CODE STROKE ALERT-Concept and Development of a Novel Open-Source Platform to Streamline Acute Stroke Management

Development of a machine learning-based real-time location system to streamline acute endovascular intervention in acute stroke: a proof-of-concept study

BACKGROUND

Delivery of acute stroke endovascular intervention can be challenging because it requires complex coordination of patient and staff across many different locations. In this proof-of-concept paper we (a) examine whether WiFi fingerprinting is a feasible machine learning (ML)-based real-time location system (RTLS) technology that can provide accurate real-time location information within a hospital setting, and (b) hypothesize its potential application in streamlining acute stroke endovascular intervention.

METHODS

We conducted our study in a comprehensive stroke care unit in Melbourne, Australia that offers a 24-hour mechanical thrombectomy service. ML algorithms including K-nearest neighbors, decision tree, random forest, support vector machine and ensemble models were trained and tested on a public WiFi dataset and the study hospital WiFi dataset. The hospital dataset was collected using the WiFi explorer software (version 3.0.2) on a MacBook Pro (AirPort Extreme, Broadcom BCM43x×1.0). Data analysis was implemented in the Python programming environment using the scikit-learn package. The primary statistical measure for algorithm performance was the accuracy of location prediction.

RESULTS

ML-based WiFi fingerprinting can accurately predict the different hospital zones relevant in the acute endovascular intervention workflow such as emergency department, CT room and angiography suite. The most accurate algorithms were random forest and support vector machine, both of which were 98% accurate. The algorithms remain robust when new data points, which were distinct from the training dataset, were tested.

CONCLUSIONS

ML-based RTLS technology using WiFi fingerprinting has the potential to streamline delivery of acute stroke endovascular intervention by efficiently tracking patient and staff movement during stroke calls.

Analysis of a Novel Inpatient Acute Limb Ischemia Alert System

OBJECTIVES

Acute limb ischemia (ALI) is a surgical emergency that generally develops in the outpatient setting. Hospitalized patients are also at risk for acute limb ischemia, but their presentation may be atypical or altered by medical therapy. Our institution developed an alert system to facilitate the prompt recognition and treatment of ALI that occurs in the inpatient population. We aimed to evaluate the usage of the system after the first 2 years of operation.

METHODS

All ALI alerts from October 2017 to December 2019 were collected from paging records and analyzed for location, timing, and the need for intervention. Alerts undergoing vascular intervention were classified as urgent (within 8 hours) or delayed (after 8 hr). Time and location data were evaluated to determine patterns of usage and true-positive rate of the system.

RESULTS

From October 2017 to December 2019, there were 237 ALI alerts obtained from paging records containing time and location information for the alert. More alerts originated from ICUs relative to non-ICU floors (68% vs. 33%, P< 0.001), however a greater proportion of non-ICU floor alerts required intervention compared to ICU alerts (32.0% vs. 5.1%, P < .0001). The highest number of ALI alerts were from the Medical ICU (MRICU) (45.9%) and medical/surgical floors (33.3%), followed by Surgical ICU (20.2%). Alerts were more common within 3 hr of morning and evening nursing shift changes (47.3%, P < 0.001). From the 237 total alerts, the patient was able to be identified retrospectively in 186 cases, and of these 27 resulted in operative interventions (14.5%, positive predictive value), with 11 patients (40.7%) requiring urgent intervention with a median time to intervention of 3.5 hr (range 2.2-4.8), and 16 (59%) alerts undergoing a delayed intervention at a mean of 3 days (range 2-4). A total of 73 (39.2%) alert patients died during their admission, of which 65 (89.0%) were in an ICU, and no deaths were directly related to ALI. The median time to death was 2 days (range 0-95 days), and in 22 cases death occurred <24 hr from time of alert.

CONCLUSION

Our novel hospital-wide ALI alert system demonstrates a 14.5% positive predictive value for ischemia that resulted in an intervention. Alerts were more likely to originate from the ICU setting and during nursing shift changes. Alerts originating from non-ICU floors were 5 times more likely to undergo surgical intervention for ALI. Further analysis is required to assess the effect of this system on patient safety, outcome, and allocation of institutional resources.

