric medicine data from a large academic medical center. The training sample comprised encounters taking place between January 2020 and December 2021 (N = 204,723 encounters); the testing sample comprised data from encounters taking place between January and March 2022 (N = 28,631 encounters). The following empirically-supported features were evaluated: anxiety and sleep disorders (primary anxiety diagnosis, any anxiety diagnosis, primary sleep diagnosis, any sleep diagnosis), demographic characteristics (age, gender, race), medications (opioid prescription, number of opioid prescriptions, antidepressant prescription, antipsychotic prescription), other clinical variables (mood disorder, psychotic disorder, neurocognitive disorder, prescriber specialty), and insurance status (any insurance, type of insurance). We took a step-wise approach to developing a prediction model, wherein Model 1 included only anxiety and sleep diagnoses, and each subsequent model included an additional group of features. For predicting benzodiazepine prescription receipt (yes/no), all models showed good to excellent overall accuracy and area under the receiver operating characteristic curve (AUC) for both SVM (Accuracy = 0.868-0.883; AUC = 0.864-0.924) and RF (Accuracy = 0.860-0.887; AUC = 0.877-0.953). Overall accuracy was also high for predicting number of benzodiazepine prescriptions (0, 1, 2+) for both SVM (Accuracy = 0.861-0.877) and RF (Accuracy = 0.846-0.878). Results suggest SVM and RF algorithms can accurately classify individuals who receive a benzodiazepine prescription and can separate patients by the number of benzodiazepine prescriptions received at a given encounter. If replicated, these predictive models could inform system-level interventions to reduce the public health burden of benzodiazepines.

Measuring the Effectiveness of Benzodiazepine Prescriptions Control in Community Setting Using Prescription Drug Monitoring Program (PDMP).

Benzodiazepines have been widely prescribed for several years for the treatment of anxiety, insomnia, and post-traumatic stress disorder (PTSD). Benzodiazepines were meant to be for short term use but in clinical settings long term use has been the "norm" for the treatment. Benzodiazepines are known for addiction potential and have been involved in accidental overdose deaths. According to the National Institute on Drug Abuse (NIDA), there has been a tenfold increase in the number of deaths due to overdose from 1999 to 2017. Benzodiazepines contributed to staggering high figures of 11,537 deaths in 2017 alone. Kentucky was ranked 4th in overdose related deaths in 2015 by CDC. Seeing this rise in overdose deaths, our community mental health clinics (CMHC) took the initiative to protect the community by removing benzodiazepines from the approved formulary in all adult outpatient community mental health clinics (total six clinics) in 2016. This project was initiated to protect the community from overdose deaths. In order to see the decrease in the benzodiazepine prescriptions, we did a quarterly Kentucky All Schedule Prescription Electronic Reporting (KASPER) prescriber's reports to see the trend. The goal of this project was to monitor the trend of benzodiazepine prescription control in CMHC. Our hypothesis was implementation of CMHC "No Benzodiazepine" policy would decrease in the number of prescriptions. To implement this change, we made a committee to educate staff including physicians, APRN's and therapists. Patients were also educated and informed regarding benzodiazepine free policy. Education materials were posted in the clinics and handed over to patients. Patients were offered individual and group therapy sessions to learn coping skills to cope with their anxiety. Patients had the option of inpatient detoxification, if clinically indicated. No new patients were started on benzodiazepines and patients who were already on benzodiazepines were slowly titrated off. Slow titration over the course of a few months was done as needed and tolerated. Quarterly, prescriber's prescription reports were generated with the help of KASPER (KASPER is PDMP in the state of Kentucky). After analyzing quarterly reports over the span of 2years, we concluded that there was a total of 89% decrease in benzodiazepine prescriptions. We are hoping to reach close to 100% in the next few years. We conduct a Mental Health Statistics Improvement Program (MHSIP) which is a general patient satisfaction survey done annually. We used this data to monitor the change with this new policy. Open patients report was run to monitor any change in case load before and after the implementation of the policy. After compilation of the KASPER/ PDMP data of all the prescribers- MD's and APRN's, we found an 89% decrease in the number of benzodiazepines prescriptions over the span of 2years. We did the open patients report and did not find any decrease in case load. In 2016, there were 10,359 open patients and in 2018 there were 12,266 open patients. We reviewed the MHSIP general patient satisfaction survey that is done annually, and we did not find any major difference in overall satisfaction as compared to previous years. These practice- based interventions implementing harm reduction strategies suggest that, although it was a difficult task, with strict adherence to no benzodiazepine policy, we were able to achieve a stark drop in the number of benzodiazepine prescriptions, in the span of 2years, and have been able to continue to maintain the low numbers of benzodiazepine prescriptions.

Change in Benzodiazepine Prescribing Practices of Mental Health Providers After Implementation of an Agency-Specific Protocol.

Purpose: As a class of drugs, benzodiazepines are highly effective in treating anxiety disorders. However, the use of benzodiazepines carries a risk for dependence with an increased incidence in individuals with cooccurring disorders. The project evaluated the impact of a benzodiazepine prescribing protocol on mental health providers' prescribing practices. Methods: A retrospective chart review (N = 237) was conducted to assess changes in benzodiazepine prescribing patterns prior to and following the implementation of an agency-specific protocol. A convenience sample of 15 providers included nurse practitioners and psychiatrists from a regional mental health center in East Tennessee. For the diagnoses of anxiety disorders, the number of benzodiazepine prescriptions written, dose reduced or discontinued was determined along with concordance to current recommendations for benzodiazepine use. Results: No statistically significant differences were found in scores between study periods, even though there was a decrease in the number of prescriptions written between the pre- (n = 81) and postmeasures (n = 34). Conclusion: The implementation of a benzodiazepine protocol does not necessarily bring about significant changes in providers' prescribing practices. Audit and feedback are an essential part of the intervention strategy and are often required to change performance-related outcomes.

Benzodiazepines: Utilization and Patterns of Use in a University Hospital

Information on the number of benzodiazepine prescriptions in all the departments of the Innsbruck University Clinics in 1985 was obtained from the hospital pharmacy. Expenditure on benzodiazepines amounted to 0.5% of total medication costs. In a second step, the authors questioned 264 patients from the five largest departments about benzodiazepine use. On the day of the interview, 24.1% of all investigated male patients and 20.5% of the female patients were taking benzodiazepines. Of the patients found to take benzodiazepines, 34.5% had already been using these before hospital admission. One-fifth of these patients reported problems when trying to stop medication.