Deep learning model to predict the need for mechanical ventilation using chest X-ray images in hospitalised patients with COVID-19

Kulkarni, Anoop R; Athavale, Ambarish M.; Sahni, Ashima; Sukhal, Shashvat; Saini, Abhimanyu; Itteera, M.; Zhukovsky, Sara; Vernik, Jane; Abraham, Mohan Chothirakottu; Joshi, Amit; Amarah, Amatur; Ruíz, Juan Gabriel; Hart, Peter D.; Kulkarni, Hemant

doi:10.1136/bmjinnov-2020-000593

Cited by 21 publications

(22 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, they found that CXR attributes can only be used for the prediction if other features such as SpO 2 , PaO 2 , and some other clinical features are available. Likewise, Kulkarni et al [20] used the CXR for early detection of COVID-19 patients requiring venti-lator support using the DL model, and found that CXR features can be used to perform the prediction 3 days in advance.…”

Section: Discussionmentioning

confidence: 99%

“…The objective was to identify the significance of the features and found that along with CXR, patients' medical history and other vitals have significantly enhanced the prediction. Conversely, another study [20] utilized CXR for predicting MV support using the DenseNet121 model. The significance of the study is that the patients that require MV were identified 3 days before the event.…”

Section: Ai-based Studies For Early Identification Of Covid-19 Patien...mentioning

confidence: 99%

“…The minimum patient age in the dataset was 19 and the maximum age was 107. A bin length of 10 was used, with the first bin range being [19][20][21][22][23][24][25][26][27][28][29], [29-39) and so on. The number of bins was 9.…”

Section: Exploratory Dataset Analysismentioning

confidence: 99%

See 2 more Smart Citations

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

Aslam

2022

Computation

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Ai-based Studies For Early Identification Of Covid-19 Patien...mentioning

confidence: 99%

See 1 more Smart Citation

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

Aslam

2022

Computation

View full text Add to dashboard Cite

show abstract

“…A weakly supervised learning architecture for predicting a multi-regional score on chest X-ray images was designed to effectively and reliably assess the severity of lung compromise in patients with COVID-19 [ 37 ]. In terms of clinical management, it has been reported that the DenseNet121 model can accurately predict the need for mechanical ventilation early in the hospitalization of patients with COVID-19 using chest X-ray images [ 38 ]. A DL-based model for classifying the severity of and monitoring COVID-19 was proposed.…”

Section: Medical Imaging Analysismentioning

confidence: 99%

Application of Artificial Intelligence in COVID-19 Diagnosis and Therapeutics

Asada

Komatsu

Shimoyama

et al. 2021

JPM

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19) pandemic began at the end of December 2019, giving rise to a high rate of infections and causing COVID-19-associated deaths worldwide. It was first reported in Wuhan, China, and since then, not only global leaders, organizations, and pharmaceutical/biotech companies, but also researchers, have directed their efforts toward overcoming this threat. The use of artificial intelligence (AI) has recently surged internationally and has been applied to diverse aspects of many problems. The benefits of using AI are now widely accepted, and many studies have shown great success in medical research on tasks, such as the classification, detection, and prediction of disease, or even patient outcome. In fact, AI technology has been actively employed in various ways in COVID-19 research, and several clinical applications of AI-equipped medical devices for the diagnosis of COVID-19 have already been reported. Hence, in this review, we summarize the latest studies that focus on medical imaging analysis, drug discovery, and therapeutics such as vaccine development and public health decision-making using AI. This survey clarifies the advantages of using AI in the fight against COVID-19 and provides future directions for tackling the COVID-19 pandemic using AI techniques.

show abstract

“…For instance, differential diagnosis (Healthy, pneumonia or COVID-19) of COVID-19 positive patients can be achieved 20 – 22 with accuracies reaching over 90% using deep networks such as the Xception architecture. Disease severity can be assessed in an objective way using radiology 23 – 25 which is useful to quickly assess the pulmonary involvement of the disease; and the potential for adverse events can be predicted (such as death, intubation or need for oxygenation) to help direct future treatments 26 Finally, ventilation need can be predicted in the near future for hospital-admitted patients 27 with over 90% accuracy. These cases demonstrate that CXRs possess enough information to predict clinical developments in the near future (around three days ahead of the event).…”

Section: Introductionmentioning

confidence: 99%

Tracking and predicting COVID-19 radiological trajectory on chest X-rays using deep learning

Gourdeau

Potvin

Archambault

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Radiological findings on chest X-ray (CXR) have shown to be essential for the proper management of COVID-19 patients as the maximum severity over the course of the disease is closely linked to the outcome. As such, evaluation of future severity from current CXR would be highly desirable. We trained a repurposed deep learning algorithm on the CheXnet open dataset (224,316 chest X-ray images of 65,240 unique patients) to extract features that mapped to radiological labels. We collected CXRs of COVID-19-positive patients from an open-source dataset (COVID-19 image data collection) and from a multi-institutional local ICU dataset. The data was grouped into pairs of sequential CXRs and were categorized into three categories: ‘Worse’, ‘Stable’, or ‘Improved’ on the basis of radiological evolution ascertained from images and reports. Classical machine-learning algorithms were trained on the deep learning extracted features to perform immediate severity evaluation and prediction of future radiological trajectory. Receiver operating characteristic analyses and Mann-Whitney tests were performed. Deep learning predictions between “Worse” and “Improved” outcome categories and for severity stratification were significantly different for three radiological signs and one diagnostic (‘Consolidation’, ‘Lung Lesion’, ‘Pleural effusion’ and ‘Pneumonia’; all P < 0.05). Features from the first CXR of each pair could correctly predict the outcome category between ‘Worse’ and ‘Improved’ cases with a 0.81 (0.74–0.83 95% CI) AUC in the open-access dataset and with a 0.66 (0.67–0.64 95% CI) AUC in the ICU dataset. Features extracted from the CXR could predict disease severity with a 52.3% accuracy in a 4-way classification. Severity evaluation trained on the COVID-19 image data collection had good out-of-distribution generalization when testing on the local dataset, with 81.6% of intubated ICU patients being classified as critically ill, and the predicted severity was correlated with the clinical outcome with a 0.639 AUC. CXR deep learning features show promise for classifying disease severity and trajectory. Once validated in studies incorporating clinical data and with larger sample sizes, this information may be considered to inform triage decisions.

show abstract

Deep learning model to predict the need for mechanical ventilation using chest X-ray images in hospitalised patients with COVID-19

Cited by 21 publications

References 26 publications

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

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

Application of Artificial Intelligence in COVID-19 Diagnosis and Therapeutics

Tracking and predicting COVID-19 radiological trajectory on chest X-rays using deep learning

Contact Info

Product

Resources

About