Artificial Intelligence AI in Healthcare & Medical Field

The hype around artificial intelligence (AI) spiked again recently with the public release of ChatGPT. The easy-to-use interface of this natural language chat model makes this AI particularly accessible to the public, allowing people to experience first-hand the potential of AI. This experience has spurred users’ imagination and generated feelings ranging from great excitement to fear and consternation. Healthcare entities and their third-party vendors are particularly vulnerable to data breaches and ransomware attacks. The healthcare industry, which is especially vulnerable to attack, also reported the most expensive data breaches, with an average cost of $10.93 million, according to IBM Security’s Cost of a Data Breach Report for 2023.

AI technologies like natural language processing (NLP), predictive analytics and speech recognition could help healthcare providers have more effective communication with patients. AI could, for instance, deliver more specific information about a patient’s treatment options, allowing the healthcare provider to have more meaningful conversations with the patient for shared decision-making. In the review article, the authors extensively examined the use of AI in healthcare settings. By imposing language restrictions, the authors ensured a comprehensive analysis of the topic. AI for healthcare offers the ability to process and analyze vast amounts of medical data far beyond human capacity.

This form of AI in healthcare is quickly becoming a must-have in the modern healthcare industry and is likely to become even more sophisticated and be used in a wider range of applications. You can foun additiona information about ai customer service and artificial intelligence and NLP. AI in healthcare refers to the use of machine learning, natural language processing, deep learning and other AI technologies to enhance the experiences of both healthcare professionals and patients. The data-processing and predictive capabilities of AI enable health professionals to better manage their resources and take a more proactive approach to various aspects of healthcare.

Finally, as suggested in the discussion section, more interdisciplinary studies are needed to strengthen AI links with data quality management and AI and ethics considerations in healthcare. Further analysis could also identify why some parts of the world have not conducted studies in this area. It would be helpful to carry out a comparative analysis between countries active in this research field and countries that are not currently involved. It would make it possible to identify variables affecting AI technologies’ presence or absence in healthcare organisations.

By analyzing data such as medical history, demographics, and lifestyle factors, predictive models can identify patients at higher risk of developing these conditions and target interventions to prevent or treat them [61]. Predicting hospital readmissions is another area where predictive analytics can be applied. These journals deal mainly with healthcare, medical information systems, and applications such as cloud computing, machine learning, and AI. Burke et al.’s [67] contribution is the most cited with an analysis of nurse rostering using new technologies such as AI. Another relevant topic is AI applications for disease prediction and diagnosis treatment, outcome prediction and prognosis evaluation [72, 77].

Cognitive computing and augmented reality helps to stimulate and solve complex human thoughts. It is one of the most helpful AI in healthcare that provides patients with a tailored experience in managing their health and removing their questions. AI helps pharmaceutical industries in drug design and also assists in deciding the right product for the machine. Artificial intelligence-enabled drug development systems are assisting businesses in utilizing massive amounts of data to swiftly identify patient response markers and create more effective and affordable appropriate treatment options.

In the former, an adversary may insert bad data into a training set thereby affecting the model’s output. In the latter, the adversary may extract enough information about the AI algorithm itself to create a substitute or competitive model. Any disagreements or concerns about the literature or methodology were discussed in detail among the authors. 2 min read – Our leading artificial intelligence (AI) solution is designed to help you find the right candidates faster and more efficiently.

From accessible EHR information through online platforms to sharing personal health data from wearable devices, technology-driven opportunities for patient engagement continue to expand. Because AI computers have the ability to “learn” from endless data sets and uncover patterns in this data, it is now being used to positively influence many areas of clinical care. What’s more, AI and machine learning are helping providers deliver more personalized medical treatments and care. A second, but equally important subset of AI known as natural language processing, or NLP, makes it easier than ever to automate many of the complex, time-consuming, repetitive tasks that eat up a lot of resources in health care administration. With NLP, health care organizations can dramatically increase efficiency and accuracy in critical areas of care. Owkin leverages AI technology for drug discovery and diagnostics with the goal of enhancing cancer treatment.

