The Future of Healthtech RESHAPED 2024

For COPD-patients, adequate remote monitoring is key to predict and prevent so-called exacerbations (flare-ups of symptoms) which may lead to harmful and costly hospitalisations, and can be avoided by intervention with corticosteroids and/or antibiotics. The problem is huge: in Europe and the US there are approximately 53 million people suffering from COPD corresponding to 66B€ of annual healthcare costs. Shortness-of-breath, the primary assessment signal for COPD patients, is today hardly and poorly monitored: it is either graded visually by a doctor, or graded by the patient itself on a scale of 0-10. We solve the underlying long standing problem: the absence of a device to objectively, frequently, and remotely measure the respiration pattern of a patient. Our technology is based on measuring the pressure-variations in the nose of a patient during two minutes of normal breathing twice a day by means of a standard nasal cannula, and converting these pressure data into medically recognised flow-volume curves. Two clinical studies in 3 hospitals in the Netherlands indicate that exacerbations can be detected or predicted in time. This can have a large impact on the healthcare system.

Medical wearables are revolutionizing healthcare by empowering patients with continuous health monitoring and data collection. To provide quality data, these devices require technical advancements, exploring how integrated biosensors capture real-time physiological data from biomarkers non-invasively.There are various types of medical wearables, from smartwatches tracking activity to vital sign monitoring. Combining different technologies of biosensors, skin adhesives and communication tool open the capabilities of personalized medicine and preventive care. We will address the technical challenges surrounding medical wearables, providing a glimpse into the future of this rapidly evolving field.

Photoplethysmography (PPG), now ubiquitous within wearables of all form-factors, has become the workhorse of biometric wearable sensor technology. Once limited to the resting use case of fingertip pulse oximetry in hospitals and clinics, contemporary innovations have liberated PPG technology for use in a diversity of form-factors (earbuds, wrist devices, armbands, smart rings, patches, eye-wear, etc.) and a diversity of free-living use cases, spanning from exercise monitoring in sports and fitness to continuous medical monitoring in telehealth. Moreover, the artificial intelligence (AI) revolution has positioned PPG at the heart of sensor fusion applications, where numerous miniaturized, orthogonal sensors contribute towards advanced biometric monitoring solutions. While many technical challenges confronting the scalability of PPG in wearables have been addressed over the past decade, many still remain. Limitations associated with PPG motion artifacts have become so stubbornly endemic that many manufacturers have simply “thrown-in the towel” in making meaningful improvements, thereby precluding important new use cases. Additionally, PPG has faced challenges in enabling accurate medical monitoring across a broad diversity of patients having a broad diversity of physical characteristics, such as differences in skin tone and vascular health. Fortunately, through a combination of thoughtful use case planning, modern technical innovations, and comprehensive clinical experimental design, these challenges can be overcome. Ultimately, PPG of the future will provide data that is more accurate (for all form-factors and activities), more available (for all use cases), and more generalizable (for a broad diversity of patient populations), enabling medical use cases that improve patient health, make life easier for medical professionals, and reduce lifetime healthcare costs for healthcare payors.

The integration of advanced biometric technologies into health monitoring has the potential to revolutionize how we approach personalized healthcare. This presentation will explore the emerging field of in-ear infrasonic biometrics, focusing on its applications in continuous and non-invasive health monitoring. By harnessing the power of infrasonic sound waves, we can obtain deep physiological insights that were previously unattainable with conventional methods.This talk will delve into the science behind in-ear infrasonic sensing, its advantages over traditional optical sensors, and its role in the future of health monitoring. As we move towards a more connected and health-conscious society, the ability to monitor critical health parameters in real-time, with minimal intrusion, will be key to unlocking new levels of preventive care and personalized treatment.

