Anatomy of an anesthesia information management system

Predicting Hypoxia Using Machine Learning: Systematic Review

Background

Hypoxia is an important risk factor and indicator for the declining health of inpatients. Predicting future hypoxic events using machine learning is a prospective area of study to facilitate time-critical interventions to counter patient health deterioration.

Objective

This systematic review aims to summarize and compare previous efforts to predict hypoxic events in the hospital setting using machine learning with respect to their methodology, predictive performance, and assessed population.

Methods

A systematic literature search was performed using Web of Science, Ovid with Embase and MEDLINE, and Google Scholar. Studies that investigated hypoxia or hypoxemia of hospitalized patients using machine learning models were considered. Risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool.

Results

After screening, a total of 12 papers were eligible for analysis, from which 32 models were extracted. The included studies showed a variety of population, methodology, and outcome definition. Comparability was further limited due to unclear or high risk of bias for most studies (10/12, 83%). The overall predictive performance ranged from moderate to high. Based on classification metrics, deep learning models performed similar to or outperformed conventional machine learning models within the same studies. Models using only prior peripheral oxygen saturation as a clinical variable showed better performance than models based on multiple variables, with most of these studies (2/3, 67%) using a long short-term memory algorithm.

Conclusions

Machine learning models provide the potential to accurately predict the occurrence of hypoxic events based on retrospective data. The heterogeneity of the studies and limited generalizability of their results highlight the need for further validation studies to assess their predictive performance.

Improving Anesthesia Start Time Documentation Through a Departmental Education Initiative at Yale New Haven Hospital, New Haven, United States

Background Reimbursement for anesthetic services in the United States utilizes a formula that incorporates procedural and patient factors with total anesthesia time. According to the Centers for Medicare & Medicaid Services and the American Society of Anesthesiologists, the period of billable time starts when the anesthesia practitioner assumes care of the patient and may include transport to the operating room from the preoperative holding area. In this report on a quality improvement effort, we implemented a departmental education initiative aimed at improving the accuracy of anesthesia start-time documentation. Methods Utilizing de-identified, internal data on surgical procedures at Yale New Haven Hospital (YNHH), New Haven, United States, the difference between documented anesthesia start and patient in-room time was determined for all cases. Those with a difference between 0-1 minute were assumed "likely underbilled," and the total revenue lost for these cases was estimated using a weighted average of institutional reimbursement per unit of time. A monthly, department-wide educational email was then introduced to inform practitioners about the guidelines around start-time documentation, and the percentage of "likely underbilled" cases and lost revenue estimates trended over a one-year period. Results Baseline data in December 2020 showed that of the 6,877 total surgical cases requiring anesthesia at YNHH, 55.1% (N=3,790) had an anesthesia start to in-room time of 0-1 minute, which were considered "likely underbilled." The average start-to-in-room time for properly recorded cases (44.9%, N=3,087) was 4.42 minutes. The baseline revenue lost in December 2020 for underbilled cases was estimated at $52,302. Over the one-year quality improvement initiative, the proportion of underbilled cases showed a downward trend, decreasing to 29.2% of total cases by November 2021. The estimate of revenue lost due to underbilling also showed a downward trend, decreasing to $29,300 in November 2021. Conclusion This quality improvement study demonstrated that a relatively simple, department-wide educational email sent monthly correlated with an improvement in anesthesia start-time documentation accuracy and a reduction in estimated revenue lost to underbilling over a one-year period.

Anesthesiologists in the Ether: Technology and Telemedicine in Anesthesiology

A new frontier in veterinary anesthesia telehealth has begun. With the adoption of electronic anesthetic records and video, phone, and chat consultations, an anesthesiologist can be integrated into the care team of any patient, anywhere in the world. This article reviews the benefits of adopting an electronic anesthetic record system, and the ways that practitioners can incorporate a virtual anesthesiologist into their care team.

