Artificial intelligence-enabled rapid diagnosis of patients with COVID-19

CovMediScanX: A medical imaging solution for COVID-19 diagnosis from chest X-ray images

INTRODUCTION

Radiologists have extensively employed the interpretation of chest X-rays (CXR) to identify visual markers indicative of COVID-19 infection, offering an alternative approach for the screening of infected individuals. This research article presents CovMediScanX, a deep learning-based framework designed for a rapid and automated diagnosis of COVID-19 from CXR scan images.

METHODS

The proposed approach encompasses gathering and preprocessing CXR image datasets, training deep learning-based custom-made Convolutional Neural Network (CNN), pre-trained and hybrid transfer learning models, identifying the highest-performing model based on key evaluation metrics, and embedding this model into a web interface called CovMediScanX, designed for radiologists to detect the COVID-19 status in new CXR images.

RESULTS

The custom-made CNN model obtained a remarkable testing accuracy of 94.32% outperforming other models. CovMediScanX, employing the custom-made CNN underwent evaluation with an independent dataset also. The images in the independent dataset are sourced from a scanning machine that is entirely different from those used for the training dataset, highlighting a clear distinction of datasets in their origins. The evaluation outcome highlighted the framework's capability to accurately detect COVID-19 cases, showcasing encouraging results with a precision of 73% and a recall of 84% for positive cases. However, the model requires further enhancement, particularly in improving its detection of normal cases, as evidenced by lower precision and recall rates.

CONCLUSION

The research proposes CovMediScanX framework that demonstrates promising potential in automatically identifying COVID-19 cases from CXR images. While the model's overall performance on independent data needs improvement, it is evident that addressing bias through the inclusion of diverse data sources during training could further enhance accuracy and reliability.

Fully automated explainable abdominal CT contrast media phase classification using organ segmentation and machine learning

BACKGROUND

Contrast-enhanced computed tomography (CECT) provides much more information compared to non-enhanced CT images, especially for the differentiation of malignancies, such as liver carcinomas. Contrast media injection phase information is usually missing on public datasets and not standardized in the clinic even in the same region and language. This is a barrier to effective use of available CECT images in clinical research.

PURPOSE

The aim of this study is to detect contrast media injection phase from CT images by means of organ segmentation and machine learning algorithms.

METHODS

A total number of 2509 CT images split into four subsets of non-contrast (class #0), arterial (class #1), venous (class #2), and delayed (class #3) after contrast media injection were collected from two CT scanners. Seven organs including the liver, spleen, heart, kidneys, lungs, urinary bladder, and aorta along with body contour masks were generated by pre-trained deep learning algorithms. Subsequently, five first-order statistical features including average, standard deviation, 10, 50, and 90 percentiles extracted from the above-mentioned masks were fed to machine learning models after feature selection and reduction to classify the CT images in one of four above mentioned classes. A 10-fold data split strategy was followed. The performance of our methodology was evaluated in terms of classification accuracy metrics.

RESULTS

The best performance was achieved by Boruta feature selection and RF model with average area under the curve of more than 0.999 and accuracy of 0.9936 averaged over four classes and 10 folds. Boruta feature selection selected all predictor features. The lowest classification was observed for class #2 (0.9888), which is already an excellent result. In the 10-fold strategy, only 33 cases from 2509 cases (∼1.4%) were misclassified. The performance over all folds was consistent.

CONCLUSIONS

We developed a fast, accurate, reliable, and explainable methodology to classify contrast media phases which may be useful in data curation and annotation in big online datasets or local datasets with non-standard or no series description. Our model containing two steps of deep learning and machine learning may help to exploit available datasets more effectively.

Binary classification model of machine learning detected altered gut integrity in controlled-cortical impact model of traumatic brain injury

Aim of the study: To examine the effect of controlled-cortical impact (CCI), a preclinical model of traumatic brain injury (TBI), on intestinal integrity using a binary classification model of machine learning (ML).Materials and methods: Adult, male C57BL/6 mice were subjected to CCI surgery using a stereotaxic impactor (Impact One™). The rotarod and hot-plate tests were performed to assess the neurological deficits.Results: Mice underwent CCI displayed a remarkable neurological deficit as noticed by decreased latency to fall and lesser paw withdrawal latency in rotarod and hot plate test, respectively. Animals were sacrificed 3 days post-injury (dpi). The colon sections were stained with hematoxylin and eosin (H&E) to integrate with machinery tool-based algorithms. Several stained colon images were captured to build a dataset for ML model to predict the impact of CCI vs sham procedure. The best results were obtained with VGG16 features with SVM RBF kernel and VGG16 features with stacked fully connected layers on top. We achieved a test accuracy of 84% and predicted the disrupted gut permeability and epithelium wall of colon in CCI group as compared to sham-operated mice.Conclusion: We suggest that ML may become an important tool in the development of preclinical TBI model and discovery of newer therapeutics.

Multi modality fusion transformer with spatio-temporal feature aggregation module for psychiatric disorder diagnosis

Bipolar disorder (BD) is characterized by recurrent episodes of depression and mild mania. In this paper, to address the common issue of insufficient accuracy in existing methods and meet the requirements of clinical diagnosis, we propose a framework called Spatio-temporal Feature Fusion Transformer (STF2Former). It improves on our previous work - MFFormer by introducing a Spatio-temporal Feature Aggregation Module (STFAM) to learn the temporal and spatial features of rs-fMRI data. It promotes intra-modality attention and information fusion across different modalities. Specifically, this method decouples the temporal and spatial dimensions and designs two feature extraction modules for extracting temporal and spatial information separately. Extensive experiments demonstrate the effectiveness of our proposed STFAM in extracting features from rs-fMRI, and prove that our STF2Former can significantly outperform MFFormer and achieve much better results among other state-of-the-art methods.

Big data analysis for Covid-19 in hospital information systems

The COVID-19 pandemic has triggered a global public health crisis, affecting hundreds of countries. With the increasing number of infected cases, developing automated COVID-19 identification tools based on CT images can effectively assist clinical diagnosis and reduce the tedious workload of image interpretation. To expand the dataset for machine learning methods, it is necessary to aggregate cases from different medical systems to learn robust and generalizable models. This paper proposes a novel deep learning joint framework that can effectively handle heterogeneous datasets with distribution discrepancies for accurate COVID-19 identification. We address the cross-site domain shift by redesigning the COVID-Net's network architecture and learning strategy, and independent feature normalization in latent space to improve prediction accuracy and learning efficiency. Additionally, we propose using a contrastive training objective to enhance the domain invariance of semantic embeddings and boost classification performance on each dataset. We develop and evaluate our method with two large-scale public COVID-19 diagnosis datasets containing CT images. Extensive experiments show that our method consistently improves the performance both datasets, outperforming the original COVID-Net trained on each dataset by 13.27% and 15.15% in AUC respectively, also exceeding existing state-of-the-art multi-site learning methods.

Quantitative radiomics analysis of imaging features in adults and children Mycoplasma pneumonia

Purpose

This study aims to explore the value of clinical features, CT imaging signs, and radiomics features in differentiating between adults and children with Mycoplasma pneumonia and seeking quantitative radiomic representations of CT imaging signs.

Materials and methods

In a retrospective analysis of 981 cases of mycoplasmal pneumonia patients from November 2021 to December 2023, 590 internal data (adults:450, children: 140) randomly divided into a training set and a validation set with an 8:2 ratio and 391 external test data (adults:121; children:270) were included. Using univariate analysis, CT imaging signs and clinical features with significant differences (p < 0.05) were selected. After segmenting the lesion area on the CT image as the region of interest, 1,904 radiomic features were extracted. Then, Pearson correlation analysis (PCC) and the least absolute shrinkage and selection operator (LASSO) were used to select the radiomic features. Based on the selected features, multivariable logistic regression analysis was used to establish the clinical model, CT image model, radiomic model, and combined model. The predictive performance of each model was evaluated using ROC curves, AUC, sensitivity, specificity, accuracy, and precision. The AUC between each model was compared using the Delong test. Importantly, the radiomics features and quantitative and qualitative CT image features were analyzed using Pearson correlation analysis and analysis of variance, respectively.

Results

For the individual model, the radiomics model, which was built using 45 selected features, achieved the highest AUCs in the training set, validation set, and external test set, which were 0.995 (0.992, 0.998), 0.952 (0.921, 0.978), and 0.969 (0.953, 0.982), respectively. In all models, the combined model achieved the highest AUCs, which were 0.996 (0.993, 0.998), 0.972 (0.942, 0.995), and 0.986 (0.976, 0.993) in the training set, validation set, and test set, respectively. In addition, we selected 11 radiomics features and CT image features with a correlation coefficient r greater than 0.35.

Conclusion

The combined model has good diagnostic performance for differentiating between adults and children with mycoplasmal pneumonia, and different CT imaging signs are quantitatively represented by radiomics.

