Integrating Artificial Intelligence Into Cancer Care: Enhancing Nursing Practice and Bridging Disparities

Abstract

Artificial intelligence (AI) in cancer care has the potential to transform nursing practice, reduce cancer disparities, and enhance patient outcomes across the continuum of care from prevention, screening, and treatment to survivorship and end-of-life care. Responsible adoption of AI in cancer care requires addressing the mistrust of AI, lack of standardized data elements, concerns about accuracy and reliability, and need to mitigate algorithmic bias. Oncology nurses have a pivotal role in applying AI to health care and addressing these challenges. Enhancing nursing practice with AI requires continuous training and education, ethical considerations, and maintenance of the patient–nurse relationship in the context of AI integration.

AT A GLANCE

• ■ AI offers transformative potential to reduce cancer disparities across the continuum of care.

• ■ Nurses play a pivotal role in the ethical and effective integration of AI in cancer care.

• ■ Training and education in AI are essential to prepare oncology nurses for advancements in the field while maintaining equitable care.

Cancer is the second leading cause of death in the United States, with an estimated 611,720 deaths annually (about 1,680 daily) (Siegel et al., 2024). Cancer survivorship has increased because of more effective treatments and improved supportive care (Lee & Gonzalez-Guarda, 2025). However, health inequities persist among cancer survivors, reflecting broader disparities in health outcomes across different populations (Islami et al., 2022). Health inequities in cancer survivorship affect various demographic and socioeconomic groups, with the most impact to those who are socially, economically, or geographically disadvantaged (Alcaraz et al., 2020; Office of Disease Prevention and Health Promotion, n.d.).

Artificial intelligence (AI) refers to a machine’s ability to perform functions usually considered to be intelligent human behaviors, such as learning, reasoning, and solving problems (National Cancer Institute [NCI], 2020). The advent of AI in health care has generated interest in new diagnostics and cancer treatments (Cabral et al., 2023). Several discoveries demonstrate that AI can enhance diagnostic efficiency, provide optimal treatments, and evaluate prognosis, potentially reducing mortality rates (Pei et al., 2022). For example, AI-based software can aid pathologists in identifying potential cancerous areas in prostate biopsy images (Eloy et al., 2025). Also, researchers funded by the NCI (2020) developed deep learning tools to automate the detection of precancerous cervical lesions, further improving cancer screening. In addition, AI imaging algorithms have enhanced breast cancer detection on mammograms, allowing clinicians to predict long-term cancer risks (NCI, 2020; Vachon et al., 2023). Taken together, these examples indicate that AI is revolutionizing oncology and offering new opportunities to enhance patient management (Lu, 2019; Luchini et al., 2022). As these new advances and others are integrated into clinical practice, cancer care is undergoing a paradigm shift (Dankwa-Mullan et al., 2025).

Although the applications of AI in cancer care are promising, several considerations must be addressed. These considerations include mistrust of AI, lack of standardized data elements, and algorithmic bias (Cabral et al., 2023). For example, AI algorithms trained using biased data can be less accurate in diagnosing conditions in individuals from racial and ethnic minority groups (Obermeyer et al., 2019), and inconsistency in data collection and reporting practices across institutions hinders the development of standardized formats and robust AI models (Papadimitroulas et al., 2021). Addressing challenges resulting from mistrust, lack of data standardization, and algorithmic bias, among other considerations, is necessary to realize AI’s full potential to equitably improve cancer outcomes for all populations.

This article aims to (a) provide an overview of the current use of AI in cancer care, (b) identify AI’s role in better understanding cancer disparities, and (c) explore AI’s potential in reducing cancer disparities. It aims to offer practical recommendations for enhancing AI usage in clinical care to reduce cancer disparities and improve patient outcomes.

Social Determinants of Health and Cancer Disparities

The term cancer disparities refers to differences among population groups in various cancer-related measures, such as incidence, prevalence, stage at diagnosis, stage-appropriate treatment, post-treatment quality of life, survivorship, and mortality (White et al., 2017). These disparities are evident across race, ethnicity, age, socioeconomic status, geography, and other social determinants of health. Sexual orientation (e.g., gender nonconforming, asexual, gay, lesbian, bisexual) and gender identity (i.e., a person’s innate sense of their gender) also contribute to unequal cancer outcomes among these groups. Recognizing the intersectionality of race, ethnicity, socioeconomic status, and other factors provides insights for understanding the unique challenges faced by populations experiencing health disparities. Individuals from sexual and gender minority groups, as well as people with disabilities, often face discrimination, stigma, and culturally incompetent health care, which negatively affect their health outcomes (Pérez-Stable & Webb Hooper, 2023).

