A deep learning algorithm to detect anaemia with ECGs: a retrospective, multicentre study

Revolutionizing anemia detection: integrative machine learning models and advanced attention mechanisms

This study addresses the critical issue of anemia detection using machine learning (ML) techniques. Although a widespread blood disorder with significant health implications, anemia often remains undetected. This necessitates timely and efficient diagnostic methods, as traditional approaches that rely on manual assessment are time-consuming and subjective. The present study explored the application of ML - particularly classification models, such as logistic regression, decision trees, random forest, support vector machines, Naïve Bayes, and k-nearest neighbors - in conjunction with innovative models incorporating attention modules and spatial attention to detect anemia. The proposed models demonstrated promising results, achieving high accuracy, precision, recall, and F1 scores for both textual and image datasets. In addition, an integrated approach that combines textual and image data was found to outperform the individual modalities. Specifically, the proposed AlexNet Multiple Spatial Attention model achieved an exceptional accuracy of 99.58%, emphasizing its potential to revolutionize automated anemia detection. The results of ablation studies confirm the significance of key components - including the blue-green-red, multiple, and spatial attentions - in enhancing model performance. Overall, this study presents a comprehensive and innovative framework for noninvasive anemia detection, contributing valuable insights to the field.

AI-enabled ECG index for predicting left ventricular dysfunction in patients with ST-segment elevation myocardial infarction

Electrocardiogram (ECG) changes after primary percutaneous coronary intervention (PCI) in ST-segment elevation myocardial infarction (STEMI) patients are associated with prognosis. This study investigated the feasibility of predicting left ventricular (LV) dysfunction in STEMI patients using an artificial intelligence (AI)-enabled ECG algorithm developed to diagnose STEMI. Serial ECGs from 637 STEMI patients were analyzed with the AI algorithm, which quantified the probability of STEMI at various time points. The time points included pre-PCI, immediately post-PCI, 6 h post-PCI, 24 h post-PCI, at discharge, and one-month post-PCI. The prevalence of LV dysfunction was significantly associated with the AI-derived probability index. A high probability index was an independent predictor of LV dysfunction, with higher cardiac death and heart failure hospitalization rates observed in patients with higher indices. The study demonstrates that the AI-enabled ECG index effectively quantifies ECG changes post-PCI and serves as a digital biomarker capable of predicting post-STEMI LV dysfunction, heart failure, and mortality. These findings suggest that AI-enabled ECG analysis can be a valuable tool in the early identification of high-risk patients, enabling timely and targeted interventions to improve clinical outcomes in STEMI patients.

Prospects for artificial intelligence-enhanced electrocardiogram as a unified screening tool for cardiac and non-cardiac conditions: an explorative study in emergency care

Aims

Current deep learning algorithms for automatic ECG analysis have shown notable accuracy but are typically narrowly focused on singular diagnostic conditions. This exploratory study aims to investigate the capability of a single deep learning model to predict a diverse range of both cardiac and non-cardiac discharge diagnoses based on a single ECG collected in the emergency department.

Methods and results

In this study, we assess the performance of a model trained to predict a broad spectrum of diagnoses. We find that the model can reliably predict 253 ICD codes (81 cardiac and 172 non-cardiac) in the sense of exceeding an AUROC score of 0.8 in a statistically significant manner.

Conclusion

The model demonstrates proficiency in handling a wide array of cardiac and non-cardiac diagnostic scenarios, indicating its potential as a comprehensive screening tool for diverse medical encounters.

Artificial Intelligence for Cardiovascular Care-Part 1: Advances: JACC Review Topic of the Week

Recent artificial intelligence (AI) advancements in cardiovascular care offer potential enhancements in diagnosis, treatment, and outcomes. Innovations to date focus on automating measurements, enhancing image quality, and detecting diseases using novel methods. Applications span wearables, electrocardiograms, echocardiography, angiography, genetics, and more. AI models detect diseases from electrocardiograms at accuracy not previously achieved by technology or human experts, including reduced ejection fraction, valvular heart disease, and other cardiomyopathies. However, AI's unique characteristics necessitate rigorous validation by addressing training methods, real-world efficacy, equity concerns, and long-term reliability. Despite an exponentially growing number of studies in cardiovascular AI, trials showing improvement in outcomes remain lacking. A number are currently underway. Embracing this rapidly evolving technology while setting a high evaluation benchmark will be crucial for cardiology to leverage AI to enhance patient care and the provider experience.

[Artificial intelligence-enhanced electrocardiography : Will it revolutionize diagnosis and management of our patients?]

The use of artificial intelligence (AI) in healthcare has made significant progress in the last 10 years. Many experts believe that utilization of AI technologies, especially deep learning, will bring about drastic changes in how physicians understand, diagnose, and treat diseases. One aspect of this development is AI-enhanced electrocardiography (ECG) analysis. It involves not only optimizing the traditional ECG analysis by the physician and improving the accuracy of automatic interpretation by the ECG device but also introducing entirely new diagnostic options enabled by AI. Examples include assessing left ventricular function, predicting atrial fibrillation, and diagnosing both cardiac and noncardiac conditions. Through AI, the ECG becomes a comprehensive tool for screening, diagnosis, and patient management, potentially revolutionizing clinical practices. This paper provides an overview of the current state of this development, discusses existing limitations, and explores the challenges that may arise for healthcare professionals in this context.

Explaining deep learning for ECG analysis: Building blocks for auditing and knowledge discovery

Deep neural networks have become increasingly popular for analyzing ECG data because of their ability to accurately identify cardiac conditions and hidden clinical factors. However, the lack of transparency due to the black box nature of these models is a common concern. To address this issue, explainable AI (XAI) methods can be employed. In this study, we present a comprehensive analysis of post-hoc XAI methods, investigating the glocal (aggregated local attributions over multiple samples) and global (concept based XAI) perspectives. We have established a set of sanity checks to identify saliency as the most sensible attribution method. We provide a dataset-wide analysis across entire patient subgroups, which goes beyond anecdotal evidence, to establish the first quantitative evidence for the alignment of model behavior with cardiologists' decision rules. Furthermore, we demonstrate how these XAI techniques can be utilized for knowledge discovery, such as identifying subtypes of myocardial infarction. We believe that these proposed methods can serve as building blocks for a complementary assessment of the internal validity during a certification process, as well as for knowledge discovery in the field of ECG analysis.

Automatic detection of cardiac conditions from photos of electrocardiogram captured by smartphones

BACKGROUND

Researchers have developed machine learning-based ECG diagnostic algorithms that match or even surpass cardiologist level of performance. However, most of them cannot be used in real-world, as older generation ECG machines do not permit installation of new algorithms.

OBJECTIVE

To develop a smartphone application that automatically extract ECG waveforms from photos and to convert them to voltage-time series for downstream analysis by a variety of diagnostic algorithms built by researchers.

METHODS

A novel approach of using objective detection and image segmentation models to automatically extract ECG waveforms from photos taken by clinicians was devised. Modular machine learning models were developed to sequentially perform waveform identification, gridline removal, and scale calibration. The extracted data were then analysed using a machine learning-based cardiac rhythm classifier.

RESULTS

Waveforms from 40 516 scanned and 444 photographed ECGs were automatically extracted. 12 828 of 13 258 (96.8%) scanned and 5399 of 5743 (94.0%) photographed waveforms were correctly cropped and labelled. 11 604 of 12 735 (91.1%) scanned and 5062 of 5752 (88.0%) photographed waveforms achieved successful voltage-time signal extraction after automatic gridline and background noise removal. In a proof-of-concept demonstration, an atrial fibrillation diagnostic algorithm achieved 91.3% sensitivity, 94.2% specificity, 95.6% positive predictive value, 88.6% negative predictive value and 93.4% F1 score, using photos of ECGs as input.

CONCLUSION

Object detection and image segmentation models allow automatic extraction of ECG signals from photos for downstream diagnostics. This novel pipeline circumvents the need for costly ECG hardware upgrades, thereby paving the way for large-scale implementation of machine learning-based diagnostic algorithms.

Electrocardiogram Features in Non-Cardiac Diseases: From Mechanisms to Practical Aspects

Despite the noteworthy advancements and the introduction of new technologies in diagnostic tools for cardiovascular disorders, the electrocardiogram (ECG) remains a reliable, easily accessible, and affordable tool to use. In addition to its crucial role in cardiac emergencies, ECG can be considered a very useful ancillary tool for the diagnosis of many non-cardiac diseases as well. In this narrative review, we aimed to explore the potential contributions of ECG for the diagnosis of non-cardiac diseases such as stroke, migraine, pancreatitis, Kounis syndrome, hypothermia, esophageal disorders, pulmonary embolism, pulmonary diseases, electrolyte disturbances, anemia, coronavirus disease 2019, different intoxications and pregnancy.

Preliminary Evidence of the Use of Generative AI in Health Care Clinical Services: Systematic Narrative Review

BACKGROUND

Generative artificial intelligence tools and applications (GenAI) are being increasingly used in health care. Physicians, specialists, and other providers have started primarily using GenAI as an aid or tool to gather knowledge, provide information, train, or generate suggestive dialogue between physicians and patients or between physicians and patients' families or friends. However, unless the use of GenAI is oriented to be helpful in clinical service encounters that can improve the accuracy of diagnosis, treatment, and patient outcomes, the expected potential will not be achieved. As adoption continues, it is essential to validate the effectiveness of the infusion of GenAI as an intelligent technology in service encounters to understand the gap in actual clinical service use of GenAI.

OBJECTIVE

This study synthesizes preliminary evidence on how GenAI assists, guides, and automates clinical service rendering and encounters in health care The review scope was limited to articles published in peer-reviewed medical journals.

METHODS

We screened and selected 0.38% (161/42,459) of articles published between January 1, 2020, and May 31, 2023, identified from PubMed. We followed the protocols outlined in the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to select highly relevant studies with at least 1 element on clinical use, evaluation, and validation to provide evidence of GenAI use in clinical services. The articles were classified based on their relevance to clinical service functions or activities using the descriptive and analytical information presented in the articles.

RESULTS

Of 161 articles, 141 (87.6%) reported using GenAI to assist services through knowledge access, collation, and filtering. GenAI was used for disease detection (19/161, 11.8%), diagnosis (14/161, 8.7%), and screening processes (12/161, 7.5%) in the areas of radiology (17/161, 10.6%), cardiology (12/161, 7.5%), gastrointestinal medicine (4/161, 2.5%), and diabetes (6/161, 3.7%). The literature synthesis in this study suggests that GenAI is mainly used for diagnostic processes, improvement of diagnosis accuracy, and screening and diagnostic purposes using knowledge access. Although this solves the problem of knowledge access and may improve diagnostic accuracy, it is oriented toward higher value creation in health care.

CONCLUSIONS

GenAI informs rather than assisting or automating clinical service functions in health care. There is potential in clinical service, but it has yet to be actualized for GenAI. More clinical service-level evidence that GenAI is used to streamline some functions or provides more automated help than only information retrieval is needed. To transform health care as purported, more studies related to GenAI applications must automate and guide human-performed services and keep up with the optimism that forward-thinking health care organizations will take advantage of GenAI.

Continual learning framework for a multicenter study with an application to electrocardiogram

Deep learning has been increasingly utilized in the medical field and achieved many goals. Since the size of data dominates the performance of deep learning, several medical institutions are conducting joint research to obtain as much data as possible. However, sharing data is usually prohibited owing to the risk of privacy invasion. Federated learning is a reasonable idea to train distributed multicenter data without direct access; however, a central server to merge and distribute models is needed, which is expensive and hardly approved due to various legal regulations. This paper proposes a continual learning framework for a multicenter study, which does not require a central server and can prevent catastrophic forgetting of previously trained knowledge. The proposed framework contains the continual learning method selection process, assuming that a single method is not omnipotent for all involved datasets in a real-world setting and that there could be a proper method to be selected for specific data. We utilized the fake data based on a generative adversarial network to evaluate methods prospectively, not ex post facto. We used four independent electrocardiogram datasets for a multicenter study and trained the arrhythmia detection model. Our proposed framework was evaluated against supervised and federated learning methods, as well as finetuning approaches that do not include any regulation to preserve previous knowledge. Even without a central server and access to the past data, our framework achieved stable performance (AUROC 0.897) across all involved datasets, achieving comparable performance to federated learning (AUROC 0.901).

Adopting artificial intelligence in cardiovascular medicine: a scoping review

Recent years have witnessed significant transformations in cardiovascular medicine, driven by the rapid evolution of artificial intelligence (AI). This scoping review was conducted to capture the breadth of AI applications within cardiovascular science. Employing a structured approach, we sourced relevant articles from PubMed, with an emphasis on journals encompassing general cardiology and digital medicine. We applied filters to highlight cardiovascular articles published in journals focusing on general internal medicine, cardiology and digital medicine, thereby identifying the prevailing trends in the field. Following a comprehensive full-text screening, a total of 140 studies were identified. Over the preceding 5 years, cardiovascular medicine's interplay with AI has seen an over tenfold augmentation. This expansive growth encompasses multiple cardiovascular subspecialties, including but not limited to, general cardiology, ischemic heart disease, heart failure, and arrhythmia. Deep learning emerged as the predominant methodology. The majority of AI endeavors in this domain have been channeled toward enhancing diagnostic and prognostic capabilities, utilizing resources such as hospital datasets, electrocardiograms, and echocardiography. A significant uptrend was observed in AI's application for omics data analysis. However, a clear gap persists in AI's full-scale integration into the clinical decision-making framework. AI, particularly deep learning, has demonstrated robust applications across cardiovascular subspecialties, indicating its transformative potential in this field. As we continue on this trajectory, ensuring the alignment of technological progress with medical ethics becomes crucial. The abundant digital health data today further accentuates the need for meticulous systematic reviews, tailoring them to each cardiovascular subspecialty.

An ECG-based artificial intelligence model for assessment of sudden cardiac death risk

BACKGROUND

Conventional ECG-based algorithms could contribute to sudden cardiac death (SCD) risk stratification but demonstrate moderate predictive capabilities. Deep learning (DL) models use the entire digital signal and could potentially improve predictive power. We aimed to train and validate a 12 lead ECG-based DL algorithm for SCD risk assessment.

METHODS

Out-of-hospital SCD cases were prospectively ascertained in the Portland, Oregon, metro area. A total of 1,827 pre- cardiac arrest 12 lead ECGs from 1,796 SCD cases were retrospectively collected and analyzed to develop an ECG-based DL model. External validation was performed in 714 ECGs from 714 SCD cases from Ventura County, CA. Two separate control group samples were obtained from 1342 ECGs taken from 1325 individuals of which at least 50% had established coronary artery disease. The DL model was compared with a previously validated conventional 6 variable ECG risk model.

RESULTS

The DL model achieves an AUROC of 0.889 (95% CI 0.861-0.917) for the detection of SCD cases vs. controls in the internal held-out test dataset, and is successfully validated in external SCD cases with an AUROC of 0.820 (0.794-0.847). The DL model performs significantly better than the conventional ECG model that achieves an AUROC of 0.712 (0.668-0.756) in the internal and 0.743 (0.711-0.775) in the external cohort.

CONCLUSIONS

An ECG-based DL model distinguishes SCD cases from controls with improved accuracy and performs better than a conventional ECG risk model. Further detailed investigation is warranted to evaluate how the DL model could contribute to improved SCD risk stratification.

A Generic Strategy to Create Mechanically Interlocked Nanocomposite/Hydrogel Hybrid Electrodes for Epidermal Electronics

Stretchable electronics are crucial enablers for next-generation wearables intimately integrated into the human body. As the primary compliant conductors used in these devices, metallic nanostructure/elastomer composites often struggle to form conformal contact with the textured skin. Hybrid electrodes have been consequently developed based on conductive nanocomposite and soft hydrogels to establish seamless skin-device interfaces. However, chemical modifications are typically needed for reliable bonding, which can alter their original properties. To overcome this limitation, this study presents a facile fabrication approach for mechanically interlocked nanocomposite/hydrogel hybrid electrodes. In this physical process, soft microfoams are thermally laminated on silver nanowire nanocomposites as a porous interface, which forms an interpenetrating network with the hydrogel. The microfoam-enabled bonding strategy is generally compatible with various polymers. The resulting interlocked hybrids have a 28-fold improved interfacial toughness compared to directly stacked hybrids. These electrodes achieve firm attachment to the skin and low contact impedance using tissue-adhesive hydrogels. They have been successfully integrated into an epidermal sleeve to distinguish hand gestures by sensing muscle contractions. Interlocked nanocomposite/hydrogel hybrids reported here offer a promising platform to combine the benefits of both materials for epidermal devices and systems.

Electrocardiographic deep learning for predicting post-procedural mortality: a model development and validation study

BACKGROUND

Preoperative risk assessments used in clinical practice are insufficient in their ability to identify risk for postoperative mortality. Deep-learning analysis of electrocardiography can identify hidden risk markers that can help to prognosticate postoperative mortality. We aimed to develop a prognostic model that accurately predicts postoperative mortality in patients undergoing medical procedures and who had received preoperative electrocardiographic diagnostic testing.

METHODS

In a derivation cohort of preoperative patients with available electrocardiograms (ECGs) from Cedars-Sinai Medical Center (Los Angeles, CA, USA) between Jan 1, 2015 and Dec 31, 2019, a deep-learning algorithm was developed to leverage waveform signals to discriminate postoperative mortality. We randomly split patients (8:1:1) into subsets for training, internal validation, and final algorithm test analyses. Model performance was assessed using area under the receiver operating characteristic curve (AUC) values in the hold-out test dataset and in two external hospital cohorts and compared with the established Revised Cardiac Risk Index (RCRI) score. The primary outcome was post-procedural mortality across three health-care systems.

FINDINGS

45 969 patients had a complete ECG waveform image available for at least one 12-lead ECG performed within the 30 days before the procedure date (59 975 inpatient procedures and 112 794 ECGs): 36 839 patients in the training dataset, 4549 in the internal validation dataset, and 4581 in the internal test dataset. In the held-out internal test cohort, the algorithm discriminates mortality with an AUC value of 0·83 (95% CI 0·79-0·87), surpassing the discrimination of the RCRI score with an AUC of 0·67 (0·61-0·72). The algorithm similarly discriminated risk for mortality in two independent US health-care systems, with AUCs of 0·79 (0·75-0·83) and 0·75 (0·74-0·76), respectively. Patients determined to be high risk by the deep-learning model had an unadjusted odds ratio (OR) of 8·83 (5·57-13·20) for postoperative mortality compared with an unadjusted OR of 2·08 (0·77-3·50) for postoperative mortality for RCRI scores of more than 2. The deep-learning algorithm performed similarly for patients undergoing cardiac surgery (AUC 0·85 [0·77-0·92]), non-cardiac surgery (AUC 0·83 [0·79-0·88]), and catheterisation or endoscopy suite procedures (AUC 0·76 [0·72-0·81]).

INTERPRETATION

A deep-learning algorithm interpreting preoperative ECGs can improve discrimination of postoperative mortality. The deep-learning algorithm worked equally well for risk stratification of cardiac surgeries, non-cardiac surgeries, and catheterisation laboratory procedures, and was validated in three independent health-care systems. This algorithm can provide additional information to clinicians making the decision to perform medical procedures and stratify the risk of future complications.

FUNDING

National Heart, Lung, and Blood Institute.

Race, Sex, and Age Disparities in the Performance of ECG Deep Learning Models Predicting Heart Failure

BACKGROUND

Deep learning models may combat widening racial disparities in heart failure outcomes through early identification of individuals at high risk. However, demographic biases in the performance of these models have not been well-studied.

METHODS

This retrospective analysis used 12-lead ECGs taken between 2008 and 2018 from 326 518 patient encounters referred for standard clinical indications to Stanford Hospital. The primary model was a convolutional neural network model trained to predict incident heart failure within 5 years. Biases were evaluated on the testing set (160 312 ECGs) using the area under the receiver operating characteristic curve, stratified across the protected attributes of race, ethnicity, age, and sex.

RESULTS

There were 59 817 cases of incident heart failure observed within 5 years of ECG collection. The performance of the primary model declined with age. There were no significant differences observed between racial groups overall. However, the primary model performed significantly worse in Black patients aged 0 to 40 years compared with all other racial groups in this age group, with differences most pronounced among young Black women. Disparities in model performance did not improve with the integration of race, ethnicity, sex, and age into model architecture, by training separate models for each racial group, or by providing the model with a data set of equal racial representation. Using probability thresholds individualized for race, age, and sex offered substantial improvements in F1 scores.

CONCLUSIONS

The biases found in this study warrant caution against perpetuating disparities through the development of machine learning tools for the prognosis and management of heart failure. Customizing the application of these models by using probability thresholds individualized by race, ethnicity, age, and sex may offer an avenue to mitigate existing algorithmic disparities.

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.

Identifying Atrial Fibrillation With Sinus Rhythm Electrocardiogram in Embolic Stroke of Undetermined Source: A Validation Study With Insertable Cardiac Monitors

BACKGROUND AND OBJECTIVES

Paroxysmal atrial fibrillation (AF) is a major potential cause of embolic stroke of undetermined source (ESUS). However, identifying AF remains challenging because it occurs sporadically. Deep learning could be used to identify hidden AF based on the sinus rhythm (SR) electrocardiogram (ECG). We combined known AF risk factors and developed a deep learning algorithm (DLA) for predicting AF to optimize diagnostic performance in ESUS patients.

METHODS

A DLA was developed to identify AF using SR 12-lead ECG with the database consisting of AF patients and non-AF patients. The accuracy of the DLA was validated in 221 ESUS patients who underwent insertable cardiac monitor (ICM) insertion to identify AF.

RESULTS

A total of 44,085 ECGs from 12,666 patient were used for developing the DLA. The internal validation of the DLA revealed 0.862 (95% confidence interval, 0.850-0.873) area under the curve (AUC) in the receiver operating curve analysis. In external validation data from 221 ESUS patients, the diagnostic accuracy of DLA and AUC were 0.811 and 0.827, respectively, and DLA outperformed conventional predictive models, including CHARGE-AF, C2HEST, and HATCH. The combined model, comprising atrial ectopic burden, left atrial diameter and the DLA, showed excellent performance in AF prediction with AUC of 0.906.

CONCLUSIONS

The DLA accurately identified paroxysmal AF using 12-lead SR ECG in patients with ESUS and outperformed the conventional models. The DLA model along with the traditional AF risk factors could be a useful tool to identify paroxysmal AF in ESUS patients.

Artificial intelligence in cardiovascular diseases: diagnostic and therapeutic perspectives

Artificial intelligence (AI), the technique of extracting information from complex database using sophisticated computer algorithms, has incorporated itself in medical field. AI techniques have shown the potential to accelerate the progression of diagnosis and treatment of cardiovascular diseases (CVDs), including heart failure, atrial fibrillation, valvular heart disease, hypertrophic cardiomyopathy, congenital heart disease and so on. In clinical scenario, AI have been proved to apply well in CVD diagnosis, enhance effectiveness of auxiliary tools, disease stratification and typing, and outcome prediction. Deeply developed to capture subtle connections from massive amounts of healthcare data, recent AI algorithms are expected to handle even more complex tasks than traditional methods. The aim of this review is to introduce current applications of AI in CVDs, which may allow clinicians who have limited expertise of computer science to better understand the frontier of the subject and put AI algorithms into clinical practice.

Development, multi-institutional external validation, and algorithmic audit of an artificial intelligence-based Side-specific Extra-Prostatic Extension Risk Assessment tool (SEPERA) for patients undergoing radical prostatectomy: a retrospective cohort study

BACKGROUND

Accurate prediction of side-specific extraprostatic extension (ssEPE) is essential for performing nerve-sparing surgery to mitigate treatment-related side-effects such as impotence and incontinence in patients with localised prostate cancer. Artificial intelligence (AI) might provide robust and personalised ssEPE predictions to better inform nerve-sparing strategy during radical prostatectomy. We aimed to develop, externally validate, and perform an algorithmic audit of an AI-based Side-specific Extra-Prostatic Extension Risk Assessment tool (SEPERA).

METHODS

Each prostatic lobe was treated as an individual case such that each patient contributed two cases to the overall cohort. SEPERA was trained on 1022 cases from a community hospital network (Trillium Health Partners; Mississauga, ON, Canada) between 2010 and 2020. Subsequently, SEPERA was externally validated on 3914 cases across three academic centres: Princess Margaret Cancer Centre (Toronto, ON, Canada) from 2008 to 2020; L'Institut Mutualiste Montsouris (Paris, France) from 2010 to 2020; and Jules Bordet Institute (Brussels, Belgium) from 2015 to 2020. Model performance was characterised by area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), calibration, and net benefit. SEPERA was compared against contemporary nomograms (ie, Sayyid nomogram, Soeterik nomogram [non-MRI and MRI]), as well as a separate logistic regression model using the same variables included in SEPERA. An algorithmic audit was performed to assess model bias and identify common patient characteristics among predictive errors.

FINDINGS

Overall, 2468 patients comprising 4936 cases (ie, prostatic lobes) were included in this study. SEPERA was well calibrated and had the best performance across all validation cohorts (pooled AUROC of 0·77 [95% CI 0·75-0·78] and pooled AUPRC of 0·61 [0·58-0·63]). In patients with pathological ssEPE despite benign ipsilateral biopsies, SEPERA correctly predicted ssEPE in 72 (68%) of 106 cases compared with the other models (47 [44%] in the logistic regression model, none in the Sayyid model, 13 [12%] in the Soeterik non-MRI model, and five [5%] in the Soeterik MRI model). SEPERA had higher net benefit than the other models to predict ssEPE, enabling more patients to safely undergo nerve-sparing. In the algorithmic audit, no evidence of model bias was observed, with no significant difference in AUROC when stratified by race, biopsy year, age, biopsy type (systematic only vs systematic and MRI-targeted biopsy), biopsy location (academic vs community), and D'Amico risk group. According to the audit, the most common errors were false positives, particularly for older patients with high-risk disease. No aggressive tumours (ie, grade >2 or high-risk disease) were found among false negatives.

INTERPRETATION

We demonstrated the accuracy, safety, and generalisability of using SEPERA to personalise nerve-sparing approaches during radical prostatectomy.

FUNDING

None.

Deep learning-based electrocardiographic screening for chronic kidney disease

BACKGROUND

Undiagnosed chronic kidney disease (CKD) is a common and usually asymptomatic disorder that causes a high burden of morbidity and early mortality worldwide. We developed a deep learning model for CKD screening from routinely acquired ECGs.

METHODS

We collected data from a primary cohort with 111,370 patients which had 247,655 ECGs between 2005 and 2019. Using this data, we developed, trained, validated, and tested a deep learning model to predict whether an ECG was taken within one year of the patient receiving a CKD diagnosis. The model was additionally validated using an external cohort from another healthcare system which had 312,145 patients with 896,620 ECGs between 2005 and 2018.

RESULTS

Using 12-lead ECG waveforms, our deep learning algorithm achieves discrimination for CKD of any stage with an AUC of 0.767 (95% CI 0.760-0.773) in a held-out test set and an AUC of 0.709 (0.708-0.710) in the external cohort. Our 12-lead ECG-based model performance is consistent across the severity of CKD, with an AUC of 0.753 (0.735-0.770) for mild CKD, AUC of 0.759 (0.750-0.767) for moderate-severe CKD, and an AUC of 0.783 (0.773-0.793) for ESRD. In patients under 60 years old, our model achieves high performance in detecting any stage CKD with both 12-lead (AUC 0.843 [0.836-0.852]) and 1-lead ECG waveform (0.824 [0.815-0.832]).

CONCLUSIONS

Our deep learning algorithm is able to detect CKD using ECG waveforms, with stronger performance in younger patients and more severe CKD stages. This ECG algorithm has the potential to augment screening for CKD.

A deep learning model for novel systemic biomarkers in photographs of the external eye: a retrospective study

BACKGROUND

Photographs of the external eye were recently shown to reveal signs of diabetic retinal disease and elevated glycated haemoglobin. This study aimed to test the hypothesis that external eye photographs contain information about additional systemic medical conditions.

METHODS

We developed a deep learning system (DLS) that takes external eye photographs as input and predicts systemic parameters, such as those related to the liver (albumin, aspartate aminotransferase [AST]); kidney (estimated glomerular filtration rate [eGFR], urine albumin-to-creatinine ratio [ACR]); bone or mineral (calcium); thyroid (thyroid stimulating hormone); and blood (haemoglobin, white blood cells [WBC], platelets). This DLS was trained using 123 130 images from 38 398 patients with diabetes undergoing diabetic eye screening in 11 sites across Los Angeles county, CA, USA. Evaluation focused on nine prespecified systemic parameters and leveraged three validation sets (A, B, C) spanning 25 510 patients with and without diabetes undergoing eye screening in three independent sites in Los Angeles county, CA, and the greater Atlanta area, GA, USA. We compared performance against baseline models incorporating available clinicodemographic variables (eg, age, sex, race and ethnicity, years with diabetes).

FINDINGS

Relative to the baseline, the DLS achieved statistically significant superior performance at detecting AST >36·0 U/L, calcium <8·6 mg/dL, eGFR <60·0 mL/min/1·73 m2, haemoglobin <11·0 g/dL, platelets <150·0 × 103/μL, ACR ≥300 mg/g, and WBC <4·0 × 103/μL on validation set A (a population resembling the development datasets), with the area under the receiver operating characteristic curve (AUC) of the DLS exceeding that of the baseline by 5·3-19·9% (absolute differences in AUC). On validation sets B and C, with substantial patient population differences compared with the development datasets, the DLS outperformed the baseline for ACR ≥300·0 mg/g and haemoglobin <11·0 g/dL by 7·3-13·2%.

INTERPRETATION

We found further evidence that external eye photographs contain biomarkers spanning multiple organ systems. Such biomarkers could enable accessible and non-invasive screening of disease. Further work is needed to understand the translational implications.

FUNDING

Google.

Current and Future Use of Artificial Intelligence in Electrocardiography

Artificial intelligence (AI) is increasingly used in electrocardiography (ECG) to assist in diagnosis, stratification, and management. AI algorithms can help clinicians in the following areas: (1) interpretation and detection of arrhythmias, ST-segment changes, QT prolongation, and other ECG abnormalities; (2) risk prediction integrated with or without clinical variables (to predict arrhythmias, sudden cardiac death, stroke, and other cardiovascular events); (3) monitoring ECG signals from cardiac implantable electronic devices and wearable devices in real time and alerting clinicians or patients when significant changes occur according to timing, duration, and situation; (4) signal processing, improving ECG quality and accuracy by removing noise/artifacts/interference, and extracting features not visible to the human eye (heart rate variability, beat-to-beat intervals, wavelet transforms, sample-level resolution, etc.); (5) therapy guidance, assisting in patient selection, optimizing treatments, improving symptom-to-treatment times, and cost effectiveness (earlier activation of code infarction in patients with ST-segment elevation, predicting the response to antiarrhythmic drugs or cardiac implantable devices therapies, reducing the risk of cardiac toxicity, etc.); (6) facilitating the integration of ECG data with other modalities (imaging, genomics, proteomics, biomarkers, etc.). In the future, AI is expected to play an increasingly important role in ECG diagnosis and management, as more data become available and more sophisticated algorithms are developed.

Deep Learning Algorithms for Estimation of Demographic and Anthropometric Features from Electrocardiograms

The electrocardiogram (ECG) has been known to be affected by demographic and anthropometric factors. This study aimed to develop deep learning models to predict the subject's age, sex, ABO blood type, and body mass index (BMI) based on ECGs. This retrospective study included individuals aged 18 years or older who visited a tertiary referral center with ECGs acquired from October 2010 to February 2020. Using convolutional neural networks (CNNs) with three convolutional layers, five kernel sizes, and two pooling sizes, we developed both classification and regression models. We verified a classification model to be applicable for age (<40 years vs. ≥40 years), sex (male vs. female), BMI (<25 kg/m² vs. ≥25 kg/m²), and ABO blood type. A regression model was also developed and validated for age and BMI estimation. A total of 124,415 ECGs (1 ECG per subject) were included. The dataset was constructed by dividing the entire set of ECGs at a ratio of 4:3:3. In the classification task, the area under the receiver operating characteristic (AUROC), which represents a quantitative indicator of the judgment threshold, was used as the primary outcome. The mean absolute error (MAE), which represents the difference between the observed and estimated values, was used in the regression task. For age estimation, the CNN achieved an AUROC of 0.923 with an accuracy of 82.97%, and a MAE of 8.410. For sex estimation, the AUROC was 0.947 with an accuracy of 86.82%. For BMI estimation, the AUROC was 0.765 with an accuracy of 69.89%, and a MAE of 2.332. For ABO blood type estimation, the CNN showed an inferior performance, with a top-1 accuracy of 31.98%. For the ABO blood type estimation, the CNN showed an inferior performance, with a top-1 accuracy of 31.98% (95% CI, 31.98-31.98%). Our model could be adapted to estimate individuals' demographic and anthropometric features from their ECGs; this would enable the development of physiologic biomarkers that can better reflect their health status than chronological age.

Extensive deep learning model to enhance electrocardiogram application via latent cardiovascular feature extraction from identity identification

BACKGROUND AND OBJECTIVE

Deep learning models (DLMs) have been successfully applied in biomedicine primarily using supervised learning with large, annotated databases. However, scarce training resources limit the potential of DLMs for electrocardiogram (ECG) analysis.

METHODS

We have developed a novel pre-training strategy for unsupervised identity identification with an area under the receiver operating characteristic curve (AUC) >0.98. Accordingly, a DLM pre-trained with identity identification can be applied to 70 patient characteristic predictions using transfer learning (TL). These ECG-based patient characteristics were then used for cardiovascular disease (CVD) risk prediction. The DLMs were trained using 507,729 ECGs from 222,473 patients and validated using two independent validation sets (n = 27,824/31,925).

RESULTS

The DLMs using our method exhibited better performance than directly trained DLMs. Additionally, our DLM performed better than those of previous studies in terms of gender (AUC [internal/external] = 0.982/0.968), age (correlation = 0.886/0.892), low ejection fraction (AUC = 0.942/0.951), and critical markers not addressed previously, including high B-type natriuretic peptide (AUC = 0.921/0.899). Additionally, approximately 50% of the ECG-based characteristics provided significantly more prediction information for cardiovascular risk than real characteristics.

