Opportunistic detection of type 2 diabetes using deep learning from frontal chest radiographs

Prediction of Future Risk of Moderate to Severe Kidney Function Loss Using a Deep Learning Model-Enabled Chest Radiography

Chronic kidney disease (CKD) remains a major public health concern, requiring better predictive models for early intervention. This study evaluates a deep learning model (DLM) that utilizes raw chest X-ray (CXR) data to predict moderate to severe kidney function decline. We analyzed data from 79,219 patients with an estimated Glomerular Filtration Rate (eGFR) between 65 and 120, segmented into development (n = 37,983), tuning (n = 15,346), internal validation (n = 14,113), and external validation (n = 11,777) sets. Our DLM, pretrained on CXR-report pairs, was fine-tuned with the development set. We retrospectively examined data spanning April 2011 to February 2022, with a 5-year maximum follow-up. Primary and secondary endpoints included CKD stage 3b progression, ESRD/dialysis, and mortality. The overall concordance index (C-index) values for the internal and external validation sets were 0.903 (95% CI, 0.885-0.922) and 0.851 (95% CI, 0.819-0.883), respectively. In these sets, the incidences of progression to CKD stage 3b at 5 years were 19.2% and 13.4% in the high-risk group, significantly higher than those in the median-risk (5.9% and 5.1%) and low-risk groups (0.9% and 0.9%), respectively. The sex, age, and eGFR-adjusted hazard ratios (HR) for the high-risk group compared to the low-risk group were 16.88 (95% CI, 10.84-26.28) and 7.77 (95% CI, 4.77-12.64), respectively. The high-risk group also exhibited higher probabilities of progressing to ESRD/dialysis or experiencing mortality compared to the low-risk group. Further analysis revealed that the high-risk group compared to the low/median-risk group had a higher prevalence of complications and abnormal blood/urine markers. Our findings demonstrate that a DLM utilizing CXR can effectively predict CKD stage 3b progression, offering a potential tool for early intervention in high-risk populations.

Assessing the Reliability of Pancreatic CT Imaging Biomarkers for Diabetes Prediction: A Dual Center Retrospective Study

RATIONALE AND OBJECTIVES

Pancreatic imaging biomarkers on CT imaging are known to be associated with diabetes. However, no studies have examined if these imaging biomarkers are resilient to changes in segmentation quality and contrast status. Here, we assess if imaging biomarkers are robust to variations in pancreatic segmentation quality and contrast status, and how these factors affect their ability to predict diabetes.

MATERIALS AND METHODS

This retrospective study selected patients with CT scans and corresponding HbA1c tests from two institutions. Patients were classified into two categories: having diabetes at the time or < 4 years after the scan (diabetic/incident) vs not having diabetes within 4 years after the scan (nondiabetic). Pancreatic imaging biomarkers, including average attenuation, intrapancreatic fat fraction, fractal dimension of the pancreatic boundary and volume, were measured using three pancreatic segmentation algorithms (TotalSegmentator, nnU-Net, and DM-UNet). Pairwise comparisons were made between algorithms when computing pancreatic imaging biomarker values for all patient scans. Predictive ability of imaging biomarkers (derived from each algorithm) was assessed for agreement between algorithms using a generalized additive model.

RESULTS

A total of 9772 patients (age, 56.1 years ± 9.1 [SD]; 5407 females) were included in this study. Imaging biomarkers based on attenuation measurements showed high algorithm agreement (ICC ≥0.93), with lower agreement on measures not reliant on attenuation. Models trained on imaging biomarkers derived from these algorithms exhibited good predictive agreement (AUC for diabetes overall, 0.84-0.91; contrast scans, 0.73-0.80; noncontrast scans, 0.62-0.80). Algorithms achieved a positive predictive value of 0.79-0.84, and negative predictive value of 0.89-0.94.