Reinvestigating the performance of artificial intelligence classification algorithms on COVID-19 X-Ray and CT images

There are concerns that artificial intelligence (AI) algorithms may create underdiagnosis bias by mislabeling patient individuals with certain attributes (e.g., female and young) as healthy. Addressing this bias is crucial given the urgent need for AI diagnostics facing rapidly spreading infectious diseases like COVID-19. We find the prevalent AI diagnostic models show an underdiagnosis rate among specific patient populations, and the underdiagnosis rate is higher in some intersectional specific patient populations (for example, females aged 20-40 years). Additionally, we find training AI models on heterogeneous datasets (positive and negative samples from different datasets) may lead to poor model generalization. The model's classification performance varies significantly across test sets, with the accuracy of the better performance being over 40% higher than that of the poor performance. In conclusion, we developed an AI bias analysis pipeline to help researchers recognize and address biases that impact medical equality and ethics.

Predictive models-assisted diagnosis of AIDS-associated Pneumocystis jirovecii pneumonia in the emergency room, based on clinical, laboratory, and radiological data

We assessed predictive models (PMs) for diagnosing Pneumocystis jirovecii pneumonia (PCP) in AIDS patients seen in the emergency room (ER), aiming to guide empirical treatment decisions. Data from suspected PCP cases among AIDS patients were gathered prospectively at a reference hospital's ER, with diagnoses later confirmed through sputum PCR analysis. We compared clinical, laboratory, and radiological data between PCP and non-PCP groups, using the Boruta algorithm to confirm significant differences. We evaluated ten PMs tailored for various ERs resource levels to diagnose PCP. Four scenarios were created, two based on X-ray findings (diffuse interstitial infiltrate) and two on CT scans ("ground-glass"), incorporating mandatory variables: lactate dehydrogenase, O2sat, C-reactive protein, respiratory rate (> 24 bpm), and dry cough. We also assessed HIV viral load and CD4 cell count. Among the 86 patients in the study, each model considered either 6 or 8 parameters, depending on the scenario. Many models performed well, with accuracy, precision, recall, and AUC scores > 0.8. Notably, nearest neighbor and naïve Bayes excelled (scores > 0.9) in specific scenarios. Surprisingly, HIV viral load and CD4 cell count did not improve model performance. In conclusion, ER-based PMs using readily available data can significantly aid PCP treatment decisions in AIDS patients.

Contrastive learning with token projection for Omicron pneumonia identification from few-shot chest CT images

Introduction

Deep learning-based methods can promote and save critical time for the diagnosis of pneumonia from computed tomography (CT) images of the chest, where the methods usually rely on large amounts of labeled data to learn good visual representations. However, medical images are difficult to obtain and need to be labeled by professional radiologists.

Methods

To address this issue, a novel contrastive learning model with token projection, namely CoTP, is proposed for improving the diagnostic quality of few-shot chest CT images. Specifically, (1) we utilize solely unlabeled data for fitting CoTP, along with a small number of labeled samples for fine-tuning, (2) we present a new Omicron dataset and modify the data augmentation strategy, i.e., random Poisson noise perturbation for the CT interpretation task, and (3) token projection is utilized to further improve the quality of the global visual representations.

Results

The ResNet50 pre-trained by CoTP attained accuracy (ACC) of 92.35%, sensitivity (SEN) of 92.96%, precision (PRE) of 91.54%, and the area under the receiver-operating characteristics curve (AUC) of 98.90% on the presented Omicron dataset. On the contrary, the ResNet50 without pre-training achieved ACC, SEN, PRE, and AUC of 77.61, 77.90, 76.69, and 85.66%, respectively.

Conclusion

Extensive experiments reveal that a model pre-trained by CoTP greatly outperforms that without pre-training. The CoTP can improve the efficacy of diagnosis and reduce the heavy workload of radiologists for screening of Omicron pneumonia.

Constructing a Deep Learning Radiomics Model Based on X-ray Images and Clinical Data for Predicting and Distinguishing Acute and Chronic Osteoporotic Vertebral Fractures: A Multicenter Study

RATIONALE AND OBJECTIVES

To construct and validate a deep learning radiomics (DLR) model based on X-ray images for predicting and distinguishing acute and chronic osteoporotic vertebral fractures (OVFs).

METHODS

A total of 942 cases (1076 vertebral bodies) with both vertebral X-ray examination and MRI scans were included in this study from three hospitals. They were divided into a training cohort (n = 712), an internal validation cohort (n = 178), an external validation cohort (n = 111), and a prospective validation cohort (n = 75). The ResNet-50 model architecture was used for deep transfer learning (DTL), with pre-training performed on RadImageNet and ImageNet datasets. DTL features and radiomics features were extracted from lateral X-ray images of OVFs patients and fused together. A logistic regression model with the least absolute shrinkage and selection operator was established, with MRI showing bone marrow edema as the gold standard for acute OVFs. The performance of the model was evaluated using receiver operating characteristic curves. Eight machine learning classification models were evaluated for their ability to distinguish between acute and chronic OVFs. The Nomogram was constructed by combining clinical baseline data to achieve visualized classification assessment. The predictive performance of the best RadImageNet model and ImageNet model was compared using the Delong test. The clinical value of the Nomogram was evaluated using decision curve analysis (DCA).

RESULTS

Pre-training resulted in 34 and 39 fused features after feature selection and fusion. The most effective machine learning algorithm in both DLR models was Light Gradient Boosting Machine. Using the Delong test, the area under the curve (AUC) for distinguishing between acute and chronic OVFs in the training cohort was 0.979 and 0.972 for the RadImageNet and ImageNet models, respectively, with no statistically significant difference between them (P = 0.235). In the internal validation cohort, external validation cohort, and prospective validation cohort, the AUCs for the two models were 0.967 vs 0.629, 0.886 vs 0.817, and 0.933 vs 0.661, respectively, with statistically significant differences in all comparisons (P < 0.05). The deep learning radiomics nomogram (DLRN) was constructed by combining the predictive model of RadImageNet with clinical baseline features, resulting in AUCs of 0.981, 0.974, 0.895, and 0.902 in the training cohort, internal validation cohort, external validation cohort, and prospective validation cohort, respectively. Using the Delong test, the AUCs for the fused feature model and the DLRN in the training cohort were 0.979 and 0.981, respectively, with no statistically significant difference between them (P = 0.169). In the internal validation cohort, external validation cohort, and prospective validation cohort, the AUCs for the two models were 0.967 vs 0.974, 0.886 vs 0.895, and 0.933 vs 0.902, respectively, with statistically significant differences in all comparisons (P < 0.05). The Nomogram showed a slight improvement in predictive performance in the internal and external validation cohort, but a slight decrease in the prospective validation cohort (0.933 vs 0.902). DCA showed that the Nomogram provided more benefits to patients compared to the DLR models.

CONCLUSION

Compared to the ImageNet model, the RadImageNet model has higher diagnostic value in distinguishing between acute and chronic OVFs. Furthermore, the diagnostic performance of the model is further improved when combined with clinical baseline features to construct the Nomogram.

A methodological showcase: utilizing minimal clinical parameters for early-stage mortality risk assessment in COVID-19-positive patients

The scarcity of data is likely to have a negative effect on machine learning (ML). Yet, in the health sciences, data is diverse and can be costly to acquire. Therefore, it is critical to develop methods that can reach similar accuracy with minimal clinical features. This study explores a methodology that aims to build a model using minimal clinical parameters to reach comparable performance to a model trained with a more extensive list of parameters. To develop this methodology, a dataset of over 1,000 COVID-19-positive patients was used. A machine learning model was built with over 90% accuracy when combining 24 clinical parameters using Random Forest (RF) and logistic regression. Furthermore, to obtain minimal clinical parameters to predict the mortality of COVID-19 patients, the features were weighted using both Shapley values and RF feature importance to get the most important factors. The six most highly weighted features that could produce the highest performance metrics were combined for the final model. The accuracy of the final model, which used a combination of six features, is 90% with the random forest classifier and 91% with the logistic regression model. This performance is close to that of a model using 24 combined features (92%), suggesting that highly weighted minimal clinical parameters can be used to reach similar performance. The six clinical parameters identified here are acute kidney injury, glucose level, age, troponin, oxygen level, and acute hepatic injury. Among those parameters, acute kidney injury was the highest-weighted feature. Together, a methodology was developed using significantly minimal clinical parameters to reach performance metrics similar to a model trained with a large dataset, highlighting a novel approach to address the problems of clinical data collection for machine learning.

Advanced Terahertz Refractive Sensing And Fingerprint Recognition Through Metasurface-Excited Surface Waves

High-sensitive metasurface-based sensors are essential for effective substance detection and insightful bio-interaction studies, which compress light in subwavelength volumes to enhance light-matter interactions. However, current methods to improve sensing performance always focus on optimizing near-field response of individual meta-atom, and fingerprint recognition for bio-substances necessitates several pixelated metasurfaces to establish a quasi-continuous spectrum. Here, a novel sensing strategy is proposed to achieve Terahertz (THz) refractive sensing, and fingerprint recognition based on surface waves (SWs). Leveraging the long-range transmission, strong confinement, and interface sensitivity of SWs, a metasurface-supporting SWs excitation and propagation is experimentally verified to achieve sensing integrations. Through wide-band information collection of SWs, the proposed sensor not only facilitates refractive sensing up to 215.5°/RIU, but also enables the simultaneous resolution of multiple fingerprint information within a continuous spectrum. By covering 5 µm thickness of polyimide, quartz and silicon nitride layers, the maximum phase change of 91.1°, 101.8°, and 126.4° is experimentally obtained within THz band, respectively. Thus, this strategy broadens the research scope of metasurface-excited SWs and introduces a novel paradigm for ultrasensitive sensing functions.

