Author's Draft: Published in the IEEE Computer Society flagship magazine Computer July 2025, pages 153-156.

Generative AI and Healthcare: Brief Survey

Roy Rada

AI is transforming healthcare. Big-Data Radiation Oncology and High-Touch Palliative Care illustrate different opportunities.

Artificial Intelligence (AI) and healthcare have impacted one another since the beginning of AI. Traditionally, the branches of healthcare most dependent on digitized information benefited the most from AI. Do the latest advances in natural language processing impact the trajectory? Since Large Language Models (LLMs) exploit free-form text, do they open opportunities for branches of healthcare traditionally reliant on human-human interaction? Or will the areas that get the most investment already be the ones that get the most investment in the future, as a continuation of the famous aphorism 'the rich get richer, while the poor get poorer'.

The history of computer applications in healthcare supports the famous "Rich get Richer" phenomenon. In 1968 Merton introduced the 'Matthew effect' [1] as "This complex pattern of the misallocation of credit for scientific work must quite evidently be described as the Matthew effect ... For unto everyone that hath shall be given." Evidence for the Matthew effect has appeared across occupations. A study of healthcare delivery in China concludes, "the Intercity Health Network generates new structural inequalities in healthcare access exhibiting a Matthew effect [2]." New investments in digital information systems in healthcare have typically gone into areas that most relied on digital information [3]. Historically, the first healthcare computer investments were in accounting and next, radiology and pathology. Healthcare and AI illustrates the Matthew effect. This essay next reviews the AI and health literature before focusing on two application areas, radiation oncology and palliative care, which sit at opposite extremes of the capital spectrum.

AI and Healthcare

Deep learning has been successfully applied to clinical medicine for more than three decades [4]. Generative AI trains on multimedia libraries, while Large Language Models (LLMs) train on document libraries [5], and both perform well on many health care tasks [6]. While LLMs lack epistemic validity, they create new opportunities for healthcare applications that converse with humans

A search of IEEE Xplore for ('artificial intelligence' AND ('health care' OR medicine) AND 'systematic reviews' AND 2020-to-2025) returned 54 citations. Most citations were for highly focused topics, such as "Multi-modal deep learning diagnosis of Parkinson s Disease" [8], but 9 were broad. One broad review shows that big data facilitates personalized medicine, predictive analytics, early illness diagnosis, precision diagnostics, and treatment optimization from electronic health records, genomes, wearables, and medical imaging [9]. In another broad review, adoption of AI applications depends on the eight factors of technical feasibility, ease of use, system quality, performance, usability, social influence, and trust [10]. The IEEE literature suggests that AI increases the effectiveness and efficiency of healthcare [11].

Large companies that develop electronic health records systems are working with large provider networks to integrate LLMs into the workflow.

Radiation Oncology and Palliative Care

Radiation oncology is one of three oncology branches, the other two being medical and surgical oncology. In preparing a radiotherapy treatment plan, the doctors acquire images, segment the target, and plan doses to kill cancer cells. Radiomics is a method to quantitatively analyze medical images to uncover tumoral patterns not appreciated by the naked eye and to support personalized therapy [12]. Doctors try to predict outcomes based on both radiomics and genomics. In the delivery of radiation, the team monitors patient changes and adapts treatment. Changing radiation based on patient motion occurs in real-time under computer control. Radiation oncology relies on massive amounts of digital information and repetitive tasks [13] -- 'Big Data' incarnate [14].

Radiation oncology is ripe for AI applications [15]: "AI ... transformative applications in radiation oncology given ... a heavy reliance on digital data processing and computer software." Radiation oncologists appreciate AI's impact and say that AI revolutionizes radiation therapy [16]. AI is transformative at every step of the radiation oncology process.

Palliative Medicine differs sharply from Radiation Oncology. The World Health Organization states [17]: "Palliative care ... improves the quality of life of patients and their families who are facing ... life-threatening illness, through the prevention and relief of suffering ... whether physical, psychosocial, or spiritual." Diseases benefiting from palliative medicine include cancer, heart failure, and stroke. Nevertheless, only 14% of people who need palliative care currently get it [17]. Health insurance underfunds palliative care, and hospitals, at a loss to themselves, provide more than half of the overall cost of palliative care [18]. A systematic review of challenges in palliative care concludes that the most significant barrier is a lack of resources [19]. If technology could reduce costs of delivering palliative care, then palliative care professionals have an obligation to explore using it [20].