CONCLUSIONS

This is the first study to use identity identification as a pre-training task for TL in ECG analysis. An extensive exploration of the relationship between ECG and 70 patient characteristics was conducted. Our DLM-enhanced ECG interpretation system extensively advanced ECG-related patient characteristic prediction and mortality risk management for cardiovascular diseases.

Advancing cardiovascular medicine with machine learning: Progress, potential, and perspective

Recent advances in machine learning (ML) have made it possible to analyze high-dimensional and complex data-such as free text, images, waveforms, videos, and sound-in an automated manner by successfully learning complex associations within these data. Cardiovascular medicine is particularly well poised to take advantage of these ML advances, due to the widespread digitization of medical data and the large number of diagnostic tests used to evaluate cardiovascular disease. Various ML approaches have successfully been applied to cardiovascular tests and diseases to automate interpretation, accurately perform measurements, and, in some cases, predict novel diagnoses from less invasive tests, effectively expanding the utility of more widely accessible diagnostic tests. Here, we present examples of some impactful advances in cardiovascular medicine using ML across a variety of modalities, with a focus on deep learning applications.

A non-invasive machine learning mechanism for early disease recognition on Twitter: The case of anemia

Social media sites, such as Twitter, provide the means for users to share their stories, feelings, and health conditions during the disease course. Anemia, the most common type of blood disorder, is recognized as a major public health problem all over the world. Yet very few studies have explored the potential of recognizing anemia from online posts. This study proposed a novel mechanism for recognizing anemia based on the associations between disease symptoms and patients' emotions posted on the Twitter platform. We used k-means and Latent Dirichlet Allocation (LDA) algorithms to group similar tweets and to identify hidden disease topics. Both disease emotions and symptoms were mapped using the Apriori algorithm. The proposed approach was evaluated using a number of classifiers. A higher prediction accuracy of 98.96 % was achieved using Sequential Minimal Optimization (SMO). The results revealed that fear and sadness emotions are dominant among anemic patients. The proposed mechanism is the first of its kind to diagnose anemia using textual information posted on social media sites. It can advance the development of intelligent health monitoring systems and clinical decision-support systems.

Cardio-Onco-Metabolism - Metabolic vulnerabilities in cancer and the heart

Cancer and cardiovascular diseases (CVDs) are the leading cause of death worldwide. Metabolic remodeling is a hallmark of both cancer and the failing heart. Tumors reprogram metabolism to optimize nutrient utilization and meet increased demands for energy provision, biosynthetic pathways, and proliferation. Shared risk factors for cancer and CVDs suggest intersecting mechanisms for disease pathogenesis and progression. In this review, we aim to highlight the role of metabolic remodeling in cancer and its potential to impair cardiac function. Understanding these mechanisms will help us develop biomarkers, better therapies, and identify patients at risk of developing heart disease after surviving cancer.

Artificial Intelligence and Machine Learning in Patient Blood Management: A Scoping Review

Machine learning (ML) and artificial intelligence (AI) are widely used in many different fields of modern medicine. This narrative review gives, in the first part, a brief overview of the methods of ML and AI used in patient blood management (PBM) and, in the second part, aims at describing which fields have been analyzed using these methods so far. A total of 442 articles were identified by a literature search, and 47 of them were judged as qualified articles that applied ML and AI techniques in PBM. We assembled the eligible articles to provide insights into the areas of application, quality measures of these studies, and treatment outcomes that can pave the way for further adoption of this promising technology and its possible use in routine clinical decision making. The topics that have been investigated most often were the prediction of transfusion (30%), bleeding (28%), and laboratory studies (15%). Although in the last 3 years a constantly increasing number of questions of ML in PBM have been investigated, there is a vast scientific potential for further application of ML and AI in other fields of PBM.

Deep-Learning-Based Detection of Paroxysmal Supraventricular Tachycardia Using Sinus-Rhythm Electrocardiograms

Background: Paroxysmal supraventricular tachycardia (PSVT) is a common arrhythmia associated with palpitation and a decline in quality of life. However, it is undetectable with sinus-rhythmic ECGs when patients are not in the symptomatic onset stage. Methods: In the current study, a convolution neural network (CNN) was trained with normal-sinus-rhythm standard 12-lead electrocardiographs (ECGs) of negative control patients and PSVT patients to identify patients with unrecognized PSVT. PSVT refers to atrioventricular nodal reentry tachycardia or atrioventricular reentry tachycardia based on a concealed accessory pathway as confirmed by electrophysiological procedure. Negative control group data were obtained from 5107 patients with at least one normal sinus-rhythmic ECG without any palpitation symptoms. All ECGs were randomly allocated to the training, validation and testing datasets in a 7:1:2 ratio. Model performance was evaluated on the testing dataset through F1 score, overall accuracy, area under the curve, sensitivity, specificity and precision. Results: We retrospectively enrolled 407 sinus-rhythm ECGs of PSVT procedural patients and 1794 ECGs of control patients. A total of 2201 ECGs were randomly divided into training (n = 1541), validation (n = 220) and testing (n = 440) datasets. In the testing dataset, the CNN algorithm showed an overall accuracy of 95.5%, sensitivity of 90.2%, specificity of 96.6% and precision of 86.0%. Conclusion: Our study reveals that a well-trained CNN algorithm may be a rapid, effective, inexpensive and reliable method to contribute to the detection of PSVT.

Artificial intelligence applications in cardio-oncology: Leveraging high dimensional cardiovascular data

Growing evidence suggests a wide spectrum of potential cardiovascular complications following cancer therapies, leading to an urgent need for better risk-stratifying and disease screening in patients undergoing oncological treatment. As many cancer patients undergo frequent surveillance through imaging as well as other diagnostic testing, there is a wealth of information that can be utilized to assess one's risk for cardiovascular complications of cancer therapies. Over the past decade, there have been remarkable advances in applying artificial intelligence (AI) to analyze cardiovascular data obtained from electrocardiograms, echocardiograms, computed tomography, and cardiac magnetic resonance imaging to detect early signs or future risk of cardiovascular diseases. Studies have shown AI-guided cardiovascular image analysis can accurately, reliably and inexpensively identify and quantify cardiovascular risk, leading to better detection of at-risk or disease features, which may open preventive and therapeutic opportunities in cardio-oncology. In this perspective, we discuss the potential for the use of AI in analyzing cardiovascular data to identify cancer patients at risk for cardiovascular complications early in treatment which would allow for rapid intervention to prevent adverse cardiovascular outcomes.

Improving explainability of deep neural network-based electrocardiogram interpretation using variational auto-encoders. EUROPEAN HEART JOURNAL. DIGITAL HEALTH 2022;3:390-404. [PMID: 36712164 PMCID: PMC9707974 DOI: 10.1093/ehjdh/ztac038]

Aims

Deep neural networks (DNNs) perform excellently in interpreting electrocardiograms (ECGs), both for conventional ECG interpretation and for novel applications such as detection of reduced ejection fraction (EF). Despite these promising developments, implementation is hampered by the lack of trustworthy techniques to explain the algorithms to clinicians. Especially, currently employed heatmap-based methods have shown to be inaccurate.

Methods and results

We present a novel pipeline consisting of a variational auto-encoder (VAE) to learn the underlying factors of variation of the median beat ECG morphology (the FactorECG), which are subsequently used in common and interpretable prediction models. As the ECG factors can be made explainable by generating and visualizing ECGs on both the model and individual level, the pipeline provides improved explainability over heatmap-based methods. By training on a database with 1.1 million ECGs, the VAE can compress the ECG into 21 generative ECG factors, most of which are associated with physiologically valid underlying processes. Performance of the explainable pipeline was similar to 'black box' DNNs in conventional ECG interpretation [area under the receiver operating curve (AUROC) 0.94 vs. 0.96], detection of reduced EF (AUROC 0.90 vs. 0.91), and prediction of 1-year mortality (AUROC 0.76 vs. 0.75). Contrary to the 'black box' DNNs, our pipeline provided explainability on which morphological ECG changes were important for prediction. Results were confirmed in a population-based external validation dataset.

Conclusions

Future studies on DNNs for ECGs should employ pipelines that are explainable to facilitate clinical implementation by gaining confidence in artificial intelligence and making it possible to identify biased models.

Deep Learning Model for Predicting Intradialytic Hypotension Without Privacy Infringement: A Retrospective Two-Center Study

Objective

Previously developed Intradialytic hypotension (IDH) prediction models utilize clinical variables with potential privacy protection issues. We developed an IDH prediction model using minimal variables, without the risk of privacy infringement.

