Artificial intelligence for stepwise diagnosis and monitoring of COVID-19

Differential privacy preserved federated learning for prognostic modeling in COVID-19 patients using large multi-institutional chest CT dataset

BACKGROUND

Notwithstanding the encouraging results of previous studies reporting on the efficiency of deep learning (DL) in COVID-19 prognostication, clinical adoption of the developed methodology still needs to be improved. To overcome this limitation, we set out to predict the prognosis of a large multi-institutional cohort of patients with COVID-19 using a DL-based model.

PURPOSE

This study aimed to evaluate the performance of deep privacy-preserving federated learning (DPFL) in predicting COVID-19 outcomes using chest CT images.

METHODS

After applying inclusion and exclusion criteria, 3055 patients from 19 centers, including 1599 alive and 1456 deceased, were enrolled in this study. Data from all centers were split (randomly with stratification respective to each center and class) into a training/validation set (70%/10%) and a hold-out test set (20%). For the DL model, feature extraction was performed on 2D slices, and averaging was performed at the final layer to construct a 3D model for each scan. The DensNet model was used for feature extraction. The model was developed using centralized and FL approaches. For FL, we employed DPFL approaches. Membership inference attack was also evaluated in the FL strategy. For model evaluation, different metrics were reported in the hold-out test sets. In addition, models trained in two scenarios, centralized and FL, were compared using the DeLong test for statistical differences.

RESULTS

The centralized model achieved an accuracy of 0.76, while the DPFL model had an accuracy of 0.75. Both the centralized and DPFL models achieved a specificity of 0.77. The centralized model achieved a sensitivity of 0.74, while the DPFL model had a sensitivity of 0.73. A mean AUC of 0.82 and 0.81 with 95% confidence intervals of (95% CI: 0.79-0.85) and (95% CI: 0.77-0.84) were achieved by the centralized model and the DPFL model, respectively. The DeLong test did not prove statistically significant differences between the two models (p-value = 0.98). The AUC values for the inference attacks fluctuate between 0.49 and 0.51, with an average of 0.50 ± 0.003 and 95% CI for the mean AUC of 0.500 to 0.501.

CONCLUSION

The performance of the proposed model was comparable to centralized models while operating on large and heterogeneous multi-institutional datasets. In addition, the model was resistant to inference attacks, ensuring the privacy of shared data during the training process.

Artificial Intelligence in the Intensive Care Unit: Current Evidence on an Inevitable Future Tool

Artificial intelligence (AI) is a technique that attempts to replicate human intelligence, analytical behavior, and decision-making ability. This includes machine learning, which involves the use of algorithms and statistical techniques to enhance the computer's ability to make decisions more accurately. Due to AI's ability to analyze, comprehend, and interpret considerable volumes of data, it has been increasingly used in the field of healthcare. In critical care medicine, where most of the patient load requires timely interventions due to the perilous nature of the condition, AI's ability to monitor, analyze, and predict unfavorable outcomes is an invaluable asset. It can significantly improve timely interventions and prevent unfavorable outcomes, which, otherwise, is not always achievable owing to the constrained human ability to multitask with optimum efficiency. AI has been implicated in intensive care units over the past many years. In addition to its advantageous applications, this article discusses its disadvantages, prospects, and the changes needed to train future critical care professionals. A comprehensive search of electronic databases was performed using relevant keywords. Data from articles pertinent to the topic was assimilated into this review article.