Opal: an implementation science tool for machine learning clinical decision support in anesthesia

Opal is the first published example of a full-stack platform infrastructure for an implementation science designed for ML in anesthesia that solves the problem of leveraging ML for clinical decision support. Users interact with a secure online Opal web application to select a desired operating room (OR) case cohort for data extraction, visualize datasets with built-in graphing techniques, and run in-client ML or extract data for external use. Opal was used to obtain data from 29,004 unique OR cases from a single academic institution for pre-operative prediction of post-operative acute kidney injury (AKI) based on creatinine KDIGO criteria using predictors which included pre-operative demographic, past medical history, medications, and flowsheet information. To demonstrate utility with unsupervised learning, Opal was also used to extract intra-operative flowsheet data from 2995 unique OR cases and patients were clustered using PCA analysis and k-means clustering. A gradient boosting machine model was developed using an 80/20 train to test ratio and yielded an area under the receiver operating curve (ROC-AUC) of 0.85 with 95% CI [0.80–0.90]. At the default probability decision threshold of 0.5, the model sensitivity was 0.9 and the specificity was 0.8. K-means clustering was performed to partition the cases into two clusters and for hypothesis generation of potential groups of outcomes related to intraoperative vitals. Opal’s design has created streamlined ML functionality for researchers and clinicians in the perioperative setting and opens the door for many future clinical applications, including data mining, clinical simulation, high-frequency prediction, and quality improvement.

An Environmental Scan of Anesthesia Information Management Systems in the American and Canadian Marketplace

Anesthesia Information Management Systems are specialized forms of electronic medical records used by anesthesiologists to automatically and reliably collect, store, and present perioperative patient data. There are no recent academic publications that outline the names and features of AIMS in the current American and Canadian marketplace. An environmental scan was performed to first identify existing AIMS in this marketplace, and then describe and compare these AIMS. We found 13 commercially available AIMS but were able to describe in detail the features and functionalities of only 10 of these systems, as three vendors did not participate in the study. While all AIMS have certain key features, other features and functionalities are only offered by some of the AIMS. Features less commonly offered included patient portals for pre-operative questionnaires, clinical decision support systems, and voice-to-text capability for documentation. The findings of this study can inform AIMS procurement efforts by enabling anesthesia departments to compare features across AIMS and find an AIMS whose features best fit their needs and priorities. Future studies are needed to describe the features and functionalities of these AIMS at a more granular level, and also assess the usability and costs of these systems.

The state of adoption of anesthesia information management systems in Canadian academic anesthesia departments: a survey

PURPOSE

Anesthesia information management systems (AIMS) are gradually replacing paper documentation of anesthesia care. This study sought to determine the current status of AIMS adoption and the level of health informatics expertise in Canadian academic anesthesia departments.

METHODS

Department heads or their designates of Canadian academic anesthesia departments were invited by e-mail to complete an online survey between September 2019 and February 2020. The survey elicited information on current AIMS or future plans for an AIMS installation, the number of department members dedicated to clinical informatics issues, the gross level of health informatics expertise at each department, perceived advantages of AIMS, and perceived disadvantages of and barriers to implementation of AIMS.

RESULTS

Of the 64 departments invited to participate, 63 (98.4%) completed the survey. Only 21 (33.3%) of the departments had AIMS. Of the 42 departments still charting on paper, 23 (54.8%) reported planning to install an AIMS within the next five years. Forty-six departments (73%) had at least one anesthesiologist tasked with dealing with AIMS or electronic health record issues. Most reported having no department members with extensive knowledge or formal training in health informatics. The top three perceived barriers and disadvantages to an AIMS installation were its initial cost, lack of funding, and a lack of technical support dedicated specifically to AIMS. The top three advantages departments wished to prioritize with AIMS were accurate clinical documentation, better data for quality improvement initiatives, and better data for research.

CONCLUSIONS

A majority of Canadian academic anesthesia departments are still using paper records, but this trend is expected to reverse in the next five years as more departments install an AIMS. Health informatics expertise is lacking in most of the departments, with a minority planning to support the training of future anesthesia informaticians.

The Use of Patient Digital Facial Images to Confirm Patient Identity in a Children's Hospital's Anesthesia Information Management System

INTRODUCTION

Patient identification errors, albeit rare, continue to occur despite the implementation of the Universal Protocol. Researchers at a tertiary care children's hospital hypothesized that introduction of a digital photograph to the preanesthesia checklist would reduce wrong-patient charting and near-miss events around the induction of anesthesia.

