Data Scientists Develop Decision-Making Tool to Improve Treatment of Covid Patients

cite this

Press release, (2021, October 14). Data scientists develop decision-making tool to improve treatment of Covid patients. Psychreg on Wellness. https://www.psychreg.org/data-scientists-develop-decision-making-tool-improve-treatment-covid-patients/

reading time: 2 Minutes

Data scientists develop decision-making tool to improve treatment of Covid patients.

Coventry University and Milton Keynes University Hospital (MKUH) have teamed up during the pandemic to develop a tool that hopes to reduce the burden of Covid on the NHS.

Data scientists from Coventry University’s Center for Computational Science and Mathematical Modeling (CSM) and MKUH used machine learning (ML) methods to support clinicians in predicting the effects of COVID-19 on every diagnosed patient participating in the study, along with the risks associated with more. ill health.

Predictive factors include tDuration of hospital stay, risk of blood clots in the lungs, possible need for ventilator support, or possible death.

After the second lockdown in the UK, coronavirus contributed to more than 150,000 deaths in the UK, while at the height of the crisis, Covid patients occupied fewer than 35,000 hospital beds.

Dr Ali Reza DaneshkhaSaid, Associate Professor and Curriculum Leader in Data Science and Artificial Intelligence at Coventry University:After entering one of the biggest global catastrophes of this century, clinicians around the world are puzzled as to what puts a person at risk for COVID-19, and whether that risk can be measured for comparison between individuals. Shortages of hospital beds, oxygen, and ventilators have prompted the need for this clinical decision-making tool that can help clinicians allocate resources during a pandemic, including allocating staff, beds and ventilation equipment.

During the first wave of the epidemic, Dr. Daneshkhah along with Dr. Abhinav Vepa, Chief Home Officer for General Medicine at MKUH, reviewed and evaluated 44 risk factor variables in more than 355 COVID-19 inpatients using the Bayesian Network ML method – a model used to represent Knowledge about an uncertain domain.

The method involved collecting data on pReturn health conditions, blood tests, and most importantly consider patient demographics including age, gender and ethnicity.

Dr. Veba said:The methodology presented in this research has the potential to be applied to all diseases and all outcomes in order to improve clinical care. In order to demonstrate that our model is robust to the extent that it can affect life, it would be a good practice to test the model on a second data set, which is why collaboration with other research teams with independent data sets would be very useful.

After external validation, and with a larger amount of data, this methodology can be applied to predict a solution to many clinical problems that can help in clinical decision making and thus relieve stress in the NHS.

This research seeks more external input and analyzes with a broader data set to ensure it is fit for purpose, and can then be implemented within hospitals to support many clinical requirements.


Disclaimer: Psychreg is mainly for information purposes only. The materials on this site are not intended as a substitute for professional advice, diagnosis, medical treatment or treatment. Never disregard professional psychological or medical advice and do not delay seeking professional advice or treatment because of something you have read on this site. Read the full disclaimer here.

Leave a Comment