CT-based Assessment at 6-Month Follow-up of COVID-19 Pneumonia patients in China

This study aimed to assess pulmonary changes at 6-month follow-up CT and predictors of pulmonary residual abnormalities and fibrotic-like changes in COVID-19 pneumonia patients in China following relaxation of COVID restrictions in 2022. A total of 271 hospitalized patients with COVID-19 pneumonia admitted between November 29, 2022 and February 10, 2023 were prospectively evaluated at 6 months. CT characteristics and Chest CT scores of pulmonary abnormalities were compared between the initial and the 6-month CT. The association of demographic and clinical factors with CT residual abnormalities or fibrotic-like changes were assessed using logistic regression. Follow-up CT scans were obtained at a median of 177 days (IQR, 170-185 days) after hospital admission. Pulmonary residual abnormalities and fibrotic-like changes were found in 98 (36.2%) and 39 (14.4%) participants. In multivariable analysis of pulmonary residual abnormalities and fibrotic-like changes, the top three predictive factors were invasive ventilation (OR 13.6; 95% CI 1.9, 45; P < .001), age > 60 years (OR 9.1; 95% CI 2.3, 39; P = .01), paxlovid (OR 0.11; 95% CI 0.04, 0.48; P = .01) and invasive ventilation (OR 10.3; 95% CI 2.9, 33; P = .002), paxlovid (OR 0.1; 95% CI 0.03, 0.48; P = .01), smoker (OR 9.9; 95% CI 2.4, 31; P = .01), respectively. The 6-month follow-up CT of recent COVID-19 pneumonia cases in China showed a considerable proportion of the patients with pulmonary residual abnormalities and fibrotic-like changes. Antivirals against SARS-CoV-2 like paxlovid may be beneficial for long-term regression of COVID-19 pneumonia.

A scalable federated learning solution for secondary care using low-cost microcomputing: privacy-preserving development and evaluation of a COVID-19 screening test in UK hospitals

BACKGROUND

Multicentre training could reduce biases in medical artificial intelligence (AI); however, ethical, legal, and technical considerations can constrain the ability of hospitals to share data. Federated learning enables institutions to participate in algorithm development while retaining custody of their data but uptake in hospitals has been limited, possibly as deployment requires specialist software and technical expertise at each site. We previously developed an artificial intelligence-driven screening test for COVID-19 in emergency departments, known as CURIAL-Lab, which uses vital signs and blood tests that are routinely available within 1 h of a patient's arrival. Here we aimed to federate our COVID-19 screening test by developing an easy-to-use embedded system-which we introduce as full-stack federated learning-to train and evaluate machine learning models across four UK hospital groups without centralising patient data.

METHODS

We supplied a Raspberry Pi 4 Model B preloaded with our federated learning software pipeline to four National Health Service (NHS) hospital groups in the UK: Oxford University Hospitals NHS Foundation Trust (OUH; through the locally linked research University, University of Oxford), University Hospitals Birmingham NHS Foundation Trust (UHB), Bedfordshire Hospitals NHS Foundation Trust (BH), and Portsmouth Hospitals University NHS Trust (PUH). OUH, PUH, and UHB participated in federated training, training a deep neural network and logistic regressor over 150 rounds to form and calibrate a global model to predict COVID-19 status, using clinical data from patients admitted before the pandemic (COVID-19-negative) and testing positive for COVID-19 during the first wave of the pandemic. We conducted a federated evaluation of the global model for admissions during the second wave of the pandemic at OUH, PUH, and externally at BH. For OUH and PUH, we additionally performed local fine-tuning of the global model using the sites' individual training data, forming a site-tuned model, and evaluated the resultant model for admissions during the second wave of the pandemic. This study included data collected between Dec 1, 2018, and March 1, 2021; the exact date ranges used varied by site. The primary outcome was overall model performance, measured as the area under the receiver operating characteristic curve (AUROC). Removable micro secure digital (microSD) storage was destroyed on study completion.

FINDINGS

Clinical data from 130 941 patients (1772 COVID-19-positive), routinely collected across three hospital groups (OUH, PUH, and UHB), were included in federated training. The evaluation step included data from 32 986 patients (3549 COVID-19-positive) attending OUH, PUH, or BH during the second wave of the pandemic. Federated training of a global deep neural network classifier improved upon performance of models trained locally in terms of AUROC by a mean of 27·6% (SD 2·2): AUROC increased from 0·574 (95% CI 0·560-0·589) at OUH and 0·622 (0·608-0·637) at PUH using the locally trained models to 0·872 (0·862-0·882) at OUH and 0·876 (0·865-0·886) at PUH using the federated global model. Performance improvement was smaller for a logistic regression model, with a mean increase in AUROC of 13·9% (0·5%). During federated external evaluation at BH, AUROC for the global deep neural network model was 0·917 (0·893-0·942), with 89·7% sensitivity (83·6-93·6) and 76·6% specificity (73·9-79·1). Site-specific tuning of the global model did not significantly improve performance (change in AUROC <0·01).

INTERPRETATION

We developed an embedded system for federated learning, using microcomputing to optimise for ease of deployment. We deployed full-stack federated learning across four UK hospital groups to develop a COVID-19 screening test without centralising patient data. Federation improved model performance, and the resultant global models were generalisable. Full-stack federated learning could enable hospitals to contribute to AI development at low cost and without specialist technical expertise at each site.

FUNDING

The Wellcome Trust, University of Oxford Medical and Life Sciences Translational Fund.

[The contribution of artificial intelligence (AI) subsequent to the processing of thoracic imaging]

The contribution of artificial intelligence (AI) to medical imaging is currently the object of widespread experimentation. The development of deep learning (DL) methods, particularly convolution neural networks (CNNs), has led to performance gains often superior to those achieved by conventional methods such as machine learning. Radiomics is an approach aimed at extracting quantitative data not accessible to the human eye from images expressing a disease. The data subsequently feed machine learning models and produce diagnostic or prognostic probabilities. As for the multiple applications of AI methods in thoracic imaging, they are undergoing evaluation. Chest radiography is a practically ideal field for the development of DL algorithms able to automatically interpret X-rays. Current algorithms can detect up to 14 different abnormalities present either in isolation or in combination. Chest CT is another area offering numerous AI applications. Various algorithms have been specifically formed and validated for the detection and characterization of pulmonary nodules and pulmonary embolism, as well as segmentation and quantitative analysis of the extent of diffuse lung diseases (emphysema, infectious pneumonias, interstitial lung disease). In addition, the analysis of medical images can be associated with clinical, biological, and functional data (multi-omics analysis), the objective being to construct predictive approaches regarding disease prognosis and response to treatment.

The 100 most-cited and 100 most-mentioned COVID-19-related radiological articles: a comparative bibliometric analysis

OBJECTIVES

This study aimed to identify the 100 most-cited and 100 most-mentioned coronavirus disease-2019 (COVID-19)-related radiological articles and compare their characteristics.

MATERIALS AND METHODS

We searched the Web of Science and Altmetric.com using the search terms "COVID," "COVID-19," "Coronavirus," "SARS-CoV-2," "nCoV," and "pandemic" to identify the most-cited and most-mentioned COVID-19-related articles. We identified the top 100 most-cited and 100 most-mentioned articles in the field of radiology, regardless of their publication journal. We extracted the information from the listed articles and compared the characteristics between the most-cited and most-mentioned.

RESULTS

Thirty (30%) articles were featured in the lists of the most-cited and most-mentioned articles. The comparison of the 100 most-cited and most-mentioned articles on each list showed that the most frequently cited articles were published in November 2020 and before (p < .001), originated from China (p < .001), covered the topic of diagnosis of COVID-19 (p < .001), and were related to the subspecialty of pulmonary imaging (p < .001); the most frequently mentioned articles were published in December 2020 and after (p < .001), originated from the USA (p < .001), covered the topic of diagnosis of sequelae of COVID-19 (p = .013) and post-vaccination complications (p < .001), and were related to the subspecialties of cardiac imaging (p < .001) and neuroradiology (p < .013).

CONCLUSION

Significant differences were observed in publication date, country of origin, topic, and subspecialty of scientific knowledge related to COVID-19 in the field of radiology, between citation and public dissemination.

CLINICAL RELEVANCE STATEMENT

This bibliometric analysis compares the 100 most-cited and 100 most-mentioned COVID-19-related radiologic articles, aiming to provide valuable insights into the patterns of knowledge dissemination during the pandemic era.

KEY POINTS

• Thirty articles were featured on the lists of the 100 most-cited and 100 most-mentioned COVID-19-related articles. • The 70 unique most-cited articles more frequently originated from China (48.6%), while the unique most-mentioned articles more frequently originated from the USA (51.4%) (p < 0.001). • The 70 unique most-mentioned articles were more frequently related to cardiac imaging (25.7% vs.0%, p < 0.001) and neuroradiology (15.7% vs. 1.4%, p < 0.005) compared to the unique most-mentioned articles.

Robust Medical Diagnosis: A Novel Two-Phase Deep Learning Framework for Adversarial Proof Disease Detection in Radiology Images

In the realm of medical diagnostics, the utilization of deep learning techniques, notably in the context of radiology images, has emerged as a transformative force. The significance of artificial intelligence (AI), specifically machine learning (ML) and deep learning (DL), lies in their capacity to rapidly and accurately diagnose diseases from radiology images. This capability has been particularly vital during the COVID-19 pandemic, where rapid and precise diagnosis played a pivotal role in managing the spread of the virus. DL models, trained on vast datasets of radiology images, have showcased remarkable proficiency in distinguishing between normal and COVID-19-affected cases, offering a ray of hope amidst the crisis. However, as with any technological advancement, vulnerabilities emerge. Deep learning-based diagnostic models, although proficient, are not immune to adversarial attacks. These attacks, characterized by carefully crafted perturbations to input data, can potentially disrupt the models' decision-making processes. In the medical context, such vulnerabilities could have dire consequences, leading to misdiagnoses and compromised patient care. To address this, we propose a two-phase defense framework that combines advanced adversarial learning and adversarial image filtering techniques. We use a modified adversarial learning algorithm to enhance the model's resilience against adversarial examples during the training phase. During the inference phase, we apply JPEG compression to mitigate perturbations that cause misclassification. We evaluate our approach on three models based on ResNet-50, VGG-16, and Inception-V3. These models perform exceptionally in classifying radiology images (X-ray and CT) of lung regions into normal, pneumonia, and COVID-19 pneumonia categories. We then assess the vulnerability of these models to three targeted adversarial attacks: fast gradient sign method (FGSM), projected gradient descent (PGD), and basic iterative method (BIM). The results show a significant drop in model performance after the attacks. However, our defense framework greatly improves the models' resistance to adversarial attacks, maintaining high accuracy on adversarial examples. Importantly, our framework ensures the reliability of the models in diagnosing COVID-19 from clean images.

Medical Imaging Applications of Federated Learning

Since its introduction in 2016, researchers have applied the idea of Federated Learning (FL) to several domains ranging from edge computing to banking. The technique's inherent security benefits, privacy-preserving capabilities, ease of scalability, and ability to transcend data biases have motivated researchers to use this tool on healthcare datasets. While several reviews exist detailing FL and its applications, this review focuses solely on the different applications of FL to medical imaging datasets, grouping applications by diseases, modality, and/or part of the body. This Systematic Literature review was conducted by querying and consolidating results from ArXiv, IEEE Xplorer, and PubMed. Furthermore, we provide a detailed description of FL architecture, models, descriptions of the performance achieved by FL models, and how results compare with traditional Machine Learning (ML) models. Additionally, we discuss the security benefits, highlighting two primary forms of privacy-preserving techniques, including homomorphic encryption and differential privacy. Finally, we provide some background information and context regarding where the contributions lie. The background information is organized into the following categories: architecture/setup type, data-related topics, security, and learning types. While progress has been made within the field of FL and medical imaging, much room for improvement and understanding remains, with an emphasis on security and data issues remaining the primary concerns for researchers. Therefore, improvements are constantly pushing the field forward. Finally, we highlighted the challenges in deploying FL in medical imaging applications and provided recommendations for future directions.