METHODS

In late 2014 a digital facial image obtained either on arrival to the preoperative preparation area or for inpatients, on admission to the hospital, was added to the initial verification screen (anesthesia sign-in) of the anesthesia information management system (AIMS). This verification process includes visual inspection of the patient's facial image and checking the patient's hospital ID bracelet for the patient's name, birthdate, and hospital number against the AIMS verification page. Wrong-patient charting and near-miss events were reviewed weekly by the electronic health record (EHR) perioperative team through analysis of AIMS records and through provider self-report to the institution's Anesthesia Incident Reporting System.

RESULTS

Between January 1, 2015, and July 1, 2018, 95,146 patients (42,255 females; 52,891 males) were anesthetized in the hospital with only one instance of charting on the wrong patient in the AIMS. A Wilson score interval would give a percentage of 0.001% (95% confidence interval: 0.0002%-0.006%). Therefore, we are 95% certain that the true rate of charting on the wrong patient is below 1 in 16,794 patients.

CONCLUSION

At the induction of anesthesia, the addition of a current digital facial image to the Universal Protocol may be useful in preventing misidentification and mischarting on the anesthetic record.

Anesthesia Information Management Systems: Evolution of the Paper Anesthetic Record to a Multisystem Electronic Medical Record Network That Streamlines Perioperative Care

Initially devised in the 1890s, the traditional anesthetic record comprises physiological changes, crucial anesthetic or surgical events, and medications administered during the perioperative period. The timely collection of quality data facilitates situational awareness and point-of-care clinical decision making. The burgeoning volume and complexity of data in conjunction with financial incentives and the push for improved clinical documentation by regulatory bodies have prompted the transition away from paper records. Anesthesia Information Management Systems (AIMS) are specialized electronic health record networks that allow the anesthesia record to interface with hospital clinical data repositories, resulting in improvements in quality of care, patient safety, operations management, reimbursement, and translational research. Like most new technological advances, adoption was slow at first due to the challenges of integrating complex systems into daily clinical practice, questions about return on investment, and medicolegal liability. Recent technological advances, coupled with government incentives, have allowed AIMS adoption to reach an acceleration phase among US academic medical centers; widespread utilization of AIMS by 84% of US academic medical centers is expected by 2018-2020. Adoption among nonacademic US and European medical centers still remains low; information concerning Asian countries is limited to literature describing only single-hospital center experiences.

A Technical Evaluation of Wireless Connectivity from Patient Monitors to an Anesthesia Information Management System During Intensive Care Unit Surgery

Surgical procedures performed at the bedside in the neonatal intensive care unit (NICU) at The Children's Hospital of Philadelphia were documented using paper anesthesia records in contrast to the operating rooms, where an anesthesia information management system (AIMS) was used for all cases. This was largely because of logistical problems related to connecting cables between the bedside monitors and our portable AIMS workstations. We implemented an AIMS for documentation in the NICU using wireless adapters to transmit data from bedside monitoring equipment to a portable AIMS workstation. Testing of the wireless AIMS during simulation in the presence of an electrosurgical generator showed no evidence of interference with data transmission. Thirty NICU surgical procedures were documented via the wireless AIMS. Two wireless cases exhibited brief periods of data loss; one case had an extended data gap because of adapter power failure. In comparison, in a control group of 30 surgical cases in which wired connections were used, there were no data gaps. The wireless AIMS provided a simple, unobtrusive, portable alternative to paper records for documenting anesthesia records during NICU bedside procedures.

A Narrative Review of Meaningful Use and Anesthesia Information Management Systems

The US federal government has enacted legislation for a federal incentive program for health care providers and hospitals to implement electronic health records. The primary goal of the Meaningful Use (MU) program is to drive adoption of electronic health records nationwide and set the stage to monitor and guide efforts to improve population health and outcomes. The MU program provides incentives for the adoption and use of electronic health record technology and, in some cases, penalties for hospitals or providers not using the technology. The MU program is administrated by the Department of Health and Human Services and is divided into 3 stages that include specific reporting and compliance metrics. The rationale is that increased use of electronic health records will improve the process of delivering care at the individual level by improving the communication and allow for tracking population health and quality improvement metrics at a national level in the long run. The goal of this narrative review is to describe the MU program as it applies to anesthesiologists in the United States. This narrative review will discuss how anesthesiologists can meet the eligible provider reporting criteria of MU by applying anesthesia information management systems (AIMS) in various contexts in the United States. Subsequently, AIMS will be described in the context of MU criteria. This narrative literature review also will evaluate the evidence supporting the electronic health record technology in the operating room, including AIMS, independent of certification requirements for the electronic health record technology under MU in the United States.