Methods

Unidentifiable data from 63,640 hemodialysis sessions (26,746 of 79 patients for internal validation, 36,894 of 255 patients for external validation) from two Korean hospital hemodialysis databases were finally analyzed, using three IDH definitions: (1) systolic blood pressure (SBP) nadir <90 mmHg (Nadir90); (2) SBP decrease ≥20 mmHg from baseline (Fall20); and (3) SBP decrease ≥20 mmHg and/or mean arterial pressure decrease ≥10 mmHg (Fall20/MAP10). The developed models use 30 min information to predict an IDH event in the following 10 min window. Area under the receiver operating characteristic curves (AUROCs) and precision-recall curves were used to compare machine learning and deep learning models by logistic regression, XGBoost, and convolutional neural networks.

Results

Among 344,714 segments, 9,154 (2.7%), 134,988 (39.2%), and 149,674 (43.4%) IDH events occurred according to three different IDH definitions (Nadir90, Fall20, and Fall20/MAP10, respectively). Compared with models including logistic regression, random forest, and XGBoost, the deep learning model achieved the best performance in predicting IDH (AUROCs: Nadir90, 0.905; Fall20, 0.864; Fall20/MAP10, 0.863) only using measurements from hemodialysis machine during dialysis session.

Conclusions

The deep learning model performed well only using monitoring measurement of hemodialysis machine in predicting IDH without any personal information that could risk privacy infringement.

Resting 12‑lead ECG tests performed by patients at home amid the COVID-19 pandemic — Results from the first 1000 patients

Background

There were surges in the demand for telehealth and home care in the COVID-19 pandemic. A new home ECG testing model was developed and used in the real-world clinical practice.

Methods

Since June 2020, QT Medical, Inc. (Diamond Bard, California) has been providing home ECG testing service by mail. Upon receiving the order from a clinician, an ECG testing kit was sent to the patient by mail. The kit included an ECG recorder, a prepositioned electrode strip of proper size for the patient (determined by the ordering clinician), printed instructions for performing the test, and a return envelope. We reviewed and analyzed the de-identified administrative dataset of the first 1000 ECG tests ordered by 37 medical practices.

Results

Of the 1000 patients served by this mail delivery home ECG testing service, 77.3% were female and 22.7% were male. Their ages ranged from 1 year old to 96 years old, mean 49.5 ± 13.4 years (median 52). 92.9% patients completed their tests with clinical quality ECGs uploaded to their ordering clinician's online accounts. Of those who did not complete the tests, the main reason was they “no longer needed the test”. Failure to complete the test due to technical issues was 1.4%. Only one patient had to repeat the test due to inadequate ECG quality as judged by the ordering physician. The median turnaround time, from the kit being mailed out to the recorder being returned, was 10 days. Overall, 2.2% of the ECG devices were lost in shipping or unreturned by patients.

Conclusion

Of the first 1000 patients who had their ECG tests at homes, it was found that this home ECG testing platform and care model could be reliably used by patients with no training to acquire clinical grade ECG. The current study proved that medical standard, resting 12‑lead ECG can be performed by the majority of patients at home.

Understanding the EKG changes in methemoglobinemia

Methemoglobin is a form of hemoglobin that has been oxidized, changing its heme iron configuration from the ferrous to the ferric state. Unlike normal hemoglobin, methemoglobin does not bind oxygen and as a result, cannot deliver oxygen to the tissues. At the presentation in the emergency department, an electrocardiogram (EKG) is usually performed as a reflex for patients admitted for shortness of breath to rule out acute coronary syndrome. Very limited data is available on EKG abnormalities in patients with methemoglobinemia. In this study, we retrospectively analyzed the pattern of EKG changes in patients with methemoglobinemia.

Multimodal deep learning enhances diagnostic precision in left ventricular hypertrophy. EUROPEAN HEART JOURNAL. DIGITAL HEALTH 2022;3:380-389. [PMID: 36712167 PMCID: PMC9707995 DOI: 10.1093/ehjdh/ztac033]

Aims

Determining the aetiology of left ventricular hypertrophy (LVH) can be challenging due to the similarity in clinical presentation and cardiac morphological features of diverse causes of disease. In particular, distinguishing individuals with hypertrophic cardiomyopathy (HCM) from the much larger set of individuals with manifest or occult hypertension (HTN) is of major importance for family screening and the prevention of sudden death. We hypothesized that an artificial intelligence method based joint interpretation of 12-lead electrocardiograms and echocardiogram videos could augment physician interpretation.

Methods and results

We chose not to train on proximate data labels such as physician over-reads of ECGs or echocardiograms but instead took advantage of electronic health record derived clinical blood pressure measurements and diagnostic consensus (often including molecular testing) among physicians in an HCM centre of excellence. Using more than 18 000 combined instances of electrocardiograms and echocardiograms from 2728 patients, we developed LVH-fusion. On held-out test data, LVH-fusion achieved an F1-score of 0.71 in predicting HCM, and 0.96 in predicting HTN. In head-to-head comparison with human readers LVH-fusion had higher sensitivity and specificity rates than its human counterparts. Finally, we use explainability techniques to investigate local and global features that positively and negatively impact LVH-fusion prediction estimates providing confirmation from unsupervised analysis the diagnostic power of lateral T-wave inversion on the ECG and proximal septal hypertrophy on the echocardiogram for HCM.

Conclusion

These results show that deep learning can provide effective physician augmentation in the face of a common diagnostic dilemma with far reaching implications for the prevention of sudden cardiac death.

Deep-Learning-Based Hemoglobin Concentration Prediction and Anemia Screening Using Ultra-Wide Field Fundus Images

Background: Anemia is the most common hematological disorder. The purpose of this study was to establish and validate a deep-learning model to predict Hgb concentrations and screen anemia using ultra-wide-field (UWF) fundus images.

Methods: The study was conducted at Peking Union Medical College Hospital. Optos color images taken between January 2017 and June 2021 were screened for building the dataset. ASModel_UWF using UWF images was developed. Mean absolute error (MAE) and area under the receiver operating characteristics curve (AUC) were used to evaluate its performance. Saliency maps were generated to make the visual explanation of the model.

Results: ASModel_UWF acquired the MAE of the prediction task of 0.83 g/dl (95%CI: 0.81–0.85 g/dl) and the AUC of the screening task of 0.93 (95%CI: 0.92–0.95). Compared with other screening approaches, it achieved the best performance of AUC and sensitivity when the test dataset size was larger than 1000. The model tended to focus on the area around the optic disc, retinal vessels, and some regions located at the peripheral area of the retina, which were undetected by non-UWF imaging.

Conclusion: The deep-learning model ASModel_UWF could both predict Hgb concentration and screen anemia in a non-invasive and accurate way with high efficiency.

Electrocardiographic biomarker based on machine learning for detecting overt hyperthyroidism

Aims

Although overt hyperthyroidism adversely affects a patient's prognosis, thyroid function tests (TFTs) are not routinely conducted. Furthermore, vague symptoms of hyperthyroidism often lead to hyperthyroidism being overlooked. An electrocardiogram (ECG) is a commonly used screening test, and the association between thyroid function and ECG is well known. However, it is difficult for clinicians to detect hyperthyroidism through subtle ECG changes. For early detection of hyperthyroidism, we aimed to develop and validate an electrocardiographic biomarker based on a deep learning model (DLM) for detecting hyperthyroidism.

Methods and results

This multicentre retrospective cohort study included patients who underwent ECG and TFTs within 24 h. For model development and internal validation, we obtained 174 331 ECGs from 113 194 patients. We extracted 48 648 ECGs from 33 478 patients from another hospital for external validation. Using 500 Hz raw ECG, we developed a DLM with 12-lead, 6-lead (limb leads, precordial leads), and single-lead (lead I) ECGs to detect overt hyperthyroidism. We calculated the model's performance on the internal and external validation sets using the area under the receiver operating characteristic curve (AUC). The AUC of the DLM using a 12-lead ECG was 0.926 (0.913-0.94) for internal validation and 0.883(0.855-0.911) for external validation. The AUC of DLMs using six and a single-lead were in the range of 0.889-0.906 for internal validation and 0.847-0.882 for external validation.

Conclusion

We developed a DLM using ECG for non-invasive screening of overt hyperthyroidism. We expect this model to contribute to the early diagnosis of diseases and improve patient prognosis.

Artificial intelligence assessment for early detection and prediction of renal impairment using electrocardiography

Purpose

Although renal failure is a major healthcare burden globally and the cornerstone for preventing its irreversible progression is an early diagnosis, an adequate and noninvasive tool to screen renal impairment (RI) reliably and economically does not exist. We developed an interpretable deep learning model (DLM) using electrocardiography (ECG) and validated its performance.

Methods

This retrospective cohort study included two hospitals. We included 115,361 patients who had at least one ECG taken with an estimated glomerular filtration rate measurement within 30 min of the index ECG. A DLM was developed using 96,549 ECGs of 55,222 patients. The internal validation included 22,949 ECGs of 22,949 patients. Furthermore, we conducted an external validation with 37,190 ECGs of 37,190 patients from another hospital. The endpoint was to detect a moderate to severe RI (estimated glomerular filtration rate < 45 ml/min/1.73m²).

