Developing and Validating Multi-Modal Models for Mortality Prediction in COVID-19 Patients: a Multi-center Retrospective Study

Machine learning in cardiovascular risk assessment: Towards a precision medicine approach

Cardiovascular diseases remain the leading cause of global morbidity and mortality. Validated risk scores are the basis of guideline-recommended care, but most scores lack the capacity to integrate complex and multidimensional data. Limitations inherent to traditional risk prediction models and the growing burden of residual cardiovascular risk highlight the need for refined strategies that go beyond conventional paradigms. Artificial intelligence and machine learning (ML) provide unique opportunities to refine cardiovascular risk assessment and surveillance through the integration of diverse data types and sources, including clinical, electrocardiographic, imaging and multi-omics derived data. In fact, ML models, such as deep neural networks, can handle high-dimensional data through which phenotyping and cardiovascular risk assessment across diverse patient populations become much more precise, fostering a paradigm shift towards more personalized care. Here, we review the role of ML in advancing cardiovascular risk assessment and discuss its potential to identify novel therapeutic targets and to improve prevention strategies. We also discuss key challenges inherent to ML, such as data quality, standardized reporting, model transparency and validation, and discuss barriers in its clinical translation. We highlight the transformative potential of ML in precision cardiology and advocate for more personalized cardiovascular prevention strategies that go beyond previous notions.

Explainable machine learning to compare the overall survival status between patients receiving mastectomy and breast conserving surgeries

The most prevalent malignancy among women is breast cancer; hence, treatment approaches are needed in consideration of tumor characteristics and disease stage but also patient preference. Two surgical options, Mastectomy and Breast Conserving Surgery (BCS), share the same survival outcomes, clinical or molecular factors; and explainable Machine Learning (ML) techniques like SHapley Additive exPlanations (SHAP) offer further insights. To compare the overall survival status of breast cancer patients undergoing Mastectomy versus BCS using ML models and SHAP values, identifying key predictors for survival. This study used the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) dataset, which contains 2509 patients with clinical and molecular features. The preprocessing steps included imputation of missing values, class balancing using Synthetic Minority Over-sampling Technique (SMOTE), and feature selection. Gradient Boosting was identified as the best model, considering metrics such as accuracy, precision, and Area Under the Receiver Operating Characteristic Curve (ROC-AUC). SHAP values were used for feature importance, detailing the contribution of predictors to survival outcomes in both surgical groups. Gradient Boosting achieved a training accuracy of 95.4% and test accuracy of 86.4% for Mastectomy, and 94.6% and 82.8% respectively for BCS. Strong predictors included Relapse Free Status, Nottingham Prognostic Index and Age at Diagnosis. SHAP analysis indicated that the Relapse Free Status was an important predictor across both surgeries though there were specific influences of Age and Menopausal State. Younger patients benefited more with BCS while older ones faced higher risks from Mastectomy. The performance for BCS was significantly higher-3.73 than the performance of Mastectomy-1.21. The SHAP-driven insights pointed toward a more personalized approach to treatment, depending on both clinical and molecular predictors. This will justify tailored surgical and adjuvant therapies in achieving optimized survival.

Efficient clinical decision-making process via AI-based multimodal data fusion: A COVID-19 case study

COVID-19 is an infectious disease that caused a global pandemic in 2020. In the critical moments of this healthcare emergencies, the medical staff needs to take important decisions in a context of limited resources that must be carefully managed. To this end, the computer-aided diagnosis methods are extremely powerful and help them to better recognize the evidences of high-risk patients. This can be done with the support of relevant information extracted from electronic health records, lab tests and imaging studies. In this work, we present a novel fully-automatic efficient method to help the clinical decision-making process in the context of COVID-19 risk estimation, using multimodal data fusion of clinical features and deep features extracted from chest X-ray images. The risk estimation is studied in two of the most relevant and critical encountered scenarios: the risk of hospitalization and mortality. This study shows which are the most important features for each scenario, the ratio of clinical and imaging features present in the top ranking and the performance of the used machine learning models. The results demonstrate a great performance by the classifiers, estimating the risk of hospitalization with an AUC-ROC of 0.8452 ± 0.0133 and the risk of death with an AUC-ROC of 0.8285 ± 0.0210, only using a subset of the original features, and highlight the significant contribution of imaging features to hospitalization risk assessment, while clinical features become more crucial for mortality risk evaluation. Furthermore, multimodal data fusion can outperform the approaches that use one data source. Despite the model's complexity, it requires fewer features, an advantage in scenarios with limited computational resources. This streamlined, fully-automated method shows promising potential to improve the clinical decision-making process and better manage medical resources, not only in the context of COVID-19, but also in other clinical scenarios.

