Characteristics of Opioid Prescribing in Non-surgical Medicine Patients with Acute Pain at Hospital Discharge.

BACKGROUND: The opioid epidemic and new Joint Commission standards around opioid stewardship have made the appropriate prescribing of opioids a priority. A knowledge gap exists pertaining to the short-term prescription of opioids at hospital discharge for acute pain in non-surgical patients. OBJECTIVE: To characterize the quantity, type, and indication of opioids prescribed for non-surgical patients on hospital discharge and subsequent patient utilization. DESIGN: This multicenter, single-health system retrospective cohort study was conducted for quality improvement purposes from December 2019 to May 2020 with patient follow-up 15 to 29 days after hospital discharge. PARTICIPANTS: Patients discharged from a medicine service with new opioid prescriptions, defined as no opioid prescription documented within the past 90 days, were identified as eligible through the electronic health record. Surveys were attempted until a total of 200 were completed, with 374 surveys attempted and a 53% response rate. INTERVENTION: Patients were contacted via phone and surveyed post-discharge. Surveys consisted of 28 questions and assessed opioid consumption, duration of use, refills, patient satisfaction, and opioid disposal. MAIN MEASURES: Prescribing indications and morphine milligram equivalents (MME) quantities were collected for patients at discharge. Subsequently, the quantity of prescribed opioids utilized, remaining, and disposed of post-discharge were collected via patient self-reported survey responses. KEY RESULTS: Indications for opioid prescribing for 200 surveyed patients were grouped into eight broad prescribing categories. A median of 112.5 total MME was prescribed to patients at hospital discharge. Median MME consumed for surveyed patients was 45. The median total MME remaining at time of survey was 35 MME. Only 5.9% of patients who had leftover opioids reported disposal of the medication. CONCLUSIONS: Given the observed variation in opioid prescribing and utilization data, standardized indication-based opioid prescribing guidance in the non-surgical medical population would help curb the amount of opioids that remain unused post-discharge.

Deep learning predicts postoperative opioids refills in a multi-institutional cohort of surgical patients.

BACKGROUND: To combat the opioid epidemic, several strategies were implemented to limit the unnecessary prescription of opioids in the postoperative period. However, this leaves a subset of patients who genuinely require additional opioids with inadequate pain control. Deep learning models are powerful tools with great potential of optimizing health care delivery through a patient-centered focus. We sought to investigate whether deep learning models can be used to predict patients who would require additional opioid prescription refills in the postoperative period after elective surgery. METHODS: This is a retrospective study of patients who received elective surgical intervention at the Mayo Clinic. Adult English-speaking patients ≥18 years old, who underwent an elective surgical procedure between 2013 and 2019, were eligible for inclusion. Machine learning models, including deep learning, random forest, and eXtreme Gradient Boosting, were designed to predict patients who require opioid refills after discharge from hospital. RESULTS: A total of 9,731 patients with mean age of 62.1 years (51.4% female) were included in the study. Deep learning and random forest models predicted patients who required opioid refills with high accuracy, 0.79 ± 0.07 and 0.78 ± 0.08, respectively. Procedure performed, highest pain score recorded during hospitalization, and total oral morphine milligram equivalents prescribed at discharge were the top 3 predictors for requiring opioid refills after discharge. CONCLUSION: Deep learning models can be used to predict patients who require postoperative opioid prescription refills with high accuracy. Other machine learning models, such as random forest, can perform equal to deep learning, increasing the applicability of machine learning for combating the opioid epidemic.

Surgical Treatment of Adolescent Breast Disorders: Institutional Experience and National Trends.

STUDY OBJECTIVE: Adolescent breast disorders are rare and typically benign in nature; however, surgical treatments might require multiple surgeries. Because of the limited existing data, we sought to evaluate national trends and describe our institutional experience to help guide patient conversations. DESIGN: Retrospective review. SETTING: National database and academic institution. PARTICIPANTS: Patients 20 years old or younger who underwent a breast procedure in the Kids' Inpatient Database from January 2000 to December 2012 and at Mayo Clinic-Rochester from January 2000 to July 2016. Conditions were categorized into common and complex breast disorders. INTERVENTIONS: None. MAIN OUTCOME MEASURES: To assess any trend of adolescent breast procedures across the United States as a whole, weighted Kids' Inpatient Database data were assessed using a Rao-Scott χ2 test. Within the institutional data, the average number of procedures needed to correct common vs complex breast disorders were compared using an unequal variance t test. RESULTS: In recent years, the estimated number of hospitalizations for breast procedures decreased in the United States from 1661 in 2000 to 1078 in 2012 (P < .001). At our institution, 241 patients underwent a breast procedure (75.1% [181/241] female) over 16 years. Common breast disorders were corrected with fewer procedures than complex breast disorders (mean 1.09 vs 2.22 procedures; P = .0003). CONCLUSION: Inpatient treatment of adolescent breast disorders has been decreasing in recent years, likely reflecting a trend to outpatient procedures. Common adolescent breast disorders might be surgically corrected with 1 procedure, whereas complex disorders often require multiple surgeries to correct. It is important to discuss this with patients and their families to adequately set up expectations.