CONCLUSION

Attenuation-based imaging biomarkers demonstrated robustness to segmentation algorithm quality and consistent predictive ability across different clinical scenarios. These findings suggest that CT-derived biomarkers could be a reliable tool for diabetes screening across multiple institutions.

Annotation-free multi-organ anomaly detection in abdominal CT using free-text radiology reports: a multi-centre retrospective study

BACKGROUND

Artificial intelligence (AI) systems designed to detect abnormalities in abdominal computed tomography (CT) could reduce radiologists' workload and improve diagnostic processes. However, development of such models has been hampered by the shortage of large expert-annotated datasets. Here, we used information from free-text radiology reports, rather than manual annotations, to develop a deep-learning-based pipeline for comprehensive detection of abdominal CT abnormalities.

METHODS

In this multicentre retrospective study, we developed a deep-learning-based pipeline to detect abnormalities in the liver, gallbladder, pancreas, spleen, and kidneys. Abdominal CT exams and related free-text reports obtained during routine clinical practice collected from three institutions were used for training and internal testing, while data collected from six institutions were used for external testing. A multi-organ segmentation model and an information extraction schema were used to extract specific organ images and disease information, CT images and radiology reports, respectively, which were used to train a multiple-instance learning model for anomaly detection. Its performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and F1 score against radiologists' ground-truth labels.

FINDINGS

We trained the model for each organ on images selected from 66,684 exams (39,255 patients) and tested it on 300 (295 patients) and 600 (596 patients) exams for internal and external validation, respectively. In the external test cohort, the overall AUC for detecting organ abnormalities was 0.886. Whereas models trained on human-annotated labels performed better with the same number of exams, those trained on larger datasets with labels auto-extracted via the information extraction schema significantly outperformed human-annotated label-derived models.

INTERPRETATION

Using disease information from routine clinical free-text radiology reports allows development of accurate anomaly detection models without requiring manual annotations. This approach is applicable to various anatomical sites and could streamline diagnostic processes.

FUNDING

Japan Science and Technology Agency.

Denoising diffusion model for increased performance of detecting structural heart disease

Recent advancements in generative artificial intelligence have shown promise in producing realistic images from complex data distributions. We developed a denoising diffusion probabilistic model trained on the CheXchoNet dataset, encoding the joint distribution of demographic data and echocardiogram measurements. We generated a synthetic dataset skewed towards younger patients with a higher prevalence of structural left ventricle disease. A diagnostic deep learning model trained on the synthetic dataset performed comparably to one trained on real data producing an AUROC=0.75(95%CI 0.72-0.77), with similar performance on an internal dataset. Combining real data with positive samples from the synthetic data improved diagnostic accuracy producing an AUROC=0.80(95%CI 0.78-0.82). Subgroup analysis showed the largest performance improvement across younger patients. These results suggest diffusion models can increase diagnostic accuracy and fine-tune models for specific populations.

Detection of hypertension from pharyngeal images using deep learning algorithm in primary care settings in Japan

BACKGROUND

The early detection of hypertension using simple visual images in a way that does not require physical interaction or additional devices may improve quality of care in the era of telemedicine. Pharyngeal images include vascular morphological information and may therefore be useful for identifying hypertension.

OBJECTIVES

This study sought to develop a deep learning-based artificial intelligence algorithm for identifying hypertension from pharyngeal images.

METHODS

We conducted a secondary analysis of data from a clinical trial, in which demographic information, vital signs and pharyngeal images were obtained from patients with influenza-like symptoms in multiple primary care clinics in Japan. A deep learning-based algorithm that included a multi-instance convolutional neural network was trained to detect hypertension from pharyngeal images and demographic information. The classification performance was measured by area under the receiver operating characteristic curve. Importance heatmaps of the convolutional neural network were also examined to interpret the algorithm.