Implementation of an Anesthesia Information Management System in an Ambulatory Surgery Center

Anesthesia information management systems (AIMS) are increasingly being implemented throughout the United States. However, little information exists on the implementation process for AIMS within ambulatory surgery centers (ASC). The objectives of this descriptive study are to document: 1) the phases of implementation of an AIMS at an ASC; and 2) lessons learnt from a socio-technical perspective. The ASC, within the Veterans Health Administration (VHA), has hosted an AIMS since 2008. As a quality improvement effort, we implemented a new version of the AIMS. This new version involved fundamental software changes to enhance clinical care such as real-time importing of laboratory data and total hardware exchange. The pre-implementation phase involved coordinated preparation over six months between multiple informatics teams along with local leadership. During this time, we conducted component, integration, and validation testing to ensure correct data flow from medical devices to AIMS and centralized databases. The implementation phase occurred in September 2014 over three days and was successful. Over the next several months, during post-implementation phase, we addressed residual items like latency of the application. Important lessons learnt from the implementation included the utility of partnering early with executive leadership; ensuring end user acceptance of new clinical workflow; continuous testing of data flow; use of a staged rollout; and providing additional personnel throughout implementation. Implementation of an AIMS at an ASC can utilize methods developed for large hospitals. However, issues unique to an ASC such as limited number of support personnel and distinctive workflows must be considered.

A case study evaluation of a Critical Care Information System adoption using the socio-technical and fit approach

BACKGROUND

Clinical information systems have long been used in intensive care units but reports on their adoption and benefits are limited. This study evaluated a Critical Care Information System implementation.

METHODS

A case study summative evaluation was conducted, employing observation, interview, and document analysis in operating theatres and 16-bed adult intensive care units in a 400-bed Malaysian tertiary referral centre from the perspectives of users (nurses and physicians), management, and information technology staff. System implementation, factors influencing adoption, fit between these factors, and the impact of the Critical Care Information System were evaluated after eight months of operation.

RESULTS

Positive influences on system adoption were associated with technical factors, including system ease of use, usefulness, and information relevancy; human factors, particularly user attitude; and organisational factors, namely clinical process-technology alignment and champions. Organisational factors such as planning, project management, training, technology support, turnover rate, clinical workload, and communication were barriers to system implementation and use. Recommendations to improve the current system problems were discussed. Most nursing staff positively perceived the system's reduction of documentation and data access time, giving them more time with patients. System acceptance varied among doctors. System use also had positive impacts on timesaving, data quality, and clinical workflow.

CONCLUSIONS

Critical Care Information Systems is crucial and has great potentials in enhancing and delivering critical care. However, the case study findings showed that the system faced complex challenges and was underutilised despite its potential. The role of socio-technical factors and their fit in realizing the potential of Critical Care Information Systems requires continuous, in-depth evaluation and stakeholder understanding and acknowledgement. The comprehensive and specific evaluation measures of the Human-Organisation-Technology Fit framework can flexibly evaluate Critical Care Information Systems.

Brief review: Adoption of electronic medical records to enhance acute pain management

PURPOSE

The purpose of this paper is to examine physician barriers to adopting electronic medical records (EMRs) as well as anesthesiologists' experiences with the EMRs used by the acute pain management service at two tertiary care centres in Canada.

SOURCE

We first review the recent literature to determine if physician barriers to adoption are changing given the exponential growth of information technology and the evolving healthcare environment. We next report on institutional experience from two academic health sciences centres regarding the challenges they encountered over the past ten years in developing and implementing an electronic medical record system for acute pain management.

PRINCIPAL FINDINGS

The key identified barriers to adoption of EMRs are financial, technological, and time constraints. These barriers are identical to those reported in a systematic review performed prior to 2009 and remain significant factors challenging implementation. These challenges were encountered during our institution's process of adopting EMRs specific to acute pain management. In addition, our findings emphasize the importance of physician participation in the development and implementation stages of EMRs in order to incorporate their feedback and ensure the EMR system is in keeping with their workflow.

