Explainable Artificial Intelligence Approach for the Early Prediction of Ventilator Support and Mortality in COVID-19 Patients

Early prediction of mortality and risk of deterioration in COVID-19 patients can reduce mortality and increase the opportunity for better and more timely treatment. In the current study, the DL model and explainable artificial intelligence (EAI) were combined to identify the impact of certain attributes on the prediction of mortality and ventilatory support in COVID-19 patients. Nevertheless, the DL model does not suffer from the curse of dimensionality, but in order to identify significant attributes, the EAI feature importance method was used. The DL model produced significant results; however, it lacks interpretability. The study was performed using COVID-19-hospitalized patients in King Abdulaziz Medical City, Riyadh. The dataset contains the patients’ demographic information, laboratory investigations, and chest X-ray (CXR) findings. The dataset used suffers from an imbalance; therefore, balanced accuracy, sensitivity, specificity, Youden index, and AUC measures were used to investigate the effectiveness of the proposed model. Furthermore, the experiments were conducted using original and SMOTE (over and under sampled) datasets. The proposed model outperforms the baseline study, with a balanced accuracy of 0.98 and an AUC of 0.998 for predicting mortality using the full-feature set. Meanwhile, for predicting ventilator support a highest balanced accuracy of 0.979 and an AUC of 0.981 was achieved. The proposed explainable prediction model will assist doctors in the early prediction of COVID-19 patients that are at risk of mortality or ventilatory support and improve the management of hospital resources.

[1]  M. Shanbehzadeh,et al.  Comparing machine learning algorithms for predicting COVID-19 mortality , 2022, BMC Medical Informatics and Decision Making.

[2]  Irfan Ullah Khan,et al.  Using a Deep Learning Model to Explore the Impact of Clinical Data on COVID-19 Diagnosis Using Chest X-ray , 2022, Sensors.

[3]  D. Fotiadis,et al.  A Multimodal Approach for the Risk Prediction of Intensive Care and Mortality in Patients with COVID-19 , 2021, Diagnostics.

[4]  D. Anton-Păduraru,et al.  Mortality Predictors in Severe COVID-19 Patients from an East European Tertiary Center: A Never-Ending Challenge for a No Happy Ending Pandemic , 2021, Journal of clinical medicine.

[5]  A. Ultsch,et al.  Explainable Artificial Intelligence (XAI) in Biomedicine: Making AI Decisions Trustworthy for Physicians and Patients , 2021, BioMedInformatics.

[6]  Zahra Asghari Varzaneh,et al.  A new COVID-19 intubation prediction strategy using an intelligent feature selection and K-NN method , 2021, Informatics in Medicine Unlocked.

[7]  Zhenxing Xu,et al.  Artificial intelligence for COVID-19: battling the pandemic with computational intelligence , 2021, Intelligent Medicine.

[8]  P. Prasanna,et al.  Predicting Mechanical Ventilation and Mortality in COVID-19 Using Radiomics and Deep Learning on Chest Radiographs: A Multi-Institutional Study , 2021, Diagnostics.

[9]  Shayan Shams,et al.  DBNet: a novel deep learning framework for mechanical ventilation prediction using electronic health records , 2021, BCB.

[10]  M. Rashid,et al.  Early Prediction of COVID-19 Ventilation Requirement and Mortality from Routinely Collected Baseline Chest Radiographs, Laboratory, and Clinical Data with Machine Learning , 2021, Journal of multidisciplinary healthcare.

[11]  Shaker El-Sappagh,et al.  Comprehensive Survey of Using Machine Learning in the COVID-19 Pandemic , 2021, Diagnostics.

[12]  Irfan Ullah Khan,et al.  Computational Intelligence-Based Model for Mortality Rate Prediction in COVID-19 Patients , 2021, International journal of environmental research and public health.

[13]  A. Athavale,et al.  Deep learning model to predict the need for mechanical ventilation using chest X-ray images in hospitalised patients with COVID-19 , 2021, BMJ Innovations.

[14]  Huchang Liao,et al.  A consensus model to manage the non-cooperative behaviors of individuals in uncertain group decision making problems during the COVID-19 outbreak , 2020, Applied Soft Computing.

[15]  Jianjiang Feng,et al.  Development and evaluation of an artificial intelligence system for COVID-19 diagnosis , 2020, Nature Communications.

[16]  Mario Silva,et al.  Chest X-ray for predicting mortality and the need for ventilatory support in COVID-19 patients presenting to the emergency department , 2020, European Radiology.

[17]  Irfan Ullah Khan,et al.  A Deep-Learning-Based Framework for Automated Diagnosis of COVID-19 Using X-ray Images , 2020, Inf..

[18]  Alaa Tharwat,et al.  Classification assessment methods , 2020, Applied Computing and Informatics.

[19]  Dinh C. Nguyen,et al.  Artificial Intelligence (AI) and Big Data for Coronavirus (COVID-19) Pandemic: A Survey on the State-of-the-Arts , 2020, IEEE Access.

[20]  Jaime S. Cardoso,et al.  Machine Learning Interpretability: A Survey on Methods and Metrics , 2019, Electronics.

[21]  A Min Tjoa,et al.  Current Advances, Trends and Challenges of Machine Learning and Knowledge Extraction: From Machine Learning to Explainable AI , 2018, CD-MAKE.

[22]  Freddy Lécué,et al.  Explainable AI: The New 42? , 2018, CD-MAKE.

[23]  Derek Doran,et al.  What Does Explainable AI Really Mean? A New Conceptualization of Perspectives , 2017, CEx@AI*IA.

[24]  Guido Bologna,et al.  Characterization of Symbolic Rules Embedded in Deep DIMLP Networks: A Challenge to Transparency of Deep Learning , 2017, J. Artif. Intell. Soft Comput. Res..

[25]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[26]  Dilini Ranasinghage Local Model-Agnostic Explanations for Machine Learning and Time-series Forecasting Models , 2022 .