A Systematic Review on Artificial Intelligence-Based Techniques for Diagnosis of Cardiovascular Arrhythmia Diseases: Challenges and Opportunities

An electrocardiogram (ECG) is used to check the electrical activity of the heart over a limited short-term or long-term period. Short-term observations are often used in hospitals or clinics, whereas long-term observations (often called continuous or stream-like ECG observations) are used to monitor the heart’s electrical activity on a daily basis and during different daily activities, such as sleeping, running, eating, etc. ECG can reflect the normal sinus rhythm as well as different heart problems, which might vary from Premature Atrial Contractions (PAC) and Premature Ventricular Contractions (PVC), to Sinus Arrest and many other problems. In order to perform such monitoring on a daily basis, it is very important to implement automated solutions that perform most of the work of the daily ECG analysis and could alert the doctors in case of any problem, and could even detect the type of the problem in order for the doctors to have an immediate report about the patient’s health status. This paper aims to provide a workflow for abnormal ECG signals detection from different sources of digitized ECG signals, including ambulatory devices. We propose an algorithm for ECG pre-annotation and beat-to-beat separation for heartbeat classification using Autoencoders. The algorithm includes the training of different models for different types of abnormal ECG signals, and has shown promising results for normal sinus rhythm and PVC compared to other solutions. This solution is proposed for no-noise and noisy signals as well.

/pdf/a-novel-algorithm-for-automated-human-single-lead-ecg-pre-19wvrik7.pdf

A Novel Algorithm for Automated Human Single-Lead ECG Pre-Annotation and Beat-to-Beat Separation for Heartbeat Classification Using Autoencoders

Electrocardiograms, also known as ECGs, are capable of representing a wide range of heart conditions, such as atrial fibrillation, arrhythmia, myopathy, and heart failure. Operations such as denoising, signal enhancement, feature extraction, feature selection, stratification, and post processing are developed in order to process ECG signals. Depending on the application that is being deployed, these processes may only work in their individual components or in combination with one another. Researchers over the years have developed a wide variety of algorithms, each specifically tailored to accomplish one of these tasks. The computational complexity of these algorithms, the number of diseases they can classify, the degree of accuracy they provide, the cost of deployment, and other factors can vary. For example, models that are based on convolutional neural networks (CNNs) have a high level of accuracy; however, these models are typically slow and highly complex to deploy, and as a result, theyare not used in clinical applications that have a low cost. However, linear classification models such as support vector machines (SVMs) have acceptable accuracy, a moderate level of complexity, but are lacking in terms of precision; as a result, they are not suitable for use in applications that require real-time processing. Because there is such a wide range of algorithms that are available, it is unclear to researchers which models would be the best fit for their application, which leads to an increase in both the cost of deployment and the amount of time needed to bring the product to market. The text that lies beneath this one examines several of the recently proposed ECG classification models and assesses them based on a number of statistical parameters, including computational delay, complexity of deployment, classification accuracy, precision, number of heart diseases covered, and so on.This is done in an effort to clarify the situation and remove some of the ambiguity. After completing this analysis, the text then compares their performance and provides an estimate of the models that are the most appropriate. Researchers now have the ability to select and implement the algorithmic models that are best suited for their deployments based on this review. In addition to that, this reviwe suggests a number of different enhancements that can be made to the models that have been examined, and researchers can implement these suggestions in order to increase the effectiveness of the models.

Pragmatic analysis of ECG classification models & architectures from a statistical perspective

In the analysis of ECG data, it is necessary to first automatically classify the quality of ECG data to facilitate the subsequent processing. PhysioNet/Computing in Cardiology Challenge 2011 and existing researches involve the quality of the entire record of ECG, which fails to maximize utilization of ECG data. In fact, single-lead ECG has been widely used in many fields, such as wearable devices, sleep apnea monitoring, and deriving respiratory rate. However, the present methods for evaluating the data quality by each channel only divide them into two categories: acceptable and unacceptable, which is relatively coarse. This paper proposes a new method for the automatic classification of ECG data quality by channel. This method divides them into four categories: (1) electrode shedding, marked as C3; (2) serious noise interference, under which it is difficult to detect R wave, marked as C2; (3) partial noise interference, under which part of R waves may not be detected correctly, marked as C1; (4) high quality signal, marked as C0. The 2011 competition data was re-marked according to the channel with the help of our designed auxiliary program. This paper defined some features and designed a tree classifier using One-Class Support Vector Machine(OCSVM). The test results of our method show that the detection accuracy of electrode shedding is 93.22%, serious noise interference is 90%, partial noise interference is 89.22%, and high quality signal is 97.19%. It shows that the method has a broad prospect in the automatic preprocessing of ECG data.

