SEPSIS DTECTION USING MACHINE LEARNING
This repository contains the Sepsis Detection project(ABHIGYATAA) source code. Abhigayataa is web solution made for the early dection of SEPSIS.It is the project TEAM - HEISENBUGS have done for SIH 2019(Smart India Hackathon, 2019).
# LIVE Visit Live SiteOverview
- The goal of this Challenge is the early detection of sepsis using physiological data.
- Develop a digital solution that uses artificial intelligence to detect patient deterioration before it’s too late and trigger notifications to clinicians and care teams.
- Train healthcare providers and front-line staff to quickly recognize symptoms to identify sepsis and treat patients at the earliest.
- Educate preventing infections in health care settings and in the community so that infections that can lead to sepsis can be stopped before they happen.
- Provide guidelines to follow infection control requirements (e.g., Hand hygiene) and ensure one to receive recommended vaccines
Table of contents
- Introduction
- Symptoms
- Causes
- Effects
- TaskToDo
- Awareness
- Detection
- Notification
- Documentation
Detail
- Awareness
- Detection
- Notification
- Documentation
- FutureScope
- Contributing
- References
- License
- Special thanks
Introduction
According to World Health Organisation (WHO) , “Sepsis is a potentially life-threatening organ dysfunction caused by a dysregulated host response to infection. Any type of infectious pathogen can potentially cause sepsis.”
Symptoms
General Symptoms
- A fever above 101ºF (38ºC) or a temperature below 96.8ºF (36ºC)
- Heart rate higher than 90 beats per minute
- Breathing rate higher than 20 breaths per minute
- Probable or confirmed infection
Causes
- Kidney infection
- Abdominal infection
- Meningitis
- Cellulitis
- Pneumonia
Effects
- Adults 65 and older
- Infants and children
- Pregnant women or women who have just given birth, had a miscarriage or had an abortion
- People suffering from a severe burn or physical trauma.
- Premature prolonged rupture of the fluid-filled membranes that surround the fetus
- Infection in the mother (such as chorioamnionitis)
- Malnutrition due to social isolation, functional limitations, poor or restricted diets, chronic disease, dementia, depression, poor dentition, polypharmacy, and alcohol or substance abuse.
- Endocrine deficiency like hypoadrenalism, hypothyroidism and hypogonadism.
Awareness
As Awareness is a very important aspect for preventing the spread of any disease.We aim to spread awareness in two ways:
- Through a Website
- Through a Telegram Bot
WEBSITE
To get more details about SEPSIS visit our website ABHIGYATAA
Features of website
- Covers all the important aspects regarding Prevention and Symptoms
- ML prediction Model is integrated with it that will do the task of early Detection of SEPSIS using the SOFA Score.
- Training Module for the employee of the Health care institutions.
Technology USED
HTML5 , CSS , BOOTSRAP4 , JAVASCRIPT , JQUERY , PYTHON in combination with FLASK
TELEGRAM BOT
To get more details about SEPSIS visit our Telegram Bot @sepsissupport
Why Telegram BOT?
- A Telegram Chatbot will be included as tool to spread Awareness.
- Real-Time Assistance along with Better Interaction will be provided once the chatbot gets trained enough.
- More people can be handled 24/7 service will be provided and only necessary queries will be forwarded to a real person.
Technology USED
Python , PHP , Telegram API
Detection
flowcharts
Notification
- Our website provide a notification section to express alerts if the prediction for sepsis label is found positive.
- a Separate user-interface will be designed using python library for triggering Alerts to the Hospital Staff.
Documentation
- We created a well docomented code with stepwise pathway for easy understanding.
- PPT for the Presentation of the Idea.
Future Scope
- More efficient Algorithms can be used for prediction of SEPSIS.
Contributing
Disclaimer: All arrays mentioned in this section must exist for the examples to work.
References
- https://www.physionet.org/content/challenge-2019/1.0.0/
- https://www.datacamp.com/community/tutorials/decision-tree-classification-python
- https://towardsdatascience.com/using-bagging-and-boosting-to-improve-classification-tree-accuracy-6d3bb6c95e5b
- https://towardsdatascience.com/early-detection-of-sepsis-using-physiological-data-78d5f31fab9d
- https://iopscience.iop.org/article/10.1088/1757-899X/428/1/012004
License
Special Thanks
To our Seniors who provided us guidance at necesscary point of time.