Int J Aging. 2024;2:e23.
doi: 10.34172/ija.2024.e23
Letter to Editor
Artificial Intelligence in Older Adults’ Health
Nazanin Masoudi 1
, Ehsan Sarbazi 2, * 
Author information:
1Social Equity Research Centre, RMIT University, Melbourne, VIC, Australia
2East Azerbaijan Province Health Center, Tabriz University of Medical Sciences, Tabriz, Iran
Copyright and License Information
© 2024 The Author(s).
This is an open access article distributed under the terms of the Creative Commons Attribution License (
http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Funding Statement
None.
Please cite this article as follows: Masoudi N, Sarbazi E. Artificial intelligence in older adults’ health. Int J Aging. 2024;2: e23. doi: 10.34172/ija.2024.e23
Dear Editor,
With the growing older adult population globally, there is an increasing need to find innovative solutions to address their health needs. Artificial Intelligence (AI) has emerged as a beneficial tool for diagnosing and predicting health issues across various medical fields.1,2 AI can enhance personalized healthcare for older adults, significantly improving their overall quality of life and well-being.3
This study aimed to provide a concise overview of AI techniques, applications, evaluation metrics, ethical considerations, biases, and associated challenges associated with AI models in healthcare.
AI Techniques and Their Real-World Applications in Older Adults’ Healthcare
Support vector machines (SVMs) and k-nearest neighbors are commonly used for tasks such as classifying falls among older adults or identifying individuals at risk of diseases, while random forest (RF) excels in analyzing clinical data and medication histories due to their ability to manage missing values.4-7 Additionally, convolutional neural networks demonstrated high accuracy in medical imaging, particularly in detecting early signs of diseases such as Alzheimer’s. Recurrent neural networks, on the other hand, are used to analyze time-series data such as electrocardiograms and cognitive monitoring, although they require more computational resources.8,9 Lastly, artificial neural networks and deep learning are utilized to predict imaging outcomes and drug interactions.9
Machine learning (ML) algorithms such as decision trees, RF, and SVMs can predict when diseases might start or worsen, facilitating early treatment and personalized care plans.10 For example, hospitals in the USA have integrated AI solutions like SVM and RF algorithms to identify cardiovascular diseases in older adults.11 In addition, in mental health, AI has been used to monitor conditions such as dementia and depression, offering timely interventions and supporting personalized care.12-14 It plays a crucial role in improving mental health by providing tailored nutrition and diet plans, optimizing rehabilitation and physical therapy programs, and reducing the risk of adverse drug reactions through improved medication management.15-17 In addition, AI-powered personalized medicine analyzes patient records to suggest tailored treatment options, thereby enhancing outcomes in older adult care.18
Furthermore, natural language processing techniques can help manage medications by analyzing and understanding patient records, ensuring that patients take their medications correctly and avoid harmful drug interactions. Furthermore, reinforcement learning algorithms can optimize rehabilitation and physical therapy programs by adapting to the specific needs and progress of older adults.19,20
Moreover, AI approaches can be applied in pain management for various conditions in older adults,and their remote monitoring can also offer a cost-effective alternative to traditional visits, improving care and reducing healthcare costs, particularly for chronic diseases in older adults.21,22
Evaluation Metrics for AI Models in Healthcare
Evaluating AI models in older adults’ healthcare involves metrics such as accuracy, precision, recall, F1-score, and area under the curve (AUC)-receiver operating characteristics (ROC). Accuracy assesses correct predictions, while precision and recall focus on positive predictability and true positives, respectively. The F1-score provides a balance between precision and recall, which is crucial in disease diagnosis, and AUC-ROC helps distinguish classes, making it valuable for imbalanced datasets.23-26 These metrics are essential for ensuring timely and reliable predictions, which are critical in older adults’ care.
Ethical Considerations, Bias, and Challenges
Challenges related to ethics, transparency, and data privacy persist in the application of AI. A key ethical challenge with AI in healthcare is the lack of transparency and interpretability, which makes it difficult for healthcare providers to understand the decision-making processes. Biases in AI models due to unbalanced training data can also affect aging populations, leading to less effective care. Addressing these issues requires age diversity in data collection, routine audits, and overcoming limitations (e.g., data privacy concerns and the digital divide).27-33 Greater trust in AI systems is associated with increased adherence to health recommendations, indicating that cultivating trust can improve health outcomes.34,35
The use of ML and AI methods in epidemiological studies, as opposed to traditional methods, has demonstrated their capacity to manage large complex datasets while detecting subtle patterns and associations. This capability is crucial given the extensive and multifaceted nature of health data.36 AI facilitates more efficient public health research and interventions, especially for older individuals.
Integrating AI and ML into older adults’ healthcare is essential for creating a more efficient and compassionate system. It is suggested that policymakers, healthcare providers, researchers, and editors collaborate and invest in these technologies for a healthier future for older adults.37,38
Author contributions
Conceptualization: Nazanin Masoudi.