/pdf/automatic-classification-of-ecg-data-quality-for-each-3nxbzhrvnt.pdf

Automatic Classification of ECG Data Quality for Each Channel

Non-linear Radical Additions-Coupling Polymerization of Monovinyl Monomers towards Polymer Networks: Theory, Tunability and Heritable Architecture


 Mutation or amplification of the human epidermal growth factor receptor 2 (HER2) gene has been identified in numerous solid tumor types, including non-small cell lung cancer (NSCLC), breast, and colorectal cancer. These genetic alterations are believed to confer elevated HER2 activity resulting in oncogenic transformation. In NSCLC, an estimated 3% of patients harbor activating mutations in the HER2 gene. Enhertu (T-DXd), a HER2-specific antibody-drug conjugate was recently approved as an important therapy for this patient population. However, for patients who are not candidates for T-DXd or have discontinued treatment due to an adverse event or disease progression, there exist few therapeutic options. Accordingly, HER2 inhibitors have the potential to provide meaningful therapeutic benefit to these patients. Due to significant structural homology between EGFR and HER2, most investigational small molecule HER2 kinase inhibitors are dual EGFR/HER2 inhibitors and are substantially dose-limited by EGFR-related toxicities in patients. These toxicities likely limit their clinical activity. Currently, tucatinib is the only HER2-selective small molecule inhibitor approved for metastatic breast cancer in combination with trastuzumab and capecitabine. However, it lacks sufficient potency against several of the key clinically relevant mutations, including HER2 YVMA, the most common exon 20 insertion mutation, prevalent in HER2 mutant NSCLC. ELVN-002 is a potent, irreversible inhibitor of HER2 with a >100-fold selectivity over EGFR. ELVN-002 potently inhibits the phosphorylation of HER2 in cell lines endogenously expressing HER2 or in those engineered to express specific clinically relevant HER2 mutants. This activity readily translates into marked anti-proliferative activity against cell lines dependent upon HER2 for their growth and survival. In addition, ELVN-002 is highly selective for HER2 and HER2 mutants versus wild-type EGFR as demonstrated via assessment of both EGFR-driven proliferation and EGFR phosphorylation in cells. Furthermore, ELVN-002 is highly active in mouse models of HER2-driven cancers, including subcutaneous models driven by wild type or mutant HER2. ELVN-002 is also active in an NCI-N87 wild-type HER2 intracranial model. In all models tested, ELVN-002 treatment is well tolerated and resulted in tumor regressions at exposures believed to be clinically achievable. Due to its selectivity and breadth of activity versus the clinically relevant HER2 mutants, ELVN-002 has the potential to be an effective treatment for HER2 mutant NSCLC as well as other HER2 mutant amplified solid tumors, including metastatic HER2 positive breast cancer. Additionally, ELVN-002 could provide a meaningful therapeutic option for patients with CNS metastases. ELVN-002 has been selected for clinical development.
 Citation Format: Monette Aujay, Amanda J. Broad, Stefan D. Gross, Li Ren, Joseph P. Lyssikatos, Samuel Kintz, Qi Wang, Helen Collins. Preclinical activity of ELVN-002: A potent, selective, and irreversible HER2 and pan-HER2 mutant small molecule inhibitor for the treatment of HER2 driven malignancies. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 4019.

Abstract 4019: Preclinical activity of ELVN-002: A potent, selective, and irreversible HER2 and pan-HER2 mutant small molecule inhibitor for the treatment of HER2 driven malignancies

Abstract Focused ultrasound ablation surgery (FUAS) is a novel therapy with a wide range of potential applications. However, synergists are crucial to the therapy process due to the ultrasonic energy's attenuation properties. As a result of the complex hypoxic environment in the tumor area and many factors, the existing synergists have limitations such as weak targeting, single imaging mode, and easy tumor recurrence after treatment. Because of the above deficiencies, this study intends to construct bio-targeted oxygen production probes consisting of Bifidobacterium that naturally target the hypoxia region of the tumor and multi-functional oxygen-producing nanoparticles equipped with IR780, perfluorohexane (PFH), CBP (carboplatin), and oxygen. The probes are expected to achieve targeted and synergistic FUAS therapy and dual-mode imaging to mediate tumor diagnosis and treatment. The oxygen and drugs carried in it are accurately released after FUAS stimulation, which is expected to alleviate tumor hypoxia, avoid tumor drug resistance, improve the effect of chemotherapy, and realize FUAS combined with chemotherapy antitumor therapy. This strategy is expected to make up for the deficiencies of existing synergists, improve the effectiveness and safety of treatment, and provide the foundation for future tumor therapy progress. Graphical Abstract 

Liqun Ren

Papers

Automatic Classification of ECG Data Quality for Each Channel

Non-linear Radical Additions-Coupling Polymerization of Monovinyl Monomers towards Polymer Networks: Theory, Tunability and Heritable Architecture

Abstract 4019: Preclinical activity of ELVN-002: A potent, selective, and irreversible HER2 and pan-HER2 mutant small molecule inhibitor for the treatment of HER2 driven malignancies

Dual mode imaging guided multi-functional bio-targeted oxygen production probes for tumor therapy