Mohammed Dalwai, an emergency clinician working with Doctors with borders describes one of his experiences:
It was in Pakistan in 2011, on my first assignment, that I saw patients dying due to incorrect triaging. One day, I lost a patient. A young woman, 22 years old, came in with abdominal pain. She was incorrectly triaged, and she waited for eight hours. She died — and it really affected me. She was a woman, she was sidelined, she was put in a corner — no one cared, no one did the triage properly. If she’d been triaged correctly, we would have realized she was pregnant, and we would have prioritized her.
Clinical Need for Intelligent Triage System
Inefficient Triage
Scarcity of Resources
Why
Low Doctor to Patient ratio.
Save 54% of lives by improving emergency facilities
Current Methods
Specialized Protocols for Initial Screening which require some training
Inadequacy
Scarcity of trained professions
Human error due to overwork
Only 22% of current triage results are correct
Based on One- Two Triage Protocol
Designed Specifically for Low and Middle Income Countries
Objective in Nature
Faster, Easy to use
Multi-platform phone and desktop application.
Using Machine Learning Algorithms predict emergency outcomes and survival probability of the patient.
Stakeholders
Patients and Doctors in overcrowded situations
Lesser Trained Nurses and Hospital Staff
Hospital Administration looking for better outcomes and management
Government who can monitor such data and be proactive to contain disease spread.
Technology behind Medi-Assess
The system inputs triage data based on the One-Two Triage Protocol and output a triage level. The collected data is further used as input features for our deep learning model trained on the NHAMCS dataset to predict emergency outcomes. Using the emergency outcome we calculate the survival probability of the patient in the emergency which is used by the clinician for resource allocation. To understand more about the tech-stack, refer to the Research page.
News
[08/02/2021] Research idea presented at Workshop on Health Intelligence, AAAI, 2021.
[15/12/2020] Research Paper accepted for a print in Springer book volume in the “Studies in Computational Intelligence” series.
[18/06/2020] Research idea presented at Engineering in Medicine and Biology Conference (EMBC), 2020.
[20/04/2020] Awarded the second-runner up position at Johns Hopkins International Healthcare Design Competition.