Table 2 - uploaded by George Duncan
Content may be subject to copyright.
Source publication
Evidence suggests that the medication lists of patients are often incomplete and could negatively affect patient outcomes. In this article, the authors propose the application of collaborative filtering methods to the medication reconciliation task. Given a current medication list for a patient, the authors employ collaborative filtering approaches...
Context in source publication
Context 1
... resulted in 20 patient exclusions in clinic 1, 0 in clinic 2, and 1 in clinic 3. We find that the most commonly prescribed drugs in all three clinics are quite similar. Table 2 presents the top five drugs for each clinic. For the most part, these are quite similar across the clinics, with Tylenol, Dulcolax, Fleet Enema, and a magnesium antacid being highly prescribed in all clinics. ...
Citations
... (Hu et al., 2012) To predict the dosage of warfarin. (Hasan et al., 2011) To improve medication reconciliation task Drug safety LR 3 , KNN 1 ...
... Studies also used AI to predict medication that a patient could consume but is missing from their medication list or health records (Hasan et al., 2011;Li et al., 2015;Long et al., 2016). ...
Most research concerning healthcare Artificial Intelligence (AI) has neglected its ecological validity and human cognition consideration, which can create challenges at the interface with clinicians and the clinical environment. Besides, there is not enough evidence ensuring appropriate implementation of AI and its perceived benefits when used in a real clinical scenario. Therefore, what’s missing from the healthcare management and the medical practitioner literature is a framework for understanding interactions between clinicians and Artificial Intelligence (AI) systems that are ecologically valid and adopt a systems approach. This dissertation aims to propose a conceptual framework that can capture the factors influencing clinicians’ intent to use AI in their clinical practice. We conducted an extensive literature review and derived a conceptual framework from the human factors and decision-making literature that can explore the role of (a) expectancy, (b) workload, (c) situation awareness, (d) trust, (e) cognitive variables related to absorptive capacity and bounded rationality, and (f) perception for risks on clinicians’ intent to use AI. The framework also captures the impact of AI on clinical decision-making. To analyze this framework, we adopted triangulation and an explanatory sequential mixed method approach and studied an AI-based Blood Utilization Calculator (BUC) in collaboration with the University of Wisconsin, Madison, USA. The findings of the dissertation imply that AI, such as the BUC, if not designed for individual users at the department level, will not be used as intended. AI technologies in healthcare are designed and developed to assist clinicians and help them identify patterns they would typically overlook. If clinicians only consider AI recommendations when it complements their professional and personal judgment, the entire motive of having an AI in the very first place will go in vain. This dissertation helps identify suchnuances created due to sub-optimal usability of AI by analyzing a particular AI-enabled BUC. The research questions the framework implies will also inform future research and clinical decision-making towards the goal of an ecologically valid model.
... We used our hospital's enterprise data warehouse (EDW) to generate a report of orders placed for patients admitted to the resident PHM service overnight between July 1, 2017, and June 29, 2018 that were either (1) placed overnight and then discontinued on rounds, or (2) added on rounds the next morning. Orders were classified as "discontinued" if they were placed by overnight residents (6)(7)(8) and then discontinued during daytime rounding hours (8 AM-12 PM). Orders were classified as "new" if they were placed during daytime rounding hours (8 AM-12 PM). ...
... The application of machine learning and collaborative filtering to address this problem has previously been described. 8 Limitations of this study include its retrospective nature, including ambiguity in clinical documentation regarding reasons for order discontinuation or addition, inability of our EDW query to capture orders that were modified but not discontinued, and inclusion of a single institution limiting generalizability. This methodology only captures errors that were detected on rounds the next morning, likely underestimating total errors. ...
OBJECTIVES
Increased focus on health care quality and safety has generally led to additional resident supervision by attending physicians. At our children’s hospital, residents place orders overnight that are not explicitly reviewed by attending physicians until morning rounds. We aimed to categorize the types of orders that are added or discontinued on morning rounds the morning after admission to a resident team and to understand the rationale for these order additions and discontinuations.
METHODS
We used our hospital’s data warehouse to generate a report of orders placed by residents overnight that were discontinued the next morning and orders that were added on rounds the morning after admission to a resident team from July 1, 2017 to June 29, 2018. Retrospective chart review was performed on included orders to determine the reason for order changes.