Methodology: Ehsan Sarbazi, Nazanin Masoudi.
Supervision: Ehsan Sarbazi.
Writing–review & editing: Ehsan Sarbazi, Nazanin Masoudi.
Data availability statement
None.
Ethical approval
Not applicable.
Consent for publication
Not applicable.
Conflict of interests
The authors declare that they have no conflict of interests.
References
- Badawy M, Ramadan N, Hefny HA. Healthcare predictive analytics using machine learning and deep learning techniques: a survey. J Electr Syst Inf Technol 2023; 10(1):40. doi: 10.1186/s43067-023-00108-y [Crossref] [ Google Scholar]
- Yang CC. Explainable artificial intelligence for predictive modeling in healthcare. J Healthc Inform Res 2022; 6(2):228-39. doi: 10.1007/s41666-022-00114-1 [Crossref] [ Google Scholar]
- Das A, Dhillon P. Application of machine learning in measurement of ageing and geriatric diseases: a systematic review. BMC Geriatr 2023; 23(1):841. doi: 10.1186/s12877-023-04477-x [Crossref] [ Google Scholar]
- Kausar F, Mesbah M, Iqbal W, Ahmad A, Sayyed I. Fall detection in the elderly using different machine learning algorithms with optimal window size. Mob Netw Appl 2024; 29(2):413-23. doi: 10.1007/s11036-023-02215-6 [Crossref] [ Google Scholar]
- Noble WS. What is a support vector machine?. Nat Biotechnol 2006; 24(12):1565-7. doi: 10.1038/nbt1206-1565 [Crossref] [ Google Scholar]
- Goldberger J, Hinton GE, Roweis S, Salakhutdinov RR. Neighbourhood components analysis. Adv Neural Inf Process Syst 2004;17.
- Breiman L. Random forests. Mach Learn 2001; 45(1):5-32. [ Google Scholar]
- Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM. Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017; 542(7639):115-8. doi: 10.1038/nature21056 [Crossref] [ Google Scholar]
- Lipton ZC, Kale DC, Elkan C, Wetzel R. Learning to diagnose with LSTM recurrent neural networks. ArXiv [Preprint]. November 11, 2015 Available from: https://arxiv.org/abs/1511.03677.
-
Iqbal S. Artificial intelligence tools and applications for elderly healthcare-review. In: Proceedings of the 2023 9th International Conference on Computing and Artificial Intelligence. New York, NY: Association for Computing Machinery; 2023. p. 394-7. doi: 10.1145/3594315.3594347.
- Johnson KW, Torres Soto J, Glicksberg BS, Shameer K, Miotto R, Ali M. Artificial intelligence in cardiology. J Am Coll Cardiol 2018; 71(23):2668-79. doi: 10.1016/j.jacc.2018.03.521 [Crossref] [ Google Scholar]
- Javed AR, Saadia A, Mughal H, Gadekallu TR, Rizwan M, Maddikunta PKR. Artificial intelligence for cognitive health assessment: state-of-the-art, open challenges and future directions. Cognit Comput 2023; 15(6):1767-812. doi: 10.1007/s12559-023-10153-4 [Crossref] [ Google Scholar]
- Ho A. Are we ready for artificial intelligence health monitoring in elder care?. BMC Geriatr 2020; 20(1):358. doi: 10.1186/s12877-020-01764-9 [Crossref] [ Google Scholar]
- Zarei M, Asheghi M, Zarei M. Artificial intelligence in dementia diagnosis: past, present, and future. Int J Aging 2023; 1(1):e14. doi: 10.34172/ija.2023.e14 [Crossref] [ Google Scholar]
- Wei DH, Hernandez B, Burdick D. Artificial intelligence in mental health for the aging population: a scoping review. Innov Aging 2023; 7(Suppl 1):805-6. doi: 10.1093/geroni/igad104.2600 [Crossref] [ Google Scholar]
- Lee MH, Siewiorek DP, Smailagic A, Bernardino A, Badia SB. Enabling AI and robotic coaches for physical rehabilitation therapy: iterative design and evaluation with therapists and post-stroke survivors. Int J Soc Robot 2024; 16(1):1-22. doi: 10.1007/s12369-022-00883-0 [Crossref] [ Google Scholar]
- Yeung A, Wu C. AI for elderly dietary care: A cyber-physical system for nutrition management. IEEE Smart Cities Newsl 2021;3(8).