Meeting Proceedings for SCI 2020: Launching a Decade of Disruption in Spinal Cord Injury Research

The spinal cord injury (SCI) research community has experienced great advances in discovery research, technology development, and promising clinical interventions in the past decade. To build upon these advances and maximize the benefit to persons with SCI, the National Institutes of Health (NIH) hosted a conference February 12-13, 2019 titled "SCI 2020: Launching a Decade of Disruption in Spinal Cord Injury Research." The purpose of the conference was to bring together a broad range of stakeholders, including researchers, clinicians and healthcare professionals, persons with SCI, industry partners, regulators, and funding agency representatives to break down existing communication silos. Invited speakers were asked to summarize the state of the science, assess areas of technological and community readiness, and build collaborations that could change the trajectory of research and clinical options for people with SCI. In this report, we summarize the state of the science in each of five key domains and identify the gaps in the scientific literature that need to be addressed to move the field forward.

Starter Kit for Geotagging and Geovisualization in Health Care: Resource Paper

BACKGROUND

Geotagging is the process of attaching geospatial tags to various media data types. In health care, the goal of geotagging is to gain a better understanding of health-related questions applied to populations. Although there has been a prevalence of geographic information in public health, in order to effectively use and expand geotagging across health care there is a requirement to understand other factors such as the disposition, standardization, data sources, technologies, and limitations.

OBJECTIVE

The objective of this document is to serve as a resource for new researchers in the field. This report aims to be comprehensive but easy for beginners to understand and adopt in practice. The optimal geocodes, their sources, and a rationale for use are suggested. Geotagging's issues and limitations are also discussed.

METHODS

A comprehensive review of technical instructions and articles was conducted to evaluate guidelines for geotagging, and online resources were curated to support the implementation of geotagging practices. Summary tables were developed to describe the available geotagging resources (free and for fee) that can be leveraged by researchers and quality improvement personnel to effectively perform geospatial analyses primarily targeting US health care.

RESULTS

This paper demonstrated steps to develop an initial geotagging and geovisualization project with clear structure and instructions. The geotagging resources were summarized. These resources are essential for geotagging health care projects. The discussion section provides better understanding of geotagging's limitations and suggests suitable way to approach it.

CONCLUSIONS

We explain how geotagging can be leveraged in health care and offer the necessary initial resources to obtain geocodes, adjustment data, and health-related measures. The resources outlined in this paper can support an individual and/or organization in initiating a geotagging health care project.

Practical Use of a Communication Application on Mobile Devices by Our Stroke Team

Objective

To describe our 1-year experience of the practical use of a mobile communication application by our stroke team.

Methods

The mobile Join application (Allm Inc., Tokyo, Japan) was introduced into our stroke team for the purpose of immediate sharing of the patient information. We analyzed the usage situation for 1 year after the introduction of Join, particularly its efficacy in improving the door-to-puncture time (D2P) for thrombectomy cases, and reported our inter-hospital collaboration with the use of Join.

Results

The total number of events notified by Join was 337, and they included acute stroke potentially leading to reperfusion therapy in 23% (76 events), head trauma in 14%, brain hemorrhage in 12%, other infarction in 10%, subarachnoid hemorrhage in 8%, and the others in 34%. The information of the patients was shared among the team members before arrival to our hospital in 42% of acute stroke cases. Of 31 patients undergoing mechanical thrombectomy, the median interval between arrival and groin puncture for the directly transported patients with/without pre-hospital information was 77.5 min/87 min, respectively, whereas that of the patients transferred from primary hospitals with/without pre-hospital information was 19 min/71 min (p <0.0001), respectively, demonstrating the efficacy of information sharing in advance through Join in improving the timing of endovascular therapy. For inter-hospital collaboration using the telestroke system, we concluded the partnership agreement with three local primary hospitals by communication via Join at a reasonable cost.

Conclusion

Active and effective utilization of the mobile Join application for communication by our stroke team was demonstrated, and it is expected to promote inter-hospital collaboration in stroke treatment.