Palliative care uses AI less than radiation oncology. Grant and patent activity evidences the divide. With the US National Institutes of Health (NIH) 'Research Portfolio Online Reporting Tools', users search a repository of both intramural and extramural NIH-funded research projects and access patents resulting from NIH funding [21]. A search on this NIH repository for 'radiation oncology' AND 'artificial intelligence' returns 68 active projects linked to 60 patents. A search on 'palliative care' AND 'artificial intelligence' retrieves 10 active projects and 0 patents. Radiation oncology is 'richer' than palliative medicine.

How are LLMs special for palliative care? LLMs can forecast mortality or monitor pain. For predicting mortality, one project uses traditional machine learning on structured data sets [22], while another project uses an LLM that reads unstructured medical records [23]. These two projects highlight the salient difference between LLM and non-LLM approaches. The LLM approach works on unstructured natural language. The LLM approach lends itself more readily to extensions and diffusion into Electronic Health Records systems.

An LLM for patient mental health showed that the LLM-system responds like a professional mental health counselor [24]. For the doctor, an LLM inferred wishes of mentally incapacitated patients based on prior records [25]. LLMs are well suited to palliative care [26].

Workflow

One challenge in the roll-out of LLM applications is gaining the trust of the intended users. While this trust is a necessary condition for diffusion, another necessary condition is fitting into the workflow. The surge of interest in expert systems in the 1980s bares comparison to the surge of interest in LLMs. The 1980s MYCIN expert system was as good as expert physicians in its problem area of bacteremia, and it offered recency, accuracy, coherence, and transparency confirmed by clinical trials [27]. However, to use MYCIN, the physician needed to access a separate, stand-alone application and re-enter patient information into that application which took enough time that the cost/benefit ratio was too high for the physician -- in other words, MYCIN did not fit into the workflow [3]. Large companies that develop electronic health records systems are working with large provider networks to integrate LLMs into the workflow [28]. However, journals underreport these efforts.

Workflow systems rely on roles defined as functions with rules for passing messages among roles. LLMs can mediate between roles and between a role and the rules of that role [29]. In radiation oncology, automation of workflow with the support of LLMs is advanced [30], but not in palliative care.

A hospice care system, which is the ultimate example of palliative care, suits LLM integration into the workflow [31, 32]. The system would represent the roles of the interdisciplinary team and the roles of patients and their family, as 'dignity therapy' illustrates. Dignity therapy helps patients reflect on end-of-life issues. The patient receives nine standard questions which guide a conversation. The dialog is recorded, transcribed, and edited into a legacy document for the patient to use in implementing the last steps of life [33]. However, dignity therapy is underutilized due to a lack of trained staff to help. With an LLM-automated social worker, patients could develop their dignity document [34, 35].

Discussion

The IEEE literature highlights that AI with Big Data will improve healthcare. Radiation oncology relies on Big Data, attracts investment, and uses AI extensively. Palliative care relies on human-human interaction, attracts little capital, and uses AI sparingly. Radiation oncology is rich and getting richer. What is the future for palliative care?

Palliative care does not process vast amounts of information in real-time, as radiation oncology does. Palliative care relies on natural language communication, and LLMs facilitate natural language communication. As death approaches, the roles of palliative care and natural language communication increase. LLMs are generalists [36] and could support palliative care applications both clinician-facing and patient-facing across every phase of the clinician and patient experience.

The betting AI entrepreneur invests in radiation oncology rather than palliative care. Radiation oncology uses LLMs, and as LLMs are commoditized, their use diffuses into poorer domains, such as palliative care. The radiation oncology patient cannot hope to understand the intricacies of radiation treatment, trusts the doctor, and hopes for a cure. For the hospice patient, by contrast, the doctor is less relevant, and the patient could benefit from LLMs but gets no help in using LLMs. Would the betting person see anything different here?

