Artificial intelligence in healthcare: past, present and future.

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.

A scanned, focused, multiple transducer ultrasonic system for localized hyperthermia treatments. 1987.

A commercial diagnostic ultrasound scanner (Octoson) was modified for performing hyperthermia treatments. The temperature elevations were induced in tissues by four large, focused ultrasonic transducers whose common focal zone was scanned along a computer controlled path as determined from B-scan images. The system is described and the results of preliminary tests demonstrating some of its capabilities are given. Extensive tests with canine thighs and kidneys were performed. The blood flow to the kidneys was controllable, and thus tumours having different blood perfusion rates could be simulated. The results showed that the system is capable of inducing a local temperature maximum deep in tissues (up to 10 cm was tested) and that tissues with high perfusion rates could be heated.

Hyperthermia classic commentary: 'A scanned, focused, multiple transducer ultrasonic system for localised hyperthermia treatments', by K. Hynynen, R. Roemer, D. Anhalt, et al., International Journal of Hyperthermia 1987;3:21-35.

This commentary reviews the development of image-guided focused ultrasound treatments since the publication of the above paper. The impact of the research presented in the paper on the development of the current image-guided noninvasive surgery and treatments will also be discussed.

TIES that BIND: an introduction to domain mapping as a visualization tool for virtual rehabilitation.

The application of virtual reality (VR) to rehabilitation is a young, interdisciplinary field where clinical implementation very rapidly follows scientific discovery and technological advancement. Implementation is often so rapid that demonstration of intervention efficacy by investigators, and establishment of research and development priorities by funding bodies tend to be more reactive than proactive. An examination of the dynamic unfolding of the history of our young discipline may help us recognize the facilitators of current practice and identify the barriers that limit greater progress. This paper presents a first step towards the examination of the past and future growth of VR-based rehabilitation by presenting the use of concept maps to explore the publication history of application of VR to rehabilitation.

Computer treatment for common mental health problems.

Perhaps the most complex and controversial role for the computer in clinical practice is as a treatment medium in which the computer effectively replaces the psychotherapist. This article outlines the historical development of computer treatment, from dialogue generators in the 1960s through to the interactive, multimedia programs of the 2000s. In evaluating the most recent developments in computer treatment, we present a small meta-analytic study demonstrating large effect sizes in favor of computer treatments for anxiety and depression for pre/post outcomes and treatment as usual/waitlist comparators. Next, we review studies of the cost effectiveness of computer treatments. Finally, we outline the implications for research, policy, and practice of this new generation of treatment options.

Selected as the best paper in the 1990s: Reducing frailty and falls in older persons: an investigation of tai chi and computerized balance training.

OBJECTIVES: To evaluate the effects of two exercise approaches, tai chi (TC) and computerized balance training (BT), on specified primary outcomes (biomedical, functional, and psychosocial indicators of frailty) and secondary outcomes (occurrences of fall). DESIGN: The Atlanta Frailty and Injuries: Cooperative Studies and Intervention Techniques, a prospective, randomized, controlled clinical trial with three arms (TC, BT, and education (ED)). Intervention length was 15 weeks, with primary outcomes measured before and after intervention and at 4-month follow-up. Falls were monitored continuously throughout the study. SETTING: Persons aged 70 and older living in the community. PARTICIPANTS: A total of 200 participants, 162 women and 38 men; mean age was 76.2. MEASUREMENTS: Biomedical (strength, flexibility, cardiovascular endurance, body composition), functional instrumental activities of daily living (IADL), and psychosocial well-being (Center for Epidemiological Studies for Depression scale, fear of falling questionnaire, self-perception of present and future health, mastery index, perceived quality of sleep, and intrusiveness) variables. RESULTS: Grip strength declined in all groups, and lower extremity range of motion showed limited but statistically significant changes. Lowered blood pressure before and after a 12-minute walk was seen following TC participation. Fear of falling responses and intrusiveness responses were reduced after the TC intervention compared with the ED group (P=.046 and P=.058, respectively). After adjusting for fall risk factors, TC was found to reduce the risk of multiple falls by 47.5%. CONCLUSION: A moderate TC intervention can impact favorably on defined biomedical and psychosocial indices of frailty. This intervention can also have favorable effects upon the occurrence of falls. TC warrants further study as an exercise treatment to improve the health of older people.