RESULTS

This study included 7710 patients from 64 clinics. The training dataset comprised 6171 patients from 51 clinics (460 positive cases), and the test dataset comprised 1539 patients from 13 clinics (130 positive cases). Our algorithm achieved an area under the receiver operating characteristic curve of 0.922 (95% CI, 0.904 to 0.940), significantly improving over the baseline prediction model incorporating only demographic information, which scored 0.887 (95% CI, 0.862 to 0.911). Our algorithm had consistent classification performance across all age and sex subgroups. Importance heatmaps revealed that the algorithm focused on the posterior pharyngeal wall area, where blood vessels are mainly located.

CONCLUSIONS

The results indicate that a deep learning-based algorithm can detect hypertension with high accuracy using pharyngeal images.

Correlation of HbA1c levels with CT-based body composition biomarkers in diabetes mellitus and metabolic syndrome

Diabetes mellitus and metabolic syndrome are closely linked with visceral body composition, but clinical assessment is limited to external measurements and laboratory values including hemoglobin A1c (HbA1c). Modern deep learning and AI algorithms allow automated extraction of biomarkers for organ size, density, and body composition from routine computed tomography (CT) exams. Comparing visceral CT biomarkers across groups with differing glycemic control revealed significant, progressive CT biomarker changes with increasing HbA1c. For example, in the unenhanced female cohort, mean changes between normal and poorly-controlled diabetes showed: 53% increase in visceral adipose tissue area, 22% increase in kidney volume, 24% increase in liver volume, 6% decrease in liver density (hepatic steatosis), 16% increase in skeletal muscle area, and 21% decrease in skeletal muscle density (myosteatosis) (all p < 0.001). The multisystem changes of metabolic syndrome can be objectively and retrospectively measured using automated CT biomarkers, with implications for diabetes, metabolic syndrome, and GLP-1 agonists.

Machine learning-based prediction of diabetic patients using blood routine data

Diabetes stands as one of the most prevalent chronic diseases globally. The conventional methods for diagnosing diabetes are frequently overlooked until individuals manifest noticeable symptoms of the condition. This study aimed to address this gap by collecting comprehensive datasets, including 1000 instances of blood routine data from diabetes patients and an equivalent dataset from healthy individuals. To differentiate diabetes patients from their healthy counterparts, a computational framework was established, encompassing eXtreme Gradient Boosting (XGBoost), random forest, support vector machine, and elastic net algorithms. Notably, the XGBoost model emerged as the most effective, exhibiting superior predictive results with an area under the receiver operating characteristic curve (AUC) of 99.90% in the training set and 98.51% in the testing set. Moreover, the model showcased commendable performance during external validation, achieving an overall accuracy of 81.54%. The probability generated by the model serves as a risk score for diabetes susceptibility. Further interpretability was achieved through the utilization of the Shapley additive explanations (SHAP) algorithm, identifying pivotal indicators such as mean corpuscular hemoglobin concentration (MCHC), lymphocyte ratio (LY%), standard deviation of red blood cell distribution width (RDW-SD), and mean corpuscular hemoglobin (MCH). This enhances our understanding of the predictive mechanisms underlying diabetes. To facilitate the application in clinical and real-life settings, a nomogram was created based on the logistic regression algorithm, which can provide a preliminary assessment of the likelihood of an individual having diabetes. Overall, this research contributes valuable insights into the predictive modeling of diabetes, offering potential applications in clinical practice for more effective and timely diagnoses.

Deep learning to predict long-term mortality from plain chest X-ray in patients referred for suspected coronary artery disease

Background

The hypothesis that a deep learning (DL) model can produce long-term prognostic information from chest X-ray (CXR) has already been confirmed within cancer screening programs. We summarize our experience with DL prediction of long-term mortality, from plain CXR, in patients referred for angina and coronary angiography.

Methods

Data of patients referred to an Italian academic hospital were analyzed retrospectively. We designed a deep convolutional neural network (DCNN) that, from CXR, could predict long-term mortality. External validation was performed on patients referred to a Dutch academic hospital.

Results

A total of 6,031 were used for model training (71%; n=4,259) and fine-tuning/validation (10%; n=602). Internal validation was performed with the remaining patients (19%; n=1,170). Patients' stratification followed the DL-CXR risk score quartiles division. Median follow-up was 6.1 years [interquartile range (IQR), 3.3-8.7 years]. We observed an increment in estimated mortality with the increase of DL-CXR risk score (low-risk 5%, moderate 17%, high 29%, very high 46%; P<0.001). The DL-CXR risk score predicted median follow-up outcome with an area under the curve (AUC) of 0.793 [95% confidence interval (CI): 0.759-0.827, sensitivity 78%, specificity 68%]. Prediction was better than that achieved using coronary angiography findings (AUC: 0.569, 95% CI: 0.52-0.61, P<0.001) and age (AUC: 0.735, 95% CI: 0.69-0.77, P<0.004). At Cox regression, the DL-CXR risk score predicted follow-up mortality (P<0.005, hazard ratio: 3.30, 95% CI: 2.35-4.64). External validation confirmed the DL-CXR risk score performance (AUC: 0.71, 95% CI: 0.49-0.92; sensitivity 0.838; specificity 0.338).

Conclusions

In patients referred for coronary angiogram because of angina, the DL-CXR risk score could be used to stratify mortality risk and predict long-term outcome better than age and coronary artery disease status.

Identifying sex from pharyngeal images using deep learning algorithm

The pharynx is one of the few areas in the body where blood vessels and immune tissues can readily be observed from outside the body non-invasively. Although prior studies have found that sex could be identified from retinal images using artificial intelligence, it remains unknown as to whether individuals' sex could also be identified using pharyngeal images. Demographic information and pharyngeal images were collected from patients who visited 64 primary care clinics in Japan for influenza-like symptoms. We trained a deep learning-based classification model to predict reported sex, which incorporated a multiple instance convolutional neural network, on 20,319 images from 51 clinics. Validation was performed using 4869 images from the remaining 13 clinics not used for the training. The performance of the classification model was assessed using the area under the receiver operating characteristic curve. To interpret the model, we proposed a framework that combines a saliency map and organ segmentation map to quantitatively evaluate salient regions. The model achieved the area under the receiver operating characteristic curve of 0.883 (95% CI 0.866-0.900). In subgroup analyses, a substantial improvement in classification performance was observed for individuals aged 20 and older, indicating that sex-specific patterns between women and men may manifest as humans age (e.g., may manifest after puberty). The saliency map suggested the model primarily focused on the posterior pharyngeal wall and the uvula. Our study revealed the potential utility of pharyngeal images by accurately identifying individuals' reported sex using deep learning algorithm.

Evolving and Novel Applications of Artificial Intelligence in Thoracic Imaging

The advent of artificial intelligence (AI) is revolutionizing medicine, particularly radiology. With the development of newer models, AI applications are demonstrating improved performance and versatile utility in the clinical setting. Thoracic imaging is an area of profound interest, given the prevalence of chest imaging and the significant health implications of thoracic diseases. This review aims to highlight the promising applications of AI within thoracic imaging. It examines the role of AI, including its contributions to improving diagnostic evaluation and interpretation, enhancing workflow, and aiding in invasive procedures. Next, it further highlights the current challenges and limitations faced by AI, such as the necessity of 'big data', ethical and legal considerations, and bias in representation. Lastly, it explores the potential directions for the application of AI in thoracic radiology.

Through the Looking Glass Darkly: How May AI Models Influence Future Underwriting?