Use of Artificial Intelligence in Improving Outcomes in Heart Disease: A Scientific Statement From the American Heart Association

A major focus of academia, industry, and global governmental agencies is to develop and apply artificial intelligence and other advanced analytical tools to transform health care delivery. The American Heart Association supports the creation of tools and services that would further the science and practice of precision medicine by enabling more precise approaches to cardiovascular and stroke research, prevention, and care of individuals and populations. Nevertheless, several challenges exist, and few artificial intelligence tools have been shown to improve cardiovascular and stroke care sufficiently to be widely adopted. This scientific statement outlines the current state of the art on the use of artificial intelligence algorithms and data science in the diagnosis, classification, and treatment of cardiovascular disease. It also sets out to advance this mission, focusing on how digital tools and, in particular, artificial intelligence may provide clinical and mechanistic insights, address bias in clinical studies, and facilitate education and implementation science to improve cardiovascular and stroke outcomes. Last, a key objective of this scientific statement is to further the field by identifying best practices, gaps, and challenges for interested stakeholders.

Homogenization of multi-institutional chest x-ray images in various data transformation schemes

Purpose

Although there are several options for improving the generalizability of learned models, a data instance-based approach is desirable when stable data acquisition conditions cannot be guaranteed. Despite the wide use of data transformation methods to reduce data discrepancies between different data domains, detailed analysis for explaining the performance of data transformation methods is lacking.

Approach

This study compares several data transformation methods in the tuberculosis detection task with multi-institutional chest x-ray (CXR) data. Five different data transformations, including normalization, standardization with and without lung masking, and multi-frequency-based (MFB) standardization with and without lung masking were implemented. A tuberculosis detection network was trained using a reference dataset, and the data from six other sites were used for the network performance comparison. To analyze data harmonization performance, we extracted radiomic features and calculated the Mahalanobis distance. We visualized the features with a dimensionality reduction technique. Through similar methods, deep features of the trained networks were also analyzed to examine the models' responses to the data from various sites.

Results

From various numerical assessments, the MFB standardization with lung masking provided the highest network performance for the non-reference datasets. From the radiomic and deep feature analyses, the features of the multi-site CXRs after MFB with lung masking were found to be well homogenized to the reference data, whereas the others showed limited performance.

Conclusions

Conventional normalization and standardization showed suboptimal performance in minimizing feature differences among various sites. Our study emphasizes the strengths of MFB standardization with lung masking in terms of network performance and feature homogenization.

Predicting the severity of postoperative scars using artificial intelligence based on images and clinical data

Evaluation of scar severity is crucial for determining proper treatment modalities; however, there is no gold standard for assessing scars. This study aimed to develop and evaluate an artificial intelligence model using images and clinical data to predict the severity of postoperative scars. Deep neural network models were trained and validated using images and clinical data from 1283 patients (main dataset: 1043; external dataset: 240) with post-thyroidectomy scars. Additionally, the performance of the model was tested against 16 dermatologists. In the internal test set, the area under the receiver operating characteristic curve (ROC-AUC) of the image-based model was 0.931 (95% confidence interval 0.910‒0.949), which increased to 0.938 (0.916‒0.955) when combined with clinical data. In the external test set, the ROC-AUC of the image-based and combined prediction models were 0.896 (0.874‒0.916) and 0.912 (0.892‒0.932), respectively. In addition, the performance of the tested algorithm with images from the internal test set was comparable with that of 16 dermatologists. This study revealed that a deep neural network model derived from image and clinical data could predict the severity of postoperative scars. The proposed model may be utilized in clinical practice for scar management, especially for determining severity and treatment initiation.

A robust COVID-19 mortality prediction calculator based on Lymphocyte count, Urea, C-Reactive Protein, Age and Sex (LUCAS) with chest X-rays

There have been numerous risk tools developed to enable triaging of SARS-CoV-2 positive patients with diverse levels of complexity. Here we presented a simplified risk-tool based on minimal parameters and chest X-ray (CXR) image data that predicts the survival of adult SARS-CoV-2 positive patients at hospital admission. We analysed the NCCID database of patient blood variables and CXR images from 19 hospitals across the UK using multivariable logistic regression. The initial dataset was non-randomly split between development and internal validation dataset with 1434 and 310 SARS-CoV-2 positive patients, respectively. External validation of the final model was conducted on 741 Accident and Emergency (A&E) admissions with suspected SARS-CoV-2 infection from a separate NHS Trust. The LUCAS mortality score included five strongest predictors (Lymphocyte count, Urea, C-reactive protein, Age, Sex), which are available at any point of care with rapid turnaround of results. Our simple multivariable logistic model showed high discrimination for fatal outcome with the area under the receiving operating characteristics curve (AUC-ROC) in development cohort 0.765 (95% confidence interval (CI): 0.738-0.790), in internal validation cohort 0.744 (CI: 0.673-0.808), and in external validation cohort 0.752 (CI: 0.713-0.787). The discriminatory power of LUCAS increased slightly when including the CXR image data. LUCAS can be used to obtain valid predictions of mortality in patients within 60 days of SARS-CoV-2 RT-PCR results into low, moderate, high, or very high risk of fatality.