Dataset Information

An end-to-end hybrid algorithm for automated medication discrepancy detection.

ABSTRACT: In this study we implemented and developed state-of-the-art machine learning (ML) and natural language processing (NLP) technologies and built a computerized algorithm for medication reconciliation. Our specific aims are: (1) to develop a computerized algorithm for medication discrepancy detection between patients' discharge prescriptions (structured data) and medications documented in free-text clinical notes (unstructured data); and (2) to assess the performance of the algorithm on real-world medication reconciliation data.We collected clinical notes and discharge prescription lists for all 271 patients enrolled in the Complex Care Medical Home Program at Cincinnati Children's Hospital Medical Center between 1/1/2010 and 12/31/2013. A double-annotated, gold-standard set of medication reconciliation data was created for this collection. We then developed a hybrid algorithm consisting of three processes: (1) a ML algorithm to identify medication entities from clinical notes, (2) a rule-based method to link medication names with their attributes, and (3) a NLP-based, hybrid approach to match medications with structured prescriptions in order to detect medication discrepancies. The performance was validated on the gold-standard medication reconciliation data, where precision (P), recall (R), F-value (F) and workload were assessed.The hybrid algorithm achieved 95.0%/91.6%/93.3% of P/R/F on medication entity detection and 98.7%/99.4%/99.1% of P/R/F on attribute linkage. The medication matching achieved 92.4%/90.7%/91.5% (P/R/F) on identifying matched medications in the gold-standard and 88.6%/82.5%/85.5% (P/R/F) on discrepant medications. By combining all processes, the algorithm achieved 92.4%/90.7%/91.5% (P/R/F) and 71.5%/65.2%/68.2% (P/R/F) on identifying the matched and the discrepant medications, respectively. The error analysis on algorithm outputs identified challenges to be addressed in order to improve medication discrepancy detection.By leveraging ML and NLP technologies, an end-to-end, computerized algorithm achieves promising outcome in reconciling medications between clinical notes and discharge prescriptions.

SUBMITTER: Li Q

PROVIDER: S-EPMC4427951 | biostudies-literature | 2015 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An end-to-end hybrid algorithm for automated medication discrepancy detection.

Li Qi Q Spooner Stephen Andrew SA Kaiser Megan M Lingren Nataline N Robbins Jessica J Lingren Todd T Tang Huaxiu H Solti Imre I Ni Yizhao Y

BMC medical informatics and decision making 20150506

<h4>Background</h4>In this study we implemented and developed state-of-the-art machine learning (ML) and natural language processing (NLP) technologies and built a computerized algorithm for medication reconciliation. Our specific aims are: (1) to develop a computerized algorithm for medication discrepancy detection between patients' discharge prescriptions (structured data) and medications documented in free-text clinical notes (unstructured data); and (2) to assess the performance of the algor ...[more]

PMID: 25943550

Similar Datasets

Project description:BackgroundAs a result of the overwhelming proportion of medication errors occurring each year, there has been an increased focus on developing medication error prevention strategies. Recent advances in electronic health record (EHR) technologies allow institutions the opportunity to identify medication administration error events in real time through computerized algorithms. MED.Safe, a software package comprising medication discrepancy detection algorithms, was developed to meet this need by performing an automated comparison of medication orders to medication administration records (MARs). In order to demonstrate generalizability in other care settings, software such as this must be tested and validated in settings distinct from the development site.ObjectiveThe purpose of this study is to determine the portability and generalizability of the MED.Safe software at a second site by assessing the performance and fit of the algorithms through comparison of discrepancy rates and other metrics across institutions.MethodsThe MED.Safe software package was executed on medication use data from the implementation site to generate prescribing ratios and discrepancy rates. A retrospective analysis of medication prescribing and documentation patterns was then performed on the results and compared to those from the development site to determine the algorithmic performance and fit. Variance in performance from the development site was further explored and characterized.ResultsCompared to the development site, the implementation site had lower audit/order ratios and higher MAR/(order + audit) ratios. The discrepancy rates on the implementation site were consistently higher than those from the development site. Three drivers for the higher discrepancy rates were alternative clinical workflow using orders with dosing ranges; a data extract, transfer, and load issue causing modified order data to overwrite original order values in the EHRs; and delayed EHR documentation of verbal orders. Opportunities for improvement were identified and applied using a software update, which decreased false-positive discrepancies and improved overall fit.ConclusionsThe execution of MED.Safe at a second site was feasible and effective in the detection of medication administration discrepancies. A comparison of medication ordering, administration, and discrepancy rates identified areas where MED.Safe could be improved through customization. One modification of MED.Safe through deployment of a software update improved the overall algorithmic fit at the implementation site. More flexible customizations to accommodate different clinical practice patterns could improve MED.Safe's fit at new sites.

