Bioscience Methods 2024, Vol.15, No.3, 124-138 http://bioscipublisher.com/index.php/bm 128 Variability in Diagnostic Criteria: There is considerable variability in the diagnostic criteria and thresholds used for different imaging modalities, which can lead to inconsistencies in diagnosis and management. For instance, the thresholds for diagnosing PH using echocardiography vary widely, leading to potential misclassification of patients (Tsujimoto et al., 2022). In summary, while traditional diagnostic methods for HHD are essential tools in clinical practice, their limitations highlight the need for continued advancements in diagnostic technologies and the development of more accurate, non-invasive methods. The integration of artificial intelligence and machine learning into diagnostic algorithms holds promise for improving the accuracy and efficiency of HHD diagnosis in the future (Sharma et al., 2021; Li et al., 2022). 4 AI-Based Diagnostic Systems: An Overview 4.1 Definition and scope of ai in medical diagnostics Artificial Intelligence (AI) in medical diagnostics refers to the use of advanced computational algorithms to analyze complex medical data and assist in the diagnosis and management of diseases. AI encompasses various techniques, including machine learning (ML) and deep learning (DL), which enable systems to learn from data and improve their performance over time without being explicitly programmed. In the context of hypertensive heart disease (HHD), AI-based diagnostic systems aim to enhance the accuracy and efficiency of diagnosis, predict disease progression, and personalize treatment plans. AI's scope in medical diagnostics is vast, covering areas such as image analysis, signal processing, and predictive modeling. For instance, AI can analyze medical images from MRI or CT scans to detect abnormalities indicative of HHD (Gogi and Gegov, 2019). Additionally, AI algorithms can process electrocardiograms (ECGs) to identify patterns associated with hypertension and other cardiovascular conditions (Kwon et al., 2020; Kwon and Kim, 2020). The integration of AI with wearable devices further extends its scope, allowing continuous monitoring of vital signs and early detection of potential health issues (Figure 2) (Lee et al., 2022). Figure 2 Schematic illustration for wearable device-based artificial intelligence for cardiovascular-related diseases (Adopted from Lee et al., 2022) Image caption: ECG, electrocardiography; PPG, photoplethysmography; CNN, convolutional neural network; RNN, recurrent neural network; LSTM, long short-term memory 4.2 Machine learning algorithms in cardiovascular diagnostics Machine learning (ML) algorithms play a crucial role in cardiovascular diagnostics by analyzing large datasets to identify patterns and make predictions. These algorithms can be broadly categorized into supervised, unsupervised, and reinforcement learning.
RkJQdWJsaXNoZXIy MjQ4ODY0NQ==