Post-COVID highlights: Challenges and solutions of artificial intelligence techniques for swift identification of COVID-19

Since the onset of the COVID-19 pandemic in 2019, there has been a concerted effort to develop cost-effective, non-invasive, and rapid AI-based tools. These tools were intended to alleviate the burden on healthcare systems, control the rapid spread of the virus, and enhance intervention outcomes, all in response to this unprecedented global crisis. As we transition into a post-COVID era, we retrospectively evaluate these proposed studies and offer a review of the techniques employed in AI diagnostic models, with a focus on the solutions proposed for different challenges. This review endeavors to provide insights into the diverse solutions designed to address the multifaceted challenges that arose during the pandemic. By doing so, we aim to prepare the AI community for the development of AI tools tailored to address public health emergencies effectively.

The unintended consequences of artificial intelligence in paediatric radiology

Over the past decade, there has been a dramatic rise in the interest relating to the application of artificial intelligence (AI) in radiology. Originally only 'narrow' AI tasks were possible; however, with increasing availability of data, teamed with ease of access to powerful computer processing capabilities, we are becoming more able to generate complex and nuanced prediction models and elaborate solutions for healthcare. Nevertheless, these AI models are not without their failings, and sometimes the intended use for these solutions may not lead to predictable impacts for patients, society or those working within the healthcare profession. In this article, we provide an overview of the latest opinions regarding AI ethics, bias, limitations, challenges and considerations that we should all contemplate in this exciting and expanding field, with a special attention to how this applies to the unique aspects of a paediatric population. By embracing AI technology and fostering a multidisciplinary approach, it is hoped that we can harness the power AI brings whilst minimising harm and ensuring a beneficial impact on radiology practice.

Utilizing multimodal AI to improve genetic analyses of cardiovascular traits

Electronic health records, biobanks, and wearable biosensors contain multiple high-dimensional clinical data (HDCD) modalities (e.g., ECG, Photoplethysmography (PPG), and MRI) for each individual. Access to multimodal HDCD provides a unique opportunity for genetic studies of complex traits because different modalities relevant to a single physiological system (e.g., circulatory system) encode complementary and overlapping information. We propose a novel multimodal deep learning method, M-REGLE, for discovering genetic associations from a joint representation of multiple complementary HDCD modalities. We showcase the effectiveness of this model by applying it to several cardiovascular modalities. M-REGLE jointly learns a lower representation (i.e., latent factors) of multimodal HDCD using a convolutional variational autoencoder, performs genome wide association studies (GWAS) on each latent factor, then combines the results to study the genetics of the underlying system. To validate the advantages of M-REGLE and multimodal learning, we apply it to common cardiovascular modalities (PPG and ECG), and compare its results to unimodal learning methods in which representations are learned from each data modality separately, but the downstream genetic analyses are performed on the combined unimodal representations. M-REGLE identifies 19.3% more loci on the 12-lead ECG dataset, 13.0% more loci on the ECG lead I + PPG dataset, and its genetic risk score significantly outperforms the unimodal risk score at predicting cardiac phenotypes, such as atrial fibrillation (Afib), in multiple biobanks.

Multi-modal deep learning methods for classification of chest diseases using different medical imaging and cough sounds

Chest disease refers to a wide range of conditions affecting the lungs, such as COVID-19, lung cancer (LC), consolidation lung (COL), and many more. When diagnosing chest disorders medical professionals may be thrown off by the overlapping symptoms (such as fever, cough, sore throat, etc.). Additionally, researchers and medical professionals make use of chest X-rays (CXR), cough sounds, and computed tomography (CT) scans to diagnose chest disorders. The present study aims to classify the nine different conditions of chest disorders, including COVID-19, LC, COL, atelectasis (ATE), tuberculosis (TB), pneumothorax (PNEUTH), edema (EDE), pneumonia (PNEU). Thus, we suggested four novel convolutional neural network (CNN) models that train distinct image-level representations for nine different chest disease classifications by extracting features from images. Furthermore, the proposed CNN employed several new approaches such as a max-pooling layer, batch normalization layers (BANL), dropout, rank-based average pooling (RBAP), and multiple-way data generation (MWDG). The scalogram method is utilized to transform the sounds of coughing into a visual representation. Before beginning to train the model that has been developed, the SMOTE approach is used to calibrate the CXR and CT scans as well as the cough sound images (CSI) of nine different chest disorders. The CXR, CT scan, and CSI used for training and evaluating the proposed model come from 24 publicly available benchmark chest illness datasets. The classification performance of the proposed model is compared with that of seven baseline models, namely Vgg-19, ResNet-101, ResNet-50, DenseNet-121, EfficientNetB0, DenseNet-201, and Inception-V3, in addition to state-of-the-art (SOTA) classifiers. The effectiveness of the proposed model is further demonstrated by the results of the ablation experiments. The proposed model was successful in achieving an accuracy of 99.01%, making it superior to both the baseline models and the SOTA classifiers. As a result, the proposed approach is capable of offering significant support to radiologists and other medical professionals.

A high-speed microscopy system based on deep learning to detect yeast-like fungi cells in blood

Background: Blood-invasive fungal infections can cause the death of patients, while diagnosis of fungal infections is challenging. Methods: A high-speed microscopy detection system was constructed that included a microfluidic system, a microscope connected to a high-speed camera and a deep learning analysis section. Results: For training data, the sensitivity and specificity of the convolutional neural network model were 93.5% (92.7-94.2%) and 99.5% (99.1-99.5%), respectively. For validating data, the sensitivity and specificity were 81.3% (80.0-82.5%) and 99.4% (99.2-99.6%), respectively. Cryptococcal cells were found in 22.07% of blood samples. Conclusion: This high-speed microscopy system can analyze fungal pathogens in blood samples rapidly with high sensitivity and specificity and can help dramatically accelerate the diagnosis of fungal infectious diseases.

Federated Learning for Decentralized Artificial Intelligence in Melanoma Diagnostics

Importance

The development of artificial intelligence (AI)-based melanoma classifiers typically calls for large, centralized datasets, requiring hospitals to give away their patient data, which raises serious privacy concerns. To address this concern, decentralized federated learning has been proposed, where classifier development is distributed across hospitals.

Objective

To investigate whether a more privacy-preserving federated learning approach can achieve comparable diagnostic performance to a classical centralized (ie, single-model) and ensemble learning approach for AI-based melanoma diagnostics.

Design, Setting, and Participants

This multicentric, single-arm diagnostic study developed a federated model for melanoma-nevus classification using histopathological whole-slide images prospectively acquired at 6 German university hospitals between April 2021 and February 2023 and benchmarked it using both a holdout and an external test dataset. Data analysis was performed from February to April 2023.

Exposures

All whole-slide images were retrospectively analyzed by an AI-based classifier without influencing routine clinical care.

Main Outcomes and Measures

The area under the receiver operating characteristic curve (AUROC) served as the primary end point for evaluating the diagnostic performance. Secondary end points included balanced accuracy, sensitivity, and specificity.

Results

The study included 1025 whole-slide images of clinically melanoma-suspicious skin lesions from 923 patients, consisting of 388 histopathologically confirmed invasive melanomas and 637 nevi. The median (range) age at diagnosis was 58 (18-95) years for the training set, 57 (18-93) years for the holdout test dataset, and 61 (18-95) years for the external test dataset; the median (range) Breslow thickness was 0.70 (0.10-34.00) mm, 0.70 (0.20-14.40) mm, and 0.80 (0.30-20.00) mm, respectively. The federated approach (0.8579; 95% CI, 0.7693-0.9299) performed significantly worse than the classical centralized approach (0.9024; 95% CI, 0.8379-0.9565) in terms of AUROC on a holdout test dataset (pairwise Wilcoxon signed-rank, P < .001) but performed significantly better (0.9126; 95% CI, 0.8810-0.9412) than the classical centralized approach (0.9045; 95% CI, 0.8701-0.9331) on an external test dataset (pairwise Wilcoxon signed-rank, P < .001). Notably, the federated approach performed significantly worse than the ensemble approach on both the holdout (0.8867; 95% CI, 0.8103-0.9481) and external test dataset (0.9227; 95% CI, 0.8941-0.9479).

Conclusions and Relevance

The findings of this diagnostic study suggest that federated learning is a viable approach for the binary classification of invasive melanomas and nevi on a clinically representative distributed dataset. Federated learning can improve privacy protection in AI-based melanoma diagnostics while simultaneously promoting collaboration across institutions and countries. Moreover, it may have the potential to be extended to other image classification tasks in digital cancer histopathology and beyond.