Project description:To improve neonatal patient safety through automated detection of medication administration errors (MAEs) in high alert medications including narcotics, vasoactive medication, intravenous fluids, parenteral nutrition, and insulin using the electronic health record (EHR); to evaluate rates of MAEs in neonatal care; and to compare the performance of computerized algorithms to traditional incident reporting for error detection.We developed novel computerized algorithms to identify MAEs within the EHR of all neonatal patients treated in a level four neonatal intensive care unit (NICU) in 2011 and 2012. We evaluated the rates and types of MAEs identified by the automated algorithms and compared their performance to incident reporting. Performance was evaluated by physician chart review.In the combined 2011 and 2012 NICU data sets, the automated algorithms identified MAEs at the following rates: fentanyl, 0.4% (4 errors/1005 fentanyl administration records); morphine, 0.3% (11/4009); dobutamine, 0 (0/10); and milrinone, 0.3% (5/1925). We found higher MAE rates for other vasoactive medications including: dopamine, 11.6% (5/43); epinephrine, 10.0% (289/2890); and vasopressin, 12.8% (54/421). Fluid administration error rates were similar: intravenous fluids, 3.2% (273/8567); parenteral nutrition, 3.2% (649/20124); and lipid administration, 1.3% (203/15227). We also found 13 insulin administration errors with a resulting rate of 2.9% (13/456). MAE rates were higher for medications that were adjusted frequently and fluids administered concurrently. The algorithms identified many previously unidentified errors, demonstrating significantly better sensitivity (82% vs. 5%) and precision (70% vs. 50%) than incident reporting for error recognition.Automated detection of medication administration errors through the EHR is feasible and performs better than currently used incident reporting systems. Automated algorithms may be useful for real-time error identification and mitigation.

Project description:BackgroundEnd stage renal disease (ESRD) describes the most severe stage of chronic kidney disease (CKD), when patients need dialysis or renal transplant. There is often a delay in recognizing, diagnosing, and treating the various etiologies of CKD. The objective of the present study was to employ machine learning algorithms to develop a prediction model for progression to ESRD based on a large-scale multidimensional database.MethodsThis study analyzed 10,000,000 medical insurance claims from 550,000 patient records using a commercial health insurance database. Inclusion criteria were patients over the age of 18 diagnosed with CKD Stages 1-4. We compiled 240 predictor candidates, divided into six feature groups: demographics, chronic conditions, diagnosis and procedure features, medication features, medical costs, and episode counts. We used a feature embedding method based on implementation of the Word2Vec algorithm to further capture temporal information for the three main components of the data: diagnosis, procedures, and medications. For the analysis, we used the gradient boosting tree algorithm (XGBoost implementation).ResultsThe C-statistic for the model was 0.93 [(0.916-0.943) 95% confidence interval], with a sensitivity of 0.715 and specificity of 0.958. Positive Predictive Value (PPV) was 0.517, and Negative Predictive Value (NPV) was 0.981. For the top 1 percentile of patients identified by our model, the PPV was 1.0. In addition, for the top 5 percentile of patients identified by our model, the PPV was 0.71. All the results above were tested on the test data only, and the threshold used to obtain these results was 0.1. Notable features contributing to the model were chronic heart and ischemic heart disease as a comorbidity, patient age, and number of hypertensive crisis events.ConclusionsWhen a patient is approaching the threshold of ESRD risk, a warning message can be sent electronically to the physician, who will initiate a referral for a nephrology consultation to ensure an investigation to hasten the establishment of a diagnosis and initiate management and therapy when appropriate.

Project description:BACKGROUND:The Veterans Affairs Portland Healthcare System developed a medication history collection software that displays prescription names and medication images. OBJECTIVE:This article measures the frequency of medication discrepancy reporting using the medication history collection software and compares with the frequency of reporting using a paper-based process. This article also determines the accuracy of each method by comparing both strategies to a best possible medication history. STUDY DESIGN:Randomized, controlled, single-blind trial. SETTING:Three community-based primary care clinics associated with the Veterans Affairs Portland Healthcare System: a 300-bed teaching facility and ambulatory care network serving Veteran soldiers in the Pacific Northwest United States. PARTICIPANTS:Of 212 patients with primary care appointments, 209 patients fulfilled the study requirements. INTERVENTION:Patients randomized to a software-directed medication history or a paper-based medication history. Randomization and allocation to treatment groups were performed using a computer-based random number generator. Assignments were placed in a sealed envelope and opened after participant consent. The research coordinator did not know or have access to the treatment assignment until the time of presentation. MAIN OUTCOME MEASURES:The primary analysis compared the discrepancy detection rates between groups with respect to the health record and a best possible medication history. RESULTS:Of 3,500 medications reviewed, we detected 1,435 discrepancies. Forty-six percent of those discrepancies were potentially high risk for causing an adverse drug event. There was no difference in detection rates between treatment arms. Software sensitivity was 83% and specificity was 91%; paper sensitivity was 81% and specificity was 94%. No participants were lost to follow-up. CONCLUSION:The medication history collection software is an efficient and scalable method for gathering a medication history and detecting high-risk discrepancies. Although it included medication images, the technology did not improve accuracy over a paper list when compared with a best possible medication history. TRIAL REGISTRATION:ClinicalTrials.gov Identifier: NCT02135731.

Dataset Information

An end-to-end hybrid algorithm for automated medication discrepancy detection.

Publications

An end-to-end hybrid algorithm for automated medication discrepancy detection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets