Radiomics analysis enables fatal outcome prediction for hospitalized patients with coronavirus disease 2019 (COVID-19)

Improving radiology workflow using ChatGPT and artificial intelligence

Artificial Intelligence is a branch of computer science that aims to create intelligent machines capable of performing tasks that typically require human intelligence. One of the branches of artificial intelligence is natural language processing, which is dedicated to studying the interaction between computers and human language. ChatGPT is a sophisticated natural language processing tool that can understand and respond to complex questions and commands in natural language. Radiology is a vital aspect of modern medicine that involves the use of imaging technologies to diagnose and treat medical conditions artificial intelligence, including ChatGPT, can be integrated into radiology workflows to improve efficiency, accuracy, and patient care. ChatGPT can streamline various radiology workflow steps, including patient registration, scheduling, patient check-in, image acquisition, interpretation, and reporting. While ChatGPT has the potential to transform radiology workflows, there are limitations to the technology that must be addressed, such as the potential for bias in artificial intelligence algorithms and ethical concerns. As technology continues to advance, ChatGPT is likely to become an increasingly important tool in the field of radiology, and in healthcare more broadly.

Predicting In-Hospital Mortality in Severe COVID-19: A Systematic Review and External Validation of Clinical Prediction Rules

Multiple prediction models for risk of in-hospital mortality from COVID-19 have been developed, but not applied, to patient cohorts different to those from which they were derived. The MEDLINE, EMBASE, Scopus, and Web of Science (WOS) databases were searched. Risk of bias and applicability were assessed with PROBAST. Nomograms, whose variables were available in a well-defined cohort of 444 patients from our site, were externally validated. Overall, 71 studies, which derived a clinical prediction rule for mortality outcome from COVID-19, were identified. Predictive variables consisted of combinations of patients′ age, chronic conditions, dyspnea/taquipnea, radiographic chest alteration, and analytical values (LDH, CRP, lymphocytes, D-dimer); and markers of respiratory, renal, liver, and myocardial damage, which were mayor predictors in several nomograms. Twenty-five models could be externally validated. Areas under receiver operator curve (AUROC) in predicting mortality ranged from 0.71 to 1 in derivation cohorts; C-index values ranged from 0.823 to 0.970. Overall, 37/71 models provided very-good-to-outstanding test performance. Externally validated nomograms provided lower predictive performances for mortality in their respective derivation cohorts, with the AUROC being 0.654 to 0.806 (poor to acceptable performance). We can conclude that available nomograms were limited in predicting mortality when applied to different populations from which they were derived.

The risk profile of patients with COVID-19 as predictors of lung lesions severity and mortality—Development and validation of a prediction model

Objective

We developed and validated a prediction model based on individuals' risk profiles to predict the severity of lung involvement and death in patients hospitalized with coronavirus disease 2019 (COVID-19) infection.

Methods

In this retrospective study, we studied hospitalized COVID-19 patients with data on chest CT scans performed during hospital stay (February 2020-April 2021) in a training dataset (TD) (n = 2,251) and an external validation dataset (eVD) (n = 993). We used the most relevant demographical, clinical, and laboratory variables (n = 25) as potential predictors of COVID-19-related outcomes. The primary and secondary endpoints were the severity of lung involvement quantified as mild (≤25%), moderate (26–50%), severe (>50%), and in-hospital death, respectively. We applied random forest (RF) classifier, a machine learning technique, and multivariable logistic regression analysis to study our objectives.

Results

In the TD and the eVD, respectively, the mean [standard deviation (SD)] age was 57.9 (18.0) and 52.4 (17.6) years; patients with severe lung involvement [n (%):185 (8.2) and 116 (11.7)] were significantly older [mean (SD) age: 64.2 (16.9), and 56.2 (18.9)] than the other two groups (mild and moderate). The mortality rate was higher in patients with severe (64.9 and 38.8%) compared to moderate (5.5 and 12.4%) and mild (2.3 and 7.1%) lung involvement. The RF analysis showed age, C reactive protein (CRP) levels, and duration of hospitalizations as the three most important predictors of lung involvement severity at the time of the first CT examination. Multivariable logistic regression analysis showed a significant strong association between the extent of the severity of lung involvement (continuous variable) and death; adjusted odds ratio (OR): 9.3; 95% CI: 7.1–12.1 in the TD and 2.6 (1.8–3.5) in the eVD.