Clinical utilization of artificial intelligence-based COVID-19 pneumonia quantification using chest computed tomography - a multicenter retrospective cohort study in Japan

BACKGROUND

Computed tomography (CT) imaging and artificial intelligence (AI)-based analyses have aided in the diagnosis and prediction of the severity of COVID-19. However, the potential of AI-based CT quantification of pneumonia in assessing patients with COVID-19 has not yet been fully explored. This study aimed to investigate the potential of AI-based CT quantification of COVID-19 pneumonia to predict the critical outcomes and clinical characteristics of patients with residual lung lesions.

METHODS

This retrospective cohort study included 1,200 hospitalized patients with COVID-19 from four hospitals. The incidence of critical outcomes (requiring the support of high-flow oxygen or invasive mechanical ventilation or death) and complications during hospitalization (bacterial infection, renal failure, heart failure, thromboembolism, and liver dysfunction) was compared between the groups of pneumonia with high/low-percentage lung lesions, based on AI-based CT quantification. Additionally, 198 patients underwent CT scans 3 months after admission to analyze prognostic factors for residual lung lesions.

RESULTS

The pneumonia group with a high percentage of lung lesions (N = 400) had a higher incidence of critical outcomes and complications during hospitalization than the low percentage group (N = 800). Multivariable analysis demonstrated that AI-based CT quantification of pneumonia was independently associated with critical outcomes (adjusted odds ratio [aOR] 10.5, 95% confidence interval [CI] 5.59-19.7), as well as with oxygen requirement (aOR 6.35, 95% CI 4.60-8.76), IMV requirement (aOR 7.73, 95% CI 2.52-23.7), and mortality rate (aOR 6.46, 95% CI 1.87-22.3). Among patients with follow-up CT scans (N = 198), the multivariable analysis revealed that the pneumonia group with a high percentage of lung lesions on admission (aOR 4.74, 95% CI 2.36-9.52), older age (aOR 2.53, 95% CI 1.16-5.51), female sex (aOR 2.41, 95% CI 1.13-5.11), and medical history of hypertension (aOR 2.22, 95% CI 1.09-4.50) independently predicted persistent residual lung lesions.

CONCLUSIONS

AI-based CT quantification of pneumonia provides valuable information beyond qualitative evaluation by physicians, enabling the prediction of critical outcomes and residual lung lesions in patients with COVID-19.

Quantitative Evaluation of COVID-19 Pneumonia CT Using AI Analysis-Feasibility and Differentiation from Other Common Pneumonia Forms

PURPOSE: To implement the technical feasibility of an AI-based software prototype optimized for the detection of COVID-19 pneumonia in CT datasets of the lung and the differentiation between other etiologies of pneumonia. METHODS: This single-center retrospective case-control-study consecutively yielded 144 patients (58 female, mean age 57.72 ± 18.25 y) with CT datasets of the lung. Subgroups including confirmed bacterial (n = 24, 16.6%), viral (n = 52, 36.1%), or fungal (n = 25, 16.6%) pneumonia and (n = 43, 30.7%) patients without detected pneumonia (comparison group) were evaluated using the AI-based Pneumonia Analysis prototype. Scoring (extent, etiology) was compared to reader assessment. RESULTS: The software achieved an optimal sensitivity of 80.8% with a specificity of 50% for the detection of COVID-19; however, the human radiologist achieved optimal sensitivity of 80.8% and a specificity of 97.2%. The mean postprocessing time was 7.61 ± 4.22 min. The use of a contrast agent did not influence the results of the software (p = 0.81). The mean evaluated COVID-19 probability is 0.80 ± 0.36 significantly higher in COVID-19 patients than in patients with fungal pneumonia (p < 0.05) and bacterial pneumonia (p < 0.001). The mean percentage of opacity (PO) and percentage of high opacity (PHO ≥ -200 HU) were significantly higher in COVID-19 patients than in healthy patients. However, the total mean HU in COVID-19 patients was -679.57 ± 112.72, which is significantly higher than in the healthy control group (p < 0.001). CONCLUSION: The detection and quantification of pneumonia beyond the primarily trained COVID-19 datasets is possible and shows comparable results for COVID-19 pneumonia to an experienced reader. The advantages are the fast, automated segmentation and quantification of the pneumonia foci.

