Explore chapters and articles related to this topic
Reliable Biomedical Applications Using AI Models
Published in Punit Gupta, Dinesh Kumar Saini, Rohit Verma, Healthcare Solutions Using Machine Learning and Informatics, 2023
Shambhavi Mishra, Tanveer Ahmed, Vipul Mishra
Biomedical informatics combine biology, medicine, and computer science to aid in the effective organization, analysis, management, and use of data in healthcare. Medical informatics has enormous opportunities and challenges as a result of the massive amount of biomedical data. Artificial intelligence is widely used in biomedical informatics, as well as dealing with massive amounts of data, such as protein structure, biological sequencing, drug discovery, and medical imaging. Different components of AI applications in the biomedical domain are shown in Figure 8.3. Recent development ideas in biomedical applications using AI are listed in Table 8.1.
Health Information Technology
Published in Kelly H. Zou, Lobna A. Salem, Amrit Ray, Real-World Evidence in a Patient-Centric Digital Era, 2023
Joseph P. Cook, Gabriel Jipa, Claudia Zavala, Lobna A. Salem
However, the adoption of advanced analytics within the organization depends on multiple factors, such as People, Process, Technology, and Governance. Applications of Artificial Intelligence in Healthcare, in a general acceptance, improve processes such as detection, diagnosis, treatment, and the prediction of the outcome (Kumar, Gadag and Nayak, 2021). Giving the complexity or real world data (RWD), diversity of sources, there are both challenges and opportunities from the volume (also mentioned as BigData), velocity and variety (What is big data? More than volume, velocity and variety 2017), adding later the data quality aspect, called veracity.
Top Informatics Trends for the Next Decade
Published in Connie White Delaney, Charlotte A. Weaver, Joyce Sensmeier, Lisiane Pruinelli, Patrick Weber, Nursing and Informatics for the 21st Century – Embracing a Digital World, 3rd Edition, Book 3, 2022
Artificial intelligence (AI) is a collection of technologies that uses complex algorithms and software to emulate human cognition in the analysis, interpretation and understanding of complex healthcare data. AI can enhance the ability for nurses to better grasp the day-to-day patterns and needs of their patients. According to Eric Topol (2019), the promise of AI is to provide a complete, panoramic view of an individual's health information; to improve decision making; to eliminate errors such as misdiagnosis and unnecessary procedures; to assist with ordering and interpreting appropriate tests; and to recommend treatment. Other experts believe that artificial intelligence will transform healthcare through intelligent diagnosis and treatment recommendations, patient communication and care coordination (Davenport & Kalakota, 2019). A recent US Government Accountability Office (GAO) report (2020) highlighted clinical and administrative applications using AI that have shown promise in reducing provider burden and increasing efficiency as shown in Figure 1.2.
Telemedicine beyond the pandemic: challenges in the pediatric immunology clinic
Published in Expert Review of Clinical Immunology, 2023
Aarti Pandya, Sonya Parashar, Morgan Waller, Jay Portnoy
The combination of telemedicine augmented by remote monitoring with EMRs makes it possible to envision the advent of computer-assisted diagnosis (CAD). This technology uses artificial intelligence (AI) and machine learning algorithms to analyze medical information including images, clinical and physiologic data, test results and remotely obtained information to support healthcare providers in making accurate diagnoses. They use algorithms to identify patterns and relationships that are indicative of specific diseases or conditions. The technology can then provide healthcare providers with a list of potential diagnoses and recommendations for further testing or treatment. By analyzing vast amounts of data and recognizing patterns that may be difficult for a human to detect, CAD systems can provide a more comprehensive and accurate assessment of a patient’s condition.
Bias and Non-Diversity of Big Data in Artificial Intelligence: Focus on Retinal Diseases
Published in Seminars in Ophthalmology, 2023
Cris Martin P Jacoba, Leo Anthony Celi, Alice C. Lorch, Ward Fickweiler, Lucia Sobrin, Judy Wawira Gichoya, Lloyd P Aiello, Paolo S. Silva
The increasing use of artificial intelligence (AI) in medicine is a response to exponential demands for healthcare services worldwide.1 Healthcare systems are increasingly strained for several reasons, including a growing population, longer life span, and more readily available therapies that promote greater utilization of these services. With no commensurate growth in healthcare capacity, AI systems are a means to expand the available medical infrastructure through decision support and process automation, increasing the scalability and expertise of healthcare providers. In the field of retinal disease, there are two Food and Drug Administration (FDA) approved algorithms for screening diabetic retinopathy (DR), with a growing list of other disease indications.2,3 Specifically, these are the IDx-DR 2.0 (IDx-LLC, Iowa City, KA, USA), a diagnostic AI machine that detects referrable DR (RDR) and vision-threatening DR (vtDR); and the EyeArt system v2.0 (Eyenuk, Inc., Los Angeles, CA), a cloud-based device that detects RDR. It is important to emphasize that these algorithms are paired with specific retinal cameras and imaging protocols as part of their FDA approval. These algorithms are deployed through point of care facilities with specific fundus photographs taken by trained operators. Digital images undergo automated image analysis, with an analysis available soon thereafter. These AI systems can accurately triage high-risk eyes that need urgent in-person evaluation and therapy, compared to eyes that can be monitored on long-term remote follow-up.
A new paradigm in adverse drug reaction reporting: consolidating the evidence for an intervention to improve reporting
Published in Expert Opinion on Drug Safety, 2022
Raymond Li, Kate Curtis, Syed Tabish Zaidi, Connie Van, Ronald Castelino
Digital initiatives have been introduced in the last decade to transform the management of patients in healthcare setting. Examples of these include the adoption of eMedical Records, eMedication Management, ePrescribing, digital health records, and mobile apps [17–20]. Natural language processing and artificial intelligence in healthcare have also been introduced in areas of clinical decision support, information management, data analysis of electronic health records for diagnosis, as well as the provision of personalized healthcare [21,22]. These measures can support improvements in adherence to guidelines for healthcare professionals, increase cost savings, enhance patient satisfaction, and promote efficiency across hospital processes. Therefore, there exists an opportunity to leverage digital technologies to improve the process and experience of reporting ADRs.