1st International Congress for Innovation in Global Surgery
ABSTRACT FIRST PRESENTED: 20.04.2022
Machine Learning based mortality prediction model for COVID-19 patients admitted in a tertiary care hospital, New Delhi.
Sanjeev P E Khanth, Manukumar Shetty , Vandana Roy, Lalit GuptaMaulana Azad Medical College, New Delhi, India
Introduction: SARS corona virus 2 is found to be responsible for the COVID-19 pandemic. It caused severe acute respiratory illness with a high mortality rate. This deadly disease infected around 4 crore population in India and costs around 5.2 lakh deaths. This enveloped RNA virus is transmitted from the aerosols of infected patients. The virus attaches to the host with its spike protein to ACE2 receptors of lung epithelial cells and begins its replication. The symptoms can range from mild severity like sore throat, fever, and cough to severe category like pneumonia and ARDS which leads to increased mortality. There is a huge interindividual variation in response to the virus. It is often unpredictable to decide the course of the disease. Comorbid conditions like diabetes, hypertension, and major organ failures have been known to increase the severity of the disease. Therefore, the aim of this study was to apply an interpretative Artificial intelligence algorithm for identifying the main features which decide the course of the disease.
Methods: It is an observational study of hospitalized COVID-19 patients. 1181 RT-PCR confirmed COVID-19 patients (both alive and dead) data was used to predict the factors responsible for the course of the disease using a ML model. Twelve features were used to train [75%] and test [25%] the datasets using logistic regression and 2 machine learning methods [ XG Boost, Random Forest (RF)]. AI model interpretability was analyzed using a SHAP summary plot.
Results: Among those patients analyzed using different AI models the Random Forest algorithms had higher sensitivity (83%) and accuracy (81%) on test datasets. Among the 12 features, AI interpretable SHAP summary plot showed age, kidney disease, heart disease, diabetes, male sex, and hypertension among the top rank features which have a high impact on the outcome of the disease (death).
Conclusions: We observed that AI interpretable model ranks the major factors that are contributing to the death of the patient and is able to predict the key ranking features with 83% sensitivity. Higher the age higher the risk of mortality. It also predicts that patients with heart disease, kidney disease, and diabetes are at higher risk for mortality. This model can be implemented in all healthcare facilities for risk stratification in COVID-19 patients. It helps in the proper management and taking necessary precautions beforehand.
Keywords: COVID-19, Artificial Intelligence
Use of autologous platelet rich fibrin in minimally invasive treatment of perianal abscess
Carica papaya fruit in the management of chronic non healing ulcer wounds
The Buddy System: An initiative to slow down the antibiotic misuse
SOCH – India (Students’ Orbit for Collaborative Healthcare – India)
Need of an Autopsy Kit in resource limited settings
Device for non-invasive detection of meconium stained amniotic fluid
A Novel Stethoscope In COVID 19 Times
Explainable AI decision model for ECG data of cardiac disorders
Satyanveshi: A New Age Mentorship Program in Medical School
Predict Easy :Pre-eclampsia Risk Stratification Tool
A new approach to stoma management
Neonatal care platform to facilitate the practice of delayed cord clamping
Urine congophilia dipstick test for preeclampsia screening in resource limited settings
Lap-Pack: a low fidelity laparoscopic box trainer
SurgiPod -The Smallest Portable Modular OT
Automatic Uterine Incision closure device
OsteQuant -A comprehensive bone age and bone health estimation tool
MeeT: A Platform for Innovation
The Metaverse as a platform for education and training within medicine and surgery
An inexpensive surgical glove bag for gall bladder retrieval during laproscopic cholecystectomy
Frugal indigenous methods for chest tube insertion and venesection
Digital videoproctoscopy: a new diagnostic test in proctology
Identifying palliative care needs for tribal-rural populations
Training 750 General surgeons in this decade for district hospitals in Kenya
Introduction of WALANT in Kenya: An innovative method to alleviate poverty
Condition monitoring of Ilizarov frames using vibration sensors
External Fixation in Polytrauma Patients from Low and Middle Income Countries – A Case Report
Lumbar Disc Degeneration, A Transdifferentiation Process-An Electron Microscopic Observation
Designing Global Surgical Technology: Benefits of a Participatory Design Approach for the Surgeon
Reverse Innovation in Healthcare from India
A New Innovation in Yogasan (A new Yogasan for quick relief of tension and sleeplessness)