Within the realm of AI for Health, WHO’s strategic approach centers around Three Pillars:

Through wearable sensors and internet-connected devices, AI algorithms can assist in continuous remote patient monitoring. One benefit the use of AI brings to health systems is making gathering and sharing information easier. Statista reports that the AI healthcare market, which was valued at $11 billion in 2021, is expected to soar to $187 billion by 2030. This significant growth suggests that substantial transformations are anticipated in the operations of medical providers, hospitals, pharmaceutical and biotechnology companies, and other healthcare industry participants. Twill describes itself as “The Intelligent Healing Company,” delivering digital healthcare products and partnering with enterprises, pharma companies and health plans to develop products using its Intelligent Healing Platform. The company uses AI to tailor personalized care tracks for managing medical conditions like multiple sclerosis and psoriasis.

By examining the metadata in a document, artificial intelligence may classify it using more sophisticated optical character recognition (OCR) techniques. This is the best technology that has automated file scanning, document classification, and precise processing. WHO envisions a future where AI serves as a powerful force for innovation, equity, and ethical integrity in healthcare. The overall goal is to help Member States take AI to the people to enable enhanced, sustainable, and smarter health care. A large part of our results shows that, at the application level, AI can be used to improve medical support for patients (Fig. 11) [64, 82]. However, we believe that, as indicated by Kalis et al. [90] on the pages of Harvard Business Review, the management of costly back-office problems should also be addressed.

The study demonstrated that antidepressant response could be accurately predicted using real-world EHR data with AI modeling, suggesting the potential for developing clinical decision support systems for more effective treatment selection. While considerable progress has been made in leveraging AI techniques and genomics to forecast treatment outcomes, it is essential to conduct further prospective and retrospective clinical research and studies [47, 50]. These endeavors are necessary for generating the comprehensive data required to train the algorithms effectively, ensure their reliability in real-world settings, and further develop AI-based clinical decision tools.

AI in drug information and consultation

Machine Learning has altered the healthcare system by enabling artificial intelligence to be used in medical diagnosis and treatment. Machine learning algorithms can quickly process large amounts of clinical documentation, identify patterns and make predictions about medical outcomes with greater accuracy than ever before. From analyzing patient records and medical imaging to discovering new therapies, the data science behind machine learning is helping healthcare professionals improve their treatments and reduce costs. By leveraging AI technologies like machine learning for tasks such as disease diagnosis or drug discovery and development, doctors can more accurately diagnose illnesses and customize treatments to individual patients’ needs. Artificial intelligence (AI) generally applies to computational technologies that emulate mechanisms assisted by human intelligence, such as thought, deep learning, adaptation, engagement, and sensory understanding [1, 2].

A final source of bias, which has been called “label choice bias”, arises when proxy measures are used to train algorithms, that build in bias against certain groups. For example, a widely used algorithm predicted health care costs as a proxy for health care needs, and used predictions to allocate resources to help patients with complex health needs. Adjusting the target led to almost double the number of Black patients being selected for the program. The practice of AI within the PCP office to care for patients is rapidly turning into online consultations, advice visits, medication refills, orders of test kits, and much more. A patient can request a consultation with a specific physician based on how they fill out their questionnaire before the visit.

AI algorithms can monitor patients’ health data over time and provide recommendations for lifestyle changes and treatment options that can help manage their condition. This can lead to better patient outcomes, improved quality of life, and reduced health care costs. A recent study found that 83% of patients report poor communication as the worst part of their experience, demonstrating a strong need for clearer communication between patients and providers.

Clinical applications

The WHO policy brief Ageism in artificial intelligence for health examines the use of artificial intelligence (AI) in medicine and public health for older… It includes all published articles, the total number of citations, and the collaboration network. The following sub-sections start with an analysis of the total number of published articles.

The company’s software helps pathology labs eliminate bottlenecks in data management and uses AI-powered image analysis to connect data points that support cancer discovery and treatment. Twin Health’s holistic method seeks to address and potentially reverse chronic conditions like Type 2 Diabetes through a mixture of IoT tech, AI, data science, medical science and healthcare. The company created the Whole Body Digital Twin — a digital representation of human metabolic function built around thousands of health data points, daily activities and personal preferences. BioXcel Therapeutics uses AI to identify and develop new medicines in the fields of immuno-oncology and neuroscience. Additionally, the company’s drug re-innovation program employs AI to find new applications for existing drugs or to identify new patients.

The research, therefore, adopts a quantitative approach to the analysis of bibliometric variables and a qualitative approach to the study of recurring keywords, which has allowed us to demonstrate strands of literature that are not purely positive. There are currently some limitations that will affect future research potential, especially in ethics, data governance and the competencies of the health workforce. In terms of practical implications, this paper aims to create a fruitful discussion with healthcare professionals and administrative staff on how AI can be at their service to increase work quality. Furthermore, this investigation offers a broad comprehension of bibliometric variables of AI techniques in healthcare.