Risk Factor Analysis and Multiple Predictive Machine Learning Models for Mortality in COVID-19: A Multicenter and Multi-Ethnic Cohort Study

BACKGROUND

The COVID-19 pandemic presents a significant challenge to the global health care system. Implementing timely, accurate, and cost-effective screening approaches is crucial in preventing infections and saving lives by guiding disease management.

OBJECTIVES

The study aimed to use machine learning algorithms to analyze clinical features from routine clinical data to identify risk factors and predict the mortality of COVID-19.

METHODS

The data used in this research were originally collected for the study titled "Neurologic Syndromes Predict Higher In-Hospital Mortality in COVID-19." A total of 4711 patients with confirmed COVID-19 were enrolled consecutively from four hospitals. Three machine learning models, including random forest (RF), partial least squares discriminant analysis (PLS-DA), and support vector machine (SVM), were used to find risk factors and predict COVID-19 mortality.

RESULTS

The predictive models were developed based on three machine learning algorithms. The RF model was trained with 20 variables and had a receiver operating characteristic (ROC) value of 0.859 (95% confidence interval [CI] 0.804-0.920). The PLS-DA model was trained with 20 variables and had a ROC value of 0.775 (95% CI 0.694-0.833). The SVM model was trained with 10 variables and had a ROC value of 0.828 (95% CI 0.785-0.865). The nine variables that were present in all three models were age, procalcitonin, ferritin, C-reactive protein, troponin, blood urea nitrogen, mean arterial pressure, aspartate transaminase, and alanine transaminase.

CONCLUSION

This study developed and validated three machine learning prediction models for COVID-19 mortality based on accessible clinical features. The RF model showed the best performance among the three models. The nine variables identified in the models may warrant further investigation as potential prognostic indicators of severe COVID-19.

Application of an artificial intelligence ensemble for detection of important secondary findings on lung ventilation and perfusion SPECT-CT

RATIONALE

Single-photon-emission-computerized-tomography/computed-tomography(SPECT/CT) is commonly used for pulmonary disease. Scant work has been done to determine ability of AI for secondary findings using low-dose-CT(LDCT) attenuation correction series of SPECT/CT.

METHODS

120 patients with ventilation-perfusion-SPECT/CT from 9/1/21-5/1/22 were included in this retrospective study. AI-RAD companion(VA10A,Siemens-Healthineers, Erlangen, Germany), an ensemble of deep-convolutional-neural-networks was evaluated for the detection of pulmonary nodules, coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss. Accuracy, sensitivity, specificity was measured for the outcomes. Inter-rater reliability were measured. Inter-rater reliability was measured using the intraclass correlation coefficient (ICC) by comparing the number of nodules identified by the AI to radiologist.

RESULTS

Overall per-nodule accuracy, sensitivity, and specificity for detection of lung nodules were 0.678(95%CI 0.615-0.732), 0.956(95%CI 0.900-0.985), and 0.456(95%CI 0.376-0.543), respectively, with an intraclass correlation coefficient (ICC) between AI and radiologist of 0.78(95%CI 0.71-0.83). Overall per-patient accuracy for AI detection of coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss was 0.939(95%CI 0.878-0.975), 0.974(95%CI 0.925-0.995), and 0.857(95%CI 0.781-0.915), respectively. Sensitivity for coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss was 0.898(95%CI 0.778-0.966), 1 (95%CI 0.958-1), and 1 (95%CI 0.961-1), respectively. Specificity for coronary artery calcium, aortic ectasia/aneurysm, and vertebral height loss was 0.969(95% CI 0.893-0.996), 0.897 (95% CI 0.726-0.978), and 0.346 (95% CI 0.172-0.557), respectively.