Results

The area under the receiver operating characteristic curve (AUC) of a DLM using a 12-lead ECG for detecting RI during the internal and external validation was 0.858 (95% confidence interval 0.851–0.866) and 0.906 (0.900–0.912), respectively. In the initial evaluation of 25,536 individuals without RI patients whose DLM was defined as having a higher risk had a significantly higher chance of developing RI than those in the low-risk group (17.2% vs. 2.4%, p < 0.001). The sensitivity map indicated that the DLM focused on the QRS complex and T-wave for detecting RI.

Conclusion

The DLM demonstrated high performance for RI detection and prediction using 12-, 6-, single-lead ECGs.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11255-022-03165-w.

State-of-the-art Deep Learning Methods on Electrocardiogram Data: A Systematic Review (Preprint)

Background

Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals.

Objective

This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications.

Methods

The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches.

Results

We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models.

Conclusions

We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making.

A Highly Stretchable and Permeable Liquid Metal Micromesh Conductor by Physical Deposition for Epidermal Electronics

Stretchable electronics allow functional devices to integrate with human skin seamlessly in an emerging wearable platform termed epidermal electronics. Compliant conductors represent key building components for functional devices. Among the various candidates, gallium-based liquid metals stand out with metallic conductivity and inherent deformability. Currently, the widespread applications of liquid metals in epidermal electronics are hindered by the low steam permeability and hence unpleasant wearing perceptions. In this study, a facile physical deposition approach is established to create a liquid metal micromesh over an elastomer sponge, which exhibits low sheet resistance (∼0.5 Ω sq^-1), high stretchability (400% strain), and excellent durability. The porous micromesh shows textile-level permeability to achieve long-term wearing comfort. The conformal interaction of the liquid metal micromesh with the skin gives rise to a low contact impedance. An integrated epidermal sensing sleeve is demonstrated as a human-machine interface to distinguish different hand gestures by recording muscle contractions. The reported stretchable and permeable liquid metal conductor shows promising potentials in next-generation epidermal electronics.

Artificial Intelligence-Enabled Electrocardiography Predicts Left Ventricular Dysfunction and Future Cardiovascular Outcomes: A Retrospective Analysis

BACKGROUND: The ejection fraction (EF) provides critical information about heart failure (HF) and its management. Electrocardiography (ECG) is a noninvasive screening tool for cardiac electrophysiological activities that has been used to detect patients with low EF based on a deep learning model (DLM) trained via large amounts of data. However, no studies have widely investigated its clinical impacts. OBJECTIVE: This study developed a DLM to estimate EF via ECG (ECG-EF). We further investigated the relationship between ECG-EF and echo-based EF (ECHO-EF) and explored their contributions to future cardiovascular adverse events. METHODS: There were 57,206 ECGs with corresponding echocardiograms used to train our DLM. We compared a series of training strategies and selected the best DLM. The architecture of the DLM was based on ECG12Net, developed previously. Next, 10,762 ECGs were used for validation, and another 20,629 ECGs were employed to conduct the accuracy test. The changes between ECG-EF and ECHO-EF were evaluated. The primary follow-up adverse events included future ECHO-EF changes and major adverse cardiovascular events (MACEs). RESULTS: The sex-/age-matching strategy-trained DLM achieved the best area under the curve (AUC) of 0.9472 with a sensitivity of 86.9% and specificity of 89.6% in the follow-up cohort, with a correlation of 0.603 and a mean absolute error of 7.436. In patients with accurate prediction (initial difference < 10%), the change traces of ECG-EF and ECHO-EF were more consistent (R-square = 0.351) than in all patients (R-square = 0.115). Patients with lower ECG-EF (≤35%) exhibited a greater risk of cardiovascular (CV) complications, delayed ECHO-EF recovery, and earlier ECHO-EF deterioration than patients with normal ECG-EF (>50%). Importantly, ECG-EF demonstrated an independent impact on MACEs and all CV adverse outcomes, with better prediction of CV outcomes than ECHO-EF. CONCLUSIONS: The ECG-EF could be used to initially screen asymptomatic left ventricular dysfunction (LVD) and it could also independently contribute to the predictions of future CV adverse events. Although further large-scale studies are warranted, DLM-based ECG-EF could serve as a promising diagnostic supportive and management-guided tool for CV disease prediction and the care of patients with LVD.

A Deep Learning Model for Inferring Elevated Pulmonary Capillary Wedge Pressures From the 12-Lead Electrocardiogram

Background

Central hemodynamic parameters are typically measured via pulmonary artery catherization-an invasive procedure that involves some risk to the patient and is not routinely available in all settings.

Objectives

This study sought to develop a noninvasive method to identify elevated mean pulmonary capillary wedge pressure (mPCWP).

Methods

We leveraged data from 248,955 clinical records at the Massachusetts General Hospital to develop a deep learning model that can infer when the mPCWP >15 mmHg using the 12-lead electrocardiogram (ECG). Of these data, 242,216 records were used to pre-train a model that generates useful ECG representations. The remaining 6,739 records contain encounters with direct measurements of the mPCWP. Eighty percent of these data were used for model development and testing (5,390), and the remaining records comprise a holdout set (1,349) that was used to evaluate the model. We developed an associated unreliability score that identifies when model predictions are likely to be untrustworthy.

Results

The model achieves an area under the receiver operating characteristic curve (AUC) of 0.80 ± 0.02 (test set) and 0.79 ± 0.01 (holdout set). Model performance varies as a function of the unreliability, where patients with high unreliability scores correspond to a subgroup where model performance is poor: for example, patients in the holdout set with unreliability scores in the highest decile have a reduced AUC of 0.70 ± 0.06.

Conclusions

The mPCWP can be inferred from the ECG, and the reliability of this inference can be measured. When invasive monitoring cannot be expeditiously performed, deep learning models may provide information that can inform clinical care.

Type I Brugada-Like Pattern with Arrhythmia in Severe Anemia

Introduction

Brugada syndrome (BrS) has been described as an inherited cardiac disorder due to gene mutations, which contributes to sudden cardiac death, especially in Southeast Asians. Brugada phenocopy, which has the same pattern caused by etiologies such as metabolic disorder, is potentially reversible and avoids unnecessary implantable medical devices.

Case Presentation

We reported a rare case of Brugada phenocopy in a 60-years-old Indonesian male with severe anemia and a history of chronic urinary tract bleeding and hemorrhoid. Brugada phenocopy, widely known as BrS look-alike, has been linked to sodium, potassium, and calcium channel dysfunction. This condition is uncommon and has been related to metabolic conditions such as anemia. Iron deficiency anemia induces ischemia in the myocardium and degrades the calcium channels. During the transfusion, hypocalcemia precipitates temporary arrhythmia with right ventricular outflow tract origin, which reverts after the hypocalcemia has been treated.

Conclusion

Due to the possibility of altered ion channels and how rarely hypocalcemia induces arrhythmia, this makes understanding the pathogenesis of Brugada phenocopy essential. Though caution is necessary, early recognition can improve prognosis as Brugada phenocopy is potentially reversible.

Artificial Intelligence for Detection of Cardiovascular-Related Diseases from Wearable Devices: A Systematic Review and Meta-Analysis

PURPOSE

Several artificial intelligence (AI) models for the detection and prediction of cardiovascular-related diseases, including arrhythmias, diabetes, and sleep apnea, have been reported. This systematic review and meta-analysis aimed to identify AI models developed for or applicable to wearable and mobile devices for diverse cardiovascular-related diseases.

MATERIALS AND METHODS

The searched databases included Medline, Embase, and Cochrane Library. For AI models for atrial fibrillation (AF) detection, a meta-analysis of diagnostic accuracy was performed to summarize sensitivity and specificity.

RESULTS

A total of 102 studies were included in the qualitative review. There were AI models for the detection of arrythmia (n=62), followed by sleep apnea (n=11), peripheral vascular diseases (n=6), diabetes mellitus (n=5), hyper/hypotension (n=5), valvular heart disease (n=4), heart failure (n=3), myocardial infarction and cardiac arrest (n=2), and others (n=4). For quantitative analysis of 26 studies reporting AI models for AF detection, meta-analyzed sensitivity was 94.80% and specificity was 96.96%. Deep neural networks showed superior performance [meta-analyzed area under receiver operating characteristics curve (AUROC) of 0.981] compared to conventional machine learning algorithms (meta-analyzed AUROC of 0.961). However, AI models tested with proprietary dataset (meta-analyzed AUROC of 0.972) or data acquired from wearable devices (meta-analyzed AUROC of 0.977) showed inferior performance than those with public dataset (meta-analyzed AUROC of 0.986) or data from in-hospital devices (meta-analyzed AUROC of 0.983).

