A3 Vertaisarvioitu kirjan tai muun kokoomateoksen osa
AI techniques for healthcare and biomedicine
Tekijät: Subasi, Abdulhamit
Toimittaja: Subasi, Abdulhamit
Kustantaja: Academic Press
Julkaisuvuosi: 2024
Kokoomateoksen nimi: Applications of Artificial Intelligence in Healthcare and Biomedicine
Sarjan nimi: Artificial Intelligence Applications in Healthcare and Medicine
Aloitussivu: 1
Lopetussivu: 35
ISBN: 978-0-443-22308-2
DOI: https://doi.org/10.1016/B978-0-443-22308-2.00013-5
Lisätietoja: This chapter is adapted from “Subasi, A. (2023). Introduction to artificial intelligence techniques for medical image analysis. In Applications of Artificial Intelligence in Medical Imaging" (pp. 1–49). Academic Press..
Tiivistelmä
Artificial intelligence (AI) techniques have emerged as powerful tools with significant potential in healthcare and biomedicine. This chapter provides a concise overview of the AI techniques for healthcare and biomedicine. AI methods, including machine learning, deep learning, natural language processing, and computer vision, have been successfully employed for disease prediction, diagnosis, treatment planning, and drug discovery. Machine learning algorithms enable the identification of patterns and correlations in patient data, while deep learning models excel in medical signal/image analysis and genomics. Natural language processing techniques facilitate the analysis of unstructured clinical text, and computer vision algorithms enable automated interpretation of medical images. This chapter will demonstrate the application of machine learning techniques from the ground up to address real-world healthcare challenges. The research community has shown considerable interest in utilizing machine learning for tasks like recognition, classification, and forecasting. Analyzing biomedical data is crucial for detecting abnormalities in the human body, involving the comparison of biomedical data features with known illnesses to identify deviations from normal patterns. An effective monitoring system must be capable of detecting abnormal data variations. Machine learning techniques offer the automation of biomedical data analysis, enabling the classification of normal and pathological patterns by creating decision surfaces. The chapter aims to guide the design of an efficient Python ecosystem for real-time monitoring, alerting clinicians when life-threatening conditions emerge. Practical examples, mainly adapted from Python libraries such as Scikit-learn (https://scikit-learn.org/stable/), TensorFlow, and KERAS, will be provided to illustrate suitable Python functions at the end of each section.
Artificial intelligence (AI) techniques have emerged as powerful tools with significant potential in healthcare and biomedicine. This chapter provides a concise overview of the AI techniques for healthcare and biomedicine. AI methods, including machine learning, deep learning, natural language processing, and computer vision, have been successfully employed for disease prediction, diagnosis, treatment planning, and drug discovery. Machine learning algorithms enable the identification of patterns and correlations in patient data, while deep learning models excel in medical signal/image analysis and genomics. Natural language processing techniques facilitate the analysis of unstructured clinical text, and computer vision algorithms enable automated interpretation of medical images. This chapter will demonstrate the application of machine learning techniques from the ground up to address real-world healthcare challenges. The research community has shown considerable interest in utilizing machine learning for tasks like recognition, classification, and forecasting. Analyzing biomedical data is crucial for detecting abnormalities in the human body, involving the comparison of biomedical data features with known illnesses to identify deviations from normal patterns. An effective monitoring system must be capable of detecting abnormal data variations. Machine learning techniques offer the automation of biomedical data analysis, enabling the classification of normal and pathological patterns by creating decision surfaces. The chapter aims to guide the design of an efficient Python ecosystem for real-time monitoring, alerting clinicians when life-threatening conditions emerge. Practical examples, mainly adapted from Python libraries such as Scikit-learn (https://scikit-learn.org/stable/), TensorFlow, and KERAS, will be provided to illustrate suitable Python functions at the end of each section.
Turun yliopiston Tutkimustietojärjestelmän portaali