Author
Hong Kuan Kok
Other affiliations: Royal College of Surgeons in Ireland, Northern Hospital, Beaumont Hospital ...read more
Bio: Hong Kuan Kok is an academic researcher from Deakin University. The author has contributed to research in topics: Medicine & Aneurysm. The author has an hindex of 14, co-authored 86 publications receiving 897 citations. Previous affiliations of Hong Kuan Kok include Royal College of Surgeons in Ireland & Northern Hospital.
Topics: Medicine, Aneurysm, Stent, Stroke, Interventional radiology
Papers
More filters
TL;DR: An overview of the theory behind ML is provided, the common ML algorithms used in medicine including their pitfalls are explored and the potential future of ML in medicine is discussed.
Abstract: Machine learning (ML) is a burgeoning field of medicine with huge resources being applied to fuse computer science and statistics to medical problems. Proponents of ML extol its ability to deal with large, complex and disparate data, often found within medicine and feel that ML is the future for biomedical research, personalized medicine, computer-aided diagnosis to significantly advance global health care. However, the concepts of ML are unfamiliar to many medical professionals and there is untapped potential in the use of ML as a research tool. In this article, we provide an overview of the theory behind ML, explore the common ML algorithms used in medicine including their pitfalls and discuss the potential future of ML in medicine.
285 citations
TL;DR: A general computational model of an ECR service, which can be used to optimize resource allocation for interventional treatment of acute ischemic stroke and large vessel occlusion is developed.
Abstract: Objective: Endovascular clot retrieval (ECR) is the standard of care for acute ischemic stroke due to large vessel occlusion. Performing ECR is a time critical and complex process involving many specialized care providers and resources. Maximizing patient benefit while minimizing service cost requires optimization of human and physical assets. The aim of this study is to develop a general computational model of an ECR service, which can be used to optimize resource allocation. Methods: Using a discrete event simulation approach, we examined ECR performance under a range of possible scenarios and resource use configurations. Results: The model demonstrated the impact of competing emergency interventional cases upon ECR treatment times and time impact of allocating more physical (more angiographic suites) or staff resources (extending work hours). Conclusion: Our DES model can be used to optimize resources for interventional treatment of acute ischemic stroke and large vessel occlusion. This proof-of-concept study of computational simulation of resource allocation for ECR can be easily extended. For example, center-specific cost data may be incorporated to optimize resource allocation and overall health care value.
216 citations
TL;DR: Attention to sample size, overfitting, underfitting, cross validation, as well as a broad knowledge of the metrics of machine learning, can help those with little or no technical knowledge begin to assess machine learning studies.
Abstract: OBJECTIVE. Machine learning (ML) and artificial intelligence (AI) are rapidly becoming the most talked about and controversial topics in radiology and medicine. Over the past few years, the numbers...
170 citations
TL;DR: Proactive and preventative strategies such as oral nimodipine and endovascular rescue therapies can reduce the morbidity and mortality associated with CV.
79 citations
TL;DR: Endovascular treatment of VRAA is associated with excellent technical success and visceral preservation rates, and major complication and periprocedural mortality rates are comparatively low.
49 citations
Cited by
More filters
01 Dec 2017
TL;DR: The current status of AI applications in healthcare, in the three major areas of early detection and diagnosis, treatment, as well as outcome prediction and prognosis evaluation, are surveyed and its future is discussed.
Abstract: Artificial intelligence (AI) aims to mimic human cognitive functions. It is bringing a paradigm shift to healthcare, powered by increasing availability of healthcare data and rapid progress of analytics techniques. We survey the current status of AI applications in healthcare and discuss its future. AI can be applied to various types of healthcare data (structured and unstructured). Popular AI techniques include machine learning methods for structured data, such as the classical support vector machine and neural network, and the modern deep learning, as well as natural language processing for unstructured data. Major disease areas that use AI tools include cancer, neurology and cardiology. We then review in more details the AI applications in stroke, in the three major areas of early detection and diagnosis, treatment, as well as outcome prediction and prognosis evaluation. We conclude with discussion about pioneer AI systems, such as IBM Watson, and hurdles for real-life deployment of AI.
1,785 citations
01 Jan 1998
TL;DR: In most cultures, there are strong standards regarding sexual behavior which differ for men and women, and cultural differences also affect the extent to which early sexual behavior is considered acceptable.
Abstract: Developing and implementing successful interventions often depend upon effectively addressing ethnicity and social class factors, as these influence sexual behavior and its risks. Sexual attitudes differ across cultures. In most cultures, there are strong standards regarding sexual behavior which differ for men and women. Cultural differences also affect the extent to which early sexual behavior is considered acceptable.
919 citations
Journal Article•
699 citations
25 Mar 2020
TL;DR: 1.2 Structured summary of study design, methods, results, and conclusions.
Abstract: 2 Structured summary of study design, methods, results, and conclusions
415 citations
TL;DR: Based on the specific prediction task evaluated and the type of input features included, ML models predicted outcomes after neurosurgery with a median accuracy and area under the receiver operating curve of 94.5% and 0.83, respectively.
263 citations