Machine Learning based mortality prediction model for COVID-19 patients admitted in a tertiary care hospital, New Delhi.

1st International Congress for Innovation in Global Surgery
ABSTRACT FIRST PRESENTED: 20.04.2022

doi: 10.52648/ICIGS.1000_2

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 Gupta
Maulana 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

Inaugural Speech: Surgery in the face of low resources


Use of autologous platelet rich fibrin in minimally invasive treatment of perianal abscess


Machine Learning based mortality prediction model for COVID-19 patients admitted in a tertiary care hospital, New Delhi.


Perceived impact of trauma audit filters on trauma care in a tertiary care hospital: a qualitative analysis


An innovative surgical method to operate the zygomatico-maxillary-orbital complex in the absence of intraoperative computer tomography or intraoperative navigation using novel zygoma analysis and virtual surgical planning software


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


SutureSure-A multifunctional laparoscopic device for simple and effortless minimally invasive surgeries


RI2 -Retract, Isolate, and Illuminate: 3 in 1 Affordable solution for effective Community Dental Program


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


DOST


Innovative multi-modality segmentation and 3d fusion in the management of giant abdominopelvic chondrosarcoma


Malunited lateral tibial plateau fracture managed by intra-articular osteotomy with help of 3D printing


SurgiPod -The Smallest Portable Modular OT


Doctors On Community Service -An attempt to shift focus from Classroom to Community among medical students


Automatic Uterine Incision closure device


Aerosol Evacuation Funnel


OsteQuant -A comprehensive bone age and bone health estimation tool


Efficacy of local application of colistimethate sodium in non-healing wounds infected by multidrug resistant bacteria


D-Cleft


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


Feasibility of the frugally-engineered ‘LeVe CPAP’ from pilot data in healthy volunteers at Mengo Hospital, Uganda; with potential for use in patients with acute hypoxaemic respiratory failure associated with COVID-19 and other respiratory illnesses


The RAIS device for low-resource laparoscopic surgery: development, evaluation and future perspectives


Introduction of WALANT in Kenya: An innovative method to alleviate poverty


Condition monitoring of Ilizarov frames using vibration sensors


The Impact of Gurukool on College Students, Residents, Faculties, and Campus life in a Medical College of New Delhi


Efficacy of Platelet-Rich Plasma in Reduction of Post-Operative Split-Thickness Skin Graft Loss and Hematoma Formation: A Meta-Analysis


Spontaneous common bile duct perforation presenting as extrahepatic bilioma: a rare clinical presentation of gall stone disease


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


Music as an adjunct cost-effective therapeutic innovation for Management of Pain in Trauma Patients: A Systematic Review and Meta-analysis


System Innovation in Laparoscopic Simulation Training for intra-corporeal tissue re-approximation, knot tying and suturing technologies


Reverse Innovation in Healthcare from India


Expressed breast milk: Awareness and opinion on storage and utilization among mothers in tertiary health care center, Belagavi


A New Innovation in Yogasan (A new Yogasan for quick relief of tension and sleeplessness)


A Comparative Study of Ripasa Scoring System and Ultrasonography in the Clinical diagnosis of the Acute Appendicitis in Resource Limited Settings