References

  1. R. K. Merton, "The Matthew effect in science: The reward and communication systems of science are considered," Science, vol. 159, no. 3810, pp. 56-63, 1968.
  2. P. Zhao, J. Li, and M. Zhang, "Unequal roles of cities in the intercity healthcare system," Nature Cities, pp. 1-12, 2025.
  3. R. Rada, Information systems and healthcare enterprises. IGI Global, 2007.
  4. S. C. Lo, M. T. Freedman, J. S. Lin, and S. K. Mun, "Automatic lung nodule detection using profile matching and back-propagation neural network techniques," J Digit Imaging, vol. 6, no. 1, pp. 48-54, Feb 1993, doi: 10.1007/bf03168418.
  5. A. J. Thirunavukarasu, D. S. J. Ting, K. Elangovan, L. Gutierrez, T. F. Tan, and D. S. W. Ting, "Large language models in medicine," Nat Med, vol. 29, no. 8, pp. 1930-1940, Aug 2023, doi: 10.1038/s41591-023-02448-8.
  6. X. Shi et al., "A Bibliographic Dataset of Health Artificial Intelligence Research," (in eng), Health Data Sci, vol. 4, p. 0125, 2024, doi: 10.34133/hds.0125.
  7. H. Berghel, "ChatGPT and AIChat Epistemology," Computer, vol. 56, no. 5, pp. 130-137, 2023, doi: 10.1109/MC.2023.3252379.
  8. V. Skaramagkas, A. Pentari, Z. Kefalopoulou, and M. Tsiknakis, "Multi-modal deep learning diagnosis of parkinson s disease A systematic review," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 31, pp. 2399-2423, 2023.
  9. A. Kumar and N. P. Singh, "A Study on Future Data Science and its Impact in Health Care Organizations," in 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2024: IEEE, pp. 1-7.
  10. G. B. Anugerah and A. N. Hidayanto, "What Factors Contribute to the Acceptance of Artificial Intelligence on Healthcare Sector: A Systematic Review," in 2023 3rd International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA), 2023: IEEE, pp. 477-482.
  11. A. Sharma and R. Kumar, "Artificial Intelligence in Health Care Sector and Future Scope," in 2023 International Conference on Innovative Data Communication Technologies and Application (ICIDCA), 2023: IEEE, pp. 210-214.
  12. A. K. Jha et al., "Implementation of Big Imaging Data Pipeline Adhering to FAIR Principles for Federated Machine Learning in Oncology," IEEE Transactions on Radiation and Plasma Medical Sciences, vol. 6, no. 2, pp. 207-213, 2022, doi: 10.1109/TRPMS.2021.3113860.
  13. F. J. P. Hoebers et al., "Artificial intelligence research in radiation oncology: a practical guide for the clinician on concepts and methods," BJR|Open, vol. 6, no. 1, 2024, doi: 10.1093/bjro/tzae039.
  14. F. Abuhijla, I. Jaradat, A. Almousa, and R. Abuhijlih, "Impact of Big Data on Radiation Oncology Practice," in 2018 1st International Conference on Cancer Care Informatics (CCI), 19-21 Nov. 2018 2018, pp. 59-59, doi: 10.1109/CANCERCARE.2018.8618145.
  15. E. Huynh et al., "Artificial intelligence in radiation oncology," Nature Reviews Clinical Oncology, vol. 17, no. 12, pp. 771-781, 2020/12/01 2020, doi: 10.1038/s41571-020-0417-8.
  16. M. Kawamura et al., "Revolutionizing radiation therapy: the role of AI in clinical practice," (in eng), J Radiat Res, vol. 65, no. 1, pp. 1-9, Jan 19 2024, doi: 10.1093/jrr/rrad090.
  17. S. Connor, Global Atlas of Palliative Care 2nd Edition. London, UK: Worldwide Hospice Palliative Care Alliance, 2020, p. 120. [Online]. Available: https://www.iccp-portal.org/system/files/resources/WHPCA_Global_Atlas_FINAL_DIGITAL.pdf
  18. R. T. Sullender and S. A. Selenich, Financial Considerations of Hospital-Based Palliative Care (RTI Press Research Report Series). Research Triangle Park, North Carolina: RTI Press, 2016, doi: 10.3768/rtipress.2016.rr.0027.1603.
  19. M. S. Amroud, P. Raeissi, S. M. Hashemi, N. Reisi, and S. A. Ahmadi, "Investigating the challenges and barriers of palliative care delivery in Iran and the World: A systematic review study," J Educ Health Promot, vol. 10, p. 246, 2021, doi: 10.4103/jehp.jehp_1325_20.