Diagnostic performance of deep learning models versus radiologists in COVID-19 pneumonia: A systematic review and meta-analysis

PURPOSE

Although several studies have compared the performance of deep learning (DL) models and radiologists for the diagnosis of COVID-19 pneumonia on CT of the chest, these results have not been collectively evaluated. We performed a meta-analysis of original articles comparing the performance of DL models versus radiologists in detecting COVID-19 pneumonia.

METHODS

A systematic search was conducted on the three main medical literature databases, Scopus, Web of Science, and PubMed, for articles published as of February 1st, 2023. We included original scientific articles that compared DL models trained to detect COVID-19 pneumonia on CT to radiologists. Meta-analysis was performed to determine DL versus radiologist performance in terms of model sensitivity and specificity, taking into account inter and intra-study heterogeneity.

RESULTS

Twenty-two articles met the inclusion criteria. Based on the meta-analytic calculations, DL models had significantly higher pooled sensitivity (0.933 vs. 0.829, p < 0.001) compared to radiologists with similar pooled specificity (0.905 vs. 0.897, p = 0.746). In the differentiation of COVID-19 versus community-acquired pneumonia, the DL models had significantly higher sensitivity compared to radiologists (0.915 vs. 0.836, p = 0.001).

CONCLUSIONS

DL models have high performance for screening of COVID-19 pneumonia on chest CT, offering the possibility of these models for augmenting radiologists in clinical practice.

Application of artificial intelligence (AI) to control COVID-19 pandemic: Current status and future prospects

The impact of the coronavirus disease 2019 (COVID-19) pandemic on the everyday livelihood of people has been monumental and unparalleled. Although the pandemic has vastly affected the global healthcare system, it has also been a platform to promote and develop pioneering applications based on autonomic artificial intelligence (AI) technology with therapeutic significance in combating the pandemic. Artificial intelligence has successfully demonstrated that it can reduce the probability of human-to-human infectivity of the virus through evaluation, analysis, and triangulation of existing data on the infectivity and spread of the virus. This review talks about the applications and significance of modern robotic and automated systems that may assist in spreading a pandemic. In addition, this study discusses intelligent wearable devices and how they could be helpful throughout the COVID-19 pandemic.

AI-Enhanced Visual-Spectral Synergy for Fast and Ultrasensitive Biodetection of Breast Cancer-Related miRNAs

In biomedical testing, artificial intelligence (AI)-enhanced analysis has gradually been applied to the diagnosis of certain diseases. This research employs AI algorithms to refine the precision of integrative detection, encompassing both visual results and fluorescence spectra from lateral flow assays (LFAs), which signal the presence of cancer-linked miRNAs. Specifically, the color shift of gold nanoparticles (GNPs) is paired with the red fluorescence from nitrogen vacancy color centers (NV-centers) in fluorescent nanodiamonds (FNDs) and is integrated into LFA strips. While GNPs amplify the fluorescence of FNDs, in turn, FNDs enhance the color intensity of GNPs. This reciprocal intensification of fluorescence and color can be synergistically augmented with AI algorithms, thereby improving the detection sensitivity for early diagnosis. Supported by the detection platform based on this strategy, the fastest detection results with a limit of detection (LOD) at the fM level and the R2 value of ∼0.9916 for miRNA can be obtained within 5 min. Meanwhile, by labeling the capture probes for miRNA-21 and miRNA-96 (both of which are early indicators of breast cancer) on separate T-lines, simultaneous detection of them can be achieved. The miRNA detection methods employed in this study may potentially be applied in the future for the early detection of breast cancer.

Harnessing of Artificial Intelligence for the Diagnosis and Prevention of Hospital-Acquired Infections: A Systematic Review

Healthcare-associated infections (HAIs) are the most common adverse events in healthcare and constitute a major global public health concern. Surveillance represents the foundation for the effective prevention and control of HAIs, yet conventional surveillance is costly and labor intensive. Artificial intelligence (AI) and machine learning (ML) have the potential to support the development of HAI surveillance algorithms for the understanding of HAI risk factors, the improvement of patient risk stratification as well as the prediction and timely detection and prevention of infections. AI-supported systems have so far been explored for clinical laboratory testing and imaging diagnosis, antimicrobial resistance profiling, antibiotic discovery and prediction-based clinical decision support tools in terms of HAIs. This review aims to provide a comprehensive summary of the current literature on AI applications in the field of HAIs and discuss the future potentials of this emerging technology in infection practice. Following the PRISMA guidelines, this study examined the articles in databases including PubMed and Scopus until November 2023, which were screened based on the inclusion and exclusion criteria, resulting in 162 included articles. By elucidating the advancements in the field, we aim to highlight the potential applications of AI in the field, report related issues and shortcomings and discuss the future directions.

Detection support of lesions in patients with prostate cancer using [Formula: see text]-PSMA 1007 PET/CT

PURPOSE

This study proposes a detection support system for primary and metastatic lesions of prostate cancer using [Formula: see text]-PSMA 1007 positron emission tomography/computed tomography (PET/CT) images with non-image information, including patient metadata and location information of an input slice image.

METHODS

A convolutional neural network with condition generators and feature-wise linear modulation (FiLM) layers was employed to allow input of not only PET/CT images but also non-image information, namely, Gleason score, flag of pre- or post-prostatectomy, and normalized z-coordinate of an input slice. We explored the insertion position of the FiLM layers to optimize the conditioning of the network using non-image information.

RESULTS

[Formula: see text]-PSMA 1007 PET/CT images were collected from 163 patients with prostate cancer and applied to the proposed system in a threefold cross-validation manner to evaluate the performance. The proposed system achieved a Dice score of 0.5732 (per case) and sensitivity of 0.8200 (per lesion), which are 3.87 and 4.16 points higher than the network without non-image information.

CONCLUSION

This study demonstrated the effectiveness of the use of non-image information, including metadata of the patient and location information of the input slice image, in the detection of prostate cancer from [Formula: see text]-PSMA 1007 PET/CT images. Improvement in the sensitivity of inactive and small lesions remains a future challenge.

Nanotechnology-based theranostic and prophylactic approaches against SARS-CoV-2

SARS-CoV-2 (COVID-19) pandemic has been an unpredicted burden on global healthcare system by infecting over 700 million individuals, with approximately 6 million deaths worldwide. COVID-19 significantly impacted all sectors, but it very adversely affected the healthcare system. These effects were much more evident in the resource limited part of the world. Individuals with acute conditions were also severely impacted. Although classical COVID-19 diagnostics such as RT-PCR and rapid antibody testing have played a crucial role in reducing the spread of infection, these diagnostic techniques are associated with certain limitations. For instance, drawback of RT-PCR diagnostics is that due to degradation of viral RNA during shipping, it can give false negative results. Also, rapid antibody testing majorly depends on the phase of infection and cannot be performed on immune compromised individuals. These limitations in current diagnostic tools require the development of nanodiagnostic tools for early detection of COVID-19 infection. Therefore, the SARS-CoV-2 outbreak has necessitated the development of specific, responsive, accurate, rapid, low-cost, and simple-to-use diagnostic tools at point of care. In recent years, early detection has been a challenge for several health diseases that require prompt attention and treatment. Disease identification at an early stage, increased imaging of inner health issues, and ease of diagnostic processes have all been established using a new discipline of laboratory medicine called nanodiagnostics, even before symptoms have appeared. Nanodiagnostics refers to the application of nanoparticles (material with size equal to or less than 100 nm) for medical diagnostic purposes. The special property of nanomaterials compared to their macroscopic counterparts is a lesser signal loss and an enhanced electromagnetic field. Nanosize of the detection material also enhances its sensitivity and increases the signal to noise ratio. Microchips, nanorobots, biosensors, nanoidentification of single-celled structures, and microelectromechanical systems are some of the most modern nanodiagnostics technologies now in development. Here, we have highlighted the important roles of nanotechnology in healthcare sector, with a detailed focus on the management of the COVID-19 pandemic. We outline the different types of nanotechnology-based diagnostic devices for SARS-CoV-2 and the possible applications of nanomaterials in COVID-19 treatment. We also discuss the utility of nanomaterials in formulating preventive strategies against SARS-CoV-2 including their use in manufacture of protective equipment, formulation of vaccines, and strategies for directly hindering viral infection. We further discuss the factors hindering the large-scale accessibility of nanotechnology-based healthcare applications and suggestions for overcoming them.

A comprehensive review on immunogen and immune-response proteins of SARS-CoV-2 and their applications in prevention, diagnosis, and treatment of COVID-19

Exposure to severe acute respiratory syndrome-corona virus-2 (SARS-CoV-2) prompts humoral immune responses in the human body. As the auxiliary diagnosis of a current infection, the existence of viral proteins can be checked from specific antibodies (Abs) induced by immunogenic viral proteins. For people with a weakened immune system, Ab treatment can help neutralize viral antigens to resist and treat the disease. On the other hand, highly immunogenic viral proteins can serve as effective markers for detecting prior infections. Additionally, the identification of viral particles or the presence of antibodies may help establish an immune defense against the virus. These immunogenic proteins rather than SARS-CoV-2 can be given to uninfected people as a vaccination to improve their coping ability against COVID-19 through the generation of memory plasma cells. In this work, we review immunogenic and immune-response proteins derived from SARS-CoV-2 with regard to their classification, origin, and diverse applications (e.g., prevention (vaccine development), diagnostic testing, and treatment (via neutralizing Abs)). Finally, advanced immunization strategies against COVID-19 are discussed along with the contemporary circumstances and future challenges.