Applications of Artificial Intelligence (AI) deep-learning models to screening for clinical conditions continue to evolve. Instances provided in this treatise include using a simple one-view PA chest radiograph to screen for Type 2 Diabetes Mellitus (T2DM), congestive heart failure, valvular heart disease, and to assess mortality in asymptomatic persons with respiratory diseases. This technology incorporates hundreds of thousands of CXRs into a convoluted neural network and is generally named AI CXR. As an example, the AUROC (Area Under Receiving Operator Characteristic) of screening for T2DM was 0.84, with sensitivity and specificities that exceed those of the United States Preventative Services Task Force (USPSTF) guidelines for screening with HBA1c or blood glucose studies. The AUROC's for diagnosing ejection fractions less than 40% was 0.92, and for detecting valvular heart diseases was 0.87. The potential implications for underwriting life and disability policies may be significant. A companion article in the Journal of Insurance Medicine addresses this same technology using a simple 12-lead ECG, generally named AI ECGs.

Transforming the cardiometabolic disease landscape: Multimodal AI-powered approaches in prevention and management

The rise of artificial intelligence (AI) has revolutionized various scientific fields, particularly in medicine, where it has enabled the modeling of complex relationships from massive datasets. Initially, AI algorithms focused on improved interpretation of diagnostic studies such as chest X-rays and electrocardiograms in addition to predicting patient outcomes and future disease onset. However, AI has evolved with the introduction of transformer models, allowing analysis of the diverse, multimodal data sources existing in medicine today. Multimodal AI holds great promise in more accurate disease risk assessment and stratification as well as optimizing the key driving factors in cardiometabolic disease: blood pressure, sleep, stress, glucose control, weight, nutrition, and physical activity. In this article we outline the current state of medical AI in cardiometabolic disease, highlighting the potential of multimodal AI to augment personalized prevention and treatment strategies in cardiometabolic disease.

A novel interpretable deep transfer learning combining diverse learnable parameters for improved T2D prediction based on single-cell gene regulatory networks

Accurate deep learning (DL) models to predict type 2 diabetes (T2D) are concerned not only with targeting the discrimination task but also with learning useful feature representation. However, existing DL tools are far from perfect and do not provide appropriate interpretation as a guideline to explain and promote superior performance in the target task. Therefore, we provide an interpretable approach for our presented deep transfer learning (DTL) models to overcome such drawbacks, working as follows. We utilize several pre-trained models including SEResNet152, and SEResNeXT101. Then, we transfer knowledge from pre-trained models via keeping the weights in the convolutional base (i.e., feature extraction part) while modifying the classification part with the use of Adam optimizer to deal with classifying healthy controls and T2D based on single-cell gene regulatory network (SCGRN) images. Another DTL models work in a similar manner but just with keeping weights of the bottom layers in the feature extraction unaltered while updating weights of consecutive layers through training from scratch. Experimental results on the whole 224 SCGRN images using five-fold cross-validation show that our model (TFeSEResNeXT101) achieving the highest average balanced accuracy (BAC) of 0.97 and thereby significantly outperforming the baseline that resulted in an average BAC of 0.86. Moreover, the simulation study demonstrated that the superiority is attributed to the distributional conformance of model weight parameters obtained with Adam optimizer when coupled with weights from a pre-trained model.

Diabetes and artificial intelligence beyond the closed loop: a review of the landscape, promise and challenges

The discourse amongst diabetes specialists and academics regarding technology and artificial intelligence (AI) typically centres around the 10% of people with diabetes who have type 1 diabetes, focusing on glucose sensors, insulin pumps and, increasingly, closed-loop systems. This focus is reflected in conference topics, strategy documents, technology appraisals and funding streams. What is often overlooked is the wider application of data and AI, as demonstrated through published literature and emerging marketplace products, that offers promising avenues for enhanced clinical care, health-service efficiency and cost-effectiveness. This review provides an overview of AI techniques and explores the use and potential of AI and data-driven systems in a broad context, covering all diabetes types, encompassing: (1) patient education and self-management; (2) clinical decision support systems and predictive analytics, including diagnostic support, treatment and screening advice, complications prediction; and (3) the use of multimodal data, such as imaging or genetic data. The review provides a perspective on how data- and AI-driven systems could transform diabetes care in the coming years and how they could be integrated into daily clinical practice. We discuss evidence for benefits and potential harms, and consider existing barriers to scalable adoption, including challenges related to data availability and exchange, health inequality, clinician hesitancy and regulation. Stakeholders, including clinicians, academics, commissioners, policymakers and those with lived experience, must proactively collaborate to realise the potential benefits that AI-supported diabetes care could bring, whilst mitigating risk and navigating the challenges along the way.