• With this information, healthcare professionals can develop more complete patient profiles while also using categories like race and ethnicity to factor social inequities into a patient’s health history.
• But as the number of rules grows too large, usually exceeding several thousand, the rules can begin to conflict with each other and fall apart.
• The scientists used 25,000 images of blood samples to teach the machines how to search for bacteria.
• Over 13,000 colorectal cancer photos were collected by the researchers from 8,803 participants and 13 separate cancer facilities in China, Germany, and the United States.
• Algorithms are being trained on immense amounts of medical data to analyze CT scans, MRIs, X-rays, microscopy images and other medical visuals.

As the use of AI expands in healthcare, all parties involved in the process must be aware of and work to avoid the known risks of bias or loss of privacy. Beyond concerns about the effectiveness of AI, there are also concerns about the potential for bias in the underlying algorithms. Some studies have found race-based discrepancies in the algorithms and limitations due to the lack of healthcare data for women and minority populations. In an analysis of current AI capabilities, it can be argued that the negatives outweigh the positives. The most popular AI platform ChatGPT, has been proven a lack of authenticity regarding references used in medical articles.

Healthcare providers can use these insights to efficiently move patients through the system. The Journal of Medical Systems is the most relevant source, with twenty-one of the published articles. This journal’s main issues are the foundations, functionality, interfaces, implementation, impacts, and evaluation of medical technologies. Another relevant source is Studies in Health Technology and Informatics, with eleven articles. This journal aims to extend scientific knowledge related to biomedical technologies and medical informatics research.

One of the prevalent challenges in drug development is non-clinical toxicity, which leads to a significant percentage of drug failures during clinical trials. However, the rise of computational modeling is opening up the feasibility of predicting drug toxicity, which can be instrumental in improving the drug development process [46]. This capability is particularly vital for addressing common types of drug toxicity, such as cardiotoxicity and hepatotoxicity, which often lead to post-market withdrawal of drugs. Being able to predict what treatment procedures are likely to be successful with patients based on their make-up and the treatment framework is a huge leap forward for the data science of many healthcare organizations. The majority of AI technology in healthcare that uses machine learning and precision medicine applications require medical images and clinical data for training, for which the end result is known. Healthcare is one of the most critical sectors in the broader landscape of big data because of its fundamental role in a productive, thriving society.

Moving on to the application, an article by Shickel et al. [51] begins with the belief that the healthcare world currently has much health and administrative data. In this context, AI and deep learning will support medical and administrative staff in extracting data, predicting outcomes, and learning medical representations. Finally, in the same line of research, Baig et al. [52], with a focus on wearable patient monitoring systems (WPMs), conclude that AI and deep learning may be landmarks for continuous patient monitoring and support for healthcare delivery.

Additionally, the pink border linking states indicates the extent of collaboration between authors. The primary cooperation between nations is between the USA and China, with two collaborative articles. This mathematical formulation originated in 1926 to describe the publication frequency by authors in a specific research field [61]. In practice, the law states that the number of authors contributing to research in a given period is a fraction of the number who make up a single contribution [14, 61]. Another risk is the unique privacy attacks that AI algorithms may be subject to, including membership inference, reconstruction, and property inference attacks. In these types of attacks, information about individuals, up to and including the identity of those in the AI training set, may be leaked.

A comprehensive literature search related to AI in healthcare was performed in the PubMed database and retrieved the relevant information from suitable ones. AI excels in aspects such as rapid adaptation, high diagnostic accuracy, and data management that can help improve workforce productivity. With this potential in sight, the FDA has continuously approved more machine learning (ML) software to be used by medical workers and scientists.

Are individuals more inclined towards AI than human healthcare providers

We found a fast-growing, multi-disciplinary stream of research that is attracting an increasing number of authors. In doing so, we use a different database, Scopus, that is typically adopted in social sciences fields. Finally, our analysis will propose and discuss a dominant framework of variables in this field, and our analysis will not be limited to AI application descriptions. The literature discussed the impacts of AI in other industries like automotive, robots, business, banking, etc. was excluded from our considerations.

” Then, as discussed by Massaro et al. [36], RQ3 is “What are the research applications of artificial intelligence for healthcare? 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.