Upper body thermal images and associated clinical data from a pilot cohort study of COVID-19

OBJECTIVES

The data was collected for a cohort study to assess the capability of thermal videos in the detection of SARS-CoV-2. Using this data, a published study applied machine learning to analyze thermal image features for Covid-19 detection.

DATA DESCRIPTION

The study recorded a set of measurements from 252 participants over 18 years of age requesting a SARS-CoV-2 PCR (polymerase chain reaction) test at the Hospital Zambrano-Hellion in Nuevo León, México. Data for PCR results, demographics, vital signs, food intake, activities and lifestyle factors, recently taken medications, respiratory and general symptoms, and a thermal video session where the volunteers performed a simple breath-hold in four different positions were collected. Vital signs recorded include axillary temperature, blood pressure, heart rate, and oxygen saturation. Each thermal video is split into 4 scenes, corresponding to front, back, left and right sides, and is available in MPEG-4 format to facilitate inclusion into pipelines for image processing. Raw JPEG images of the background between subjects are included to register variations in room temperatures.

Machine Learning for COVID-19 Determination Using Surface-Enhanced Raman Spectroscopy

The rapid, low cost, and efficient detection of SARS-CoV-2 virus infection, especially in clinical samples, remains a major challenge. A promising solution to this problem is the combination of a spectroscopic technique: surface-enhanced Raman spectroscopy (SERS) with advanced chemometrics based on machine learning (ML) algorithms. In the present study, we conducted SERS investigations of saliva and nasopharyngeal swabs taken from a cohort of patients (saliva: 175; nasopharyngeal swabs: 114). Obtained SERS spectra were analyzed using a range of classifiers in which random forest (RF) achieved the best results, e.g., for saliva, the precision and recall equals 94.0% and 88.9%, respectively. The results demonstrate that even with a relatively small number of clinical samples, the combination of SERS and shallow machine learning can be used to identify SARS-CoV-2 virus in clinical practice.

Acute ischemic stroke prediction and predictive factors analysis using hematological indicators in elderly hypertensives post-transient ischemic attack

Elderly hypertensive patients diagnosed with transient ischemic attack (TIA) are at a heightened risk for developing acute ischemic stroke (AIS). This underscores the critical need for effective risk prediction and identification of predictive factors. In our study, we utilized patient data from peripheral blood tests and clinical profiles within hospital information systems. These patients were followed for a three-year period to document incident AIS. Our cohort of 11,056 individuals was randomly divided into training, validation, and testing sets in a 5:2:3 ratio. We developed an XGBoost model, developed using selected indicators, provides an effective and non-invasive method for predicting the risk of AIS in elderly hypertensive patients diagnosed with TIA. Impressively, this model achieved a balanced accuracy of 0.9022, a recall of 0.8688, and a PR-AUC of 0.9315. Notably, our model effectively encapsulates essential data variations involving mixed nonlinear interactions, providing competitive performance against more complex models that incorporate a wider range of variables. Further, we conducted an in-depth analysis of the importance and sensitivity of each selected indicator and their interactions. This research equips clinicians with the necessary tools for more precise identification of high-risk individuals, thereby paving the way for more effective stroke prevention and management strategies.

Applications of artificial intelligence in dentomaxillofacial imaging-a systematic review

BACKGROUND

Artificial intelligence (AI) technology has been increasingly developed in oral and maxillofacial imaging. The aim of this systematic review was to assess the applications and performance of the developed algorithms in different dentomaxillofacial imaging modalities.

STUDY DESIGN

A systematic search of PubMed and Scopus databases was performed. The search strategy was set as a combination of the following keywords: "Artificial Intelligence," "Machine Learning," "Deep Learning," "Neural Networks," "Head and Neck Imaging," and "Maxillofacial Imaging." Full-text screening and data extraction were independently conducted by two independent reviewers; any mismatch was resolved by discussion. The risk of bias was assessed by one reviewer and validated by another.

RESULTS

The search returned a total of 3,392 articles. After careful evaluation of the titles, abstracts, and full texts, a total number of 194 articles were included. Most studies focused on AI applications for tooth and implant classification and identification, 3-dimensional cephalometric landmark detection, lesion detection (periapical, jaws, and bone), and osteoporosis detection.

CONCLUSION

Despite the AI models' limitations, they showed promising results. Further studies are needed to explore specific applications and real-world scenarios before confidently integrating these models into dental practice.

Combating COVID-19 Crisis using Artificial Intelligence (AI) Based Approach: Systematic Review

BACKGROUND

SARS-CoV-2, the unique coronavirus that causes COVID-19, has wreaked damage around the globe, with victims displaying a wide range of difficulties that have encouraged medical professionals to look for innovative technical solutions and therapeutic approaches. Artificial intelligence-based methods have contributed a significant part in tackling complicated issues, and some institutions have been quick to embrace and tailor these solutions in response to the COVID-19 pandemic's obstacles. Here, in this review article, we have covered a few DL techniques for COVID-19 detection and diagnosis, as well as ML techniques for COVID-19 identification, severity classification, vaccine and drug development, mortality rate prediction, contact tracing, risk assessment, and public distancing. This review illustrates the overall impact of AI/ML tools on tackling and managing the outbreak.

PURPOSE

The focus of this research was to undertake a thorough evaluation of the literature on the part of Artificial Intelligence (AI) as a complete and efficient solution in the battle against the COVID-19 epidemic in the domains of detection and diagnostics of disease, mortality prediction and vaccine as well as drug development.

METHODS

A comprehensive exploration of PubMed, Web of Science, and Science Direct was conducted using PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) regulations to find all possibly suitable papers conducted and made publicly available between December 1, 2019, and August 2023. COVID-19, along with AI-specific words, was used to create the query syntax.

RESULTS

During the period covered by the search strategy, 961 articles were published and released online. Out of these, a total of 135 papers were chosen for additional investigation. Mortality rate prediction, early detection and diagnosis, vaccine as well as drug development, and lastly, incorporation of AI for supervising and controlling the COVID-19 pandemic were the four main topics focused entirely on AI applications used to tackle the COVID-19 crisis. Out of 135, 60 research papers focused on the detection and diagnosis of the COVID-19 pandemic. Next, 19 of the 135 studies applied a machine-learning approach for mortality rate prediction. Another 22 research publications emphasized the vaccine as well as drug development. Finally, the remaining studies were concentrated on controlling the COVID-19 pandemic by applying AI AI-based approach to it.

CONCLUSION

We compiled papers from the available COVID-19 literature that used AI-based methodologies to impart insights into various COVID-19 topics in this comprehensive study. Our results suggest crucial characteristics, data types, and COVID-19 tools that can aid in medical and translational research facilitation.

Application of Artificial intelligence in COVID-19-related geriatric care: A scoping review

BACKGROUND

Older adults have been disproportionately affected by the COVID-19 pandemic. This scoping review aimed to summarize the current evidence of artificial intelligence (AI) use in the screening/monitoring, diagnosis, and/or treatment of COVID-19 among older adults.

METHOD

The review followed the Joanna Briggs Institute and Arksey and O'Malley frameworks. An information specialist performed a comprehensive search from the date of inception until May 2021, in six bibliographic databases. The selected studies considered all populations, and all AI interventions that had been used in COVID-19-related geriatric care. We focused on patient, healthcare provider, and healthcare system-related outcomes. The studies were restricted to peer-reviewed English publications. Two authors independently screened the titles and abstracts of the identified records, read the selected full texts, and extracted data from the included studies using a validated data extraction form. Disagreements were resolved by consensus, and if this was not possible, the opinion of a third reviewer was sought.

RESULTS

Six databases were searched , yielding 3,228 articles, of which 10 were included. The majority of articles used a single AI model to assess the association between patients' comorbidities and COVID-19 outcomes. Articles were mainly conducted in high-income countries, with limited representation of females in study participants, and insufficient reporting of participants' race and ethnicity.

DISCUSSION

This review highlighted how the COVID-19 pandemic has accelerated the application of AI to protect older populations, with most interventions in the pilot testing stage. Further work is required to measure effectiveness of these technologies in a larger scale, use more representative datasets for training of AI models, and expand AI applications to low-income countries.

Development and External Validation of Clinical Features-based Machine Learning Models for Predicting COVID-19 in the Emergency Department

Introduction

Timely diagnosis of patients affected by an emerging infectious disease plays a crucial role in treating patients and avoiding disease spread. In prior research, we developed an approach by using machine learning (ML) algorithms to predict serious acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection based on clinical features of patients visiting an emergency department (ED) during the early coronavirus 2019 (COVID-19) pandemic. In this study, we aimed to externally validate this approach within a distinct ED population.

