SN6006 Information Technology in Healthcare Lecture Notes PDF

Document Details

EnchantedCharoite6373

Uploaded by EnchantedCharoite6373

The Hong Kong Polytechnic University

Justin Tse

Tags

mobile technology healthcare brain-computer interface lecture notes

Summary

These lecture notes cover mobile and wearable applications in healthcare, including mobile integrated healthcare (MIH), mobile technology for patients and doctors, challenges and trends, and brain-computer interfaces (BCIs).

Full Transcript

SN6006 Information Technology in Healthcare School of Nursing The Hong Kong Polytechnic University Lecture 11: Mobile & Wearable Applications and Brain-Computer Interface Lecturer: Justin Tse ([email protected])...

SN6006 Information Technology in Healthcare School of Nursing The Hong Kong Polytechnic University Lecture 11: Mobile & Wearable Applications and Brain-Computer Interface Lecturer: Justin Tse ([email protected]) 11 November 2024 Content Part 1: Mobile and Wearable Applications Mobile Integrated Healthcare (MIH) Mobile Technology for Patients and Doctors Challenges and Trends Part 2: Brain-Computer Interface (BCI) BCI Concept and Various Application Common Types of BCIs Brain Signal (EEG) Processing Recent BCI and Ethical Consideration Revision 2 Mobile and Wearable Applications 3 Intended Learning Outcomes (Part 1) Describe the evolution from personal digital assistance to smartphones and the emergence of mHealth Introduce the various ways mobile technology is currently being used in healthcare Compare and contrast mobile technology for patients and doctors Recognize challenges and trends of mobile technology in healthcare 4 History of Mobile Technology Primitive mobile phones arose in the 1970s. 2G cellular networks appeared in Finland in the early 1990s. Adoption with 3G cellular networks became a reality around 2000. 3G cellular networks started to be commercialized around 2010. 4.5G, 5G… high speed and high capacity communication 5 History of Mobile Technology https://iot.telenor.com/technologies/evolution-mobile-technology/ 6 Mobile Devices Personal digital assistants (PDAs) – Apple Newton PDA – Palm Pilot 1000 – Epocrates http://www.epocrates.com/ PDAs to Smartphones – One platform – Same functions 7 Smartphone Definition: – Has an operation that can support the execution of third party applications. – Capable of hosting medical software (note that more and more medical programs will be hosted in the cloud and not on the device). mHealth is increasingly accessible Smartphones enable healthcare Patient engagement is often mobile 8 Mobile Integrated Healthcare The Patient Protection and Affordable Care Act – Improving patient experience of care – Improving the health of populations – Reducing the per capita cost of healthcare MIH is the provision of healthcare using patient- centered, mobile resources in the out-of-hospital environment that are integrated with the entire spectrum of healthcare and social service resources available in the local community Fully integrated, collaborative, supplemental, data driven, patient-centered… 9 Text Messaging or (need) Short Message Service (SMS) Used for: Appointment reminders Education Disease management Behavior modification Medication compliance Laboratory results notification Public health 10 First Aid Apps Disaster Preparedness Apps 11 Mobile Software or Apps for Patients Apple app store and google play Connected with healthcare system – Group Health 12 https://www.apple.com/hk/en/ios/health/ 13 Mobile and Wearable Applications Discussion (10 minutes) In a group of 4-6 members, discuss the mobile apps and/or wearable applications you have used (healthcare related) Arrange one group member to share your discussion result with the whole class: 1. Name 1-2 apps/wearable applications 2. Briefly introduce the apps and major features 3. How do you feel about it? Recommended? 