Dr. Bipasha Kashyap, Ph.D., veski fellow, M.E., B.E.
Lecturer, Deakin University’s School of Engineering, Australia
[Cover Image source – https://www.freepik.com/free-vector/digital-health-technologies-flat-composition_7272631.htm#query=healthcare%20technology&position=4&from_view=search&track=sph]
Precision medicine is a rapidly evolving field in healthcare, focused on delivering individualised treatments to patients based on their unique characteristics. Biosignals, including audio, inertial measurement unit (IMU) signals, and physiological signals obtained through biosensors, are critical components in precision medicine. The utilisation of Artificial Intelligence (AI) has the potential to greatly enhance the analysis of these signals, enabling the processing of large amounts of data with high accuracy and speed.
In speech analysis, AI algorithms can be trained to recognize patterns in audio signals that indicate speech disorders or other health issues. For instance, changes in speech patterns, tone, or pitch can be detected by AI algorithms and used to alert healthcare professionals. IMU signals generated by sensors that measure body movements and orientation provide valuable insights into an individual’s physical activity levels and mobility. AI algorithms can process IMU signals and detect changes that may suggest a decline in mobility or physical activity, which may indicate the onset of neurological disorders such as Cerebellar Ataxia and Parkinson.
Wearable biosensors can continuously monitor physiological signals like heart rate and blood pressure, and AI algorithms can analyse these signals in real-time to detect changes that may indicate health issues, like heart attacks, or identify patterns in the data that are not easily recognizable by human experts. This continuous monitoring can provide early warning signs and allow for early intervention, potentially leading to better health outcomes.
One of the significant benefits of AI in biosignal analysis for precision medicine is the potential for cost and time savings in medical research. Automated analysis of biosignal data through AI algorithms can free up researchers’ time to focus on other critical tasks, such as developing new treatments and drugs. In addition, AI algorithms can analyze vast amounts of data more efficiently and identify new treatment options that might not have been apparent to human experts.
AI algorithms can also enhance the accuracy of personalised treatment plans. By training machine learning algorithms on individual patients’ biosignal data, AI algorithms can determine the most effective treatment plan for a specific condition, leading to improved health outcomes and reduced costs for both patients and healthcare providers. In addition, AI algorithms can continuously monitor patients and adjust treatment plans as needed, leading to even more personalised care.
The integration of Field-Programmable Gate Array (FPGA) and cloud-based architecture can further enhance the capabilities of AI in biosignal analysis. FPGAs can process data in real-time with low latency, making them well-suited for real-time biosignal analysis. In addition, the cloud provides an infrastructure for the storage, processing, and sharing of large amounts of data, making it an ideal platform for AI-based biosignal analysis.
In conclusion, AI holds significant potential for advancing biosignal analysis in precision medicine. The ability of AI algorithms to process large amounts of data with high accuracy and speed, as well as their potential to reduce the cost and time of medical research, makes AI a promising tool in the field of precision medicine. The integration of FPGAs and cloud-based architecture can further enhance the capabilities of AI algorithms in biosignal analysis. The development and testing of AI algorithms must be conducted carefully to ensure their safety and efficacy, but if done properly, AI has the potential to revolutionise the way healthcare is delivered.
Johnson, K.B., Wei, W.Q., Weeraratne, D., Frisse, M.E., Misulis, K., Rhee, K., Zhao, J. and Snowdon, J.L., 2021. Precision medicine, AI, and the future of personalized health care. Clinical and translational science, 14(1), pp.86-93.
Uddin, M., Wang, Y. and Woodbury-Smith, M., 2019. Artificial intelligence for precision medicine in neurodevelopmental disorders. NPJ digital medicine, 2(1), p.112.
Wang, L. and Alexander, C.A., 2020. Big data analytics in medical engineering and healthcare: methods, advances and challenges. Journal of medical engineering & technology, 44(6), pp.267-283.
Kashyap, B., Phan, D., Pathirana, P.N., Horne, M., Power, L. and Szmulewicz, D., 2020. Objective assessment of cerebellar ataxia: A comprehensive and refined approach. Scientific reports, 10(1), p.9493.
Kashyap, B., Pathirana, P.N., Horne, M., Power, L. and Szmulewicz, D.J., 2021. Modeling the Progression of Speech Deficits in Cerebellar Ataxia Using a Mixture Mixed-Effect Machine Learning Framework. IEEE Access, 9, pp.135343-135353.
Dr. Bipasha Kashyap is a Lecturer in Mechatronics at Deakin University’s School of Engineering. Before her academic career, she served as an Applied Machine Learning Research Engineer for the NSBE Research Group at Deakin, leading a team on a Medical Research Future Fund (MRFF) project to commercialise medical-grade assistive devices. She has received recognition for her contributions to the field of Applied AI in eHealth, including the prestigious Veski Fellowship, Data61 Ph.D. Scholarship from CSIRO, completion of her Ph.D. in Biomedical Engineering, a M.E. degree in Electronics and Management Engineering, and a B.E. degree in Electronics, both with first-class honours. Dr. Kashyap has also been profiled in the media and published in Q1 scientific journals.
Major Media highlights:
https://www.deakin.edu.au/research/research-news-and-publications/articles/from-fighting- corrosion,-to-using-milk-to-improve-mental-health,-deakins-3mt-and-vyt-winners-are-set-to- make-an-impact