Methods

To create our training/validation cohort (model development) we collected data retrospectively from suspected COVID-19 patients at a US ED from February 23-May 12, 2020. Another dataset was collected as an external validation (testing) cohort from an ED in another country from May 12-June 15, 2021. Clinical features including patient demographics and triage information were used to train and test the models. The primary outcome was the confirmed diagnosis of COVID-19, defined as a positive reverse transcription polymerase chain reaction test result for SARS-CoV-2. We employed three different ML algorithms, including gradient boosting, random forest, and extra trees classifiers, to construct the predictive model. The predictive performances were evaluated with the area under the receiver operating characteristic curve (AUC) in the testing cohort.

Results

In total, 580 and 946 ED patients were included in the training and testing cohorts, respectively. Of them, 98 (16.9%) and 180 (19.0%) were diagnosed with COVID-19. All the constructed ML models showed acceptable discrimination, as indicated by the AUC. Among them, random forest (0.785, 95% confidence interval [CI] 0.747-0.822) performed better than gradient boosting (0.774, 95% CI 0.739-0.811) and extra trees classifier (0.72, 95% CI 0.677-0.762). There was no significant difference between the constructed models.

Conclusion

Our study validates the use of ML for predicting COVID-19 in the ED and demonstrates its potential for predicting emerging infectious diseases based on models built by clinical features with temporal and spatial heterogeneity. This approach holds promise for scenarios where effective diagnostic tools for an emerging infectious disease may be lacking in the future.

SuPAR, biomarkers of inflammation, and severe outcomes in patients hospitalized for COVID-19: The International Study of Inflammation in COVID-19

Severe coronavirus disease 2019 (COVID-19) is a hyperinflammatory syndrome. The biomarkers of inflammation best suited to triage patients with COVID-19 are unknown. We conducted a prospective multicenter observational study of adult patients hospitalized specifically for COVID-19 from February 1, 2020 to October 19, 2022. Biomarkers measured included soluble urokinase plasminogen activator receptor (suPAR), C-reactive protein, interleukin-6, procalcitonin, ferritin, and D-dimer. In-hospital outcomes examined include death and the need for mechanical ventilation. Patients admitted in the United States (US, n = 1962) were used to compute area under the curves (AUCs) and identify biomarker cutoffs. The combined European cohorts (n = 1137) were used to validate the biomarker cutoffs. In the US cohort, 356 patients met the composite outcome of death (n = 197) or need for mechanical ventilation (n = 290). SuPAR was the most important predictor of the composite outcome and had the highest AUC (0.712) followed by CRP (0.642), ferritin (0.619), IL-6 (0.614), D-dimer (0.606), and lastly procalcitonin (0.596). Inclusion of other biomarkers did not improve discrimination. A suPAR cutoff of 4.0 ng/mL demonstrated a sensitivity of 95.4% (95% CI: 92.4%-98.0%) and negative predictive value (NPV) of 92.5% (95% CI: 87.5%-96.9%) for the composite outcome. Patients with suPAR < 4.0 ng/mL comprised 10.6% of the cohort and had a 0.8% probability of the composite outcome. Applying this cutoff to the validation cohort yielded a sensitivity of 93.8% (90.4%-96.7%) and NPV of 95.5% (93.1%-97.8%) for the composite outcome. Among commonly measured biomarkers, suPAR offered stronger discriminatory ability and may be useful in triaging low-risk patients with COVID-19.

Clinically-Inspired Multi-Agent Transformers for Disease Trajectory Forecasting From Multimodal Data

Deep neural networks are often applied to medical images to automate the problem of medical diagnosis. However, a more clinically relevant question that practitioners usually face is how to predict the future trajectory of a disease. Current methods for prognosis or disease trajectory forecasting often require domain knowledge and are complicated to apply. In this paper, we formulate the prognosis prediction problem as a one-to-many prediction problem. Inspired by a clinical decision-making process with two agents-a radiologist and a general practitioner - we predict prognosis with two transformer-based components that share information with each other. The first transformer in this framework aims to analyze the imaging data, and the second one leverages its internal states as inputs, also fusing them with auxiliary clinical data. The temporal nature of the problem is modeled within the transformer states, allowing us to treat the forecasting problem as a multi-task classification, for which we propose a novel loss. We show the effectiveness of our approach in predicting the development of structural knee osteoarthritis changes and forecasting Alzheimer's disease clinical status directly from raw multi-modal data. The proposed method outperforms multiple state-of-the-art baselines with respect to performance and calibration, both of which are needed for real-world applications. An open-source implementation of our method is made publicly available at https://github.com/Oulu-IMEDS/CLIMATv2.

The underuse of AI in the health sector: Opportunity costs, success stories, risks and recommendations

Purpose

This contribution explores the underuse of artificial intelligence (AI) in the health sector, what this means for practice, and how much the underuse can cost. Attention is drawn to the relevance of an issue that the European Parliament has outlined as a "major threat" in 2020. At its heart is the risk that research and development on trusted AI systems for medicine and digital health will pile up in lab centers without generating further practical relevance. Our analysis highlights why researchers, practitioners and especially policymakers, should pay attention to this phenomenon.

Methods

The paper examines the ways in which governments and public agencies are addressing the underuse of AI. As governments and international organizations often acknowledge the limitations of their own initiatives, the contribution explores the causes of the current issues and suggests ways to improve initiatives for digital health.

Results

Recommendations address the development of standards, models of regulatory governance, assessment of the opportunity costs of underuse of technology, and the urgency of the problem.

Conclusions

The exponential pace of AI advances and innovations makes the risks of underuse of AI increasingly threatening.

Graphical Abstract

Symptom-based scoring technique by machine learning to predict COVID-19: a validation study

BACKGROUND

Coronavirus disease 2019 (COVID-19) surges, such as that which occurred when omicron variants emerged, may overwhelm healthcare systems. To function properly, such systems should balance detection and workloads by improving referrals using simple yet precise and sensitive diagnostic predictions. A symptom-based scoring system was developed using machine learning for the general population, but no validation has occurred in healthcare settings. We aimed to validate a COVID-19 scoring system using self-reported symptoms, including loss of smell and taste as major indicators.

METHODS

A cross-sectional study was conducted to evaluate medical records of patients admitted to Dr. Sardjito Hospital, Yogyakarta, Indonesia, from March 2020 to December 2021. Outcomes were defined by a reverse-transcription polymerase chain reaction (RT-PCR). We compared the symptom-based scoring system, as the index test, with antigen tests, antibody tests, and clinical judgements by primary care physicians. To validate use of the index test to improve referral, we evaluated positive predictive value (PPV) and sensitivity.

RESULTS

After clinical judgement with a PPV of 61% (n = 327/530, 95% confidence interval [CI]: 60% to 62%), confirmation with the index test resulted in the highest PPV of 85% (n = 30/35, 95% CI: 83% to 87%) but the lowest sensitivity (n = 30/180, 17%, 95% CI: 15% to 19%). If this confirmation was defined by either positive predictive scoring or antigen tests, the PPV was 92% (n = 55/60, 95% CI: 90% to 94%). Meanwhile, the sensitivity was 88% (n = 55/62, 95% CI: 87% to 89%), which was higher than that when using only antigen tests (n = 29/41, 71%, 95% CI: 69% to 73%).

CONCLUSIONS

The symptom-based COVID-19 predictive score was validated in healthcare settings for its precision and sensitivity. However, an impact study is needed to confirm if this can balance detection and workload for the next COVID-19 surge.

Discovery Viewer (DV): Web-Based Medical AI Model Development Platform and Deployment Hub

The rapid rise of artificial intelligence (AI) in medicine in the last few years highlights the importance of developing bigger and better systems for data and model sharing. However, the presence of Protected Health Information (PHI) in medical data poses a challenge when it comes to sharing. One potential solution to mitigate the risk of PHI breaches is to exclusively share pre-trained models developed using private datasets. Despite the availability of these pre-trained networks, there remains a need for an adaptable environment to test and fine-tune specific models tailored for clinical tasks. This environment should be open for peer testing, feedback, and continuous model refinement, allowing dynamic model updates that are especially important in the medical field, where diseases and scanning techniques evolve rapidly. In this context, the Discovery Viewer (DV) platform was developed in-house at the Biomedical Engineering and Imaging Institute at Mount Sinai (BMEII) to facilitate the creation and distribution of cutting-edge medical AI models that remain accessible after their development. The all-in-one platform offers a unique environment for non-AI experts to learn, develop, and share their own deep learning (DL) concepts. This paper presents various use cases of the platform, with its primary goal being to demonstrate how DV holds the potential to empower individuals without expertise in AI to create high-performing DL models. We tasked three non-AI experts to develop different musculoskeletal AI projects that encompassed segmentation, regression, and classification tasks. In each project, 80% of the samples were provided with a subset of these samples annotated to aid the volunteers in understanding the expected annotation task. Subsequently, they were responsible for annotating the remaining samples and training their models through the platform's "Training Module". The resulting models were then tested on the separate 20% hold-off dataset to assess their performance. The classification model achieved an accuracy of 0.94, a sensitivity of 0.92, and a specificity of 1. The regression model yielded a mean absolute error of 14.27 pixels. And the segmentation model attained a Dice Score of 0.93, with a sensitivity of 0.9 and a specificity of 0.99. This initiative seeks to broaden the community of medical AI model developers and democratize the access of this technology to all stakeholders. The ultimate goal is to facilitate the transition of medical AI models from research to clinical settings.