Modern AI has come a long way, and is able to make determinations and find outcomes without direct human input. H2O.ai’s AI analyzes data throughout a healthcare system to mine, automate and predict processes. It has been used to predict ICU transfers, improve clinical workflows and pinpoint a patient’s risk of hospital-acquired infections. Using the company’s AI to mine health data, hospitals can predict and detect sepsis, which ultimately reduces death rates. The Cleveland Clinic teamed up with IBM on the Discovery Accelerator, an AI-infused initiative focused on faster healthcare breakthroughs.

• Emergency department providers understand that integrating AI into their work processes is necessary for solving these problems by enhancing efficiency, and accuracy, and improving patient outcomes [28, 29].
• In another study performed by Sheu et al., the authors aimed to predict the response to different classes of antidepressants using electronic health records (EHR) of 17,556 patients and AI [52].
• In addition, digital assistants can collect information daily regarding patients’ health and forward the reports to the assigned physician.
• By quickly analyzing massive amounts of research data, AI technologies and methodologies can aid in the understanding of the COVID-19 virus and speed up research on remedies.

Healthcare industry has benefited a lot from the great advancements in the field of technology. To understand the impacts of AI in the healthcare industry, one must know exactly what artificial intelligence https://chat.openai.com/ is and what are the different areas where it is used to make healthcare better. This section provides information on the relationship between the keywords artificial intelligence and healthcare.

AI in healthcare can enhance preventive care and quality of life, produce more accurate diagnoses and treatment plans, and lead to better patient outcomes overall. AI can also predict and track the spread of infectious diseases by analyzing data from a government, healthcare, and other sources. As a result, AI can play a crucial role in global public health as a tool for combatting epidemics and pandemics. The company describes its automated system to be the clinical “co-pilot” to electronic medical records (EMRs). The system also updates patient documents automatically to reduce burnout among healthcare workers.

A study conducted by Huang et al. where authors utilized patients’ gene expression data for training a support ML, successfully predicted the response to chemotherapy [51]. In this study, the authors included 175 cancer patients incorporating their gene-expression profiles to predict the patients’ responses to various standard-of-care chemotherapies. Notably, the research showed encouraging outcomes, achieving a prediction accuracy of over 80% across multiple drugs. In another study performed by Sheu et al., the authors aimed to predict the response to different classes of antidepressants using electronic health records (EHR) of 17,556 patients and AI [52]. The AI models considered features predictive of treatment selection to minimize confounding factors and showed good prediction performance.

As AI continues to evolve, it is crucial to ensure that it is developed responsibly and for the benefit of all [5,6,7,8]. 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 [1,2,3]. 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. NLP is a subfield of AI that focuses on the interaction between computers and humans through natural language, including understanding, interpreting, and generating human language.

A study conducted among radiology residents showed that 86% of students agreed that AI would change and improve their practice, and up to 71% felt that AI should be taught at medical schools for better understanding and application [118]. This integration ensures that future healthcare professionals receive foundational knowledge about AI and its applications from the early stages of their education. By analyzing large datasets of patient data, these algorithms can identify potential drug interactions.

AI is aiming to improve healthcare for the general population by leveraging real-time data to optimize anything from ambulance routes to waiting times. The development of chatbots to aid patients, track their progress, and send notifications tailored to their health is advancing greatly thanks to conversational AI. Some of these initiatives may conduct whole visits from the patients’ homes, and by assessing the symptoms and examining the information provided by the patient, they can then direct the patient toward treatment or specialized appointments. AI-powered ultrasound technology offers the potential to speed up the widespread application of medical ultrasound in a range of clinical contexts. AI models can account only for information ‘seen’ during training, so in this example, non‐imaging clinical information is not taken into account by the AI model. Hence, an important emerging area of healthcare AI research focuses on building AI models that integrate imaging and electronic health record data for ‘personalized diagnostic imaging’.

The scientific articles reported show substantial differences in keywords and research topics that have been previously studied. The bibliometric analysis of Huang et al. [19] describes rehabilitative medicine using virtual reality technology. According to the authors, the primary goal of rehabilitation is to enhance and restore functional ability and quality of life for patients with physical impairments importance of ai in healthcare or disabilities. In recent years, many healthcare disciplines have been privileged to access various technologies that provide tools for both research and clinical intervention. The influence of artificial intelligence (AI) has drastically risen in recent years, especially in the field of medicine. Its influence has spread so greatly that it is determined to become a pillar in the future medical world.

