Improvement and Innovation Showcase 35: Diagnostic Tools for General Medicine Patients with Shortness of Breath
Iain Bertram, Data Scientist, Commission on Excellence and Innovation in Health
Machine learning is a technology that's rapidly becoming pivotal to healthcare to improve the accuracy of diagnoses, personalise health care, and find solutions to problems. ML can assist clinicians in identifying anomalies, patterns, and trends while also helping to reduce human error.
In this episode, Iain shares his work with the CEIH to develop a machine learning model for diagnosing general medicine patients with shortness of breath.
Iain is a Professor of Particle Physics and worked at Lancaster University from 1999 -2022. Before joining The CEIH Iain spent his time using machine learning on extremely big data sets to investigate the fundamental properties of the Universe, such as the structure of the proton, “Why is the universe made of matter instead of antimatter?”, and is there something weird lurking just beyond reach. Iain is now using this experience to use machine learning to improve health outcomes in South Australia.
Improvement and Innovation Showcase 36: AI's Influence on Healthcare, a Disruptive Force
Lucie Marsh-Smith, Senior Manager - Digital Design, Innovation and Change, Southern Adelaide Local Health Network.
The healthcare landscape is in the midst of a disruptive transformation, all thanks to the infusion of Artificial Intelligence (AI). Join us as Lucie delves into the ever-evolving synergy between AI and healthcare. Together, we'll explore the enormous potential, current applications, and future prospects AI brings to this vital industry.
Lucie has a comprehensive and diversified background in Digital Health with over seven years of hands-on experience in Digital Health SA and CALHN.
Lucie's career trajectory includes a noteworthy stint of 11 years as the Director of Technology at Blue Box IT in the United Kingdom, where she honed her expertise in leading technology-driven initiatives.
Lucie is currently pursuing a Ph.D. program at the University of South Australia, with a research focus on Digital Innovation and AI's pivotal role in revolutionising healthcare on a global scale.
Improvement and Innovation Showcase 37: Natural Language Processing to Predict Hospital Discharge, Derivation, Validation and a Case for Implementation
Samuel Gluck, Medical Administration Registrar, Northern Adelaide Local Health Network
The ability to predict when a patient is likely to be discharged will help clinical teams to ensure the patient is ready. Sam's solution uses RAH data to derive an NLP algorithm, validated in both the RAH and QE, that predicts the likelihood of discharge within 48 hours. Sam's team is conducting an implementation study at RAH and QEH to assist with identifying patients who will be ready for discharge at the weekend.
Sam Gluck is a duel RACMA and CICM trainee. He grew up in Wales and trained in Cambridge, undertaking anaesthetic training in the NHS prior to emigrating to Australia in 2013. He has just completed a PhD in the use of passive smartphone data in the measurement of patient outcomes. Sam is well published in machine learning and natural language processing and when not working he can be found restoring a small part of the Adelaide Hills to native bushland with his wife and 2 young sons.
Improvement and Innovation Showcase 38: Statewide Deep-Learning Models to Estimate Length of Stay
Alex Al-Saffar, Data Scientist, Southern Adelaide Local Health Network.
Hospital length of stay (LoS) of patients is a crucial factor for the effective planning and management of hospital resources. There is considerable interest in predicting the length of stay in order to improve patient care and increase service efficiency.
Alex has developed a tripartite deep learning model for statewide LoS Estimation at the time of patient admission. The model performance exceeds a model that unrealistically utilizes the DRG of the patient. The model is re-trained for every service of SA Health to provide LoS for all patients with zero input from any clinician.
Dr Alex completed his PhD on Data-driven techniques for biomedical electromagnetic imaging at The University of Queensland in 2021. He has a patent imaging neural network and is currently working with SALHN as data-scientist. Alex's interest span mathematics, statistics & programming and He's the author and maintainer of multiple Python packages.