​

​

The use of machine learning to transform raw vital sign sensor data into objective health-related symptoms represents an important advancement for remote patient monitoring. This is especially valuable in women’s health which has traditionally been underserved by healthcare systems. Women’s health needs exist throughout the lifespan and many are not disease-related. Menopause is a life transition experienced by every woman and in the 5-10 years before menopause, known as perimenopause, women experience a broad range of symptoms that negatively impact their quality of life, health, and work productivity. Critically, untreated, these symptoms also place women at a increased risk of chronic disease post-menopause. There is no objective way to diagnose perimenopause and clinicians have to validate self-reported symptoms from women in the clinic. This leads to an underdiagnosis of perimenopause, leading women to require unnecessary visits to clinicians and for hospital procedures, while suffering unnecessarily with symptoms. The objective detection of perimenopausal symptoms is an ideal application of machine learning, based on vital sign sensor data. This approach can utilise the features from different sensors to develop specific algorithms for individual symptoms, rather than just relying on physiological responses, for example heart rate; thereby differentiating between perimenopausal symptoms and other daily events such as exercise. Predictive accuracy is crucial in managing perimenopausal symptoms and machine learning algorithms are capable of continuous learning, meaning they can adapt and improve over time as they process more data. The objective detection of perimenopausal symptoms will lead to earlier diagnosis, better and personalised management, a reduction in the number of hospital-based procedures and, most importantly, empower women with information about their symptoms that will allow them to live healthier and more productive lives, for longer.

​

Hearing loss affects over 1.5 billion people globally, with an annual economic impact exceeding $980 billion. While medical treatments remain limited, technological solutions have evolved dramatically from the early days of ear horns to today's sophisticated devices. This talk explores how artificial intelligence (AI) is reshaping the future of hearing assistance, promising to revolutionize hearing healthcare for millions. We'll briefly survey the state of hearing technology before AI and how AI is driving the next transformative leap in this field. We'll define AI in the context of hearing assistance, contrast it with traditional approaches, and showcase its diverse applications—from automatic scene analysis and live captioning to advanced noise removal and speech enhancement. Looking ahead, we will examine the future directions of AI-driven hearing technologies and what is being worked on today. Join us to discover how AI is poised to transform hearing healthcare, reduce the global burden of hearing loss, and potentially serve as a model for AI integration across various healthtech domains.

​

For this talk I will go through neurological disorders such as Parkinson’s disease and describe some of the ways we have been using to understand them.The OxQUIP (Oxford QUantification In Parkinsonism) study has been recruiting patients with Parkinson's Disease and Progressive Supranuclear Palsy. Currently available treatments for these diseases are symptomatic only, and do not have any preventive or disease-slowing effect. As new drugs are developed, we need to be able to evaluate them quickly, so that precious time and resources can be devoted to those showing most promise. In our work we use various types of wearables to quantify such abnormalities present in these disorders coupled with classical machine learning techniques.

As the conversation around brain implants heats up, we introduce a groundbreaking alternative: neural earbuds. In this presentation, we will reveal how these cutting-edge, non-invasive devices can seamlessly control computers, wheelchairs, and video games—offering unparalleled safety, comfort, and ease of use. By harnessing the power of facial microgestures, neural earbuds can rival the performance of the most advanced brain implants, particularly for individuals with limited but functional head mobility. Attendees will gain a comprehensive understanding of neural earbuds' capabilities, comparing them against traditional brain implants, and witness their potential to transform voice-free, touch-free, and screen-free interaction. This raises a critical question for the tech and medical industries: “Should people with upper-body mobility but without severe neurodegenerative conditions be recommended brain implants before exploring safer, non-invasive options like neural earbuds?” Join us to explore the future of neural interfaces, where innovation meets accessibility.

​

AI has become a catch all word for everything from ChatGPT, large language models, machine learning, and neural networks, to routine data analysis or robotic process automation. The clinical trials industry has been evolving over the years with the adoption of electronic data capture, decentralized clinical trials, site less clinical trials, and remote patient monitoring, In this presentation, we explore the evolving landscape of artificial intelligence in clinical research. We will examine how AI technologies are currently applied across various stages of clinical trials, from patient recruitment to data analysis and beyond. The presentation aims to separate the realistic impacts from the overhyped expectations, providing a balanced view of AI's capabilities and limitations. By analyzing real-world case studies and empirical data, attendees will gain insights into how AI can truly enhance clinical trial efficiency, accuracy, and outcomes, distinguishing between practical applications and common misconceptions in the field. Question is - who is well positioned to take advantage of AI in clinical research?