Enhancing artificial intelligence chatbot dependability in Parkinson's disease patients: future of care

Aumentando a confiabilidade do chatbot com inteligência artificial em pacientes com doença de Parkinson: futuro dos cuidados

Dear Editor,

Parkinson's disease (PD) is a common neurodegenerative disorder characterized by motor and non-motor symptoms such as tremors, bradykinesia, and dystonias, which lead to difficulty in speaking¹. The prevalence of PD rises with increasing age, with more than 10 million people affected worldwide². Genetic and environmental factors, such as pollution and pesticides, contribute to the increased risk of PD. There is no cure for PD to date, and management lies in therapies such as medicines, rehabilitation, and surgery to limit the progression of the disease³.

Artificial intelligence (AI) has emerged as a solution for PD patients, as technologies can delay or improve PD symptoms⁴. Various AI applications have been developed for the management of PD, such as deep-learning-based pose estimation algorithms (Convolution Pose Machines) to detect disease severity or levodopa-induced dyskinesia, clinical decision support systems, Microsoft Kinect multimodal off-the-shelf sensors to assess adherence to drug treatment, epiNet, a novel artificial gene regulatory network to monitor movement, robotic systems and AI in gait management, and home-based telemedicine systems for diagnosis and management of PD⁵-⁷. These technologies help improve the quality of life of patients with PD and reduce the financial burden on them.

AI chatbots have helped to get a better understanding of patient responses in PD. AI chatbots are technologies that utilize automatic speech recognition and natural language processing to simulate communication with users. The use of AI chatbots in healthcare has been increasing in recent years⁸. The 24-h availability of chatbots can reduce the burden of healthcare workers involved in the management of PD patients by collecting patients’ health information daily and facilitating patient communication⁹. AI chatbots have been found to enhance smiles and speech in PD patients. Smile and speech features, in turn, may help to detect the motor, cognitive, and mental status of PD patients¹⁰.

Available data on AI chatbots highlights their potential as a promising solution for managing PD. AI chatbots can assess adherence to drug treatment and be incorporated into telemedicine systems for improved diagnosis and management of PD. AI-assisted apps incorporating chatbots can be developed to communicate with PD patients. There is a lack of research on the use of AI chatbots in treating PD, suggesting the need for future research in this area.

DATA AVAILABILITY STATEMENT

The datasets generated and/or analyzed during the current study are available from the corresponding author upon reasonable request.

REFERENCES

• ¹ Tolosa E, Garrido A, Scholz SW, Poewe W. Challenges in the diagnosis of Parkinson's disease. Lancet Neurol. 2021;20(5):385-97. https://doi.org/10.1016/S1474-4422(21)00030-2
  » https://doi.org/10.1016/S1474-4422(21)00030-2
• ² Tysnes OB, Storstein A. Epidemiology of Parkinson's disease. J Neural Transm (Vienna). 2017;124(8):901-5. https://doi.org/10.1007/s00702-017-1686-y
  » https://doi.org/10.1007/s00702-017-1686-y
• ³ Vijiaratnam N, Simuni T, Bandmann O, Morris HR, Foltynie T. Progress towards therapies for disease modification in Parkinson's disease. Lancet Neurol. 2021;20(7):559-72. https://doi.org/10.1016/S1474-4422(21)00061-2
  » https://doi.org/10.1016/S1474-4422(21)00061-2
• ⁴ Perju-Dumbrava L, Barsan M, Leucuta DC, Popa LC, Pop C, Tohanean N, et al. Artificial intelligence applications and robotic systems in Parkinson's disease (Review). Exp Ther Med. 2022;23(2):153. https://doi.org/10.3892/etm.2021.11076
  » https://doi.org/10.3892/etm.2021.11076
• ⁵ Li MH, Mestre TA, Fox SH, Taati B. Vision-based assessment of parkinsonism and levodopa-induced dyskinesia with pose estimation. J Neuroeng Rehabil. 2018;15(1):97. https://doi.org/10.1186/s12984-018-0446-z
  » https://doi.org/10.1186/s12984-018-0446-z
• ⁶ Shamir RR, Dolber T, Noecker AM, Walter BL, McIntyre CC. Machine learning approach to optimizing combined stimulation and medication therapies for Parkinson's disease. Brain Stimul. 2015;8(6):1025-32. https://doi.org/10.1016/j.brs.2015.06.003
  » https://doi.org/10.1016/j.brs.2015.06.003
• ⁷ Tucker CS, Behoora I, Nembhard HB, Lewis M, Sterling NW, Huang X. Machine learning classification of medication adherence in patients with movement disorders using non-wearable sensors. Comput Biol Med. 2015;66:120-34. https://doi.org/10.1016/j.compbiomed.2015.08.012
  » https://doi.org/10.1016/j.compbiomed.2015.08.012
• ⁸ Jadczyk T, Wojakowski W, Tendera M, Henry TD, Egnaczyk G, Shreenivas S. Artificial intelligence can improve patient management at the time of a pandemic: the role of voice technology. J Med Internet Res. 2021;23(5):e22959. https://doi.org/10.2196/22959
  » https://doi.org/10.2196/22959
• ⁹ Conte L, Lupo R, Lezzi P, Pedone A, Rubbi I, Lezzi A, et al. Statistical analysis and generative Artificial Intelligence (AI) for assessing pain experience, pain-induced disability, and quality of life in Parkinson's disease patients. Brain Res Bull. 2024;208:110893. https://doi.org/10.1016/j.brainresbull.2024.110893
  » https://doi.org/10.1016/j.brainresbull.2024.110893
• ¹⁰ Ogawa M, Oyama G, Morito K, Kobayashi M, Yamada Y, Shinkawa K, et al. Can AI make people happy? The effect of AI-based chatbot on smile and speech in Parkinson's disease. Parkinsonism Relat Disord. 2022;99:43-6. https://doi.org/10.1016/j.parkreldis.2022.04.018
  » https://doi.org/10.1016/j.parkreldis.2022.04.018

Edited by

• Editor-in-Chief:
  Sonia M. D. Brucki. https://orcid.org/0000-0002-8303-6732

• Associate Editor:
  Jacy Bezerra Parmera. https://orcid.org/0000-0002-3565-5328

Publication Dates

• Publication in this collection
  03 Apr 2026
• Date of issue
  2026

History

• Received
  02 July 2025
• Accepted
  14 Dec 2025