A Tool to Retrieve Alert Dwell Time from a Homegrown Computerized Physician Order Entry (CPOE) System of an Academic Medical Center: An Exploratory Analysis

Alert dwell time, defined as the time elapsed from the generation of an interruptive alert to its closure, has rarely been used to describe the time required by clinicians to respond to interruptive alerts. Our study aimed to develop a tool to retrieve alert dwell times from a homegrown CPOE (computerized physician order entry) system, and to conduct exploratory analysis on the impact of various alert characteristics on alert dwell time. Additionally, we compared this impact between various professional groups. With these aims, a dominant window detector was developed using the Golang programming language and was implemented to collect all alert dwell times from the homegrown CPOE system of a 726-bed, Taiwanese academic medical center from December 2019 to February 2021. Overall, 3,737,697 interruptive alerts were collected. Correlation analysis was performed for alerts corresponding to the 100 most frequent alert categories. Our results showed that there was a negative correlation (ρ = −0.244, p = 0.015) between the number of alerts and alert dwell times. Alert dwell times were strongly correlated between different professional groups (physician vs. nurse, ρ = 0.739, p < 0.001). A tool that retrieves alert dwell times can provide important insights to hospitals attempting to improve clinical workflows.

Functional IT Complementarity and Hospital Performance in the United State: A Longitudinal Investigation

For healthcare practitioners and policymakers, one of the most challenging problems is understanding how to implement health information technology (HIT) applications in a way that yields the most positive impacts on quality and cost of care. We identify four clinical HIT functions which we label as order entry and management (OEM), decision support (DS), electronic clinical documentation (ECD), and results viewing (RV). We view OEM and DS as primary clinical functions and ECD and RV as support clinical functions. Our results show that no single combination of applications uniformly improves clinical and experiential quality and reduces cost for all hospitals. Thus, managers must assess which HIT interactions improve which performance metric under which conditions. Our results suggest that synergies can be realized when these systems are implemented simultaneously. Additionally, synergies can occur when support HIT is implemented before primary HIT and irrespective of the order in which primary HITs are implemented. Practitioners should also be aware that the synergistic effects of HITs and their impact on cost and quality are different for chronic and acute diseases. Our key message to top managers is to prioritize different combinations of HIT contingent on the performance variables they are targeting for their hospitals but also to realize that technology may not impact all outcomes.

Application of the Failure Mode and Effects Analysis (FMEA) to identify vulnerabilities and opportunities for improvement prior to implementing a computerized prescription order entry (CPOE) system in a university hospital oncology clinic

Introduction Prior to implementing a new computerized prescription order entry (CPOE) application, the potential risks associated with this system were assessed and compared to those of paper-based prescriptions. The goal of this study is to identify the vulnerabilities of the CPOE process in order to adapt its design and prevent these potential risks. Methods and materials Failure mode and effects analysis (FMEA) was used as a prospective risk-management technique to evaluate the chemotherapy medication process in a university hospital oncology clinic. A multidisciplinary team assessed the process and compared the critical steps of a newly developed CPOE application versus paper-based prescriptions. The potential severity, occurrence and detectability were assessed prior to the implementation of the CPOE application in the clinical setting. Results The FMEA led to the identification of 24 process steps that could theoretically be vulnerable, therefore called failure modes. These failure modes were grouped into four categories of potential risk factors: prescription writing, patient scheduling, treatment dispensing and patient follow-up. Criticality scores were calculated and compared for both strategies. Three failure modes were prioritized and led to modification of the CPOE design. Overall, the CPOE pathway showed a potential risk reduction of 51% compared to paper-based prescriptions. Conclusion FMEA was found to be a useful approach to identify potential risks in the chemotherapy medication process using either CPOE or paper-based prescriptions. The e-prescription mode was estimated to result in less risk than the traditional paper mode.