RESULTS
Our report identified 5927 orders; 538 were included for analysis after exclusion of duplicate orders, administrative orders, and orders for patients admitted to non-Pediatric Hospital Medicine services. The reason for order discontinuation or addition was medical decision-making (n = 357, 66.4%), change in patient trajectory (n = 151, 28.1%), and medical error (n = 30, 5.6%). Medical errors were most commonly related to medications (n = 24, 80%) and errors of omission (n = 19, 63%).
CONCLUSIONS
New or discontinued orders commonly resulted from evolving patient management decisions or changes in patient trajectory; medical errors represented a small subset of identified orders. Medical errors were often errors of omission, suggesting an area to direct future safety initiatives.
... Data were obtained from health records for nine studies (noted as EHR data in seven studies) and pharmacy dispensing data for two studies. 85,90 Two studies tested models in patient care settings and measured prescriber response after receiving clinical decision support alerts identifying potential ADEs. 81,88 Most studies evaluated models that were designed to identify ADEs or errors in general, with ...
... [81][82][83] Most studies tested a single AI model, with only four studies evaluating multiple models. 80,84,85,90 Three studies used a software system (MedAware) that identified potential medication errors or ADEs in EHRs using several machine learning methods including neural networks. [87][88][89] This software was designed to alert prescribers about clinical or medication dosage outliers, time-dependent irregularities occurring between medication use and patients' data, and potential drug duplication. ...
Adverse drug events (ADEs) represent one of the most prevalent types of health-care-related harm, and there is substantial room for improvement in the way that they are currently predicted and detected. We conducted a scoping review to identify key use cases in which artificial intelligence (AI) could be leveraged to reduce the frequency of ADEs. We focused on modern machine learning techniques and natural language processing. 78 articles were included in the scoping review. Studies were heterogeneous and applied various AI techniques covering a wide range of medications and ADEs. We identified several key use cases in which AI could contribute to reducing the frequency and consequences of ADEs, through prediction to prevent ADEs and early detection to mitigate the effects. Most studies (73 [94%] of 78) assessed technical algorithm performance, and few studies evaluated the use of AI in clinical settings. Most articles (58 [74%] of 78) were published within the past 5 years, highlighting an emerging area of study. Availability of new types of data, such as genetic information, and access to unstructured clinical notes might further advance the field.
... Aspekte wie IT-Governance und IT-Strategie sind dagegen noch ausbaufähig [5]. Beispiele für Lösungsansätze sind u. a. die Benchmarks der GMDS und der Entscheiderfabrik [6] sowie des CIO-UK [7] und des IT-Reports Gesundheitswesen 2014 [8]. ...
... Dabei wurde weiterhin darauf geachtet, dass die Zahl der Reifegradmodelle überschaubar bleibt, um den Anwendungsaufwand und die Pflege im Rahmen der KIT-CON sicherstellen zu können. Der Ansatz des IT-Report Gesundheitswesen 2014 verwendet zum Teil eine ähnliche Prozessauswahl, allerdings mit dem Messziel der IT-Umsetzung/-Durchdringung von Funktionen[8].Im Gesamtüberblick lassen sich die Prozesse wie folgt gruppieren:(A) dispositiveProzesse, die den Behandlungskernprozess steuern (B) Prozesse der direkten oder indirekten Leistungserbringung am Patienten (C) patientenbezogene Dokumentationsprozesse (D) Prozesse, die der Erfüllung regulatorischer Anforderungen dienen (E) Prozesse der übergreifenden Unternehmenssteuerung (F) administrative Prozesse, die Querschnittaufgaben eines Krankenhauses abbilden. Tabelle 1 (S. ...
... After every 6 trial sets, drug and adverse event dictionaries were updated, and rules were modified to improve the system. The model identified adverse events with 92% precision and recall NLP Drug safety To identify adverse drug effects from unstructured hospital discharge summaries Tang et al [90] The proposed model improved warfarin dosage when compared to the baseline (mean absolute error 0.394); reduced mean absolute error by 40 [92] Mean (SD) cumulative adherence based on the AI platform was 90.5% (7.5%). Plasma drug concentration levels indicated that adherence was 100% (15/15) and 50% (6/12) in the intervention and control groups, respectively Cell phone-based AI platform Drug safety To evaluate the use of a mobile AI platform on medication adherence in stroke patients on anticoagulation therapy Labovitz et al [93] All patients completed the task. ...
... One study used AI to monitor stroke patients and track their medication (anticoagulation) intake [93]. Several studies used AI to predict a medication that a patient could be consuming but was missing from their medication list or health records [92,94,97]. Another study used AI to review clinical notes and identify evidence of opioid abuse [98]. ...
