MedStatStudio Logo

MedStatStudio Projects

This is a sample of some MedStatStudio projects, both current and past.

Project List

A pilot study on the use of a computerized surge capacity simulation exercise in a low resource environment: an evaluative tool for hospital preparedness and a training tool for students attending a course in emergency management in low resource environments.
Automatic for the People
Pediatric Disaster Medicine
Band on the Run
A high influx of patients during a mass-casualty incident (MCI) may disrupt patient flow in an already overcrowded emergency department (ED) that is functioning beyond its operating capacity. This pilot study examined the impact of a two-step ED triage model using Simple Triage and Rapid Treatment (START) for pre-triage, followed by triage with the Canadian Triage and Acuity Scale (CTAS), on patient flow during a MCI simulation exercise
Surge capacity, or the ability to manage an extraordinary volume of patients, is fundamental for hospital management of mass-casualty incidents. However, quantification of surge capacity is difficult and no universal standard for its measurement has emerged, nor has a standardized statistical method been advocated. As mass-casualty incidents are rare, simulation may represent a viable alternative to measure surge capacity.
Confidence Builder
Disaster Medicine is an increasingly important part of medicine. Emergency Medicine residency programs have very high curriculum commitments, and adding Disaster Medicine training to this busy schedule can be difficult. Development of a short Disaster Medicine curriculum that is effective and enjoyable for the participants may be a valuable addition to Emergency Medicine residency training.
Training in practical aspects of disaster medicine is often impossible, and simulation may offer an educational opportunity superior to traditional didactic methods. We sought to determine whether exposure to an electronic simulation tool would improve the ability of medical students to manage a simulated disaster.
Flow Rider
The University of Alberta hospital emergency department provides care for approximately 150 adult patients each day. Emergency physician consists of seven shift of eight hours each. Informal observation suggests that the patient volume appears to be unequally distributed among the shifts, with certain shifts being routinely over-worked while others and under-worked. A statistical analysis of the patient volume seen during each shift may allow a more rational approach to shift scheduling.
Disaster management for emergency departments is often problematic. Although an organized system of command and control is often needed to manage the additional chaos brought on by the disaster, emergency physicians are often ill prepared for the situation. Although several current systems exist for command and control structure, including Incident Command System (ICS) and Hospital Incident Command System (HEICS), these systems are extremely comprehensive, and simulation physicians often comment that the systems are too complex. The Incident Command for Emergency Departments (ICED) system represents a novel instrument for emergency department management during disasters. This simplified incident command system consists of an introductory text, a simplified organizational chart with only thirteen color coded positions, job actions sheet for each position, and a set of only five forms.
Primary Care Assessment Triage Tool. During a disaster, hospitals may become quickly overrun with patients affected by minor injuries. In many cases, these minor injuries may be suitable for treatement in an outpatient primary care setting. The PCATT can be used to safely decide which patients may be suitable for triage directly to an outpatient primary care clinic.

MedStatStudio is seeking beta-testers for the PCATT app. Expected release data is March 30, 2017 for iOS, and June 30, 2017 for android. Please contact us to request beta-test version if you are interested in being a bete tester.

Facilitating patient flow through the emergency departmentcan sometimes be difficult administration task. The ability to predict which patients will require admission to the hospital can be an important factor in facilitating this flow. For instance, patients who are likely to require a short emergency department visit can often be assigned to low acuity areas. Conversely, patients who are likely to require admission to the hospital maybe assigned to areas with such resources as cardiac monitors, and nursing staff. The University of Alberta Hospital in Edmonton, Alberta, Canada is a large tertiary care hospital. The emergency department receives approximately 250 adult and pediatric patients each day. The goal of this study is to create an admission rule based on logistic regression to predict which patients are unlikely to require admission to the hospital and are thus suitable for inclusion in the rapid assessment zone. A logistic regression model was be fitted to the existing data with the null hypothesis of all coefficients equal to 0 was tested against the alternative hypothesis that some coefficients do not equal 0.
Assessment of validity and reliability of an Italian language global rating scale for simulation performance based on the Ottawa GRS
High fidelity simulation requires a high fidelity timer. SimChron provides a realistic time estimate for common Emergency Department and Intensive Care procedures including patient history and exam, intravenous lines, intubation, and more. SimChron provides a realistic estimate based on a mathematical model developed from data obtained in multiple emergency departments and intensive care units. Is your simulation time too short for realistic time delays? SimChron can be run at 2X or 4X speed. Need more time for junior learners to carefully learn procedures? SimChron can be run at 0.5X SimChron can also be useful for time delays in other simulations: table top scenarios, examinations, and disaster medicine live exercises. SimChron is exceptionally easy to use, allowing Sim Masters to focus their efforts on their simulation scenario while SimChron works independently in the background. A robust interface allows use in field simulations.
Although disaster medicine may be an important part of residency training in emergency medicine, many residency programs do not have a structured disaster medicine curriculum. Rather than simply designing a curriculum by consensus, use of the design for six sigma business process management technology – which emphasizes creation of product solution based on customer needs - may allow a more structured approach to curriculum design. The present study describes the use of design for six sigma to create a disaster medicine curriculum for emergency medicine residency training.
Use of the Kernel Support Vector Machine for Prediction of Need for Admission and Time for Disposition among Simulated Emergency Department Patients During Disaster Exercises
The state of Oklahoma, known for destructive tornados, has a native Spanish-speaking (NSS) population of approximately 180,241, of which 50% report being able to speak English “very well” (US Census Bureau). With almost 50% of these native Spanish-speaking persons being limited English proficient (LEP), their reception of tornado hazard communications may be restricted. This study conducted in northeast Oklahoma (USA) evaluates the association between native language and receiving tornado hazard communications.
Tweet Machine
During large-scale disasters, social media may give insight into the societal implications, concerns, and sentiments of the affected area. Twitter is a commonly used social media and may represent a valuable source of information. However, as tweets are generally formed of unstructured text, they can be difficult and time consuming to analyze. The present study compares the ability of several machine learning algorithms to classify tweets from the 2012 Emilia-Romagna earthquake into meaningful categories. Machine learning was performed using three algorithms: k-nearest neighbors (KNN), kernel support vector machine using a term-document matrix (KSVM), and string kernel support vector machine (SKSVM). Accuracy of machine learning classification was compared to that of a group of three skilled reviewers.
To compare accuracy of a computer simulation in predicting patient flow during a mass casualty incident with that of a real-time virtual live exercise (VLE), 136 simulated victims of a mass casualty incident, the database, was used as input into a computer simulation which was developed using the SimProcess (CACI Products, San Diego CA) platform to represent the Emergency Department of the University of Alberta Hospital. The VLE was performed using a training version of the hospital's Emergency Department Information System (HASS/iSoft, Branbury, UK). Prospective data collection was performed to compare the results of the computer simulation to that of the VLE.