14 Mobile Software or Apps for Patients (need) Mind fitness and mental health Immunization guides Disease management Diagnostic Drug information Calculators Diagnostic Image viewer Monitoring 15 Mobile Software or Apps for Patients (need) Mind fitness and mental health – Cognitive training and relieve stress – Brain Trainer, BioZen, Breathe2Relax… Immunization guides – Guide for what immunizations are needed based on age and gender, other important information Disease management – Monitors meal, blood sugar and insulin doses – Blood pressure cuff or weight scale sends results to iPhone or iPdad – Diabetes Manager, iHealth BPM https://www.youtube.com/watch?v=GUplk0JOAUc 16 Mobile Software or Apps for Patients (need) Diagnostic – Phone camera takes picture of skin lesion and estimate risk of malignant melanoma – MelApp https://www.youtube.com/watch?v=QKLlUadGt38 17 Mobile Software or Apps for Doctors (need) Drug information – Drug library, drug interactions… – Epocrates, Medscape… https://www.medscape.com/ Calculators – Perform multiple common calculations: MedCalc – Calculate 10 year risk of heart disease based on risk factors: Framingham risk scores – Blood gas interpretation: ABG Interpreter 18 Mobile Software or Apps for Doctors (need) Diagnostic – Electronic eye chart: Eye Chart Pro – Using iPhone plus hardware to take pictures of retina: iExaminer – Portable ultrasound: Mobisante Ultrasound https://www.youtube.com/watch?v=902lg1fhV9M Image viewer – Mobile access to image server: Resolution MD mobile, Mobile MIM – Work with cloud Monitoring – Mobile views of multiple physiologic parameters: AirStrip https://www.airstrip.com/ 19 Wearable Devices Tech Fashion Medical Sport 20 Wearable Devices https://mobisoftinfotech.com/resources/blog/wearable-technology-in-healthcare/ 21 Key Facts about Wearable Devices https://www.businessinsider.com/wearable-technology-healthcare-medical-devices 22 Wearable Devices Wearables for Preventive health Medical consultation Medication management Tracking pulse and blood pressure for stress monitoring Minute-to-minute monitoring of chronic disease conditions 23 Micro-electromechanical sensors (need) The availability of small, cheap, micro-electromechanical sensors (MEMS) has rocketed. MEMS Shipments 2007 – 10 million 2014 – 3.5 billion 2020 – 300 billion They measure movement, position, temperature, activity and vital signs, but only cost a few tens of cents. Initially developed for cars, they’re now in every smartphone, tablet and wearable device. 24 The Internet of Things The glue binding these together is Analysts predict over 50 billion connected devices will be in use by 2020, generating a tsunami of personal data. A significant proportion of those could be wearable devices. 25 The Internet of Things Pebble Watch: $10M 26 Wireless Body Area Network Wearable health monitoring systems integrated into a telemedicine system Continuous monitoring as a part of a diagnostic procedure Support early detection of abnormal conditions and prevention of its serious consequences Provides supervised recovery from an acute event or surgical procedure 27 Wireless Body Area Network Sensor level Personal Server Level Medical Service Level 28 Mobile Technology Challenges and Trends Security will always be an issue so additional protection such as encryption is necessary. Inputting information is inconvenient and slow: speech recognition Small screen size Interoperability Regulatory Trends: more devices, more convenient interactions, integrating with cloud… 29 Brain-Computer Interface (BCI) https://www.youtube.com/watch?v=7t84lGE5TXA 30 Intended Learning Outcomes (Part 2) Acquire the concepts of Brain-Computer Interface (BCI) Introduce various applications of BCIs Introduce the common types of BCIs – Invasive, Partially-invasive, Non-invasive BCIs Brain Signal (EEG) Processing Future of BCI: Technical Challenges Ethical Considerations 31 Introduction to BCI (need) A brain–computer interface (BCI) is a interdisciplinary field that seeks to explore direct communication pathway between brain and external device Translate a measure of a user’s brain activity into messages or commands for an interactive application. The term BCI was coined in the 1970s. 32 BCI Technology and its Historical Event (no need) 33 Applications Developing technologies for people with disabilities: – Need to develop hardware and software to disable people for restoring lost sensory and motor function Assist blind people to visualize external images Assist paralyzed people to operate external devices without physical movement Decode information stored on human brain (as memory) Decode information from brain to display human thinking or dream on a screen 34 Sensory Restoration: Hearing Cochlear implant 35 Sensory Restoration: Sight Cortical and Retinal implant 36 Sensory Restoration: Somatosensation Somatosensation 37 Sensory Restoration: Olfaction and Taste Artificial nose 38 Motor Restoration Prosthetic devices 39 Cognitive Restoration: Seizures Seizure forecasting system 40 Rehabilitation (need) Rehabilitating patients recovering from a stroke, surgery, or other neurological conditions – BCI would be part of a close-loop feedback system that converts brain signals into a stimulus on a computer screen or into movements of a rehabilitative device. 