A multifaceted approach in leveraging electronic health record tools for safe inpatient use of concentrated U-500 insulin

Disclaimer In an effort to expedite the publication of articles, AJHP is posting manuscripts online as soon as possible after acceptance. Accepted manuscripts have been peer-reviewed and copyedited, but are posted online before technical formatting and author proofing. These manuscripts are not the final version of record and will be replaced with the final article (formatted per AJHP style and proofed by the authors) at a later time. Purpose The Institute for Safe Medication Practices classifies subcutaneous insulin as a high-risk medication. Concentrated U-500 insulin carries additional risks in comparison to conventional U-100 insulin, as the 5-fold more concentrated nature of this product, limitations to insulin pen dosing, and various devices for dose measurement may lead to miscommunication of patient-reported doses, resulting in downstream errors in ordering, verification, or administration. We describe a multifaceted approach to leveraging technical tools within the electronic health record (EHR) for U-500 insulin use. Summary At Cleveland Clinic, the U-500 insulin use process evolved in a number of phases using EHR tools. Phase 1 included new clinical decision support and documentation tools during order entry, including a customized alert that fired during order entry recommending that the prescriber order a consult with endocrinology and requiring the prescriber to provide the patient’s home insulin measuring device and the source of the patient’s reported home dose. In order verification, a customized alert fired directing the pharmacist to contact the patient or patient’s nurse and validate the information provided by the prescriber. Phase 2 involved transitioning dispensing of patient-specific doses from tuberculin syringes to U-500 insulin syringes. Phase 3 transitioned to use of U-500 insulin pens and included automatic dose rounding of ordered doses down to the nearest 5 units, and an additional customized pharmacist alert intended for cost conservation was added to fire if the patient had a recent administration of U-500 insulin documented, directing the pharmacist to determine whether the nurse needed a new pen dispensed. Conclusion Cleveland Clinic successfully implemented customized tools and processes within the EHR pertaining to the prescribing, verification, dispensing, and administration of U-500 insulin.

Impact of artificial intelligence in healthcare

Artificial intelligence (AI) is prepared to become a transformational force in healthcare. From chronic diseases and cancer to radiology and risk assessment, there are nearly endless opportunities to influence technology to install more precise, efficient, and impactful interventions at exactly the right moment in a patient’s care.AI offers a number of benefits over traditional analytics and clinical decision-making techniques. Learning algorithms can become more specific and accurate as they interact with training data, allowing humans to gain unique insights into diagnostics, care processes, treatment variability, and patient outcomes (1). Using computers to communicate is not a new idea by any means, but creating direct interfaces between technology and the human mind without the need for keyboards, mice, and monitors is a cutting-edge area of research that has significant applications for some patients. Neurological diseases and trauma to the nervous system can take away some patients’ abilities to speak, move, and interact meaningfully with people and their environments. Brain-computer interfaces (BCIs) backed by artificial intelligence could restore those fundamental experiences to those who feared them lost forever. Brain-computer interfaces could drastically improve quality of life for patients with ALS, strokes, or locked-in syndrome, as well as the 500,000 people worldwide who experience spinal cord injuries every year (2). Radiological images obtained by MRI machines, CT scanners, and x-rays offer non-invasive visibility into the inner workings of the human body. But many diagnostic processes still rely on physical tissue samples obtained through biopsies, which carry risks including the potential for infection. AI will enable the next generation of radiology tools that are accurate and detailed enough to replace the need for tissue samples in some cases, experts predict. Diagnostic imaging team with the surgeon and the pathologist can be brought together which will be a big challenge (3). Succeeding in the pursuit may allow clinicians to develop a more accurate understanding of how tumours behave as a whole instead of basing treatment decisions on the properties of a small segment of the malignancy. Providers may also be able to better define the aggressiveness of cancers and target treatments more appropriately. Artificial intelligence is helping to enable “virtual biopsies” and advance the innovative field of radiomics, which focuses on harnessing image-based algorithms to characterize the phenotypes and genetic properties of tumours (1). Shortages of trained healthcare providers, including ultrasound technicians and radiologists can significantly limit access to life-saving care in developing nations around the world. AI could help mitigate the impacts of this severe deficit of qualified clinical staff by taking over some of the diagnostic duties typically allocated to humans (4). For example, AI imaging tools can screen chest x-rays for signs of tuberculosis, often achieving a level of accuracy comparable to humans. This capability could be deployed through an app available to providers in low-resource areas, reducing the need for a trained diagnostic radiologist on site. However, algorithm developers must be careful to account for the fact that different ethnic groups or residents of different regions may have unique physiologies and environmental factors that will influence the presentation of disease.The course of a disease and population affected by the disease may look very different in India than in the US. As these algorithms are being developed, it is very important to make sure that the data represents a diversity of disease presentations and populations. we cannot just develop an algorithm based on a single population and expect it to work as well on others (1). Electronic health records (EHRs) have played an instrumental role in the healthcare industry’s journey towards digitalization, but the switch has brought myriad problems associated with cognitive overload, endless documentation, and user burnout. EHR developers are now using AI to create more intuitive interfaces and automate some of the routine processes that consume so much of a user’s time. Users spend the majority of their time on three tasks: clinical documentation, order entry, and sorting through the in-basket (5). Voice recognition and dictation are helping to improve the clinical documentation process, but natural language processing (NLP) tools might not be going far enough. Video recording a clinical encounter would be helpful while using AI and machine learning to index those videos for future information retrieval. And it would be just like in the home, where we are using Siri and Alexa. The future will bring virtual assistants to the bedside for clinicians to use with embedded intelligence for order entry(5). AI may also help to process routine requests from the inbox, like