CONCLUSION

This review found that AI models for diverse cardiovascular-related diseases are being developed, and that they are gradually developing into a form that is suitable for wearable and mobile devices.

Deep learning evaluation of biomarkers from echocardiogram videos

BACKGROUND

Laboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos can provide additional value in understanding disease states and can evaluate common biomarkers results.

METHODS

We developed EchoNet-Labs, a video-based deep learning algorithm to detect evidence of anemia, elevated B-type natriuretic peptide (BNP), troponin I, and blood urea nitrogen (BUN), as well as values of ten additional lab tests directly from echocardiograms. We included patients (n = 39,460) aged 18 years or older with one or more apical-4-chamber echocardiogram videos (n = 70,066) from Stanford Healthcare for training and internal testing of EchoNet-Lab's performance in estimating the most proximal biomarker result. Without fine-tuning, the performance of EchoNet-Labs was further evaluated on an additional external test dataset (n = 1,301) from Cedars-Sinai Medical Center. We calculated the area under the curve (AUC) of the receiver operating characteristic curve for the internal and external test datasets.

FINDINGS

On the held-out test set of Stanford patients not previously seen during model training, EchoNet-Labs achieved an AUC of 0.80 (0.79-0.81) in detecting anemia (low hemoglobin), 0.86 (0.85-0.88) in detecting elevated BNP, 0.75 (0.73-0.78) in detecting elevated troponin I, and 0.74 (0.72-0.76) in detecting elevated BUN. On the external test dataset from Cedars-Sinai, EchoNet-Labs achieved an AUC of 0.80 (0.77-0.82) in detecting anemia, of 0.82 (0.79-0.84) in detecting elevated BNP, of 0.75 (0.72-0.78) in detecting elevated troponin I, and of 0.69 (0.66-0.71) in detecting elevated BUN. We further demonstrate the utility of the model in detecting abnormalities in 10 additional lab tests. We investigate the features necessary for EchoNet-Labs to make successful detection and identify potential mechanisms for each biomarker using well-known and novel explainability techniques.

INTERPRETATION

These results show that deep learning applied to diagnostic imaging can provide additional clinical value and identify phenotypic information beyond current imaging interpretation methods.

FUNDING

J.W.H. and B.H. are supported by the NSF Graduate Research Fellowship. D.O. is supported by NIH K99 HL157421-01. J.Y.Z. is supported by NSF CAREER 1942926, NIH R21 MD012867-01, NIH P30AG059307 and by a Chan-Zuckerberg Biohub Fellowship.

Deep-learning model for screening sepsis using electrocardiography

Background

Sepsis is a life-threatening organ dysfunction and a major healthcare burden worldwide. Although sepsis is a medical emergency that requires immediate management, screening for the occurrence of sepsis is difficult. Herein, we propose a deep learning-based model (DLM) for screening sepsis using electrocardiography (ECG).

Methods

This retrospective cohort study included 46,017 patients who were admitted to two hospitals. A total of 1,548 and 639 patients had sepsis and septic shock, respectively. The DLM was developed using 73,727 ECGs from 18,142 patients, and internal validation was conducted using 7774 ECGs from 7,774 patients. Furthermore, we conducted an external validation with 20,101 ECGs from 20,101 patients from another hospital to verify the applicability of the DLM across centers.

Results

During the internal and external validations, the area under the receiver operating characteristic curve (AUC) of the DLM using 12-lead ECG was 0.901 (95% confidence interval, 0.882–0.920) and 0.863 (0.846–0.879), respectively, for screening sepsis and 0.906 (95% confidence interval (CI), 0.877–0.936) and 0.899 (95% CI, 0.872–0.925), respectively, for detecting septic shock. The AUC of the DLM for detecting sepsis using 6-lead and single-lead ECGs was 0.845–0.882. A sensitivity map revealed that the QRS complex and T waves were associated with sepsis. Subgroup analysis was conducted using ECGs from 4,609 patients who were admitted with an infectious disease, and the AUC of the DLM for predicting in-hospital mortality was 0.817 (0.793–0.840). There was a significant difference in the prediction score of DLM using ECG according to the presence of infection in the validation dataset (0.277 vs. 0.574, p < 0.001), including severe acute respiratory syndrome coronavirus 2 (0.260 vs. 0.725, p = 0.018).

Conclusions

The DLM delivered reasonable performance for sepsis screening using 12-, 6-, and single-lead ECGs. The results suggest that sepsis can be screened using not only conventional ECG devices but also diverse life-type ECG machines employing the DLM, thereby preventing irreversible disease progression and mortality.

Deep learning methods for screening patients' S-ICD implantation eligibility

Subcutaneous Implantable Cardioverter-Defibrillators (S-ICDs) are used for prevention of sudden cardiac death triggered by ventricular arrhythmias. T Wave Over Sensing (TWOS) is an inherent risk with S-ICDs which can lead to inappropriate shocks. A major predictor of TWOS is a high T:R ratio (the ratio between the amplitudes of the T and R waves). Currently, patients' Electrocardiograms (ECGs) are screened over 10 s to measure the T:R ratio to determine the patients' eligibility for S-ICD implantation. Due to temporal variations in the T:R ratio, 10 s is not a long enough window to reliably determine the normal values of a patient's T:R ratio. In this paper, we develop a convolutional neural network (CNN) based model utilising phase space reconstruction matrices to predict T:R ratios from 10-second ECG segments without explicitly locating the R or T waves, thus avoiding the issue of TWOS. This tool can be used to automatically screen patients over a much longer period and provide an in-depth description of the behavior of the T:R ratio over that period. The tool can also enable much more reliable and descriptive screenings to better assess patients' eligibility for S-ICD implantation.

Biosignal-Based Digital Biomarkers for Prediction of Ventilator Weaning Success

We evaluated new features from biosignals comprising diverse physiological response information to predict the outcome of weaning from mechanical ventilation (MV). We enrolled 89 patients who were candidates for weaning from MV in the intensive care unit and collected continuous biosignal data: electrocardiogram (ECG), respiratory impedance, photoplethysmogram (PPG), arterial blood pressure, and ventilator parameters during a spontaneous breathing trial (SBT). We compared the collected biosignal data's variability between patients who successfully discontinued MV (n = 67) and patients who did not (n = 22). To evaluate the usefulness of the identified factors for predicting weaning success, we developed a machine learning model and evaluated its performance by bootstrapping. The following markers were different between the weaning success and failure groups: the ratio of standard deviations between the short-term and long-term heart rate variability in a Poincaré plot, sample entropy of ECG and PPG, α values of ECG, and respiratory impedance in the detrended fluctuation analysis. The area under the receiver operating characteristic curve of the model was 0.81 (95% confidence interval: 0.70-0.92). This combination of the biosignal data-based markers obtained during SBTs provides a promising tool to assist clinicians in determining the optimal extubation time.

Acute Myocardial Infarction Detection Using Deep Learning-Enabled Electrocardiograms

Background: Acute myocardial infarction (AMI) is associated with a poor prognosis. Therefore, accurate diagnosis and early intervention of the culprit lesion are of extreme importance. Therefore, we developed a neural network algorithm in this study to automatically diagnose AMI from 12-lead electrocardiograms (ECGs). Methods: We used the open-source PTB-XL database as the training and validation sets, with a 7:3 sample size ratio. Twenty-One thousand, eight hundred thirty-seven clinical 12-lead ECGs from the PTB-XL dataset were available for training and validation (15,285 were used in the training set and 6,552 in the validation set). Additionally, we randomly selected 205 ECGs from a dataset built by Chapman University, CA, USA and Shaoxing People's Hospital, China, as the testing set. We used a residual network for training and validation. The model performance was experimentally verified in terms of area under the curve (AUC), precision, sensitivity, specificity, and F1 score. Results: The AUC of the training, validation, and testing sets were 0.964 [95% confidence interval (CI): 0.961-0.966], 0.944 (95% CI: 0.939-0.949), and 0.977 (95% CI: 0.961-0.991), respectively. The precision, sensitivity, specificity, and F1 score of the deep learning model for AMI diagnosis from ECGs were 0.827, 0.824, 0.950, and 0.825, respectively, in the training set, 0.789, 0.818, 0.913, and 0.803, respectively, in the validation set, and 0.830, 0.951, 0.951, and 0.886, respectively, in the testing set. The AUC for automatic AMI location diagnosis of LMI, IMI, ASMI, AMI, ALMI were 0.969 (95% CI: 0.959-0.979), 0.973 (95% CI: 0.962-0.978), 0.987 (95% CI: 0.963-0.989), 0.961 (95% CI: 0.956-0.989), and 0.996 (95% CI: 0.957-0.997), respectively. Conclusions: The residual network-based algorithm can effectively automatically diagnose AMI and MI location from 12-lead ECGs.