41 Brain-Controlled Wheelchairs Control a wheelchair directly by brain signals 42 Robotic Avatars Robotic Avatars – “Avatar” and “Surrogates” – Assist paralyzed and disabled individuals in performing various tasks in day-to-day life 43 Monitoring Alertness (need) Monitoring Alertness – Monitoring the alertness of humans during the performance of critical but potentially monotonous tasks such as driving or surveillance. 44 Gaming and Entertainment Gaming and Entertainment 45 Basic Concepts: Neurons A neurons is a type of cell that is generally regarded as the basic computational unit of the nervous system. When the neuron receives sufficiently strong inputs from other neurons, a cascade of events is triggered Rapid rise and drop of membrane potential: action potential or spike Firing rate: number of spikes per second Neurons are therefore often modeled as emitting a 0 and 1 digital output. 46 Classification of BCI Brain Signal Pattern – A brain signal is a set of electrical impulses that flows on groups of active neurons. – P300 event-related potentials (ERPs): reach a maximum positive peak in voltage about 300ms after a stimulus onset. P300 ERPs require little initial training Evoked by visual, auditory, tactile, olfactory and gustatory paradigms – Steady-state evoked potentials (SSEPs), which are the electrical activity of the brain in response to stimulation of specific sensory nerve pathways, as distinct from spontaneous potentials. Steady-state auditory evoked potentials (SSAEP) Steady-state visually evoked potentials (SSVEP) Steady-state somatosensory evoked potentials (SSSEP) 47 Recording Method for Use of BCI (need) Recording Method for Use of BCI: – Invasive – Partially invasive – Non Invasive Invasive: – Implanted directly into the grey matter of the brain during neurosurgery Partially-Invasive: – Partially invasive BCI devices are implanted inside the skull but rest outside the brain rather than within the grey matter Non-Invasive: – Implanted outside the skull 48 Invasive BCI Implanted directly into the grey matter of the brain during neurosurgery Targeted repairing damaged sight – Providing new functionality to persons with paralysis produce the highest quality signals Vision Science: The Human Brain – Direct brain implants have been used (Lennon, J. 2010) to treat non-congenital (acquired) blindness – William Dobelle was one of the first scientists to come up with a working brain interface to restore sight 49 Partial Invasive BCI Implanted inside the skull but rest outside the brain – Produce better resolution signals than non- invasive BCIs having a lower risk of forming scar- tissue in the brain than fully-invasive BCIs. Examples: – Electrocorticography (ECoG) – Light Reactive Imaging BCI 50 Partial Invasive BCI (Continues) Electrocorticography (ECoG) – Measures the electrical activity of the brain taken from beneath the skull – Electrodes are embedded in a thin plastic pad that is placed above the cortex, beneath the dura mater. First trialed in humans in 2004 by Eric Leuthardt and Daniel Moran – Enabled a teenage boy to play Space Invaders using ECoG implant: Controls are rapid, and requires minimal training 51 Partial Invasive BCI (Continues) Light Reactive Imaging BCI – Light Reactive Imaging BCI devices are still in the realm of theory – Involve implanting a laser inside the skull. – Laser is trained on a single neuron and the neuron's reflectance measured by a separate sensor. When the neuron fires, the laser light pattern and wavelengths would change Advantages of Partial Invasive BCI – Better signal to noise ratio – Higher spatial ratio – Better Frequency Range 52 Non-Invasive BCI Although the waves are still detectable, it is hard to determine the area of the brain or the neuron that created the signal Examples: – Electroencephalography (EEG) – Magnetoencephalography (MEG) – Magnetic resonance imaging (MRI) 53 Non-Invasive BCI One of the most popular noninvasive neurophysiological recording techniques This method measures electrical activity in the brain through the use of surface electrodes placed on the scalp Advantages of EEG Most studied potential non-invasive interface Fine temporal resolution Ease