In addition, race and ethnicity commonly correlate with social determinants that drive cancer disparities in the United States (Grabinski & Brawley, 2022). For example, Black or African American individuals have the highest mortality and the shortest survival rates of any racial or ethnic groups in the United States for most cancers (American Cancer Society, n.d.). Although specific genetic variants associated with cancer are hereditary, the predominant factors contributing to health disparities among African American individuals are not solely biologic but result from variations in access to cancer care, delays in cancer screening and treatment, and socioeconomic determinants that may include poverty, cultural bias, and social injustice (Grabinski & Brawley, 2022; Patel et al., 2020; Patt et al., 2020). Addressing these cancer disparities requires a focused approach within oncology nursing education and practice.

Although health outcome disparities have long been recognized in the United States, little progress has been made in reducing them (National Academies of Science, Engineering, and Medicine, 2024). They endure within and across multiple cancer diagnoses and population groups, leading to increased mortality rates and decreased quality of life for affected individuals (Patel et al., 2020). Systemic barriers, such as limited access to care, insurance coverage disparities, and geographic isolation, exacerbate the inequity. For example, delayed cancer screenings and treatments because of inequitable access can lead to advanced disease stages at diagnosis, which are more complex and costly to treat (Marcondes et al., 2021; Richardson-Parry et al., 2023). This increases the financial burden on the healthcare system and reduces the availability of resources for other patients. In addition, disparities in cancer care often result in higher rates of hospital readmission and more extended hospital stays, further straining healthcare resources (Barrington et al., 2022; Hodges et al., 2021). Addressing these disparities is important for improving individual outcomes and enhancing the overall efficiency and equity of the U.S. healthcare system.

AI in Cancer Care

AI is increasingly pervasive in health care, reshaping the medical landscape through various applications from diagnosis to treatment, such as advancing knowledge of cancer care; expediting cancer screening, detection, and diagnosis; facilitating precision oncology treatment; and improving cancer surveillance and access to care (NCI, 2024). AI applications are increasingly included as part of electronic health records (EHRs), patient mobile health applications, other health-related applications, patient-facing chatbots, augmented reality surgical tools, and hospital scheduling systems. Research studies indicate that AI can perform on par with or surpass humans in key healthcare tasks, such as disease diagnosis (Davenport & Kalakota, 2019; Park, 2024).

In oncology, AI-based techniques are advancing in cancer genomics and image analysis, with modeling algorithms enhancing precision oncology by offering more precise interpretations of a patient’s cancer status (Shreve et al., 2022). Successful AI applications in cancer care, such as radionic analysis and machine learning models for diagnosis and biomarker identification, enable virtual biopsies, which are noninvasive techniques that use imaging data to assess tumor characteristics without requiring tissue extraction (Shreve et al., 2022). AI enhances decision-making support tools by analyzing EHR data to predict acute events, prompting timely clinical actions for improved patient outcomes (Starr et al., 2023).

Advanced AI-based techniques have been developed for oncology, but additional research is needed for effective clinical translation. Several factors impede AI’s advancement in oncology. One obstacle is the scarcity of structured cancer-related health data, as well as the lack of standardization in collecting and storing unstructured data within EHRs (Shreve et al., 2022). The absence of clinical validation for AI prediction models and limited transparency of AI algorithms create a black box phenomenon, where nothing is known about the technology’s internal process, complicating oncologists’ ability to interpret or explain decisions made by AI and resulting in a lack of trust among patients, families, and clinical providers (Davenport & Kalakota, 2019; O’Connor et al., 2024). Addressing these gaps will require a concerted effort, with nurses taking a role in integrating AI into oncology practice.