Background: Artificial intelligence (AI) provides opportunities to identify the health risks of patients and thus influence patient safety outcomes.
Objective: The purpose of this systematic literature review was to identify and analyze quantitative studies utilizing or integrating AI to address and report clinical-level patient safety outcomes.
Results: We identified 53 eligible studies, which were summarized concerning their patient safety subcategories, the most frequently used AI, and reported performance metrics. Recognized safety subcategories were clinical alarms (n=9; mainly based on decision tree models), clinical reports (n=21; based on support vector machine models), and drug safety (n=23; mainly based on decision tree models). Analysis of these 53 studies also identified two essential findings: (1) the lack of a standardized benchmark and (2) heterogeneity in AI reporting.
Conclusions: This systematic review indicates that AI-enabled decision support systems, when implemented correctly, can aid in enhancing patient safety by improving error detection, patient stratification, and drug management. Future work is still needed for robust validation of these systems in prospective and real-world clinical environments to understand how well AI can predict safety outcomes in health care settings.
... 41 In clinical medicine, RSs have been applied since 2008 to improve treatment recommendation schemes. For example, the RS approaches were used for automatic detection of omissions in medication lists, 42,43 as well as for treatment optimization in the context of the information overload problem, by suggesting knowledge-based items of interest to clinicians for specific diseases. 44 The search for new antivirals is an attractive field for the application of the RS approach. ...
Recommender systems (RSs), which underwent rapid development and had an enormous impact on e-commerce, have the potential to become useful tools for drug discovery. In this paper, we applied RS methods for the prediction of the antiviral activity class (active/inactive) for compounds extracted from ChEMBL. Two main RS approaches were applied: collaborative filtering (Surprise implementation) and content-based filtering (sparse-group inductive matrix completion (SGIMC) method). The effectiveness of RS approaches was investigated for prediction of antiviral activity classes (“interactions”) for compounds and viruses, for which some of their interactions with other viruses or compounds are known, and for prediction of interaction profiles for new compounds. Both approaches achieved relatively good prediction quality for binary classification of individual interactions and compound profiles, as quantified by cross-validation and external validation receiver operating characteristic (ROC) score >0.9. Thus, even simple recommender systems may serve as an effective tool in antiviral drug discovery.
... 8,9 In order to enhance clinical order efficiency and consistency, previous studies have focused on designing order sets, which are the collections of orders grouped by specific clinical purposes such as a certain type of diagnoses or procedures. 1,2,10,11 Literature shows that well-developed order sets can save time in searching necessary and sufficient orders for patients and lower the variability in medical care. 1,11,12 However, order sets require high cost of development, maintenance and updating. ...
This study aims at developing SuperOrder, an order recommendation system for outpatient clinics. Using the electronic health record data available at midnight, SuperOrder predicts the order contents for each upcoming appointment on a daily basis. A two-level prediction framework is proposed. At the base-level, the predictions are produced by aggregating three machine learning methods. The meta-level predictions are generated by integrating the base-level predictions with the order co-occurrence network. We used the retrospective data between 1 April 2014 and 31 March 2015 in pulmonary clinics from five hospital sites within a large rural health care facility in Pennsylvania to test the feasibility. With a decrease of 6 per cent in the precision, the improvement of the recall at the meta-level is approximately 20 per cent from the base-level. This demonstrates that the proposed order co-occurrence network helps in increasing the performance of order predictions. The implementation will bring a more effective and efficient way to place outpatient orders.
... After every 6 trial sets, drug and adverse event dictionaries were updated, and rules were modified to improve the system. The model identified adverse events with 92% precision and recall NLP Drug safety To identify adverse drug effects from unstructured hospital discharge summaries Tang et al [90] The proposed model improved warfarin dosage when compared to the baseline (mean absolute error 0.394); reduced mean absolute error by 40 [92] Mean (SD) cumulative adherence based on the AI platform was 90.5% (7.5%). Plasma drug concentration levels indicated that adherence was 100% (15/15) and 50% (6/12) in the intervention and control groups, respectively Cell phone-based AI platform Drug safety To evaluate the use of a mobile AI platform on medication adherence in stroke patients on anticoagulation therapy Labovitz et al [93] All patients completed the task. ...
... One study used AI to monitor stroke patients and track their medication (anticoagulation) intake [93]. Several studies used AI to predict a medication that a patient could be consuming but was missing from their medication list or health records [92,94,97]. Another study used AI to review clinical notes and identify evidence of opioid abuse [98]. ...
