Tech Bundle

AI In Healthcare

Artificial Intelligence (AI) in healthcare explores the AI systems which can be consisted of sensors, AI hardware and AI software. Sensors explore detection tools that integrated with AI system to diagnose and monitor one’s health. AI Hardware explores the chipset design and architecture, rather than algorithms, to achieve the next big breakthrough in AI. AI software explores computer program which mimics human behaviour by learning various data patterns and insights. Shaped by the AI systems, AI-powered technologies and its applications, such as personalized implants, AI-assisted personalized rehabilitation, AI-assisted robotic surgery, wireless body sensor networks and AI-powered assistive technologies may soon become a reality.

Clinically validated mobile-based digital psychotherapy for stress and mental wellbeing
Mental health has become one of the biggest risk factors in accelerating illness and accounting for the largest component in occupational health claims. Managing mental health-related issues often require individuals’ conscientious efforts to seek suitable treatment regime including psychotherapy, which may be dependent on the availability of therapists or mental health practitioners. This calls for alternative solutions that can support individuals for managing their mental wellbeing, thereby improving their quality of life.  Digital therapeutics (DTx) are evidence-based therapeutic interventions for the prevention, management or treatment of medical conditions or diseases, including mental health-related issues. These include digital self-management implementations in formats such as mobile apps, sensors, virtual reality, or other tools to prompt behavioral changes in users. Aiming as a transformative DTx to improve health and reduce healthcare-associated costs, the current technology is a clinically proven digital mobile-based psychotherapy tool that collectively measures certain physiological parameters as an objective digital biomarker of stress. With its implementation in smartphones and mobile apps, this provides ease of accessibility to individuals for his/her objective stress assessment. The technology is currently a CE Class I Medical Device and is approved with GDPR, HIPPA, PHIPA, ISO 13485, ISO 9000 and ISO 27001. The Singapore-based technology owner has completed three clinical trials in use cases including cancer, anxiety and athletic endurance.  The technology owner is seeking potential licensees, including players in telemedicine sector, pharmaceutical companies or insurance companies who may have interests to license their stress digital biomarkers via API/white label, and/or the associated proprietary technology.
AI-Based Medical Imaging Assistant For Breast Cancer Screening
Breast cancer is one of the leading causes of mortality in the world and the most commonly occurring cancer in women. On average, one in 11 women will be affected by breast cancer in their lifetime, with more than 2.3 million women diagnosed in the year of 2020 alone. Early detection has the potential to save lives by significantly enhancing the survival rates as the chances of recovery drops significantly beyond stage 2 of the disease. Many countries have established screening programs for breast cancer as measures for early disease detection, as well as implemented relevant reimbursement schemes for supporting these programs. Among various screening methods, 2D mammography has been found to be the most accurate way of conducting such programs for large populations. However, there still lies challenges with existing mammography screening including inefficiencies in current clinical care workflow causing long waiting periods and inaccuracies in manual reading interpretation. The technology addresses these issues by augmenting the existing clinical workflow for radiologists diagnosing breast cancer by first, allowing for faster mammogram readings, and second eliminating the requirement for double-blind reading per screen for each diagnosis. The AI assistive technology tops in Asia for its proven AI algorithm for breast cancer detection at one of the highest AUC accuracy levels of 0.96, and is capable of reducing false positives for dense breast in Asian women.
Tactile Sensing Glove
A tactile sensing glove embedded with multiple tactile sensors can measure each sensing point’s applied pressure and its corresponding position. Its pressure sensing layer is constructed with multiple rows and columns of piezoresistive sensing points. The piezoresistive sensor’s electrical resistance decreases when a pressure is applied on it. The tactile sensing glove can be put on a robotic gripper or prosthetic device to receive haptic feedback during manipulation tasks.
Dedicated Neural Network Accelerator for IoT Edge Processing
This technology offer is a small, secure, low power and cost-effective hardware module with a dedicated convolutional neural network (CNN) accelerator. The hardware accelerator supports many pre-trained artificial intelligence (AI) models, allowing edge processing at the IoT sensor node itself. As such, real time AI inference can be done without the need for high bandwidth communications to the cloud. Simple API calls through one of many communication interfaces makes adding AI capability to IoT nodes an easy task.
Noninvasive Intracranial Pressure (ICP) Monitor