Bridging Disparities With AI

AI has the potential to affect oncology care, including cancer prevention, screening, treatment, and survivorship, and end-of-life care (Tawfik et al., 2023). By analyzing large amounts of data from diverse sources, AI can aid in early detection and diagnosis, addressing healthcare access and quality gaps, particularly in underserved areas (Fadiel et al., 2024). AI can personalize treatment plans by considering genetic, environmental, and lifestyle factors to tailor care to each patient’s needs (Johnson et al., 2021). By continuously learning from diverse datasets, AI can help to mitigate biases and improve equity in cancer care, thereby benefiting all populations (Dankwa-Mullan & Weeraratne, 2022). Integrating AI into clinical workflows can foster a collaborative environment and enhance overall care quality (Rony et al., 2024). AI holds promise to reduce healthcare disparities and promote more equitable outcomes in cancer treatment (Nagy & Sisk, 2020; Ueda et al., 2024).

AI has successfully addressed disparities in cancer care by improving healthcare accessibility, providing tailored interventions, and incorporating cultural intelligence. Examples include a mobile-based oral cancer image analysis software program in rural India, an AI algorithm for breast cancer detection using deep learning with novel ultrasound techniques in low-resource settings, and AI-driven chatbots and virtual assistants supporting cancer survivors who lack access to care (Corti et al., 2022; Mema & McGinty, 2020; Song et al., 2022; Wang et al., 2023). These tools also improve cultural intelligence by offering tailored support to cancer survivors from diverse backgrounds, demonstrating how AI can have a role in mitigating healthcare disparities and improving cancer care across various contexts and settings.

Although AI can enhance various nursing tasks, the core human elements of nursing, such as compassionate care, clinical judgment, personalized care plans, and establishment of trusting relationships, remain indispensable (Busch et al., 2019; Nagy & Sisk, 2020). With their frontline experience and direct patient interactions, nurses are positioned to identify opportunities where AI can reduce healthcare disparities. They understand the nuances of patient care that may not be captured in data alone (Montemayor et al., 2022) and can advocate for patients’ rights, provide empathy, and address ethical considerations (Starr et al., 2023). By leveraging AI’s ability to integrate diverse data types, nurses can mitigate bias, identify high-risk patients early, and customize interventions to specific needs. The shift toward personalized medicine allows for proactive, tailored care plans to improve individual patient outcomes, enhance care quality, and increase healthcare efficiency. Nurses’ advocacy for equitable AI implementation and their adaptability to each patient’s unique situation underscores their value in reducing healthcare disparities.

Enhancing Nursing Practice With AI

Impact of AI on Oncology Nursing and Patient Care

Oncology nurses have an important role within interprofessional teams, enhancing cancer care services by assessing patients, facilitating diagnostic procedures, executing treatment plans, and managing long-term survivorship plans. AI has become integrated into their daily workflow through tools like EHRs, telehealth consultations, and online health services. Various uses for AI can mitigate health disparities in oncology, such as predictive modeling, geospatial AI, natural language processing, and AI in telehealth and robotics, all of which can enhance clinical decision-making, optimize resource allocation, and improve patient outcomes (Fadiel et al., 2024; Istasy et al., 2022; O’Connor et al., 2024; Zhang et al., 2023) (see Table 1). Although some nurses are engaging in the AI-driven oncology landscape, many others are passive participants (O’Connor et al., 2024). Because of the rapid growth and use of AI tools in health care, there is an urgent need to upskill current practicing nurses and educate new nursing students about their applications in oncology.

TABLE 1.

EXEMPLARY STUDIES OF AI THAT ADDRESS CANCER DISPARITIES IN CLINICAL NURSING PRACTICE (N = 10)