Conclusion

In hospitalized patients with COVID-19, the severity of lung involvement is a strong predictor of death. Age, CRP levels, and duration of hospitalizations are the most important predictors of severe lung involvement. A simple prediction model based on available clinical and imaging data provides a validated tool that predicts the severity of lung involvement and death probability among hospitalized patients with COVID-19.

Outcome Prediction for SARS-CoV-2 Patients Using Machine Learning Modeling of Clinical, Radiological, and Radiomic Features Derived from Chest CT Images

(1) Background: Chest Computed Tomography (CT) has been proposed as a non-invasive method for confirming the diagnosis of SARS-CoV-2 patients using radiomic features (RFs) and baseline clinical data. The performance of Machine Learning (ML) methods using RFs derived from semi-automatically segmented lungs in chest CT images was investigated regarding the ability to predict the mortality of SARS-CoV-2 patients. (2) Methods: A total of 179 RFs extracted from 436 chest CT images of SARS-CoV-2 patients, and 8 clinical and 6 radiological variables, were used to train and evaluate three ML methods (Least Absolute Shrinkage and Selection Operator [LASSO] regularized regression, Random Forest Classifier [RFC], and the Fully connected Neural Network [FcNN]) for their ability to predict mortality using the Area Under the Curve (AUC) of Receiver Operator characteristic (ROC) Curves. These three groups of variables were used separately and together as input for constructing and comparing the final performance of ML models. (3) Results: All the ML models using only RFs achieved an informative level regarding predictive ability, outperforming radiological assessment, without however reaching the performance obtained with ML based on clinical variables. The LASSO regularized regression and the FcNN performed equally, both being superior to the RFC. (4) Conclusions: Radiomic features based on semi-automatically segmented CT images and ML approaches can aid in identifying patients with a high risk of mortality, allowing a fast, objective, and generalizable method for improving prognostic assessment by providing a second expert opinion that outperforms human evaluation.

CT Quantification of COVID-19 Pneumonia at Admission Can Predict Progression to Critical Illness: A Retrospective Multicenter Cohort Study

Objective: Early identification of coronavirus disease 2019 (COVID-19) patients with worse outcomes may benefit clinical management of patients. We aimed to quantify pneumonia findings on CT at admission to predict progression to critical illness in COVID-19 patients.

Methods: This retrospective study included laboratory-confirmed adult patients with COVID-19. All patients underwent a thin-section chest computed tomography (CT) scans showing evidence of pneumonia. CT images with severe moving artifacts were excluded from analysis. Patients' clinical and laboratory data were collected from medical records. Three quantitative CT features of pneumonia lesions were automatically calculated using a care.ai Intelligent Multi-disciplinary Imaging Diagnosis Platform Intelligent Evaluation System of Chest CT for COVID-19, denoting the percentage of pneumonia volume (PPV), ground-glass opacity volume (PGV), and consolidation volume (PCV). According to Chinese COVID-19 guidelines (trial version 7), patients were divided into noncritical and critical groups. Critical illness was defined as a composite of admission to the intensive care unit, respiratory failure requiring mechanical ventilation, shock, or death. The performance of PPV, PGV, and PCV in discrimination of critical illness was assessed. The correlations between PPV and laboratory variables were assessed by Pearson correlation analysis.

Results: A total of 140 patients were included, with mean age of 58.6 years, and 85 (60.7%) were male. Thirty-two (22.9%) patients were critical. Using a cutoff value of 22.6%, the PPV had the highest performance in predicting critical illness, with an area under the curve of 0.868, sensitivity of 81.3%, and specificity of 80.6%. The PPV had moderately positive correlation with neutrophil (%) (r = 0.535, p < 0.001), erythrocyte sedimentation rate (r = 0.567, p < 0.001), d-Dimer (r = 0.444, p < 0.001), high-sensitivity C-reactive protein (r = 0.495, p < 0.001), aspartate aminotransferase (r = 0.410, p < 0.001), lactate dehydrogenase (r = 0.644, p < 0.001), and urea nitrogen (r = 0.439, p < 0.001), whereas the PPV had moderately negative correlation with lymphocyte (%) (r = −0.535, p < 0.001).

Conclusions: Pneumonia volume quantified on initial CT can non-invasively predict the progression to critical illness in advance, which serve as a prognostic marker of COVID-19.