of use Portable Low setup cost 54 Non-Invasive BCI Magnetoencephalography (MEG) MEG is a technique for mapping brain activity by recording magnetic fields produced by electrical currents occurring naturally in the brain Despite MEGs having better spatial resolution and very similar temporal resolution to EEG, they are used less in BCI research due to the nonportability and high cost – In addition, MEG requires highly sensitive instrumentation and sophisticated methods, such as a magnetically shielded room for eliminating environmental magnetic interference. Application : – Localizing the regions affected by pathology, before surgical removal – determining the function of various parts of the brain 55 Non-Invasive BCI Magnetic resonance imaging (MRI) MRI is a technique used in radiology to visualize detailed internal structures Functional MRI or fMRI is a type of MRI scan that measures the hemodynamic response (change in blood flow) related to neural activity in the brain or spinal cord – fMRI allowed two users being scanned to play Pong in real-time – by altering their haemodynamic response or brain blood flow Recent research in ATR (Advanced Telecommunications Research, in Kyoto, Japan) on fMRI – Allowed the scientists to reconstruct images directly from the brain and display them on a computer. https://zhuanlan.zhihu.com/p/75042882 56 Improving Signal Quality The raw signals recorded from the brain during the signal acquisition stage often contain other information reduces signal quality. – Environmental sources: power line electrode contact device drift – Physiological sources: eye blink heart rate motion 57 Enhancing EEG Signals via VR While research on the brain–computer interface (BCI) has been active in recent years, how to get high-quality electrical brain signals to accurately recognize human intentions for reliable communication and interaction is still a challenging task. Investigate the effect of using object-oriented movements in a virtual environment as visual guidance on the modulation of sensorimotor EEG rhythms generated by hand MI. 58 Future of BCI Challenges have to overcome in Hybrid BCI architectures User-machine adaptation algorithms BCI reliability analysis by exploiting users’ mental states BCI performance analysis and confidence measures Incorporate HCI to improve BCI Development of novel EEG devices Integration of new findings in neuroscience into BCI https://www.dw.com/en/whats-the-future-of-brain-computer-interfaces/video-65804607 59 Hybrid BCI Improve Non-invasive BCI based assistive technologies Develop Hybrid BCI (hBCI) – Severe motor disabilities do not allow people to have full benefit of current assistive products. BCI + Assistive Enhancement Products (AP) hBCI approach The hBCI needs “at least” one BCI channel to work: other channel(s) can be AP input/biosignals or another BCI channel 60 Dynamic Adaptation Dynamic Adaptation  Two-level adaptation process First Level 2nd level Self Adaptation Dynamic Adaptation The best interaction channel The best EEG phenomena that each should be dynamically chosen user better controls should be dynamically chosen: P300 or SSVEP This necessitates the development of novel training protocols to determine the optimal EEG phenomenon for each user, working on psychological factors in BCI. 61 Improving BCI Outputs Improvement needs on current BCI outputs – Current BCI Low bit rate, Noisy and has less reliability Promising solution: – To adjust the “dynamics of BCI”, modern Human-Computer Interaction (HCI) principles can be used Alternative solution: – Use “shared autonomy (or shared control)” to shape the dynamics between user and brain-actuated device such that tasks are able to be performed as easily as possible. 62 Users’ Condition BCI assisted technology can benefit from the recent research on the following- – Recognition of user’s “mental states” – Mental workload, stress, tiredness, attention level – Recognition of user’s “cognitive processes” – Awareness to errors made by the BCI This is another aspect of “self-adaptation. the dynamics and complexity of the Example: High mental interaction will be simplified workload OR Or stress level it will trigger OFF brain interaction and move on to muscle-based interaction 63 Portable Equipment There are challenges to develop easy-to-use and aesthetic EEG equipment. Issues to address: Portability Aesthetic design Aesthetic and engineering design should be merged. One key issue for any