  20. C. Barry, P. Paes, S. Noble, and A. Davies, "Challenges to delivering evidence-based palliative medicine," Clin Med (Lond), vol. 23, no. 2, pp. 182-184, Mar 2023, doi: 10.7861/clinmed.2022-0336.
  21. National Institues of Health. NIH RePORTER (Research Portfolio Online Reporting Tool) [Online] Available: report.nih.gov
  22. M. N. Patel et al., "Machine Learning for Targeted Advance Care Planning in Cancer Patients: A Quality Improvement Study," J Pain Symptom Manage, vol. 68, no. 6, pp. 539-547.e3, Dec 2024, doi: 10.1016/j.jpainsymman.2024.08.036.
  23. N. D. Agaronnik, J. Davis, C. R. Manz, J. A. Tulsky, and C. Lindvall, "Large Language Models to Identify Advance Care Planning in Patients With Advanced Cancer," (in eng), J Pain Symptom Manage, Nov 24 2024, doi: 10.1016/j.jpainsymman.2024.11.016.
  24. H. Qiu, A. Li, L. Ma, and Z. Lan, "Psychat: A client-centric dialogue system for mental health support," in 2024 27th International Conference on Computer Supported Cooperative Work in Design (CSCWD), 08-10 May 2024 2024: IEEE, pp. 2979-2984, doi: 10.1109/CSCWD61410.2024.10580641.
  25. V. J. Nolan et al., "Incorporating Patient Values in Large Language Model Recommendations for Surrogate and Proxy Decisions," Crit Care Explor, vol. 6, no. 8, p. e1131, Aug 1 2024, doi: 10.1097/cce.0000000000001131.
  26. S. Tripathi, R. Sukumaran, and T. S. Cook, "Efficient healthcare with large language models: optimizing clinical workflow and enhancing patient care," Journal of the American Medical Informatics Association, vol. 31, no. 6, pp. 1436-1440, 2024, doi: 10.1093/jamia/ocad258.
  27. V. L. Yu et al., "Evaluating the performance of a computer-based consultant," (in eng), Comput Programs Biomed, vol. 9, no. 1, pp. 95-102, Jan 1979, doi: 10.1016/0010-468x(79)90022-9.
  28. H. Landi, "HIMSS24: How Epic is building out AI, ambient technology for clinicians," in Fierce Healthcare, ed: Fierce, 2024, p. 1.
  29. K. Joel Prabhod, "Integrating Large Language Models for Enhanced Clinical Decision Support Systems in Modern Healthcare," Journal of Machine Learning for Healthcare Decision Support, vol. 3, no. 1, pp. 18-62, 06/30 2023. [Online]. Available: https://medlines.uk/index.php/JMLHDS/article/view/23.
  30. R. Krishnamurthy, N. Mummudi, J. S. Goda, S. Chopra, B. Heijmen, and J. Swamidas, "Using Artificial Intelligence for Optimization of the Processes and Resource Utilization in Radiotherapy," JCO Glob Oncol, vol. 8, p. e2100393, Nov 2022, doi: 10.1200/go.21.00393.
  31. G. Demiris, D. Parker Oliver, and E. Wittenberg-Lyles, "Technologies to support end-of-life care," Semin Oncol Nurs, vol. 27, no. 3, pp. 211-7, Aug 2011, doi: 10.1016/j.soncn.2011.04.006.
  32. A. Suslow, C. Giehl, J. Hergesell, H. C. Vollmar, and I. Otte, "Impact of information and communication software on multiprofessional team collaboration in outpatient palliative care - a qualitative study on providers' perspectives," BMC Palliat Care, vol. 22, no. 1, p. 19, Mar 8 2023, doi: 10.1186/s12904-023-01141-4.
  33. M. Mart nez et al., " Dignity therapy , a promising intervention in palliative care: A comprehensive systematic literature review," Palliative medicine, vol. 31, no. 6, pp. 492-509, 2017.
  34. Y. Lim, "Dignity and Dignity Therapy in End-of-Life Care," J Hosp Palliat Care, vol. 26, no. 3, pp. 145-148, Sep 1 2023, doi: 10.14475/jhpc.2023.26.3.145.
  35. E. Wild, J. Weng, D. Pachman, C. Ingram, and M. Felt, "Feasibility and acceptability of virtual dignity therapy for palliative care patients with advanced cancer," Journal of Pain and Symptom Management, vol. 67, no. 5, pp. e609-e610, 2024, doi: 10.1016/j.jpainsymman.2024.02.032.
  36. M. Moor et al., "Foundation models for generalist medical artificial intelligence," Nature, vol. 616, no. 7956, pp. 259-265, Apr 2023, doi: 10.1038/s41586-023-05881-4.

Roy Rada is a Professor Emeritus at the Department of Information Systems, ITE Building, University of Maryland, Baltimore County, MD 21250. Contact rada@umbc.edu.

Return Home