CONCLUSION

AI ensemble was accurate for coronary artery calcium and aortic ectasia/aneurysm, while sensitive for aortic ectasia/aneurysm, lung nodules and vertebral height loss on LDCT attenuation correction series of SPECT/CT.

Combating Covid-19 using machine learning and deep learning: Applications, challenges, and future perspectives

COVID-19, a worldwide pandemic that has affected many people and thousands of individuals have died due to COVID-19, during the last two years. Due to the benefits of Artificial Intelligence (AI) in X-ray image interpretation, sound analysis, diagnosis, patient monitoring, and CT image identification, it has been further researched in the area of medical science during the period of COVID-19. This study has assessed the performance and investigated different machine learning (ML), deep learning (DL), and combinations of various ML, DL, and AI approaches that have been employed in recent studies with diverse data formats to combat the problems that have arisen due to the COVID-19 pandemic. Finally, this study shows the comparison among the stand-alone ML and DL-based research works regarding the COVID-19 issues with the combinations of ML, DL, and AI-based research works. After in-depth analysis and comparison, this study responds to the proposed research questions and presents the future research directions in this context. This review work will guide different research groups to develop viable applications based on ML, DL, and AI models, and will also guide healthcare institutes, researchers, and governments by showing them how these techniques can ease the process of tackling the COVID-19.

Fusing clinical and image data for detecting the severity level of hospitalized symptomatic COVID-19 patients using hierarchical model

Purpose

Based on medical reports, it is hard to find levels of different hospitalized symptomatic COVID-19 patients according to their features in a short time. Besides, there are common and special features for COVID-19 patients at different levels based on physicians’ knowledge that make diagnosis difficult. For this purpose, a hierarchical model is proposed in this paper based on experts’ knowledge, fuzzy C-mean (FCM) clustering, and adaptive neuro-fuzzy inference system (ANFIS) classifier.

Methods

Experts considered a special set of features for different groups of COVID-19 patients to find their treatment plans. Accordingly, the structure of the proposed hierarchical model is designed based on experts’ knowledge. In the proposed model, we applied clustering methods to patients’ data to determine some clusters. Then, we learn classifiers for each cluster in a hierarchical model. Regarding different common and special features of patients, FCM is considered for the clustering method. Besides, ANFIS had better performances than other classification methods. Therefore, FCM and ANFIS were considered to design the proposed hierarchical model. FCM finds the membership degree of each patient’s data based on common and special features of different clusters to reinforce the ANFIS classifier. Next, ANFIS identifies the need of hospitalized symptomatic COVID-19 patients to ICU and to find whether or not they are in the end-stage (mortality target class). Two real datasets about COVID-19 patients are analyzed in this paper using the proposed model. One of these datasets had only clinical features and another dataset had both clinical and image features. Therefore, some appropriate features are extracted using some image processing and deep learning methods.

Results

According to the results and statistical test, the proposed model has the best performance among other utilized classifiers. Its accuracies based on clinical features of the first and second datasets are 92% and 90% to find the ICU target class. Extracted features of image data increase the accuracy by 94%.

Conclusion

The accuracy of this model is even better for detecting the mortality target class among different classifiers in this paper and the literature review. Besides, this model is compatible with utilized datasets about COVID-19 patients based on clinical data and both clinical and image data, as well.

Highlights

• A new hierarchical model is proposed using ANFIS classifiers and FCM clustering method in this paper. Its structure is designed based on experts’ knowledge and real medical process. FCM reinforces the ANFIS classification learning phase based on the features of COVID-19 patients.

• Two real datasets about COVID-19 patients are studied in this paper. One of these datasets has both clinical and image data. Therefore, appropriate features are extracted based on its image data and considered with available meaningful clinical data. Different levels of hospitalized symptomatic COVID-19 patients are considered in this paper including the need of patients to ICU and whether or not they are in end-stage.

