Revolutionizing healthcare: the role of artificial intelligence in clinical practice

One of the main aims of such activity monitoring approaches, as well as other monitoring tools, is to support healthcare practitioners in identifying symptoms of cognitive functioning or providing diagnosis and prognosis in a quantitative and objective manner using a smart home system [56]. There are various other assistive technology devices for people with dementia including motion detectors, electronic medication dispensers, and robotic devices for tracking. Some surveys have indicated that people are generally willing to use or interact with AI for health-related purposes such as diagnosis, treatment, monitoring, or decision support [108,109,110]. AI has the potential to revolutionize mental health support by providing personalized and accessible care to individuals [87, 88]. Several studies showed the effectiveness and accessibility of using Web-based or Internet-based cognitive-behavioral therapy (CBT) as a psychotherapeutic intervention [89, 90]. Even though psychiatric practitioners rely on direct interaction and behavioral observation of the patient in clinical practice compared to other practitioners, AI-powered tools can supplement their work in several ways.

Artificial Intelligence (AI) is a rapidly evolving field of computer science that aims to create machines that can perform tasks that typically require human intelligence. AI includes various techniques such as machine learning (ML), deep learning (DL), and natural language processing (NLP). Large Language Models (LLMs) are a type of AI algorithm that uses deep learning techniques and massively large data sets to understand, summarize, generate, and predict new text-based content [1–3]. LLMs have been architected to generate text-based content and possess broad applicability for various NLP tasks, including text generation, translation, content summary, rewriting, classification, categorization, and sentiment analysis.

The widespread implementation of AI in healthcare has the role to revolutionize patients’ outcomes and transform the way healthcare is practiced, leading to improved accessibility, affordability, and quality of care. This article explores the diverse applications and reviews the current state of AI adoption in healthcare. It concludes by emphasizing the need for collaboration between physicians and technology experts to harness the full potential of AI.

2.2. Drug discovery and development

For instance, a technique can use sound analysis to recognize COVID-19 from different respiratory sounds, e.g., cough, breathing, and voice [25]. Additionally, for a precise diagnosis, AI algorithms can be used for the analysis of medical scans and pathology images. Imaging applications include the determination of ejection fraction from echocardiograms [26], the detection and volumetric quantification of lung nodules from radiographs [27], and the detection and quantification of breast densities via mammography [28]. Imaging applications in pathology include an FDA-cleared system for whole-slide imaging (WSI) and their integration into a laboratory offers many benefits over light microscopy [29].

Furthermore, Gulshan V. et al. (2016) demonstrated the clinical utility of a deep machine-learning algorithm that evaluated retinal fundus photographs from adults that detected referable diabetic retinopathy with high sensitivity and specificity [51]. Et al. (2017) showed that an AI agent, using deep learning and neural networks, accurately diagnosed and provided treatment decisions for congenital cataracts in a multihospital clinical trial, performing just as well as individual ophthalmologists [52]. (2020), AI has the potential to create a paradigm shift in the diagnosis, treatment, prediction, and economics of neurological disease [47]. Et al. (2017) stated that a deep learning algorithm used magnetic resonance imaging (MRI) of the brain of individuals 6 to 12 months old to predict the diagnosis of autism in individual high-risk children at 24 months, with a positive predictive value of 81% [48].

Potential uses of generative AI in healthcare

Given the potential for gen AI to come up with potentially inaccurate answers, it will remain critical to keep a human in the loop. The Pew Research Center published a report this year analyzing Americans’ views on the impacts of their providers relying on AI. The survey found that less than half of U.S. adults surveyed believe that AI in health and medicine would improve patient outcomes; 60 percent say they would feel uncomfortable if their healthcare provider relied on AI to do things such as diagnose disease and recommend treatments.

As such, it illustrates a spectrum of AI solutions, where encoding clinical guidelines or existing clinical protocols through a rules-based system often provides a starting point, which then can be augmented by models that learn from data. AI has the potential to revolutionize clinical practice, but several challenges must be addressed to realize its full potential. Among these challenges is the lack of quality medical data, which can lead to inaccurate outcomes. Data privacy, availability, and security are also potential limitations to applying AI in clinical practice. Additionally, determining relevant clinical metrics and selecting an appropriate methodology is crucial to achieving the desired outcomes. Human contribution to the design and application of AI tools is subject to bias and could be amplified by AI if not closely monitored [113].

Legal, ethical, and risk associated with AI in healthcare system

NLP is being used to analyze data from EMRs and gather large-scale information on the late-stage complications of a certain medical condition [26]. Today Stanford Medicine made a big announcement about a tool they hope will address some of them. Any disagreements or concerns about the literature or methodology were discussed in detail among the authors. Diseases such as sickle cell anemia, cystic fibrosis and Tay-Sachs disease are caused by errors in the order of DNA letters that codify the operating instructions for every human cell. In some cases, these errors can be corrected with a gene-editing process that rearranges these letters. VirtuSense, for example, uses AI to remotely identify patients’ “intent to exit their bed seconds before they get up and sends alerts to the right staff immediately” contributing to a reduction in the number of falls.

We cover prospective studies and advances in medical image analysis, which have reduced the gap between research and deployment. We also address several promising avenues for novel medical AI research, including non-image data sources, unconventional problem formulations and human–AI collaboration. Finally, we consider serious technical and ethical challenges in issues spanning from data scarcity to racial bias. As these challenges are addressed, AI’s potential may be realized, making healthcare more accurate, efficient and accessible for patients worldwide.

