مریم قنبری

Artificial intelligence and machine learning (as its subset)are thebranchesof computer science in which machines are trained to imitate human intelligence and perform defined tasks. Accurate results and analysis of a large amount of data that cannot be done through conventional statistical methods can be provided by artificial intelligence. Artificial intelligence has been used in pulmonary medicine since almost two decades ago. So it can help to diagnose and predict lung diseases,based on clinical data, lung pathology, chest imaging, and pulmonary function tests. Applications based on artificial intelligence enable doctors to increase their precision in the treatment of lung diseases by using a huge amount of data. It is important for clinicians to understand how AI can address heterogeneous conditions such as asthma and chronic obstructive pulmonary disease where diagnostic criteria overlap. They should be able to understand the use of artificial intelligence in daily clinical practice, while, the patient safety issues should be considered. Artificial intelligence has aclear role in supporting of the physiciansin the clinical environment. However, it seems that the trust in its usagehas not yet been fully established. In general, artificial intelligence is expected to play a key role in helping doctors for diagnosisand management of therespiratory diseases in future, which will be followed byexciting benefits to patients and doctors. The purpose of this review is to discuss the use of artificial intelligence in pulmonarymedicine and imaging in cases of obstructive lung disease, interstitial lung disease, infections, nodules and lung cancer.

In the modern era, the complexity and increase in healthcare data will drive us towards the growing use of artificial intelligence. For optimal progress in precision medicine, a thorough examination of comprehensive patient data alongside various and extensive factors is essential to differentiate between sick and relatively healthy individuals. Artificial intelligence has the potential to enhance patient care and facilitate easier decision-making for healthcare professionals through advanced computations and inferences, enabling the system to reason, learn, and ultimately streamline medical decision-making. Artificial intelligence is currently being employed by healthcare providers and life sciences companies in various domains. In this article, we will review recent advancements in the application of artificial intelligence in the fields of medicine, pharmaceuticals, and genomics. Additionally, we will discuss the role of machine learning in medical imaging, precision medicine, and biosensors. The article will also explore some advances in biosensor technologies that utilize artificial intelligence to assist in monitoring electro-physiological and electrochemical signals of the body and diagnosing diseases. These advancements indicate a trend towards personalized medicine, which is both highly effective, cost-effective, and precise in the point of care. Researchers, with access to a wide range of datasets and modern computational techniques such as machine learning (ML) and deep learning (DL), can usher in a new era of genomics and effective drug discovery. Deep learning, using algorithms to create an artificial neural network (ANN), can autonomously learn and make decisions, mimicking the human brain.

Entropy gives meaning to energy, but they have always created misconceptions among students, or that learners who had difficulty. Therefore, designing educational content to better learn the concept of entropy and its applications based on the STEM approach and concept map will be an important step for students to learn and acquire skills in the long run. The method of the present study is descriptive-analytical which has been done using the content analysis technique. The statistical sample used is a collection of books, articles, journals, and dissertations related to entropy that were selected and analyzed until the theoretical saturation of the data. By reviewing the literature on how to design entropy educational content, with the guidance of experts in this field, during several round-trip stages of axial coding, topics were determined and then based on the topics assigned, goals for each subject in the content goal table was written. In the present project, learners can perform experiments, practical activities, and knowledge building with new teaching methods and approaches. The STEM approach and concept map are two of the new teaching methods and approaches. Their use in teaching and designing an educational content helps students learn in a long-term and meaningful way, and also leads to exploration and skills acquisition in learners.