• Well-known classification methods including case-based reasoning (CBR), decision tree, convolutional neural networks (CNN), K-nearest neighbors (KNN), learning vector quantization (LVQ), multi-layer perceptron (MLP), Naive Bayes (NB), radial basis function network (RBF), support vector machine (SVM), recurrent neural networks (RNN), fuzzy type-I inference system (FIS), and adaptive neuro-fuzzy inference system (ANFIS) are designed for these datasets and their results are analyzed for different random groups of the train and test data;

• According to unbalanced utilized datasets, different performances of classifiers including accuracy, sensitivity, specificity, precision, F-score, and G-mean are compared to find the best classifier. ANFIS classifiers have the best results for both datasets.

• To reduce the computational time, the effects of the Principal Component Analysis (PCA) feature reduction method are studied on the performances of the proposed model and classifiers. According to the results and statistical test, the proposed hierarchical model has the best performances among other utilized classifiers.

Graphical Abstract

Supplementary Information

The online version contains supplementary material available at 10.1007/s42600-023-00268-w.

Prognostic significance of chest CT severity score in mortality prediction of COVID-19 patients, a machine learning study

Background

The high mortality rate of COVID-19 makes it necessary to seek early identification of high-risk patients with poor prognoses. Although the association between CT-SS and mortality of COVID-19 patients was reported, its prognosis significance in combination with other prognostic parameters was not evaluated yet.

Methods

This retrospective single-center study reviewed a total of 6854 suspected patients referred to Imam Khomeini hospital, Ilam city, west of Iran, from February 9, 2020 to December 20, 2020. The prognostic performances of k-Nearest Neighbors (kNN), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and J48 decision tree algorithms were evaluated based on the most important and relevant predictors. The metrics derived from the confusion matrix were used to determine the performance of the ML models.

Results

After applying exclusion criteria, 815 hospitalized cases were entered into the study. Of these, 447(54.85%) were male and the mean (± SD) age of participants was 57.22(± 16.76) years. The results showed that the performances of the ML algorithms were improved when they are fed by the dataset with CT-SS data. The kNN model with an accuracy of 94.1%, sensitivity of 100. 0%, precision of 89.5%, specificity of 88.3%, and AUC around 97.2% had the best performance among the other three ML techniques.

Conclusions

The integration of CT-SS data with demographics, risk factors, clinical manifestations, and laboratory parameters improved the prognostic performances of the ML algorithms. An ML model with a comprehensive collection of predictors could identify high-risk patients more efficiently and lead to the optimal use of hospital resources.

The Artificial Intelligence in Digital Radiology: Part 2: Towards an Investigation of acceptance and consensus on the Insiders

Background. The study deals with the introduction of the artificial intelligence in digital radiology. There is a growing interest in this area of scientific research in acceptance and consensus studies involving both insiders and the public, based on surveys focused mainly on single professionals. Purpose. The goal of the study is to perform a contemporary investigation on the acceptance and the consensus of the three key professional figures approaching in this field of application: (1) Medical specialists in image diagnostics: the medical specialists (MS)s; (2) experts in physical imaging processes: the medical physicists (MP)s; (3) AI designers: specialists of applied sciences (SAS)s. Methods. Participants (MSs = 92: 48 males/44 females, averaged age 37.9; MPs = 91: 43 males/48 females, averaged age 36.1; SAS = 90: 47 males/43 females, averaged age 37.3) were properly recruited based on specific training. An electronic survey was designed and submitted to the participants with a wide range questions starting from the training and background up to the different applications of the AI and the environment of application. Results. The results show that generally, the three professionals show (a) a high degree of encouraging agreement on the introduction of AI both in imaging and in non-imaging applications using both standalone applications and/or mHealth/eHealth, and (b) a different consent on AI use depending on the training background. Conclusions. The study highlights the usefulness of focusing on both the three key professionals and the usefulness of the investigation schemes facing a wide range of issues. The study also suggests the importance of different methods of administration to improve the adhesion and the need to continue these investigations both with federated and specific initiatives.