STUDY	AI TECHNIQUES USED AND KEY FINDINGS	RELEVANCE TO NURSING PRACTICE
Abreu et al., 2024	■ Technique: AI chatbots (ChatGPT, version 4.0) ■ The AI chatbots enhanced the readability of online patient-facing content from 34 websites associated with National Comprehensive Cancer Network member institutions for the 5 deadliest cancers (breast, colon, lung, prostate, and pancreatic cancer) in the United States.	Enhancing the readability of online patient-facing content for the deadliest cancers improves patient education and communication, leading to better health outcomes and adherence to treatment plans. This aligns with nursing goals to provide patient-centered care and reduce health disparities.
Arora et al., 2022	■ Technique: telementoring (telehealth-enabled learning program) ■ Health informatics systems can be leveraged to help mitigate the impact of implicit bias in cancer care delivery through real-time monitoring and feedback to clinicians regarding treatment delays and missed care milestones. ■ Telementoring programs, such as Project ECHO (Extension for Community Healthcare Outcomes), build workforce capacity in areas that lack oncologists and other cancer care providers.	Technology alone is not a solution; it needs to be thoughtfully integrated into health care and reflect the lived experiences of healthcare workers and patients. Telementoring, through patient-centric inquiry, humanizes patient care by reducing bias and enhancing peer-to-peer learning, making it highly relevant to nursing practice.
Fadiel et al., 2024	■ Techniques: AI and GIS ■ The neighborhood safety rate may be a contributor to the cervical cancer mortality rate rather than the poverty rate. ■ AI–GIS analysis may reduce the disease burden by revealing higher cervical cancer rates in specific neighborhoods by discovery of environmental exposures or lifestyle behaviors. ■ This can help community leaders implement interventions like increasing access to screening and education about risk reduction strategies.	Using AI–GIS platforms can leverage big data to provide useful conclusions about regional disparities and help communities make decisions to optimize resource allocation, such as healthcare accessibility, healthcare resources, education, and economic opportunities.
Han et al., 2024	■ Technique: machine learning with natural language processing ■ Survivorship management across all gastrointestinal cancer types includes a focus on cancer risk prevention and awareness, lifestyle risk factors (primarily diet), and survivorship discussions, particularly related to gastrointestinal symptoms and quality of life. Social media posts about colorectal and stomach cancer highlighted gastrointestinal symptoms, and posts about liver/biliary and pancreatic cancer emphasized clinical trials, palliative care, and disease prognosis.	Individualized management of gastrointestinal cancers may consider lifestyle and diet, comprehensive survivorship care, and targeted interventions. Assessing social media data using machine learning tools can help nurses understand public concerns and interests, guiding patient-centered research and care strategies in gastrointestinal cancer survivors to mitigate cancer disparities.
Istasy et al., 2022	■ Techniques: various AI technologies, including algorithms, machine learning, deep learning, and convolutional neural networks ■ AI technologies can help address health disparities in low- and middle-income countries, as well as in high-income countries. ■ Biased AI algorithms may be used in clinical decision-making, which may affect the quality and accuracy of decisions and consequently lead to adverse health outcomes for patients. ■ AI may be used to examine determinants of health outcomes in oncology.	AI has the potential to affect health equity in oncology by addressing health disparities, mitigating or exacerbating bias, and elucidating determinants of health. For nursing practice, it is important to consider the ethical challenges of using AI in low- and middle-income countries, issues of bias in AI algorithms, and lack of justification for using AI technologies rather than traditional statistical methods to address specific research questions in oncology.
Jordan et al., 2021	■ Technique: natural language processing ■ A novel AI-based tool improved the process of finding clinical trials and enhanced the clarity and understanding of the presented information. It also provided clear guidance on the next steps for enrollment, resulting in higher patient satisfaction.	An AI-driven clinical trial support tool can streamline and help navigate trial access for all patients. This tool could be of value for nurse researchers who face issues when navigating and recruiting participants for clinical trials.
O’Connor et al., 2024	■ Technique: predictive AI algorithm models in oncology datasets ■ AI has enhanced cancer care, including for breast, colorectal, liver, and ovarian cancers, by using models trained on diverse datasets, thus improving the accuracy of predicting health outcomes and identifying key predictive variables.	Oncology nurses need enhanced education in machine learning and natural language processing to lead and contribute to AI developments. Rigorous research is important to assess AI’s real-world impact on oncology nursing, with the aim of improving professional practice, patient care, and service delivery. Addressing AI’s limitations and risks can maximize its potential benefits for patients and the nursing profession.
Park et al., 2023	■ Technique: survival machine learning ■ Race- and ethnicity-specific models for Hispanic and Black women consistently outperformed a general model in predicting outcomes among these groups.	Findings enable more personalized care by using race- and ethnicity-specific models to predict outcomes. This approach supports culturally competent care and helps address healthcare disparities among Hispanic and Black women.
Rony et al., 2024	■ Techniques: AI-enabled robotics and telehealth solutions ■ AI-enabled robotics and telehealth solutions expand the reach of nursing care, improving the accessibility of healthcare services and capabilities to remotely monitor patients’ health conditions.	AI-powered clinical decision support systems, patient monitoring, predictive analytics, and care coordination enhance nursing practice. Preparing nurses for these advancements involves providing comprehensive AI education and training, as well as addressing ethical considerations and challenges.
Zhang et al., 2023	■ Techniques: machine learning and AI algorithms in cancer prognosis, prediction, and treatment selection ■ Machine learning, a subset of AI, has proven highly effective at predicting various cancers, including breast, brain, lung, liver, and prostate cancer, often with greater accuracy than clinicians.	AI technologies have the potential to enhance diagnosis, prognosis, and quality of life, helping nurses mitigate cancer disparities and improve patient outcomes.

