New System Simplifies Emergency Patient Transfers
|
By HospiMedica International staff writers Posted on 15 Apr 2015 |

Image: Ronald Cohen, MD, and Brandon Bond (Photo courtesy of Norbert von der Groeben/ Stanford).
A new electronic medical record (EMR) system helps make patient transport to other facilities safer and more efficient in the event of a major crisis, such as an earthquake or power outage.
Developed by researchers at Stanford University (CA, USA) the triage by resource allocation for inpatients (TRAIN) program helps determine what vehicles and equipment are necessary for continuous patient care during a crisis event, as well as simplifying communicating patients’ needs to other hospitals or command centers coordinating transfers. Using the system, caregivers have prompt access to a fully automated report that categorizes patients in terms of their specific needs, such as what medication they receive, whether they are on ventilators, if they need intravenous (IV) lines, or whether they require an intensive care unit (ICU) bed.
Under TRAIN, all patients are assigned a color. For example, patients that need specialized transport, such as an ambulance or military vehicle, in addition to life-support equipment, such as ventilators and multiple intravenous drips for medication, can be categorized instantly with a single word: red. In comparison, patients marked with blue tags are considered stable and can be transported in a car or bus, without any specialized equipment. TRAIN thus allows care teams to communicate the medical needs of the specific patient, as well as the severity of his or her condition.
“We can see exactly what resources are needed for each patient at all times. Should we have to evacuate, which we hope we never have to do, TRAIN puts us far ahead in terms of keeping our patients safe during an incident,” said Brandon Bond, director of the office of emergency management for the hospitals at Stanford. “We can see exactly what resources are needed for each patient at all times.”
“Once we had the algorithm, we knew our electronic medical record could easily calculate the TRAIN classification. Most importantly, the calculation could be done in an instant, without any additional work from doctors or nurses,” said Ronald Cohen, MD, clinical professor of neonatal and developmental medicine at Stanford school of medicine. “The computer system automatically categorizes patients based on their needs, and that report is always on hand. This would take hours to do manually, but it’s now available instantly, 24 hours a day. It’s an extremely valuable tool that hopefully we’ll never need.”
TRAIN is based on the Epic (Verona, WI, USA) EMR, a fully integrated health care software platform that allows physicians and nurses to record the condition of every patient, with constant updates in real time.
Related Links:
Stanford University
Epic
Developed by researchers at Stanford University (CA, USA) the triage by resource allocation for inpatients (TRAIN) program helps determine what vehicles and equipment are necessary for continuous patient care during a crisis event, as well as simplifying communicating patients’ needs to other hospitals or command centers coordinating transfers. Using the system, caregivers have prompt access to a fully automated report that categorizes patients in terms of their specific needs, such as what medication they receive, whether they are on ventilators, if they need intravenous (IV) lines, or whether they require an intensive care unit (ICU) bed.
Under TRAIN, all patients are assigned a color. For example, patients that need specialized transport, such as an ambulance or military vehicle, in addition to life-support equipment, such as ventilators and multiple intravenous drips for medication, can be categorized instantly with a single word: red. In comparison, patients marked with blue tags are considered stable and can be transported in a car or bus, without any specialized equipment. TRAIN thus allows care teams to communicate the medical needs of the specific patient, as well as the severity of his or her condition.
“We can see exactly what resources are needed for each patient at all times. Should we have to evacuate, which we hope we never have to do, TRAIN puts us far ahead in terms of keeping our patients safe during an incident,” said Brandon Bond, director of the office of emergency management for the hospitals at Stanford. “We can see exactly what resources are needed for each patient at all times.”
“Once we had the algorithm, we knew our electronic medical record could easily calculate the TRAIN classification. Most importantly, the calculation could be done in an instant, without any additional work from doctors or nurses,” said Ronald Cohen, MD, clinical professor of neonatal and developmental medicine at Stanford school of medicine. “The computer system automatically categorizes patients based on their needs, and that report is always on hand. This would take hours to do manually, but it’s now available instantly, 24 hours a day. It’s an extremely valuable tool that hopefully we’ll never need.”
TRAIN is based on the Epic (Verona, WI, USA) EMR, a fully integrated health care software platform that allows physicians and nurses to record the condition of every patient, with constant updates in real time.