BACKGROUND
Artificial intelligence (AI) provides opportunities to identify the health risks of patients and thus influence patient safety outcomes.
OBJECTIVE
The purpose of this systematic literature review was to identify and analyze quantitative studies utilizing or integrating AI to address and report clinical-level patient safety outcomes.
METHODS
We restricted our search to the PubMed, PubMed Central, and Web of Science databases to retrieve research articles published in English between January 2009 and August 2019. We focused on quantitative studies that reported positive, negative, or intermediate changes in patient safety outcomes using AI apps, specifically those based on machine-learning algorithms and natural language processing. Quantitative studies reporting only AI performance but not its influence on patient safety outcomes were excluded from further review.
RESULTS
We identified 53 eligible studies, which were summarized concerning their patient safety subcategories, the most frequently used AI, and reported performance metrics. Recognized safety subcategories were clinical alarms (n=9; mainly based on decision tree models), clinical reports (n=21; based on support vector machine models), and drug safety (n=23; mainly based on decision tree models). Analysis of these 53 studies also identified two essential findings: (1) the lack of a standardized benchmark and (2) heterogeneity in AI reporting.
CONCLUSIONS
This systematic review indicates that AI-enabled decision support systems, when implemented correctly, can aid in enhancing patient safety by improving error detection, patient stratification, and drug management. Future work is still needed for robust validation of these systems in prospective and real-world clinical environments to understand how well AI can predict safety outcomes in health care settings.
... [3][4][5][6][7][8][9][10][11] Unintentional discrepancies in allergy and medication information contribute to nearly half a million hospitalizations and cost the United States' (U.S.) health care system upwards of $1 billion annually. [12][13][14][15] According to the Institute of Healthcare Improvement, medication reconciliation (MR) is the "process of identifying the most accurate list of all medications a patient is taking… and using this list to provide correct medications for patients anywhere within the healthcare system." 16 Studies show that standardized MR programs reliably identify discrepancies and reduce medical error. ...
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.
... Number of articles per category after the final iterative review through the literature CategoryDescription of a need for or the creation of an algorithm to detect or a data model for…Adverse eventsThe potential for or the occurrence of unexpected and/or undesirable medical events such as drug allergies, drug side effects, falls, unexpected diseases, or other treatment-related injury Storage of data for medical fields or aspects of medical fields in a standard medical format (e.g., HL7, C-CDA, or an author-specific format) or mapping of data models of commonly used resources (e.g., Web sites or apps) to standard medical data formats for the purpose of EHR interoperability among other EHRs and external applicationsMedication list data capture More robust medication data storage (e.g., medications prescribed by other hospitals, medication and/or illicit drug abuse information), including additional drug metadata (e.g., adherence to medication schedule) that would allow clinicians to easily determine patients' medication status along with storage of patient medication information in medication list rather than free text 14[42][43][44][45][46][47][48][49][50][51][52][53][54]128 Patient preferences Storage of patient's desires for treatment, therapy, or lack thereof for health events such as end-of-life care, diseases, or AEs Note: The categories and their definition of data content described in the literature that could be used to expand the EHR. ...
Objective:
Clinical informatics researchers depend on the availability of high-quality data from the electronic health record (EHR) to design and implement new methods and systems for clinical practice and research. However, these data are frequently unavailable or present in a format that requires substantial revision. This article reports the results of a review of informatics literature published from 2010 to 2016 that addresses these issues by identifying categories of data content that might be included or revised in the EHR.
Materials and methods:
We used an iterative review process on 1,215 biomedical informatics research articles. We placed them into generic categories, reviewed and refined the categories, and then assigned additional articles, for a total of three iterations.
Results:
Our process identified eight categories of data content issues: Adverse Events, Clinician Cognitive Processes, Data Standards Creation and Data Communication, Genomics, Medication List Data Capture, Patient Preferences, Patient-reported Data, and Phenotyping.
Discussion:
These categories summarize discussions in biomedical informatics literature that concern data content issues restricting clinical informatics research. These barriers to research result from data that are either absent from the EHR or are inadequate (e.g., in narrative text form) for the downstream applications of the data. In light of these categories, we discuss changes to EHR data storage that should be considered in the redesign of EHRs, to promote continued innovation in clinical informatics.
Conclusion:
Based on published literature of clinical informaticians' reuse of EHR data, we characterize eight types of data content that, if included in the next generation of EHRs, would find immediate application in advanced informatics tools and techniques.