CONCLUSIONS

Use of EMRs will inevitably become the standard of care; however, many barriers persist to impede their implementation and adoption. These challenges to implementation can be facilitated by a corporate strategy for change that acknowledges the barriers and provides the resources for implementation. Adoption will facilitate benefits in communication, patient management, research, and improved patient safety.

Are anesthesia start and end times randomly distributed? The influence of electronic records

STUDY OBJECTIVE

To perform a frequency analysis of start minute digits (SMD) and end minute digits (EMD) taken from the electronic, computer-assisted, and manual anesthesia billing-record systems.

DESIGN

Retrospective cross-sectional review.

SETTING

University medical center.

MEASUREMENTS

This cross-sectional review was conducted on billing records from a single healthcare institution over a 15-month period. A total of 30,738 cases were analyzed. For each record, the start time and end time were recorded. Distributions of SMD and EMD were tested against the null hypothesis of a frequency distribution equivalently spread between zero and nine.

MAIN RESULTS

SMD and EMD aggregate distributions each differed from equivalency (P < 0.0001). When stratified by type of anesthetic record, no differences were found between the recorded and expected equivalent distribution patterns for electronic anesthesia records for start minute (P < 0.98) or end minute (P < 0.55). Manual and computer-assisted records maintained nonequivalent distribution patterns for SMD and EMD (P < 0.0001 for each comparison). Comparison of cumulative distributions between SMD and EMD distributions suggested a significant difference between the two patterns (P < 0.0001).

CONCLUSION

An electronic anesthesia record system, with automated time capture of events verified by the user, produces a more unified distribution of billing times than do more traditional methods of entering billing times.

An observational study of the accuracy and completeness of an anesthesia information management system: recommendations for documentation system changes

Anesthesia information management systems must often be tailored to fit the environment in which they are implemented. Extensive customization necessitates that systems be analyzed for both accuracy and completeness of documentation design to ensure that the final record is a true representation of practice. The purpose of this study was to determine the accuracy of a recently installed system in the capture of key perianesthesia data. This study used an observational design and was conducted using a convenience sample of nurse anesthetists. Observational data of the nurse anesthetists'delivery of anesthesia care were collected using a touch-screen tablet computer utilizing an Access database customized observational data collection tool. A questionnaire was also administered to these nurse anesthetists to assess perceived accuracy, completeness, and satisfaction with the electronic documentation system. The major sources of data not documented in the system were anesthesiologist presence (20%) and placement of intravenous lines (20%). The major sources of inaccuracies in documentation were gas flow rates (45%), medication administration times (30%), and documentation of neuromuscular function testing (20%)-all of the sources of inaccuracies were related to the use of charting templates that were not altered to reflect the actual interventions performed.

Evaluation of the clinical process in a critical care information system using the Lean method: a case study

Background

There are numerous applications for Health Information Systems (HIS) that support specific tasks in the clinical workflow. The Lean method has been used increasingly to optimize clinical workflows, by removing waste and shortening the delivery cycle time. There are a limited number of studies on Lean applications related to HIS. Therefore, we applied the Lean method to evaluate the clinical processes related to HIS, in order to evaluate its efficiency in removing waste and optimizing the process flow. This paper presents the evaluation findings of these clinical processes, with regards to a critical care information system (CCIS), known as IntelliVue Clinical Information Portfolio (ICIP), and recommends solutions to the problems that were identified during the study.

Methods

We conducted a case study under actual clinical settings, to investigate how the Lean method can be used to improve the clinical process. We used observations, interviews, and document analysis, to achieve our stated goal. We also applied two tools from the Lean methodology, namely the Value Stream Mapping and the A3 problem-solving tools. We used eVSM software to plot the Value Stream Map and A3 reports.

Results

We identified a number of problems related to inefficiency and waste in the clinical process, and proposed an improved process model.

Conclusions

The case study findings show that the Value Stream Mapping and the A3 reports can be used as tools to identify waste and integrate the process steps more efficiently. We also proposed a standardized and improved clinical process model and suggested an integrated information system that combines database and software applications to reduce waste and data redundancy.