Related Links:
Stanford University
Epic
Latest Critical Care News
- AI Method Turns Toe Scan into Rapid PAD Screening Tool
- Integrated AI Pulmonary Workflow System Streamlines Detection and Follow-Up
- AI Model Predicts 10-Year Stroke Risk from Standard ECG
- Portable Ultrasound Tool Quantifies Liver Fat with MRI-Like Accuracy
- AI Tool Predicts Risk of Out-of-Hospital Cardiac Arrest
- Implantable Cytokine Device Enables Localized Immunotherapy for Ovarian Cancer
- Wearable Defibrillator Supports Quicker Beta-Blocker Optimization in Women
- High-Frequency Ultrasound Disables Viruses While Sparing Human Cells
- New Nasal Spray Enables Prehospital Neuroprotection in Ischemic Stroke
- AI-Enhanced ECG Screens for Heart Failure Risk in Resource-Limited Settings
- Single-Lead AI ECG Tool Detects Moderate-to-Severe Hyperkalemia Outside Clinic
- Reduced-Intensity Transplant Regimen Expands Donor Access in Sickle Cell Disease
- Battery-Free ECG Patch Enables Continuous Arrhythmia Monitoring
- Spinal Cord Interface Restores Bladder Control in Preclinical Study
- Rapid Clotting Gel Improves Emergency Bleeding Control
- AI Tool Predicts In-Hospital Cardiac Arrest Minutes in Advance
Channels
Artificial Intelligence
view channel
FDA-Cleared AI System Detects Sepsis Earlier and Reduces Mortality
Sepsis remains one of the deadliest complications for hospitalized patients, in part because its early signs overlap with other conditions. Each hour of delayed recognition measurably decreases survival,... Read moreFacial Image Analysis Tracks Biological Aging, Predicts Cancer Outcomes
Biological aging is the progressive loss of physiological function that may diverge from chronological age. In cancer care, clinicians need simple tools that reflect dynamic changes in patient resilience... Read moreSurgical Techniques
view channel
Stretchable Bioelectronic Implant Lowers Blood Pressure in Preclinical Study
Hypertension, or high blood pressure, drives major cardiovascular morbidity and affects nearly half of adults in the United States. About one in ten patients develop drug‑resistant hypertension that persists... Read more
FDA-Cleared Nerve Stimulator Advances Intraoperative Peripheral Nerve Assessment
The Evala Nerve Stimulator from Epineuron (Mississauga, ON, Canada) is a handheld, intraoperative electrical stimulation system designed to provide surgeons with a rapid and accurate method for nerve identification... Read morePatient Care
view channel
AI Avatar Doctor Improves Patient Understanding Before Radiotherapy
Radiation oncology consultations require patients to grasp complex concepts quickly, yet anxiety and information overload often undermine understanding and informed consent. Poor comprehension can also... Read more
Wearable Sleep Data Predict Adherence to Pulmonary Rehabilitation
Chronic obstructive pulmonary disease (COPD) is a long-term lung disorder that makes breathing difficult and often disturbs sleep, reducing energy for daily activities. Limited engagement in pulmonary... Read moreHealth IT
view channel
EHR-Integrated Screening Workflow Detects Cognitive Impairment at Admission
Cognitive impairment involves difficulties with thinking, learning, memory, and decision-making, and is more common in older adults. In U.S. hospitals, more than 40% of admitted older adults have dementia,... Read more
AI System Detects and Quantifies Chronic Subdural Hematoma
Viz.ai (San Francisco, CA, USA) announced a strategic commercialization collaboration with Johnson & Johnson (New Brunswick, NJ, USA) to expand access in the United States to the Viz Subdural solution... Read more
Continuous Monitoring Platform Detects Infection Risk Across Care Transitions
Patients leaving skilled nursing facilities often lose continuous physiologic monitoring, increasing the risk of undetected infection and delayed intervention. Nursing home residents are seven times more... Read more
Automated System Classifies and Tracks Cardiogenic Shock Across Hospital Settings
Cardiogenic shock remains a difficult, time-sensitive emergency, with delayed identification driving poor outcomes and persistently high mortality. Many cases go undocumented even at advanced stages, hindering... Read morePoint of Care
view channel
Point-of-Care Viscoelastic Testing System Supports Obstetric Bleeding Management
HemoSonics (Durham, NC, USA) announced on May 5, 2026 that the company's Quantra Hemostasis System for Obstetric Procedures won Silver in the 2026 Edison Awards in the Women’s Health and Reproductive Innovations... Read moreBusiness
view channel
Olympus Partnership Aims to Expand Access to Robot-Assisted Endoscopic Therapy
Olympus has signed an exclusive global distribution agreement with EndoRobotics Co., Ltd., under which robot-assisted technologies developed by EndoRobotics will be distributed worldwide as part of the... Read more