1. Disease Detection and Diagnosis and Medical Imaging

AI-driven predictive analytics can enhance the accuracy, efficiency, and cost-effectiveness of disease diagnosis and clinical laboratory testing. Additionally, AI can aid in population health management and guideline establishment, providing real-time, accurate information and optimizing medication choices. Integrating AI in virtual health and mental health support has shown promise in improving patient care. However, it to address limitations such as bias and lack of personalization to ensure equitable and effective use of AI. The potential applications of AI in assisting clinicians with treatment decisions, particularly in predicting therapy response, have gained recognition [49].

The EMR databases contain the history of hospital encounters, records of diagnoses and interventions, lab test, medical images, and clinical narratives. All these datasets can be used to build predictive models that can help clinicians with diagnostics and various treatment decision support. As AI tools mature it will be possible to extract all kinds of information such as related disease effects and correlations between historical and future medical events [37]. The only data often missing is data from in between interventions and between hospital visits when the patient is well or may not be showing symptoms.

Recognizing biases before they reach the machines may provide a chance to break this cycle. “Can we end up training the machines better because we learned from the mistakes that we have in our own society about training people? Other NIH-funded researchers are studying whether chatbots can help in additional areas, like suicide prevention and encouraging heart-healthy diet changes. “AI can look at images very closely, in a way that’s much more detailed than we can do with the human eye,” Kontos says.

Overall, virtual health assistants have the potential to significantly improve the quality, efficiency, and cost of healthcare delivery while also increasing patient engagement and providing a better experience for them. The advent of high-throughput genomic sequencing technologies, combined with advancements in AI and ML, has laid a strong foundation for accelerating personalized medicine and drug discovery [41]. Despite being a treasure trove of valuable insights, the complex nature of extensive genomic data presents substantial obstacles to its interpretation.

Enhancing Diagnostics Through Big Data

The company’s technology can identify potential patients for clinical trials, track the adoption of new treatments, and identify disparities in care and outcomes. While many point to AI’s potential to make the health care system work better, some say its potential to fill gaps in medical resources is also considerable. In medical imaging, a field where experts say AI holds the most promise soonest, the process begins with a review of thousands of images — of potential lung cancer, for example — that have been viewed and coded by experts. Using that feedback, the algorithm analyzes an image, checks the answer, and moves on, developing its own expertise.

In a September 2019 issue of the Annals of Surgery, Ozanan Meireles, director of MGH’s Surgical Artificial Intelligence and Innovation Laboratory, and general surgery resident Daniel Hashimoto offered a view of what such a backstop might look like. They described a system that they’re training to assist surgeons during stomach surgery by having it view thousands of videos of the procedure. Their goal is to produce a system that one day could virtually peer over a surgeon’s shoulder and offer advice in real time. A key success, Kohane said, may yet turn out to be the use of machine learning in vaccine development. We won’t likely know for some months which candidates proved most successful, but Kohane pointed out that the technology was used to screen large databases and select which viral proteins offered the greatest chance of success if blocked by a vaccine.

Such assistive robots can help in various activities such as mobility, housekeeping, medication management, eating, grooming, bathing, and various social communications. An assistive robot named RIBA with human-type arms was designed to help patients with lifting and moving heavy things. It has been demonstrated that the robot is able to carry the patient from the bed to a wheelchair and vice versa. Instructions can be provided to RIBA either by using tactile sensors using a method known as tactile guidance to teach by showing [57]. A smart home is a normal residential home, which has been augmented using different sensors and monitoring tools to make it “smart” and facilitate the lives of the residents in their living space. Other popular applications of AAL that can be a part of a smart home or used as an individual application include remote monitoring, reminders, alarm generation, behavior analysis, and robotic assistance.

• It would not be an exaggeration to refer to them as ever-present digital health coaches, as increasingly it is encouraged to wear them at all times in order to get the most out of your data.
• Such robots assist elderly patients with their stress or depression by connecting emotionally with the patient with enhanced social interaction and assistance with various daily tasks.
• AI has the potential to revolutionize mental health support by providing personalized and accessible care to individuals [87, 88].
• Researchers continue exploring ways to use AI in medical diagnosis and treatment, such as analyzing medical images, X-rays, CT scans, and MRIs.
• In addition, AI technologies can help with early diagnosis, imaging, emergency call triage, and much more.

This special communication discusses whether large language models (LLMs) are being trained with the right kind of self-supervision and if the purported value propositions of using LLMs in medicine are being verified. Responsible AI for Safe and Equitable Health will address ethical and safety issues in AI innovation, define standards for the field, and convene experts on the topic. Over the past decade, synthetic biology has produced developments like CRISPR gene editing and some personalised cancer therapies.

Remote monitoring and picking up on early signs of disease could be immensely beneficial for those who suffer from chronic conditions and the elderly. Here, by wearing a smart device or manual data entry for a prolonged period, individuals will be able to communicate to their healthcare workers without the need of disrupting their daily lives [35]. This is a great example of algorithms collaborating with healthcare professionals to produce an outcome that is beneficial for patients. Augmented and virtual reality (AR and VR) can be incorporated at every stage of a healthcare system. These systems can be implemented at the early stages of education for medical students, to those training for a specific specialty and experienced surgeons. On the other hand, these technologies can be beneficial and have some negative consequences for patients.

Read more about AI for Way to Revolutionize Medicine here.