Development of a Minimum Data Set for Drug Module of Computerized Physician Order Entry System

Introduction: One way to reduce medication errors in the cardiovascular settings is to electronically prescribe medication through the computerized physician order entry system (CPOE). Improper design and non-compliance with users' needs are obstacles to implementing this system. Therefore, it is necessary to consider the standard minimum data set (MDS) of this system in order to meet the basic needs of its users. The aim of this study was to introduce MDS in the cardiovascular CPOE drug system to standardize data items as well as to facilitate data sharing and integration with other systems.Material and Methods: This study was a survey study conducted in 1399 in Iran. The study population was all cardiologists in Iran. The data collection tool was a researcher-made questionnaire consisting of 33 questions. Data were analyzed in SPSS-24 using descriptive statistics.Results: A total of 31 cardiologists participated in this study. The participants identified 19 of the 25 drug data items as essential for drug MDS. Five data items (Medication name, Medication dosage, Medication frequency, Medication start date and Patient medication history) were considered essential by more than 90% of the participants.Conclusion: The results of this study identified drug MDS for the cardiovascular CPOE system. The results of this study can be a model for CPOE system designers to develop new systems or upgrade existing systems.

The impact of a computerized physician order entry system implementation on 20 different criteria of medication documentation—a before-and-after study

Background The medication process is complex and error-prone. To avoid medication errors, a medication order should fulfil certain criteria, such as good readability and comprehensiveness. In this context, a computerized physician order entry (CPOE) system can be helpful. This study aims to investigate the distinct effects on the quality of prescription documentation of a CPOE system implemented on general wards in a large tertiary care hospital. Methods In a retrospective analysis, the prescriptions of two groups of 160 patients each were evaluated, with data collected before and after the introduction of a CPOE system. According to nationally available recommendations on prescription documentation, it was assessed whether each prescription fulfilled the established 20 criteria for a safe, complete, and actionable prescription. The resulting fulfilment scores (prescription-Fscores) were compared between the pre-implementation and the post-implementation group and a multivariable analysis was performed to identify the effects of further covariates, i.e., the prescription category, the ward, and the number of concurrently prescribed drugs. Additionally, the fulfilment of the 20 criteria was assessed at an individual criterion-level (denoted criteria-Fscores). Results The overall mean prescription-Fscore increased from 57.4% ± 12.0% (n = 1850 prescriptions) before to 89.8% ± 7.2% (n = 1592 prescriptions) after the implementation (p < 0.001). At the level of individual criteria, criteria-Fscores significantly improved in most criteria (n = 14), with 6 criteria reaching a total score of 100% after CPOE implementation. Four criteria showed no statistically significant difference and in two criteria, criteria-Fscores deteriorated significantly. A multivariable analysis confirmed the large impact of the CPOE implementation on prescription-Fscores which was consistent when adjusting for the confounding potential of further covariates. Conclusions While the quality of prescription documentation generally increases with implementation of a CPOE system, certain criteria are difficult to fulfil even with the help of a CPOE system. This highlights the need to accompany a CPOE implementation with a thorough evaluation that can provide important information on possible improvements of the software, training needs of prescribers, or the necessity of modifying the underlying clinical processes.