Posters
« Back
Machine Learning: A New Breakthrough in Medical Diagnosis
EP30196
Poster Title: Machine Learning: A New Breakthrough in Medical Diagnosis
Submitted on 28 May 2019
Author(s): Punitha Mahendran, Anis Joelaira, Chai Yong Chia, Fazidatul Aziz, Hasyimah Emran, Siew Fun Lee, Wai Kit Wong, Yee Yan Tang, Li Yang Wong
Affiliations: Department of Biomedical Science, Faculty of Medicine, University of Malaya, Kuala Lumpur, Malaysia
This poster was presented at The CUBE, Faculty of Medicine, University of Malaya
Poster Views: 658
View poster »


Poster Information
Abstract: According to the World Health Organization (WHO), 5% of adult patients in USA encountered diagnostic errors (delayed, missed or wronged) in 2015, mainly due to inefficient integration of health information technologies and inadequate support of diagnostic processes by the existing healthcare system. Time-consuming diagnostic process will eventually delay patient triage. Furthermore, massive increase of complex biological datasets poses an urgent need for high-level analysis. Therefore, technology and healthcare innovators had brought in machine learning (ML) as a strategy to optimize and improve the current diagnostic processes. ML is a branch of artificial intelligence where machine is programmed to learn patterns from data and make decisions with minimal human intervention. It has demonstrated a life-impacting potential in medical diagnosis, primarily in the field of oncology, pathology, ophthalmology and cardiology. Currently, in cancer study, Augmented Reality Microscope (ARM) based on convolutional neural network, can detect breast cancer metastases in lymph nodes by outlining tumor regions on whole slide image, facilitating the screening process and decreasing the workload for pathologists. Besides, application of deep learning and visual analytic technologies help in early detection of diabetic retinopathy, which is a leading cause of blindness in diabetic patients. In medical image analysis, ML algorithm analyzes 3-D medical scans and provides meaningful comparison in almost 1,000 times shorter duration than conventional analysis. Correspondingly, comprehensive algorithmic analysis of retinal fundus image caters prediction of multiple cardiovascular risk factors, including age, gender and systolic blood pressure, which facilitate the risk stratification in cardiovascular disease management. In conclusion, integration of ML in medical diagnosis primes a great promise in pertaining maximal diagnostic accuracy whilst facilitating the diagnostic process entirely. Unfortunately, collection of overwhelming large datasets from various biological aspects for ML algorithm training remains the major challenge.Summary: A poster on machine learning as a new medical invention for improving medical diagnosis in the future.References: Balakrishnan, G., Zhao, A., Sabuncu, M. R., Guttag, J., & Dalca, A. V. (2018). An unsupervised learning model for deformable medical image registration. In Proceedings of the IEEE conference on computer vision and pattern recognition(pp. 9252-9260).
Camacho, D. M., Collins, K. M., Powers, R. K., Costello, J. C., & Collins, J. J. (2018). Next-generation machine learning for biological networks. Cell.
Orion health. (2019). Introduction to machine learning in healthcare. Retrieved from http://web.orionhealth.com/rs/981-HEV-035/images/Introduction_to_Machine_Learning.pdf
Poplin, R., Varadarajan, A. V., Blumer, K., Liu, Y., McConnell, M. V., Corrado, G. S., ... & Webster, D. R. (2018). Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nature Biomedical Engineering, 2(3), 158.
Sedai, S., Tennakoon, R., Roy, P., Cao, K., & Garnavi, R. (2017, April). Multi-stage segmentation of the fovea in retinal fundus images using fully convolution
Report abuse »
Questions
Ask the author a question about this poster.
Ask a Question »

Creative Commons