Individual-Level Fatality Prediction of COVID-19 Patients Using AI Methods

The global covid-19 pandemic puts great pressure on medical resources worldwide and leads healthcare professionals to question which individuals are in imminent need of care. With appropriate data of each patient, hospitals can heuristically predict whether or not a patient requires immediate care. We adopted a deep learning model to predict fatality of individuals tested positive given the patient's underlying health conditions, age, sex, and other factors. As the allocation of resources toward a vulnerable patient could mean the difference between life and death, a fatality prediction model serves as a valuable tool to healthcare workers in prioritizing resources and hospital space. The models adopted were evaluated and refined using the metrics of accuracy, specificity, and sensitivity. After data preprocessing and training, our model is able to predict whether a covid-19 confirmed patient is likely to be dead or not, given their information and disposition. The metrics between the different models are compared. Results indicate that the deep learning model outperforms other machine learning models to solve this rare event prediction problem.

[1]  Man Chen,et al.  The effect of low frequency and low intensity ultrasound combined with microbubbles on the sonoporation efficiency of MDA-MB-231 cells , 2020, Annals of translational medicine.

[2]  Graciela Gonzalez-Hernandez,et al.  Utilizing social media data for pharmacovigilance: A review , 2015, J. Biomed. Informatics.

[3]  Yanfang Ye,et al.  Semi-supervised Multi-instance Interpretable Models for Flu Shot Adverse Event Detection , 2018, 2018 IEEE International Conference on Big Data (Big Data).

[4]  Smriti Mallapaty,et al.  How deadly is the coronavirus? Scientists are close to an answer , 2020, Nature.

[5]  Sherri Rose,et al.  Classifying Lung Cancer Severity with Ensemble Machine Learning in Health Care Claims Data , 2017, MLHC.

[6]  Jimeng Sun,et al.  Using recurrent neural network models for early detection of heart failure onset , 2016, J. Am. Medical Informatics Assoc..

[7]  De-Min Han,et al.  Gender Differences in Patients With COVID-19: Focus on Severity and Mortality , 2020, Frontiers in Public Health.

[8]  Xingdong Chen,et al.  Early prediction of mortality risk among severe COVID-19 patients using machine learning , 2020, medRxiv.

[9]  Manzhu Yu,et al.  Leveraging LSTM for rapid intensifications prediction of tropical cyclones , 2017 .

[10]  Cindy Leung,et al.  Association of a Workplace Sales Ban on Sugar-Sweetened Beverages With Employee Consumption of Sugar-Sweetened Beverages and Health. , 2020, JAMA internal medicine.

[11]  Paloma Martínez,et al.  Detecting drugs and adverse events from Spanish social media streams , 2014, Louhi@EACL.

[12]  Teresa Conner-Kerr,et al.  Effects of Low Frequency Ultrasound on Adriamycin (ADR) Uptake and Cell Growth in Breast Cancer Cells , 2014 .

[13]  Limin Ou,et al.  Development and Validation of a Clinical Risk Score to Predict the Occurrence of Critical Illness in Hospitalized Patients With COVID-19. , 2020, JAMA internal medicine.

[14]  Haym Hirsh,et al.  Learning to Predict Extremely Rare Events , 2000 .

[15]  Nazli Goharian,et al.  ADRTrace: Detecting Expected and Unexpected Adverse Drug Reactions from User Reviews on Social Media Sites , 2013, ECIR.

[16]  Mohammadreza Nemati,et al.  Machine-Learning Approaches in COVID-19 Survival Analysis and Discharge-Time Likelihood Prediction Using Clinical Data , 2020, Patterns.

[17]  Mario Guarino,et al.  Predictors of Intensive Care Unit admission in patients with coronavirus disease 2019 (COVID-19). , 2020, Monaldi archives for chest disease = Archivio Monaldi per le malattie del torace.

[18]  John S. Brownstein,et al.  Epidemiological data from the COVID-19 outbreak, real-time case information , 2020, Scientific Data.

[19]  Ruben Morales-Menendez,et al.  Correlation Between Temperature and COVID-19 (Suspected, Confirmed and Death) Cases based on Machine Learning Analysis , 2020, Journal of Pure and Applied Microbiology.

[20]  SchmidhuberJürgen.  Deep learning in neural networks , 2015 .

[21]  Roy T Sabo,et al.  Excess Deaths From COVID-19 and Other Causes, March-July 2020. , 2020, JAMA.

[22]  Y. Tie,et al.  Coronavirus Disease 2019 Case Surveillance — United States, January 22–May 30, 2020 , 2020, MMWR. Morbidity and mortality weekly report.

[23]  Gaurav Chaudhari,et al.  How Essential Is to Focus on Physician's Health and Burnout in Coronavirus (COVID-19) Pandemic? , 2020, Cureus.

[24]  Roy T Sabo,et al.  Excess Deaths From COVID-19 and Other Causes, March-April 2020. , 2020, JAMA.

[25]  Umut Ozkaya,et al.  Coronavirus (Covid-19) Classification Using CT Images by Machine Learning Methods , 2020, RTA-CSIT.

[26]  P. Adab,et al.  Covid-19: risk factors for severe disease and death , 2020, BMJ.

[27]  Sabine Van Huffel,et al.  Detecting rare events using extreme value statistics applied to epileptic convulsions in children , 2014, Artif. Intell. Medicine.

[28]  Liang Zhao,et al.  Multi-instance Domain Adaptation for Vaccine Adverse Event Detection , 2018, WWW.

[29]  K. Stewart,et al.  Spatiotemporal analysis of medical resource deficiencies in the U.S. under COVID-19 pandemic , 2020, medRxiv.

[30]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[31]  GonzalezGraciela,et al.  Utilizing social media data for pharmacovigilance , 2015 .

[32]  Dieter Pfoser,et al.  Taking the pulse of COVID-19: a spatiotemporal perspective , 2020, Int. J. Digit. Earth.

[33]  Dong Chen,et al.  Genome-wide gene expression profiling of the melon fly, Zeugodacus cucurbitae, during thirteen life stages , 2020, Scientific Data.