Feasibility of the deep learning method for estimating the ventilatory threshold with electrocardiography data

Development of deep-learning models for real-time anaerobic threshold and peak VO2 prediction during cardiopulmonary exercise testing

AIMS

Exercise intolerance is a clinical feature of patients with heart failure (HF). Cardiopulmonary exercise testing (CPET) is the first-line examination for assessing exercise capacity in patients with HF. However, the need for extensive experience in assessing anaerobic threshold (AT) and the potential risk associated with the excessive exercise load when measuring peak oxygen uptake (peak VO2) limit the utility of CPET. This study aimed to use deep-learning approaches to identify AT in real time during testing (defined as real-time AT) and to predict peak VO2 at real-time AT.

METHODS AND RESULTS

This study included the time-series data of CPET recorded at the Department of Cardiovascular Medicine, Kyushu University Hospital. Two deep neural network models were developed to: (i) estimate the AT probability using breath-by-breath data and (ii) predict peak VO2 using the data at the real-time AT. The eligible CPET contained 1472 records of 1053 participants aged 18-90 years and 20% were used for model evaluation. The developed model identified real-time AT with 0.82 for correlation coefficient (Corr) and 1.20 mL/kg/min for mean absolute error (MAE), and the corresponding AT time with 0.86 for Corr and 0.66 min for MAE. The peak VO2 prediction model achieved 0.87 for Corr and 2.25 mL/kg/min for MAE.

CONCLUSION

Deep-learning models for real-time CPET analysis can accurately identify AT and predict peak VO2. The developed models can be a competent assistant system to assess a patient's condition in real time, expanding CPET utility.

Deep learning-based dynamic ventilatory threshold estimation from electrocardiograms

BACKGROUND AND OBJECTIVE

The ventilatory threshold (VT) marks the transition from aerobic to anaerobic metabolism and is used to assess cardiorespiratory endurance. A conventional way to assess VT is cardiopulmonary exercise testing, which requires a gas analyzer. Another method for measuring VT involves calculating the heart rate variability (HRV) from an electrocardiogram (ECG) by computing the variability of heartbeats. However, the HRV method has some limitations. ECGs should be recorded for at least 5 minutes to calculate the HRV, and the result may depend on the utilized ECG preprocessing algorithms.

METHODS

To overcome these problems, we developed a deep learning-based model consisting of long short-term memory (LSTM) and convolutional neural network (CNN) for a lead II ECG. Variables reflecting subjects' physical characteristics, as well as ECG signals, were input into the model to estimate VT. We applied joint optimization to the CNN layers to generate an informative latent space, which was fed to the LSTM layers. The model was trained and evaluated on two datasets, one from the Bruce protocol and the other from a protocol including multiple tasks (MT).

RESULTS

Acceptable performances (mean and 95% CI) were obtained on the datasets from the Bruce protocol (-0.28[-1.91,1.34] ml/min/kg) and the MT protocol (0.07[-3.14,3.28] ml/min/kg) regarding the differences between the predictions and labels. The coefficient of determination, Pearson correlation coefficient, and root mean square error were 0.84, 0.93, and 0.868 for the Bruce protocol and 0.73, 0.97, and 3.373 for the MT protocol, respectively.

CONCLUSIONS

The results indicated that it is possible for the proposed model to simultaneously assess VT with the inputs of successive ECGs. In addition, from ablation studies concerning the physical variables and the joint optimization process, it was demonstrated that their use could boost the VT assessment performance of the model. The proposed model enables dynamic VT estimation with ECGs, which could help with managing cardiorespiratory fitness in daily life and cardiovascular rehabilitation in patients.

Estimating age and gender from electrocardiogram signals: A comprehensive review of the past decade

Twelve lead electrocardiogram signals capture unique fingerprints about the body's biological processes and electrical activity of heart muscles. Machine learning and deep learning-based models can learn the embedded patterns in the electrocardiogram to estimate complex metrics such as age and gender that depend on multiple aspects of human physiology. ECG estimated age with respect to the chronological age reflects the overall well-being of the cardiovascular system, with significant positive deviations indicating an aged cardiovascular system and a higher likelihood of cardiovascular mortality. Several conventional, machine learning, and deep learning-based methods have been proposed to estimate age from electronic health records, health surveys, and ECG data. This manuscript comprehensively reviews the methodologies proposed for ECG-based age and gender estimation over the last decade. Specifically, the review highlights that elevated ECG age is associated with atherosclerotic cardiovascular disease, abnormal peripheral endothelial dysfunction, and high mortality, among many other cardiovascular disorders. Furthermore, the survey presents overarching observations and insights across methods for age and gender estimation. This paper also presents several essential methodological improvements and clinical applications of ECG-estimated age and gender to encourage further improvements of the state-of-the-art methodologies.