AI can help providers gather that information, store and analyze it, and provide data-driven insights from vast numbers of people. Leveraging this information can help healthcare professionals determine how to better treat and manage diseases. Administrative, repetitive tasks that can be automated with AI are things like billing, patient check-in, filing, data input and more. When a health system moves those tasks to AI, that allows them to shift the focus of their most valuable resources — providers and health care professionals — to delivering care. Documentation deficiencies and incomplete coding pose an even greater threat to revenue today than they did a few years ago.

AI algorithms can process large amounts of data quickly and accurately, making it easier for health care providers to diagnose and treat diseases. Firstly, comprehensive cybersecurity strategies and robust security measures should be developed and implemented to protect patient data and critical healthcare operations. Collaboration between healthcare organizations, AI researchers, and regulatory bodies is crucial to establishing guidelines and standards for AI algorithms and their use in clinical decision-making. Investment in research and development is also necessary to advance AI technologies tailored to address healthcare challenges. Therapeutic drug monitoring (TDM) is a process used to optimize drug dosing in individual patients.

Recently, bibliometrics has been an essential method for analysing and predicting research trends [18]. Table 1 lists other research that has used a similar approach in the research stream investigated. Jon Moore is chief risk officer and head of consulting services and customer success of Clearwater, a cybersecurity firm. There are other types of unique AI attacks as well, including data input poisoning and model extraction.

Benefits and risks of using artificial intelligence for pharmaceutical development and delivery

In this article, it is discussed how artificial intelligence can positively impact the future of medicine, along with its downsides. The current investigation analyzed the use of AI in the healthcare system with a comprehensive review of relevant indexed literature, such as PubMed/Medline, Scopus, and EMBASE, with no time constraints but limited to articles published in English. The focused question explores the impact of applying AI in healthcare settings and the potential outcomes of this application. According to the Centers for Disease Control and Prevention, 10% of the US population has diabetes. Patients can now use wearable and other monitoring devices that provide feedback about their glucose levels to themselves and their medical team.

With continuously increasing demands of health care services and limited resources worldwide, finding solutions to overcome these challenges is essential [82]. Virtual health assistants are a new and innovative technology transforming the healthcare industry to support healthcare professionals. It is designed to simulate human conversation to offer personalized patient care based on input from the patient [83]. In addition, digital assistants can collect information daily regarding patients’ health and forward the reports to the assigned physician.

Concerning future research perspectives, researchers believe that an analysis of the overall amount that a healthcare organisation should pay for AI technologies could be helpful. If these technologies are essential for health services management and patient treatment, governments should invest and contribute to healthcare organisations’ modernisation. New investment funds could be made available in the healthcare world, as in the European case with the Next Generation EU programme or national investment programmes [95]. Additionally, this should happen especially in the poorest countries around the world, where there is a lack of infrastructure and services related to health and medicine [96]. On the other hand, it might be interesting to evaluate additional profits generated by healthcare organisations with AI technologies compared to those that do not use such technologies.

This section discusses articles on AI in healthcare in terms of single or multiple publications in each country. 10 highlight the average citations by state and show that the UK, the USA, and Kuwait have a higher average number of citations than other countries. The distribution frequency of the articles (Fig. 3) indicates the journals dealing with the topic and related issues.

The company’s AI tools help identify new drug targets, recommend possible drug combinations and suggest additional diseases that a drug can be repurposed to treat. Owkin also produces RlapsRisk, a diagnostic tool for assessing a breast cancer patient’s risk of relapse, and MSIntuit, a tool that assists with screening for colorectal cancer. The drug development industry is bogged down by skyrocketing development costs and research that takes thousands of human hours. Putting each drug through clinical trials costs an estimated average of $1.3 billion, and only 10 percent of those drugs are successfully brought to market. Due to breakthroughs in technology, AI is speeding up this process by helping design drugs, predicting any side effects and identifying ideal candidates for clinical trials.

Moreover, people’s trust and acceptance of AI may vary depending on their age, gender, education level, cultural background, and previous experience with technology [111, 112]. Today, AI is transforming healthcare, finance, and transportation, among other fields, and its impact is only set to grow. In academia, AI has been used to develop intelligent tutoring systems, which are computer programs that can adapt to the needs of Chat PG individual students. These systems have improved student learning outcomes in various subjects, including math and science. In research, AI has been used to analyze large datasets and identify patterns that would be difficult for humans to detect; this has led to breakthroughs in fields such as genomics and drug discovery. AI has been used in healthcare settings to develop diagnostic tools and personalized treatment plans.