Landscape of Innovative Methods for Early Diagnosis of Gastric Cancer: A Systematic Review

From a global perspective, gastric cancer (GC) persists as a significant healthcare issue. In the Western world, the majority of cases are discovered at late stages, when the treatment is generally unsuccessful. There are no organized screening programs outside of Asia (Japan and Republic of Korea). Traditional diagnosis techniques (such as upper endoscopy), conventional tumor markers (CEA, CA19-9, and CA72-4), radiographic imaging, and CT scanning all have drawbacks. The gold standard for the earliest detection of cancer and related premalignant lesions is still endoscopy with a proper biopsy follow-up. Since there are currently no clinically approved biomarkers for the early diagnosis of GC, the identification of non-invasive biomarkers is expected to help improve the prognosis and survival rate of these patients. The search for new screening biomarkers is currently underway. These include genetic biomarkers, such as circulating tumor cells, microRNAs, and exosomes, as well as metabolic biomarkers obtained from biofluids. Meanwhile, cutting-edge high-resolution endoscopic technologies are demonstrating promising outcomes in the visual diagnosis of mucosal lesions with the aid of linked color imaging and machine learning models. Following the PRISMA guidelines, this study examined the articles in databases such as PubMed, resulting in 167 included articles. This review discusses the currently available and emerging methods for diagnosing GC early on, as well as new developments in the endoscopic detection of early lesions of the stomach.

A clinically applicable AI system for diagnosis of congenital heart diseases based on computed tomography images

Congenital heart disease (CHD) is the most common type of birth defect. Without timely detection and treatment, approximately one-third of children with CHD would die in the infant period. However, due to the complicated heart structures, early diagnosis of CHD and its types is quite challenging, even for experienced radiologists. Here, we present an artificial intelligence (AI) system that achieves a comparable performance of human experts in the critical task of classifying 17 categories of CHD types. We collected the first-large CT dataset from three different CT machines, including more than 3750 CHD patients over 14 years. Experimental results demonstrate that it can achieve diagnosis accuracy (86.03%) comparable with junior cardiovascular radiologists (86.27%) in a World Health Organization appointed research and cooperation center in China on most types of CHD, and obtains a higher sensitivity (82.91%) than junior cardiovascular radiologists (76.18%). The accuracy of the combination of our AI system (97.20%) and senior radiologists achieves comparable results to that of junior radiologists and senior radiologists (97.16%) which is the current clinical routine. Our AI system can further provide 3D visualization of hearts to senior radiologists for interpretation and flexible review, surgeons for precise intuition of heart structures, and clinicians for more precise outcome prediction. We demonstrate the potential of our model to be integrated into current clinic practice to improve the diagnosis of CHD globally, especially in regions where experienced radiologists can be scarce.

A Multiclass Radiomics Method-Based WHO Severity Scale for Improving COVID-19 Patient Assessment and Disease Characterization From CT Scans

OBJECTIVES

The aim of this study was to evaluate the severity of COVID-19 patients' disease by comparing a multiclass lung lesion model to a single-class lung lesion model and radiologists' assessments in chest computed tomography scans.

MATERIALS AND METHODS

The proposed method, AssessNet-19, was developed in 2 stages in this retrospective study. Four COVID-19-induced tissue lesions were manually segmented to train a 2D-U-Net network for a multiclass segmentation task followed by extensive extraction of radiomic features from the lung lesions. LASSO regression was used to reduce the feature set, and the XGBoost algorithm was trained to classify disease severity based on the World Health Organization Clinical Progression Scale. The model was evaluated using 2 multicenter cohorts: a development cohort of 145 COVID-19-positive patients from 3 centers to train and test the severity prediction model using manually segmented lung lesions. In addition, an evaluation set of 90 COVID-19-positive patients was collected from 2 centers to evaluate AssessNet-19 in a fully automated fashion.

RESULTS

AssessNet-19 achieved an F1-score of 0.76 ± 0.02 for severity classification in the evaluation set, which was superior to the 3 expert thoracic radiologists (F1 = 0.63 ± 0.02) and the single-class lesion segmentation model (F1 = 0.64 ± 0.02). In addition, AssessNet-19 automated multiclass lesion segmentation obtained a mean Dice score of 0.70 for ground-glass opacity, 0.68 for consolidation, 0.65 for pleural effusion, and 0.30 for band-like structures compared with ground truth. Moreover, it achieved a high agreement with radiologists for quantifying disease extent with Cohen κ of 0.94, 0.92, and 0.95.

CONCLUSIONS

A novel artificial intelligence multiclass radiomics model including 4 lung lesions to assess disease severity based on the World Health Organization Clinical Progression Scale more accurately determines the severity of COVID-19 patients than a single-class model and radiologists' assessment.

Novel research and future prospects of artificial intelligence in cancer diagnosis and treatment

Research into the potential benefits of artificial intelligence for comprehending the intricate biology of cancer has grown as a result of the widespread use of deep learning and machine learning in the healthcare sector and the availability of highly specialized cancer datasets. Here, we review new artificial intelligence approaches and how they are being used in oncology. We describe how artificial intelligence might be used in the detection, prognosis, and administration of cancer treatments and introduce the use of the latest large language models such as ChatGPT in oncology clinics. We highlight artificial intelligence applications for omics data types, and we offer perspectives on how the various data types might be combined to create decision-support tools. We also evaluate the present constraints and challenges to applying artificial intelligence in precision oncology. Finally, we discuss how current challenges may be surmounted to make artificial intelligence useful in clinical settings in the future.

Ensemble classification of integrated CT scan datasets in detecting COVID-19 using feature fusion from contourlet transform and CNN

The COVID-19 disease caused by coronavirus is constantly changing due to the emergence of different variants and thousands of people are dying every day worldwide. Early detection of this new form of pulmonary disease can reduce the mortality rate. In this paper, an automated method based on machine learning (ML) and deep learning (DL) has been developed to detect COVID-19 using computed tomography (CT) scan images extracted from three publicly available datasets (A total of 11,407 images; 7397 COVID-19 images and 4010 normal images). An unsupervised clustering approach that is a modified region-based clustering technique for segmenting COVID-19 CT scan image has been proposed. Furthermore, contourlet transform and convolution neural network (CNN) have been employed to extract features individually from the segmented CT scan images and to fuse them in one feature vector. Binary differential evolution (BDE) approach has been employed as a feature optimization technique to obtain comprehensible features from the fused feature vector. Finally, a ML/DL-based ensemble classifier considering bagging technique has been employed to detect COVID-19 from the CT images. A fivefold and generalization cross-validation techniques have been used for the validation purpose. Classification experiments have also been conducted with several pre-trained models (AlexNet, ResNet50, GoogleNet, VGG16, VGG19) and found that the ensemble classifier technique with fused feature has provided state-of-the-art performance with an accuracy of 99.98%.

The Diagnostic Utility of Artificial Intelligence-Guided Computed Tomography-Based Severity Scores for Predicting Short-Term Clinical Outcomes in Adults with COVID-19 Pneumonia

Chest computed tomography (CT) imaging with the use of an artificial intelligence (AI) analysis program has been helpful for the rapid evaluation of large numbers of patients during the COVID-19 pandemic. We have previously demonstrated that adults with COVID-19 infection with high-risk obstructive sleep apnea (OSA) have poorer clinical outcomes than COVID-19 patients with low-risk OSA. In the current secondary analysis, we evaluated the association of AI-guided CT-based severity scores (SSs) with short-term outcomes in the same cohort. In total, 221 patients (mean age of 52.6 ± 15.6 years, 59% men) with eligible chest CT images from March to May 2020 were included. The AI program scanned the CT images in 3D, and the algorithm measured volumes of lobes and lungs as well as high-opacity areas, including ground glass and consolidation. An SS was defined as the ratio of the volume of high-opacity areas to that of the total lung volume. The primary outcome was the need for supplemental oxygen and hospitalization over 28 days. A receiver operating characteristic (ROC) curve analysis of the association between an SS and the need for supplemental oxygen revealed a cut-off score of 2.65 on the CT images, with a sensitivity of 81% and a specificity of 56%. In a multivariate logistic regression model, an SS > 2.65 predicted the need for supplemental oxygen, with an odds ratio (OR) of 3.98 (95% confidence interval (CI) 1.80-8.79; p < 0.001), and hospitalization, with an OR of 2.40 (95% CI 1.23-4.71; p = 0.011), adjusted for age, sex, body mass index, diabetes, hypertension, and coronary artery disease. We conclude that AI-guided CT-based SSs can be used for predicting the need for supplemental oxygen and hospitalization in patients with COVID-19 pneumonia.