Deep learning-based model detects atrial septal defects from electrocardiography: a cross-sectional multicenter hospital-based study

Background

Atrial septal defect (ASD) increases the risk of adverse cardiovascular outcomes. Despite the potential for risk mitigation through minimally invasive percutaneous closure, ASD remains underdiagnosed due to subtle symptoms and examination findings. To bridge this diagnostic gap, we propose a novel screening strategy aimed at early detection and enhanced diagnosis through the implementation of a convolutional neural network (CNN) to identify ASD from 12-lead electrocardiography (ECG).

Methods

ECGs were collected from patients with at least one recorded echocardiogram at 3 hospitals from 2 continents (Keio University Hospital from July 2011 to December 2020, Brigham and Women's Hospital from January 2015 to December 2020, and Dokkyo Medical University Saitama Medical Center from January 2010 and December 2021). ECGs from patients with a diagnosis of ASD were labeled as positive cases while the remainder were labeled as negative. ECGs after the closure of ASD were excluded. After randomly splitting the ECGs into 3 datasets (50% derivation, 20% validation, and 30% test) with no patient overlap, a CNN-based model was trained using the derivation datasets from 2 hospitals and was tested on held-out datasets along with an external validation on the 3rd hospital. All eligible ECGs were used for derivation and validation whereas the earliest ECG for each patient was used for the test and external validation. The discrimination of ASD was assessed by the area under the receiver operating characteristic curve (AUROC). Multiple subgroups were examined to identify any heterogeneity.

Findings

A total of 671,201 ECGs from 80,947 patients were collected from the 3 institutions. The AUROC for detecting ASD was 0.85-0.90 across the 3 hospitals. The subgroup analysis showed excellent performance across various characteristics Screening simulation using the model greatly increased sensitivity from 80.6% to 93.7% at specificity 33.6% when compared to using overt ECG abnormalities.

Interpretation

A CNN-based model using 12-lead ECG successfully identified the presence of ASD with excellent generalizability across institutions from 2 separate continents.

Funding

This work was supported by research grants from JST (JPMJPF2101), JSR corporation, Taiju Life Social Welfare Foundation, Kondou Kinen Medical Foundation, Research fund of Mitsukoshi health and welfare foundation, Tokai University School of Medicine Project Research and Internal Medicine Project Research, Secom Science and Technology Foundation, and Grants from AMED (JP23hma922012 and JP23ym0126813). This work was partially supported by One Brave Idea, co-funded by the American Heart Association and Verily with significant support from AstraZeneca and pillar support from Quest Diagnostics.

Heart Rate Variability and its Association with Second Ventilatory Threshold Estimation in Maximal Exercise Test

During incremental exercise, two ventilatory thresholds (VT1, VT2) can normally be identified from gas exchange and ventilatory measurements, such as oxygen uptake, carbon dioxide production and ventilation. In this paper, we attempt to estimate the VT2 using HRV indices derived from a wearable electrocardiogram during a maximal exercise test. The exercise test is conducted on a treadmill that raises its speed by 0.5 km/h every minute. We have 42 measured exercise tests from 24 healthy male volunteers. Three experts determined the VT2 in each exercise test independently and we used principal component subspace reconstruction of their determinations to compute a collective VT2 for our machine learning model. The results demonstrate that the VT2 can be estimated from HRV using the proposed method with a reasonable performance during a maximal exercise test. In 28 out of 42 exercise tests, the HRV-derived threshold (HRVT) is within a minute (one phase) of the collective expert's determination.

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.

Temporal convolutional networks predict dynamic oxygen uptake response from wearable sensors across exercise intensities

Oxygen consumption ([Formula: see text]) provides established clinical and physiological indicators of cardiorespiratory function and exercise capacity. However, [Formula: see text] monitoring is largely limited to specialized laboratory settings, making its widespread monitoring elusive. Here we investigate temporal prediction of [Formula: see text] from wearable sensors during cycle ergometer exercise using a temporal convolutional network (TCN). Cardiorespiratory signals were acquired from a smart shirt with integrated textile sensors alongside ground-truth [Formula: see text] from a metabolic system on 22 young healthy adults. Participants performed one ramp-incremental and three pseudorandom binary sequence exercise protocols to assess a range of [Formula: see text] dynamics. A TCN model was developed using causal convolutions across an effective history length to model the time-dependent nature of [Formula: see text]. Optimal history length was determined through minimum validation loss across hyperparameter values. The best performing model encoded 218 s history length (TCN-VO2 A), with 187, 97, and 76 s yielding <3% deviation from the optimal validation loss. TCN-VO2 A showed strong prediction accuracy (mean, 95% CI) across all exercise intensities (-22 ml min^-1, [-262, 218]), spanning transitions from low-moderate (-23 ml min^-1, [-250, 204]), low-high (14 ml min^-1, [-252, 280]), ventilatory threshold-high (-49 ml min^-1, [-274, 176]), and maximal (-32 ml min^-1, [-261, 197]) exercise. Second-by-second classification of physical activity across 16,090 s of predicted [Formula: see text] was able to discern between vigorous, moderate, and light activity with high accuracy (94.1%). This system enables quantitative aerobic activity monitoring in non-laboratory settings, when combined with tidal volume and heart rate reserve calibration, across a range of exercise intensities using wearable sensors for monitoring exercise prescription adherence and personal fitness.