- Johnson KB, Wei WQ, Weeraratne D, Frisse ME, Misulis K, Rhee K. Precision medicine, AI, and the future of personalized health care. Clin Transl Sci 2021; 14(1):86-93. doi: 10.1111/cts.12884 [Crossref] [ Google Scholar]
- Shiwani T, Relton S, Evans R, Kale A, Heaven A, Clegg A. New horizons in artificial intelligence in the healthcare of older people. Age Ageing 2023; 52(12):afad219. doi: 10.1093/ageing/afad219 [Crossref] [ Google Scholar]
- Padhan S, Mohapatra A, Ramasamy SK, Agrawal S. Artificial intelligence (AI) and robotics in elderly healthcare: enabling independence and quality of life. Cureus 2023; 15(8):e42905. doi: 10.7759/cureus.42905 [Crossref] [ Google Scholar]
- Latifi K, Negaresh M, Javanshir N, Safari S. The advent of artificial intelligence in anesthesiology and pain management: a review article. Int J Drug Res Clin 2023; 1(1):e14. doi: 10.34172/ijdrc.2023.e14 [Crossref] [ Google Scholar]
- Dubey A, Tiwari A. Artificial intelligence and remote patient monitoring in US healthcare market: a literature review. J Mark Access Health Policy 2023; 11(1):2205618. doi: 10.1080/20016689.2023.2205618 [Crossref] [ Google Scholar]
- Hand DJ, Anagnostopoulos C. When is the area under the receiver operating characteristic curve an appropriate measure of classifier performance?. Pattern Recognit Lett 2013; 34(5):492-5. doi: 10.1016/j.patrec.2012.12.004 [Crossref] [ Google Scholar]
- Saito T, Rehmsmeier M. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS One 2015; 10(3):e0118432. doi: 10.1371/journal.pone.0118432 [Crossref] [ Google Scholar]
- Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med 2019; 25(1):44-56. doi: 10.1038/s41591-018-0300-7 [Crossref] [ Google Scholar]
- Chicco D, Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics 2020; 21(1):6. doi: 10.1186/s12864-019-6413-7 [Crossref] [ Google Scholar]
- Reddy S, Fox J, Purohit MP. Artificial intelligence-enabled healthcare delivery. J R Soc Med 2019; 112(1):22-8. doi: 10.1177/0141076818815510 [Crossref] [ Google Scholar]
- Lipton ZC. The mythos of model interpretability: in machine learning, the concept of interpretability is both important and slippery. Queue 2018; 16(3):31-57. doi: 10.1145/3236386.3241340 [Crossref] [ Google Scholar]
- Tonekaboni S, Joshi S, McCradden MD, Goldenberg A. What clinicians want: contextualizing explainable machine learning for clinical end use. In: Machine Learning for Healthcare Conference. PMLR; 2019. p. 359-80.
- Char DS, Shah NH, Magnus D. Implementing machine learning in health care - addressing ethical challenges. N Engl J Med 2018; 378(11):981-3. doi: 10.1056/NEJMp1714229 [Crossref] [ Google Scholar]
- Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science 2019; 366(6464):447-53. doi: 10.1126/science.aax2342 [Crossref] [ Google Scholar]
- Seyyed-Kalantari L, Zhang H, McDermott MB, Chen IY, Ghassemi M. Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations. Nat Med 2021; 27(12):2176-82. doi: 10.1038/s41591-021-01595-0 [Crossref] [ Google Scholar]
- Parikh RB, Teeple S, Navathe AS. Addressing bias in artificial intelligence in health care. JAMA 2019; 322(24):2377-8. doi: 10.1001/jama.2019.18058 [Crossref] [ Google Scholar]
- Sarbazi E, Sadeghi-Bazargani H, Sheikhalipour Z, Farahbakhsh M, Ala A, Soleimanpour H. Trust in medicine: a scoping review of the instruments designed to measure trust in medical care studies. J Caring Sci 2024; 13(2):116-37. doi: 10.34172/jcs.33152 [Crossref] [ Google Scholar]
-
Giorgi I, Minutolo A, Tirotto F, Hagen O, Esposito M, Gianni M, et al. I am robot, your health adviser for older adults: do you trust my advice? Int J Soc Robot. 2023. doi: 10.1007/s12369-023-01019-8.
- Chen S, Yu J, Chamouni S, Wang Y, Li Y. Integrating machine learning and artificial intelligence in life-course epidemiology: pathways to innovative public health solutions. BMC Med 2024; 22(1):354. doi: 10.1186/s12916-024-03566-x [Crossref] [ Google Scholar]
- Masoudi N, Sarbazi E, Soleimanpour H, Abbasian M, Ghasemi M, Rostami Z. Loneliness and its correlation with self-care and activities of daily living among older adults: a partial least squares model. BMC Geriatr 2024; 24(1):621. doi: 10.1186/s12877-024-05215-7 [Crossref] [ Google Scholar]
- Soleimanpour H, Ghaffari Fam S, Sarbazi E, Gholami R, Azizi H, Daliri M. The association between self-care and quality of life among iranian older adults: evidence from a multicenter survey. J Rehabil Sci Res 2024; 11(4):196-201. doi: 10.30476/jrsr.2023.99026.1378 [Crossref] [ Google Scholar]