AI—artificial intelligence; GIS—geographic information system

AI Training and Education for Oncology Nurses

Continuous training and education for nurses and other healthcare professionals about how to use AI tools can ensure that they understand the capabilities and limitations of AI. As AI technologies become integrated into clinical workflows, nurses need to enhance their knowledge and skills to evaluate AI-generated results and translate them into actionable insights for patient care (Cary et al., 2024). Comprehensive training programs can help nurses understand the capabilities and limitations of AI, interpret AI-driven recommendations in their practice, and integrate these insights into holistic care plans that address patients’ medical and emotional needs (Nagy & Sisk, 2020; Rony et al., 2024). Through this education, nurses can leverage the combined strengths of humans and AI to enhance patient care delivery and improve outcomes in cancer care.

Ethical Considerations and Patient–Nurse Relationships

Ethical considerations and patient–nurse relationships in AI-driven cancer care are complex and require careful attention to ensure that technological advancements enhance rather than compromise patient care (Morley & Floridi, 2020; Peirce et al., 2020). Critical ethical issues include patient privacy, data security, transparency, and equity. AI systems rely on large datasets, raising concerns about data privacy and security. Nurses need to ensure ethical use, and obtaining informed consent for AI in treatment decisions is paramount. Transparency around AI algorithms can build trust and help verify decisions to mitigate biases and ensure equitable treatment outcomes (Cary et al., 2023). Nurses’ understanding of patients and the healthcare system can ensure representative training data and prevent unintentional bias (Ronquillo et al., 2021). Strong patient–nurse relationships are responsible for AI integration in cancer research and clinical practice. These relationships can ensure that AI tools enhance rather than replace the human elements of care (American Nurses Association, 2022; Nagy & Sisk, 2020). Nurses can guide AI integration to support equitable, patient-centered oncology care by cultivating compassionate, empathetic patient interactions alongside technological advancement.

Conclusion

Despite challenges, AI can enhance cancer care by improving prevention, diagnosis, and treatment across populations. Embracing AI can equip future oncology nurses with skills for these tasks, fostering critical thinking and care delivery to advance health equity. Comprehensive training programs that integrate AI into clinical workflows and address ethical considerations may lead to successful adoption, preparing nurses to manage AI-driven decisions with empathy and integrity. Thoughtful AI integration considers the diverse needs of patient populations, mitigates potential biases in algorithms, and ensures equitable care. By addressing health disparities and offering personalized interventions, AI can advance health equity for people affected by cancer. The careful and deliberate integration of AI into oncology nursing practice will substantially contribute to this goal.

PROFESSIONAL DEVELOPMENT ACTIVITY.

EARN 1 CONTACT HOUR

ONS members can earn free nursing continuing professional development (NCPD) for reading this article and completing an evaluation online. To do so, visit www.ons.org/publications-research/cjon/ncpd to link to this article and then access its evaluation link after logging in. ONS is accredited as a provider of nursing continuing professional development by the American Nurses Credentialing Center’s Commission on Accreditation.

Certified nurses can claim no more than 1 total ILNA point for this program. Up to 1 ILNA point may be applied to Oncology Nursing Practice OR Nursing Practice OR Professional Practice/Performance. See www.oncc.org for complete details on certification.

Consider how you can apply findings from this article to your own practice using the following questions:

• ■ How can the integration of artificial intelligence (AI) in cancer care be tailored to address the specific needs and challenges of your patient population, particularly those who are socially, economically, or geographically disadvantaged?

• ■ What strategies can your team implement to ensure continuous training and education for healthcare professionals on the use of AI tools, while also maintaining the essential human elements of nursing like compassionate care and clinical judgment?