Non-invasive diagnosis of deep vein thrombosis from ultrasound imaging with machine learning

Deep vein thrombosis (DVT) is a blood clot most commonly found in the leg, which can lead to fatal pulmonary embolism (PE). Compression ultrasound of the legs is the diagnostic gold standard, leading to a definitive diagnosis. However, many patients with possible symptoms are not found to have a DVT, resulting in long referral waiting times for patients and a large clinical burden for specialists. Thus, diagnosis at the point of care by non-specialists is desired. We collect images in a pre-clinical study and investigate a deep learning approach for the automatic interpretation of compression ultrasound images. Our method provides guidance for free-hand ultrasound and aids non-specialists in detecting DVT. We train a deep learning algorithm on ultrasound videos from 255 volunteers and evaluate on a sample size of 53 prospectively enrolled patients from an NHS DVT diagnostic clinic and 30 prospectively enrolled patients from a German DVT clinic. Algorithmic DVT diagnosis performance results in a sensitivity within a 95% CI range of (0.82, 0.94), specificity of (0.70, 0.82), a positive predictive value of (0.65, 0.89), and a negative predictive value of (0.99, 1.00) when compared to the clinical gold standard. To assess the potential benefits of this technology in healthcare we evaluate the entire clinical DVT decision algorithm and provide cost analysis when integrating our approach into diagnostic pathways for DVT. Our approach is estimated to generate a positive net monetary benefit at costs up to £72 to £175 per software-supported examination, assuming a willingness to pay of £20,000/QALY.

Sensitivity of movement features to fatigue during an exhaustive treadmill run

HIGHLIGHTS

Trunk frontal plane kinematics is the most sensitive parameter to fatigue. Practitioners should consider this finding during endurance training.Kinetics exhibit a stable linear increase in mean values but a non-linear increase in variance during an exhaustive incremental treadmill run. This may affect training at a submaximal fatigued state.Specific areas in the joint distributions of kinetics and kinematics during treadmill running exhibit increased sensitivity in predicting fatigue state.

From Precision Metapharmacology to Patient Empowerment: Delivery of Self-Care Practices for Epilepsy, Pain, Depression and Cancer Using Digital Health Technologies

To improve long-term outcomes of therapies for chronic diseases, health promotion and lifestyle modifications are the most promising and sustainable strategies. In addition, advances in digital technologies provide new opportunities to address limitations of drug-based treatments, such as medication non-adherence, adverse effects, toxicity, drug resistance, drug shortages, affordability, and accessibility. Pharmaceutical drugs and biologics can be combined with digital health technologies, including mobile medical apps (digital therapeutics), which offer additional clinical benefits and cost-effectiveness. Promises of drug+digital combination therapies are recognized by pharmaceutical and digital health companies, opening opportunities for integrating pharmacotherapies with non-pharmacological interventions (metapharmacology). Herein we present unique features of digital health technologies which can deliver personalized self-care modalities such as breathing exercises, mindfulness meditation, yoga, physical activity, adequate sleep, listening to preferred music, forgiveness and gratitude. Clinical studies reveal how aforementioned complimentary practices may support treatments of epilepsy, chronic pain, depression, cancer, and other chronic diseases. This article also describes how digital therapies delivering “medicinal” self-care and other non-pharmacological interventions can also be personalized by accounting for: 1) genetic risks for comorbidities, 2) adverse childhood experiences, 3) increased risks for viral infections such as seasonal influenza, or COVID-19, and 4) just-in-time stressful and traumatic circumstances. Development and implementation of personalized pharmacological-behavioral combination therapies (precision metapharmacology) require aligning priorities of key stakeholders including patients, research communities, healthcare industry, regulatory and funding agencies. In conclusion, digital technologies enable integration of pharmacotherapies with self-care, lifestyle interventions and patient empowerment, while concurrently advancing patient-centered care, integrative medicine and digital health ecosystems.

A novel device for detecting anaerobic threshold using sweat lactate during exercise

The lactate threshold (LT1), which is defined as the first rise in lactate concentration during incremental exercise, has not been non-invasively and conveniently determined in a clinical setting. We aimed to visualize changes in lactate concentration in sweat during exercise using our wearable lactate sensor and investigate the relationship between the lactate threshold (LT1) and ventilatory threshold (VT1). Twenty-three healthy subjects and 42 patients with cardiovascular diseases (CVDs) were enrolled. During exercise, the dynamic changes in lactate values in sweat were visualized in real-time with a sharp continuous increase up to volitional exhaustion and a gradual decrease during the recovery period. The LT1 in sweat was well correlated with the LT1 in blood and the VT1 (r = 0.92 and 0.71, respectively). In addition, the Bland–Altman plot described no bias between the mean values (mean differences: − 4.5 and 2.5 W, respectively). Continuous monitoring of lactate concentrations during exercise can provide additional information for detecting the VT1.