Integrating Medical Domain Knowledge for Early Diagnosis of Fever of Unknown Origin: An Interpretable Hierarchical Multimodal Neural Network Approach

Accurate and interpretable differential diagnostic technologies are crucial for supporting clinicians in decision-making and treatment-planning for patients with fever of unknown origin (FUO). Existing solutions commonly address the diagnosis of FUO by transforming it into a multi-classification task. However, after the emergence of COVID-19 pandemic, clinicians have recognized the heightened significance of early diagnosis in patients with FUO, particularly for practical needs such as early triage. This has resulted in increased demands for identifying a wider range of etiologies, shorter observation windows, and better model interpretability. In this article, we propose an interpretable hierarchical multimodal neural network framework (iHMNNF) to facilitate early diagnosis of FUO by incorporating medical domain knowledge and leveraging multimodal clinical data. The iHMNNF comprises a top-down hierarchical reasoning framework (Td-HRF) built on the class hierarchy of FUO etiologies, five local attention-based multimodal neural networks (La-MNNs) trained for each parent node of the class hierarchy, and an interpretable module based on layer-wise relevance propagation (LRP) and attention mechanism. Experimental datasets were collected from electronic health records (EHRs) at a large-scale tertiary grade-A hospital in China, comprising 34,051 hospital admissions of 30,794 FUO patients from January 2011 to October 2020. Our proposed La-MNNs achieved area under the receiver operating characteristic curve (AUROC) values ranging from 0.7809 to 0.9035 across all five decomposed tasks, surpassing competing machine learning (ML) and single-modality deep learning (DL) methods while also providing enhanced interpretability. Furthermore, we explored the feasibility of identifying FUO etiologies using only the first N-hour time series data obtained after admission.

Rapid azoospermia classification by stimulated Raman scattering and second harmonic generation microscopy

Disease diagnosis and classification pose significant challenges due to the limited capabilities of traditional methods to obtain molecular information with spatial distribution. Optical imaging techniques, utilizing (auto)fluorescence and nonlinear optical signals, introduce new dimensions for biomarkers exploration that can improve diagnosis and classification. Nevertheless, these signals often cover only a limited number of species, impeding a comprehensive assessment of the tissue microenvironment, which is crucial for effective disease diagnosis and therapy. To address this challenge, we developed a multimodal platform, termed stimulated Raman scattering and second harmonic generation microscopy (SRASH), capable of simultaneously providing both chemical bonds and structural information of tissues. Applying SRASH imaging to azoospermia patient samples, we successfully identified lipids, protein, and collagen contrasts, unveiling molecular and structural signatures for non-obstructive azoospermia. This achievement is facilitated by LiteBlendNet-Dx (LBNet-Dx), our diagnostic algorithm, which achieved an outstanding 100% sample-level accuracy in classifying azoospermia, surpassing conventional imaging modalities. As a label-free technique, SRASH imaging eliminates the requirement for sample pre-treatment, demonstrating great potential for clinical translation and enabling molecular imaging-based diagnosis and therapy.

Harnessing digital technology for COVID-19 response in Uganda: lessons and implications for future public health emergencies

COVID-19 was one of the greatest disruptors of the 21st century, causing significant morbidity and mortality globally. Countries around the world adopted digital technologies and innovations to support the containment of the pandemic. This study explored the use of digital technology and barriers to its utilisation in responding to COVID-19 and sustaining essential health services in Uganda to inform response to future public health emergencies in low-resource settings. We reviewed published and grey literature on the use of digital technology in Uganda's response from March 2020 to April 2021 and conducted interviews with key informants. We thematically synthesised and summarised information on digital technology use as well as related challenges. During the COVID-19 response, digital technology was used in testing, contact tracing and surveillance, risk communication, supportive supervision and training, and maintenance of essential health services. The challenges with technology use were the disparate digital tools and health information systems leading to duplication of effort; limited access and coverage of digital tools, poor data quality; inaccessibility of data and an inability to support data manipulation, analysis and visualisation. Moreover, the inherent inadequate technology support systems such as poor internet and electricity infrastructure in some areas posed challenges of inequity. The harnessing of technology was key in supporting the COVID-19 response in Uganda. However, gaps existed in access, adoption, harmonisation, evaluation, sustainability and scale up of technology options. These issues should be addressed in preparedness efforts to foster technology adoption and application in public health emergencies with a focus on equity.

Hybrid morphological-convolutional neural networks for computer-aided diagnosis

Training deep Convolutional Neural Networks (CNNs) presents challenges in terms of memory requirements and computational resources, often resulting in issues such as model overfitting and lack of generalization. These challenges can only be mitigated by using an excessive number of training images. However, medical image datasets commonly suffer from data scarcity due to the complexities involved in their acquisition, preparation, and curation. To address this issue, we propose a compact and hybrid machine learning architecture based on the Morphological and Convolutional Neural Network (MCNN), followed by a Random Forest classifier. Unlike deep CNN architectures, the MCNN was specifically designed to achieve effective performance with medical image datasets limited to a few hundred samples. It incorporates various morphological operations into a single layer and uses independent neural networks to extract information from each signal channel. The final classification is obtained by utilizing a Random Forest classifier on the outputs of the last neural network layer. We compare the classification performance of our proposed method with three popular deep CNN architectures (ResNet-18, ShuffleNet-V2, and MobileNet-V2) using two training approaches: full training and transfer learning. The evaluation was conducted on two distinct medical image datasets: the ISIC dataset for melanoma classification and the ORIGA dataset for glaucoma classification. Results demonstrate that the MCNN method exhibits reliable performance in melanoma classification, achieving an AUC of 0.94 (95% CI: 0.91 to 0.97), outperforming the popular CNN architectures. For the glaucoma dataset, the MCNN achieved an AUC of 0.65 (95% CI: 0.53 to 0.74), which was similar to the performance of the popular CNN architectures. This study contributes to the understanding of mathematical morphology in shallow neural networks for medical image classification and highlights the potential of hybrid architectures in effectively learning from medical image datasets that are limited by a small number of case samples.

Quantitative Analysis for Lung Disease on Thin-Section CT

Thin-section computed tomography (CT) is widely employed not only for assessing morphology but also for evaluating respiratory function. Three-dimensional images obtained from thin-section CT provide precise measurements of lung, airway, and vessel volumes. These volumetric indices are correlated with traditional pulmonary function tests (PFT). CT also generates lung histograms. The volume ratio of areas with low and high attenuation correlates with PFT results. These quantitative image analyses have been utilized to investigate the early stages and disease progression of diffuse lung diseases, leading to the development of novel concepts such as pre-chronic obstructive pulmonary disease (pre-COPD) and interstitial lung abnormalities. Quantitative analysis proved particularly valuable during the COVID-19 pandemic when clinical evaluations were limited. In this review, we introduce CT analysis methods and explore their clinical applications in the context of various lung diseases. We also highlight technological advances, including images with matrices of 1024 × 1024 and slice thicknesses of 0.25 mm, which enhance the accuracy of these analyses.

Covid-19 triage in the emergency department 2.0: how analytics and AI transform a human-made algorithm for the prediction of clinical pathways

The Covid-19 pandemic has pushed many hospitals to their capacity limits. Therefore, a triage of patients has been discussed controversially primarily through an ethical perspective. The term triage contains many aspects such as urgency of treatment, severity of the disease and pre-existing conditions, access to critical care, or the classification of patients regarding subsequent clinical pathways starting from the emergency department. The determination of the pathways is important not only for patient care, but also for capacity planning in hospitals. We examine the performance of a human-made triage algorithm for clinical pathways which is considered a guideline for emergency departments in Germany based on a large multicenter dataset with over 4,000 European Covid-19 patients from the LEOSS registry. We find an accuracy of 28 percent and approximately 15 percent sensitivity for the ward class. The results serve as a benchmark for our extensions including an additional category of palliative care as a new label, analytics, AI, XAI, and interactive techniques. We find significant potential of analytics and AI in Covid-19 triage regarding accuracy, sensitivity, and other performance metrics whilst our interactive human-AI algorithm shows superior performance with approximately 73 percent accuracy and up to 76 percent sensitivity. The results are independent of the data preparation process regarding the imputation of missing values or grouping of comorbidities. In addition, we find that the consideration of an additional label palliative care does not improve the results.

Integrated point-of-care RT-PCR methods during and after COVID-19 pandemic

The COVID-19 pandemic has taken the world by surprise and people and organisations worldwide worked in some way or the other to combat the spread; isolate from the infected and get back to normal life, as it was before the pandemic hit. In this regard, the diagnosis of COVID-19 was at the centre of control and prevention and have seen a vehement change in every aspect, especially development of point-of-care testing for better and quick diagnosis. Among different types of techniques developed, the most important was the RT-PCR method of detection which detects nucleic acid of the virus in samples. RT-PCR is a laboratory-based method requiring trained professionals and precise steps for accurate testing. With the advent and spread of the pandemic, number of RT-PCR diagnostic centres rose significantly, and the detection process became less cumbersome, easy to use, ability to handle large volume of samples, more accurate, less time-consuming, and cost-effective. Different industries developed RT-PCR kits, reducing the efforts to prepare laboratory samples. Machines were employed for labour-driven tasks in PCR testing. In addition, new age technologies such as artificial intelligence, IoT, digital systems were combined with RT-PCR for accurate and easy testing. In this review, point-of-care RT-PCR methods, when the COVID-19 started, and the methods now, has been compared on the basis of technological advancements.