According to Harvard’s School of Public Health, although it’s early days for this use, using AI to make diagnoses may reduce treatment costs by up to 50% and improve health outcomes by 40%. Let’s take a look at a few of the different types of artificial intelligence and healthcare industry benefits that can be derived from their use. The SubtlePET and SubtleMR products work with the machines a facility already uses to speed up MRI and PET scans while reducing image noise.

But with AI, health care professionals across disciplines are able to gain new insights and improve the ability to provide care. A secondary but equally important benefit of AI in the health care setting is that it frees up providers to do more patient-centric work simply by offloading simpler or more menial tasks to automated solutions. Iterative Health applies AI to gastroenterology to improve disease diagnosis and treatment. The company’s AI recruitment service uses computational algorithms to automate the process of identifying patients who are eligible to be potential candidates for inflammatory bowel disease clinical trials. Iterative Health also produces SKOUT, a tool that uses AI to help doctors identify potentially cancerous polyps. During patient consultations, the company’s platform automates notetaking and locates important patient details from past records, saving oncologists time.

For instance, we observed the emergence of a stream of research on patient data management and protection related to AI applications [82]. The USA tops the list of countries with the maximum number of articles on the topic (215). It is immediately evident that the theme has developed on different continents, highlighting a growing interest in AI in healthcare. The figure shows that many areas, such as Russia, Eastern Europe and Africa except for Algeria, Egypt, and Morocco, have still not engaged in this scientific debate.

The potential benefits of incorporating AI into health care are numerous but like every technology, AI comes with risks that must be managed if the benefits of these tools are to outweigh the potential costs. The joint ITU-WHO Focus Group on Artificial Intelligence for Health (FG-AI4H) has built a platform – known as the ITU-WHO AI for Health Framework – for the testing and benchmarking of AI applications in health domain. As of November 2018, eight use cases are being benchmarked, including assessing breast cancer risk from histopathological imagery, guiding anti-venom selection from snake images, and diagnosing skin lesions.

Bibliometric usage enables the recognition of the main quantitative variables of the study stream [12]. This method facilitates the detection of the required details of a particular research subject, including field authors, number of publications, keywords for interaction between variables (policies, properties and governance) and country data [13]. Our paper adopted the Bibliometrix R package and the biblioshiny web interface as tools of analysis [14].

AI technologies can ingest, analyse, and report large volumes of data across different modalities to detect disease and guide clinical decisions [3, 8]. AI applications can deal with the vast amount of data produced in medicine and find new information that would otherwise remain hidden in the mass of medical big data [9,10,11]. These technologies can also identify new drugs for health services management and patient care treatments [5, 6]. AI can be used to optimize healthcare by improving the accuracy and efficiency of predictive models. AI can also automate specific public health management tasks, such as patient outreach and care coordination [61, 62].

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]. However, other studies have suggested that people still prefer human healthcare practitioners over AI, especially for complex or sensitive issues such as mental health, chronic diseases, or end-of-life care [108, 111]. In a US-based study, 60% of participants expressed discomfort with providers relying on AI for their medical care. However, the same study found that 80% of Americans would be willing to use AI-powered tools to help manage their health [109].

Models like this one are trained on thousands of previous mammograms to identify telltale signs of breast cancer, including irregular shapes, sizes and edges of lesions. But whether rules-based or algorithmic, using artificial intelligence in healthcare for diagnosis and treatment plans can often be difficult to marry with clinical workflows and EHR systems. Integration issues into healthcare organizations has been a greater barrier to widespread adoption of AI in healthcare when compared to the accuracy of suggestions. Much of the AI and healthcare capabilities for diagnosis, treatment and clinical trials from medical software vendors are standalone and address only a certain area of care. Some EHR software vendors are beginning to build limited healthcare analytics functions with AI into their product offerings, but are in the elementary stages. Natural language processing is already used to identify missing medical records, but in the future, it could very likely be used to spot deficiencies in treatments or diagnosis.

The United States, China, and the United Kingdom contributed the highest number of studies. Keyword analysis revealed that AI can support physicians in making a diagnosis, predicting the spread of diseases and customising treatment paths. AI tools can improve accuracy, reduce costs, and save time compared to traditional diagnostic methods. Additionally, AI can reduce the risk of human errors and provide more accurate results in less time. In the future, AI technology could be used to support medical decisions by providing clinicians with real-time assistance and insights.