Head injuries are a significant cause of injury and death, with approximately 50,000 cases of severe traumatic brain injury per year in the UK, the majority leading to death or severe disability. Cerebral damage sustained at the time of impact is referred to as primary injury and is irreversible and best treated by prevention (seatbelts, cycle helmets etc). Secondary brain injury occurs after the initial injury and is defined as damage arising from the body’s physiologic response to the primary injury. As the skull is a closed cavity containing water and other largely incompressible material, even minor swelling can cause significant increases in ICP (intracranial pressure). Various strategies exist to arrest or reverse the pressure in the brain due to head trauma, so monitoring the ICP is a vital tool in the management of severe head injuries. A new non-invasive system for continuous monitoring of ICP via a forehead-mounted probe has been developed. Although the cranium is a closed rigid structure, interrogation using infrared light provides a potential ‘window’ for monitoring cerebral haemodynamics. The probe contains infrared light sources that can illuminate the deep brain tissue of the frontal lobe, while photodetectors in the probe detect the backscattered light, which is modulated by pulsation of the cerebral arteries. Changes in the pressure surrounding the cerebral arteries affect the morphology of the recorded optical pulse, so analysis of the acquired signal using an appropriate algorithm will enable calculation of non-invasive ICP (nICP) that can be displayed continuously to clinicians.
Non-invasive Breath Tests for Lung Cancer Early Detection
A Singapore company has developed a non-invasive breath analysis device and test to detect early stage lung cancer by collecting and analysing a patient's exhaled breath. According to The National Lung Screening Trial Research Team, 80% of lung cancer cases are diagnosed at late stage when the 5-year survival rate is only 5%. If detected at stage 1, the survival rate can be increased to 80%. Current diagnostic techniques such as Computer Tomography (CT) are not able to capture most of the early stage cases because the tumour at this stage is too small to be distinguished. This non-invasive breath-based solution analyses the Volatile Organic Compounds (VOC) in a patient's exhaled breath to detect the changes in metabolic activities caused by lung cancer. In the pilot clinical trial, the breath analyser with machine learning algorithms was able to detect more early stage lung cancer cases than current diagnostic techniques.
Artificial Intelligence (AI) Platform for Digital Therapeutics and Brain Fitness Solutions
The platform assists and empowers health care professionals, researchers and third-party developers to develop their own solutions with an Artificial Intelligence (AI) driven platform. The AI platform works seamlessly with the company's award-winning portable EEG headset to provide developers with the ability to analyze the brain signals of users; measuring mental states including but not limited to attention, relaxation, mental workload and fatigue.  The technology reveals numerous potential avenues to explore complementary, intervention programs for mental wellness, such as Attention Deficit Hyperactivity Disorder (ADHD) in children, rehabilitation programs for stroke patients, cognitive rehabilitation for seniors and other neurological issues. 
Artificial Intelligence Enhanced Millimeter-Wave Indoor Real-time Location System
There is a need in healthcare delivery for higher accuracy location sensing at low costs. The Covid-19 pandemic has highlighted the need for accurate contact tracing to identify at-risk individuals. Furthermore, hospitals demand globally continues to outstrip capacity growth, and therefore technological solutions are required to: 1) more quickly allocate bed spaces, to reduce patient length-of-stay and increase patient throughput; 2) more efficiently find resources, to save staff time and decrease working capital; 3) more effectively monitor room occupancy, patient-staff interactions, and wait times, to better use valuable hospital space and optimise contact time. We have developed a system to use sensor mesh networks of IoT devices — based on millimetre-wave technology coupled with artificial intelligence (AI) — to provide more accurate indoor real-time location sensing (RTLS) for improved contact tracing, patient flow and equipment finding in hospitals. The deployment of these technologies can improve healthcare delivery and patient outcomes, while reducing costs.
Robotic Capsule Endoscope for GI Tract Inspection
The capsule endoscope (CE) has revolutionised gastrointestinal (GI) tract inspection. Traditional endoscopy requires a camera on the end of a cable to be inserted into the patient, with understandable anxiety prior to the procedure, additional risk during the procedure, and considerable discomfort both during and after the procedure. In contrast, CEs are pill-like miniature cameras, taken orally like any pill medication in an easy and angst-free manner, prior to travelling through the body and imaging the GI tract with minimal discomfort. Using these images, clinicians can make routine diagnoses of a range of diseases, including bowel cancer, Crohn’s Disease and ulcerative colitis, to name a few. However, CEs travel through the digestive system in a passive manner. This limits the utility of the device in terms of speed, positioning and overall control. Therefore, a capsule endoscope capable of locomotion has been developed by our researchers. Using impact forces, friction in the GI tract is overcome and allows control over speed and positioning when inspecting the GI tract. Further, the underlying locomotion technology is likely applicable for delivery of other cargo, such as other miniaturised medical devices or drugs.