Mortality Prediction Analysis among COVID-19 Inpatients Using Clinical Variables and Deep Learning Chest Radiography Imaging Features

Relationship between ultra-short heart rate variability and short-term mortality in hospitalized COVID-19 patients

OBJECTIVE

To assess the association between ultra-short heart rate variability (US-HRV) and short-term mortality in patients with COVID-19 and develop prognostic prediction models to identify high-risk patients as early as possible.

METHODS

A retrospective cohort study was performed on 488 patients diagnosed with COVID-19 and hospitalized in the First Affiliated Hospital of Fujian Medical University from December 2022 to January 2023. 10-s electrocardiogram (ECG) data were available for these patients. The US-HRV parameters including standard deviation of all normal-to-normal R-R intervals (SDNN) and root mean square of successive differences between normal-to-normal R-R intervals (rMSSD) were calculated using Nalong ECG software. The endpoint was short-term mortality, including in-hospital mortality or mortality within 1 week after discharge.

RESULTS

Of the 488 patients, 76 (15.6%) died. The SDNN and rMSSD in the death group were significantly lower than those in the survival group (P < 0.001). The area under the receiver operating characteristic (ROC) curve (AUC) for SDNN and rMSSD to predict mortality was 0.761 and 0.715, respectively. The combined use of SDNN and rMSSD had an AUC of 0.774. The mortality rate in the group with SDNN ≤7.5 ms was higher than that of SDNN >7.5 ms group (P < 0.05). With the decrease of SDNN, the mortality of patients showed an upward trend, and the mortality of patients with SDNN ≤2 ms was the highest (66.7%). Multivariate logistic regression analysis identified SDNN as an independent predictor of prognosis (odds ratio (OR) = 5.791, 95% confidential interval (CI) 1.615-20.765, P = 0.007). The AUC of Model 1 (simple model) was 0.866 (95% CI 0.826-0.905). The AUC of Model 2 (comprehensive model) was 0.914 (95% CI 0.881-0.947).

CONCLUSION

SDNN was associated with short-term mortality and provided the additional discriminatory power of the risk stratification model for hospitalized COVID-19 patients.

[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.

A scoping review of interpretability and explainability concerning artificial intelligence methods in medical imaging

PURPOSE

To review eXplainable Artificial Intelligence/(XAI) methods available for medical imaging/(MI).

METHOD

A scoping review was conducted following the Joanna Briggs Institute's methodology. The search was performed on Pubmed, Embase, Cinhal, Web of Science, BioRxiv, MedRxiv, and Google Scholar. Studies published in French and English after 2017 were included. Keyword combinations and descriptors related to explainability, and MI modalities were employed. Two independent reviewers screened abstracts, titles and full text, resolving differences through discussion.

RESULTS

228 studies met the criteria. XAI publications are increasing, targeting MRI (n = 73), radiography (n = 47), CT (n = 46). Lung (n = 82) and brain (n = 74) pathologies, Covid-19 (n = 48), Alzheimer's disease (n = 25), brain tumors (n = 15) are the main pathologies explained. Explanations are presented visually (n = 186), numerically (n = 67), rule-based (n = 11), textually (n = 11), and example-based (n = 6). Commonly explained tasks include classification (n = 89), prediction (n = 47), diagnosis (n = 39), detection (n = 29), segmentation (n = 13), and image quality improvement (n = 6). The most frequently provided explanations were local (78.1 %), 5.7 % were global, and 16.2 % combined both local and global approaches. Post-hoc approaches were predominantly employed. The used terminology varied, sometimes indistinctively using explainable (n = 207), interpretable (n = 187), understandable (n = 112), transparent (n = 61), reliable (n = 31), and intelligible (n = 3).

CONCLUSION

The number of XAI publications in medical imaging is increasing, primarily focusing on applying XAI techniques to MRI, CT, and radiography for classifying and predicting lung and brain pathologies. Visual and numerical output formats are predominantly used. Terminology standardisation remains a challenge, as terms like "explainable" and "interpretable" are sometimes being used indistinctively. Future XAI development should consider user needs and perspectives.