Digital Health in Diabetes and Cardiovascular Disease

BACKGROUND

Digital health technologies are rapidly evolving and transforming the care of diabetes and cardiovascular disease (CVD).

PURPOSE OF THE REVIEW

In this review, we discuss emerging approaches incorporating digital health technologies to improve patient outcomes through a more continuous, accessible, proactive, and patient-centered approach. We discuss various mechanisms of potential benefit ranging from early detection to enhanced physiologic monitoring over time to helping shape important management decisions and engaging patients in their care. Furthermore, we discuss the potential for better individualization of management, which is particularly important in diseases with heterogeneous and complex manifestations, such as diabetes and cardiovascular disease. This narrative review explores ways to leverage digital health technology to better extend the reach of clinicians beyond the physical hospital and clinic spaces to address disparities in the diagnosis, treatment, and prevention of diabetes and cardiovascular disease.

CONCLUSION

We are at the early stages of the shift to digital medicine, which holds substantial promise not only to improve patient outcomes but also to lower the costs of care. The review concludes by recognizing the challenges and limitations that need to be addressed for optimal implementation and impact. We present recommendations on how to navigate these challenges as well as goals and opportunities in utilizing digital health technology in the management of diabetes and prevention of adverse cardiovascular outcomes.

The leading global health challenges in the artificial intelligence era

Millions of people's health is at risk because of several factors and multiple overlapping crises, all of which hit the vulnerable the most. These challenges are dynamic and evolve in response to emerging health challenges and concerns, which need effective collaboration among countries working toward achieving Sustainable Development Goals (SDGs) and securing global health. Mental Health, the Impact of climate change, cardiovascular diseases (CVDs), diabetes, Infectious diseases, health system, and population aging are examples of challenges known to pose a vast burden worldwide. We are at a point known as the "digital revolution," characterized by the expansion of artificial intelligence (AI) and a fusion of technology types. AI has emerged as a powerful tool for addressing various health challenges, and the last ten years have been influential due to the rapid expansion in the production and accessibility of health-related data. The computational models and algorithms can understand complicated health and medical data to perform various functions and deep-learning strategies. This narrative mini-review summarizes the most current AI applications to address the leading global health challenges. Harnessing its capabilities can ultimately mitigate the Impact of these challenges and revolutionize the field. It has the ability to strengthen global health through personalized health care and improved preparedness and response to future challenges. However, ethical and legal concerns about individual or community privacy and autonomy must be addressed for effective implementation.

Review: Machine learning in precision pharmacotherapy of type 2 diabetes-A promising future or a glimpse of hope?

Precision pharmacotherapy of diabetes requires judicious selection of the optimal therapeutic agent for individual patients. Artificial intelligence (AI), a swiftly expanding discipline, holds substantial potential to transform current practices in diabetes diagnosis and management. This manuscript provides a comprehensive review of contemporary research investigating drug responses in patient subgroups, stratified via either supervised or unsupervised machine learning approaches. The prevalent algorithmic workflow for investigating drug responses using machine learning involves cohort selection, data processing, predictor selection, development and validation of machine learning methods, subgroup allocation, and subsequent analysis of drug response. Despite the promising feature, current research does not yet provide sufficient evidence to implement machine learning algorithms into routine clinical practice, due to a lack of simplicity, validation, or demonstrated efficacy. Nevertheless, we anticipate that the evolving evidence base will increasingly substantiate the role of machine learning in molding precision pharmacotherapy for diabetes.