practical BCI for disabled people. Users don’t want to look unusual  social acceptability Example of advanced devices: Dry electrodes instead of gel 64 Neuroscience and Neuroengineering Some of these obstacles arise because of a growing separation between neuroscience and neuroengineering. Much of modern neuroscience research operates at the cortical level, so it is difficult to leverage this basic science research in BCIs that use noninvasive recordings because those BCI data are recorded from outside the head. Methods to connecting the new findings of neuroscience and the recordings obtained outside the head. 65 Usability Evaluation A suggested classification structure of BCI usability – User: Demographics, Knowledge/experience, Impairment – Task: Type of tasks, Description of task – Environment: Modality, Location – Technology: BCI signature type, Acquisition device, BCI application – Method: Inspection method, Testing method, Inquiry method – Measurement: Subjective measure, Objective measure 66 Usability Evaluation (need) Three core constructs for the measurement of usability: – Efficiency: Degree to which the product enables the tasks to be performed in a quick, effective, and economical manner, or hinders performance – Effectiveness: Accuracy and completeness with which specified users achieved specified goals in a particular environment – Satisfaction: The degree to which a product gives contentment. 67 Some Recent BCI http://spectrum.ieee.org/biomedical/bionics/brainco mputer-interface-eavesdrops-on-a-daydream/ Scientists from Germany, Israel, Korea, the United Kingdom, and the United States have performed combined experiments: – Are able to monitor individual neurons in a human brain associated with specific visual memories – Display visual memory onto a television monitor, and to replace with another – Scientists have found a neural mechanism equivalent to imagination and daydreaming the mental creation of images overrides visual input 68 Some Recent BCI The researchers inserted microwires into the brains of patients with severe epilepsy as part of a pre-surgery evaluation to treat their seizures The subjects were interviewed after the surgery about places they’d recently visited or movies or television shows they’d recently seen: – images of the actors or visual landmarks the subjects had described are shown on a display – Slides of the Eiffel Tower, for instance, or Michael Jackson—who had recently died at the time of the experiment—would appear on a screen. 69 Some Recent BCI Technical Challenges: – about 5 million neurons in the brain encode for the same concept, Cerf says. – Need to decode 5 millions neurons to get the complete picture We are only able to read a limited number (for example: 64 ) Complexity of Neural network (Lennon, J. 2010) 70 Ethical Considerations There has not been a vigorous debate about the ethical implications of BCI Important topics in neuroethical debate are: – Risk/benefit analysis – Obtaining informed consent – Possible side effects and consequences in life styles for the patient relatives Professor Michael Crutcher expressed concern about BCI specially for ear and eye implants: – “If only the rich can afford it, it puts everyone else at a disadvantage” 71 Ethical Considerations (Continues) Clausen concluded in 2009: – “BCIs pose ethical challenges, but these are conceptually similar to those that bioethicists have addressed for other realms of therapy” Recently more effort is made inside the BCI community to initiate the development of ethical guidelines for BCI research, development and dissemination Requirements for the social acceptance: – Sound ethical guidelines – Appropriately moderated enthusiasm in media coverage – Education about BCI systems 72 Conclusions Brain Computer Interaction is: – Send outside signal to brain neuron vision signal for blind person – Read the neuron signal To operate external devices without physical intervention To read memory or display user imagination Significant progress in last ten years – Technical challenges need to be overcome Significant potential uses in medical science to assist physically disabled persons 73 Conclusions Some challenges should be addressed before wide use in practice – Equipment and hardware – Signal enhancement – Generality and adaptation – Evaluation and Usability – Practical Validation 74 Reflection Would you share one point you have learnt in this session? 75

Use Quizgecko on...
Browser
Browser