Development and validation of a machine-learning prediction model to improve abdominal aortic aneurysm screening.

OBJECTIVE: Despite recommendations by the United States Preventive Services Task Force and the Society for Vascular Surgery, adoption of screening for abdominal aortic aneurysms (AAAs) remains low. One challenge is the low prevalence of AAAs in the unscreened population, and therefore a low detection rate for AAA screenings. We sought to use machine learning to identify factors associated with the presence of AAAs and create a model to identify individuals at highest risk for AAAs, with the aim of increasing the detection rate of AAA screenings. METHODS: A machine-learning model was trained using longitudinal medical records containing lab results, medications, and other data from our institutional database. A retrospective cohort study was performed identifying current or past smoking in patients aged 65 to 75 years and stratifying the patients by sex and smoking status as well as determining which patients had a confirmed diagnosis of AAA. The model was then adjusted to maximize fairness between sexes without significantly reducing precision and validated using six-fold cross validation. RESULTS: Validation of the algorithm on the single-center institutional data utilized 18,660 selected patients over 2 years and identified 314 AAAs. There were 41 factors identified in the medical record included in the machine-learning algorithm, with several factors never having been previously identified to be associated with AAAs. With an estimated 100 screening ultrasounds completed monthly, detection of AAAs is increased with a lift of 200% using the algorithm as compared with screening based on guidelines. The increased detection of AAAs in the model-selected individuals is statistically significant across all cutoff points. CONCLUSIONS: By utilizing a machine-learning model, we created a novel algorithm to detect patients who are at high risk for AAAs. By selecting individuals at greatest risk for targeted screening, this algorithm resulted in a 200% lift in the detection of AAAs when compared with standard screening guidelines. Using machine learning, we also identified several new factors associated with the presence of AAAs. This automated process has been integrated into our current workflows to improve screening rates and yield of high-risk individuals for AAAs.

Characterizing non-heroin opioid overdoses using electronic health records.

INTRODUCTION: The opioid epidemic is a modern public health emergency. Common interventions to alleviate the opioid epidemic aim to discourage excessive prescription of opioids. However, these methods often take place over large municipal areas (state-level) and may fail to address the diversity that exists within each opioid case (individual-level). An intervention to combat the opioid epidemic that takes place at the individual-level would be preferable. METHODS: This research leverages computational tools and methods to characterize the opioid epidemic at the individual-level using the electronic health record data from a large, academic medical center. To better understand the characteristics of patients with opioid use disorder (OUD) we leveraged a self-controlled analysis to compare the healthcare encounters before and after an individual's first overdose event recorded within the data. We further contrast these patients with matched, non-OUD controls to demonstrate the unique qualities of the OUD cohort. RESULTS: Our research confirms that the rate of opioid overdoses in our hospital significantly increased between 2006 and 2015 (P < 0.001), at an average rate of 9% per year. We further found that the period just prior to the first overdose is marked by conditions of pain or malignancy, which may suggest that overdose stems from pharmaceutical opioids prescribed for these conditions. CONCLUSIONS: Informatics-based methodologies, like those presented here, may play a role in better understanding those individuals who suffer from opioid dependency and overdose, and may lead to future research and interventions that could successfully prevent morbidity and mortality associated with this epidemic.

Multimodal Analgesia After Posterior Fossa Decompression With and Without Duraplasty for Children With Chiari Type I.

BACKGROUND: Multimodal analgesia (MMA) may reduce opioid use after surgery for Chiari malformation type I. An MMA protocol was implemented after both posterior fossa decompression without dural opening (PFD) and posterior fossa decompression with duraplasty (PFDD). METHODS: Scheduled nonsteroidal antiinflammatory drugs (ketorolac or ibuprofen) and diazepam were alternated with acetaminophen, and as-needed oxycodone or intravenous morphine. The primary outcome was total opioid requirement over postoperative days 0 to 2. RESULTS: From 2012 to 2017, 49 PFD and 29 PFDD procedures were performed, and 46 of 78 patients used the protocol. Patients with PFD required less opioids than patients with PFDD. Among patients with PFDD, patients with MMA protocol usage had a lower mean opioid requirement than patients with no MMA protocol usage (0.53 ± 0.49 mgEq/kg versus 1.4 ± 1.0 mgEq/kg, P = .0142). In multivariable analysis, MMA protocol usage status independently predicted a mean decrease in opioid requirement of 0.146 mg equivalents/kg (P = .0497) after adjustment for procedure and surgeon. Statistically significant differences were not demonstrated in antiemetic requirements, discharge opioid prescriptions, total direct cost, and length of stay. CONCLUSIONS: A protocol of scheduled nonsteroidal antiinflammatory drugs alternating with scheduled acetaminophen and diazepam was associated with opioid use reductions.

Opioid-Sparing Multimodal Analgesia After Selective Dorsal Rhizotomy.

OBJECTIVES: Multimodal analgesia (MMA) may reduce opioid use among children who are hospitalized, and may contribute toward enhanced recovery after selective dorsal rhizotomy (SDR) for patients with spasticity in pediatric cerebral palsy. In this retrospective cohort study, we assess an MMA protocol consisting of scheduled nonsteroidal antiinflammatory drug doses (ketorolac or ibuprofen), alternating with scheduled acetaminophen and diazepam doses, with as-needed opioids. It was hypothesized that protocol use would be associated with reductions in opioid requirements and other clinical improvements. METHODS: Data were obtained for 52 patients undergoing SDR at an academic tertiary care pediatric hospital (2012-2017, with the protocol implemented in 2014). Using a retrospective cohort design, we compared outcomes between protocol and nonprotocol patients, employing both univariate t test and Wilcoxon rank test comparisons as well as multivariable regression methods. The primary outcome was total as-needed opioid requirements over postoperative days (PODs) 0 to 2, measured in oral morphine milligram equivalents per kilogram. Additional outcomes included antiemetic medication doses, discharge opioid prescriptions, total direct cost, and length of stay. RESULTS: Twelve patients received the MMA protocol, and 40 patients did not. POD-0 MMA initiation was independently associated with a reduction of 0.14 morphine milligram equivalents per kilogram in mean opioid requirements over PODs 0 to 2 in the multiple regression analysis (95% confidence interval 0.01 to 0.28; P = .04). No statistically significant differences were demonstrated in doses of antiemetic medications, discharge opioid prescriptions, total direct cost, and length of stay. CONCLUSIONS: This MMA protocol may help reduce opioid use after SDR. Improving protocol implementation in a prospective, multisite study will help elucidate further MMA effects on pain, costs, and recovery.