****I think that the best senior design projects will involve automating some process.
****It would also be fulfilling to develop a medical device to improve my own condition.
SUMMARY
********https://docs.google.com/document/d/1lVbAIerSifOm9Dm4_DX6fpNnmf6cswkUBbtTklOAC68/edit
- Reducing the cost of IGG Infusions, mechanism for taking unique dosages and infusing over unique periods of time
- Lawn Mowing Rumba, solar-powered
- Reducing Subjectivity - Improved Monitoring of Lungs
- Reducing Subjectivity - Quantifying Pupil Reactivity
- Developing a Medication Assistance Device to Reduce Noncompliance With Prescription Medication
- Automating / At-Home the pulmonary function test
- Automating / At-Home Skin Cancer Exam
- Smart Wireless Power Desk
- Lifting Posture / Form Monitoring Device / Monitoring curvature of lower back
- Reducing the frequency of incorrect implant sizing / Making cheaper prosthetics so available to poor in developing countries
- (Athletic Induced) Asthma Diagnosis - Fitness Respiration Monitor
- Improving Hospital Efficiency / CHOPtimization
- Improving engineering skills in children
- Concussions in Sports
- Homeless Swollen Limbs
- Solar Water Disinfection
- Fake News
- Smart House Technology
- Optimizing Penn's Events
A Sleep Detection and Prevention System for Automobile Drivers
Hydration Monitor like Pulse Oximeter
Early Detection of Diseases (Bronchitis, Pneumonia, etc.) - Option #1
http://auscultaid.wixsite.com/auscultaid
The physical exam of the lung holds enormous potential for early and noninvasive detection of diseases. When done efficiently, physicians can hear signs of conditions like pneumonia, bronchitis and chronic obstructive pulmonary disease (COPD). Unfortunately, the physical exam presents many challenges to physicians and is underutilized.
AUSCULTAID is a complementary alternative to the current physical exam that helps physicians get more out of this traditional procedure, particularly for high-risk patients.
With AUSCULTAID, hear everything you've been missing.
The Problem
“Robust
acoustic devices…may provide the long-awaited portable
objective means to record, analyze, and store lung sounds.” - New England
Journal of Medicine, February 2014
Imagine you’re trying to describe a
song to someone, but you can only use words. Now imagine that a patient’s
diagnosis depends on the accuracy of your description. This is what auscultation, the process of listening to lung sounds,
is like today. Auscultation is the ubiquitous first step in detecting signs of
lung pathologies, yet it relies on qualitative descriptors like “moist” and
“musical.”
The highly subjective process can
vary widely between doctors, and for a high-incidence disease like
community-acquired pneumonia, auscultation has a positive predictive value of
at most 57%, meaning that almost half of the patients who are told that
something is wrong are not actually sick.
High numbers of false positives lead
to significant unnecessary treatment and testing. Preventable, follow-up chest
x-rays for pneumonia alone cost hospitals $830 million a year. Many patients
are also given prophylactic antibiotics, which add up at an average of
$40/course and contribute to the growing problem of antibiotic
resistance.
Proposed Solution
The AUSCULTAID solution simultaneously records sounds across the entire lung and provides analysis in an intuitive user interface. We offer doctors a quantitative measure of sound intensity, as well as a color-coded classification of the sounds as normal or adventitious. All of the lobes can be covered in a single breath, and the intensity values can be used for accurate comparison between different regions. The device is made of disposable diaphragms and reusable microphones and ensures that every patient gets a comprehensive exam.
Given the problems with the traditional approach to auscultation of the lung, we envision several key benefits arising from our solution. Our initial target market is the outpatient setting of high-volume hospitals, where our device would reduce the amount of unnecessary testing and treatment. This would allow doctors to spend more time with patients who are actually sick. We believe future versions of our device could also be tailored to make a powerful impact in two other clinical environments: the emergency room and the intensive care unit.
The following pages will take you through our engineering design process, our plans for integrating this solution into the current cycle of care, reimbursement, and regulatory landscape, and finally our projected next steps.
Engineering and Design
From Concept to Completed Prototype
Design Inputs
Through interviews with physicians, searches of the research literature, and many brainstorming sessions, we identified several functional requirements, constraints, and customer needs, all of which can be summarized in three primary design inputs:
1. Increase the sensitivity and specificity of auscultation
2. Identify regions with abnormal sounds
3. Integrate with current clinical practice
User Experience
Our final prototype balances ease of use and accuracy of placement by integrating ten transducers into a single system of straps. The patient puts the straps on themselves and tightens them as necessary, then the doctor places adhesive diaphragms at the correct anatomical locations. The diaphragms attach to the microphones with snap-in connectors, and the entire set up can be completed in under a minute and a half.
Once the device is in position, the doctor simply instructs the patient to breath and records for any length of time through our intuitive user interface. After the recording is complete, the results fill the diagram of the lung. Each number is a normalized intensity value and each of the four colors expresses how confident the software is that the sound is normal or adventitious. Clicking on each location allows for playback of the sound, and all the data can be saved for longitudinal comparison.
How It's Done
In order to make this happen, we performed some analog filtering and amplification to clean up the sounds and built a software classification program to identify normal and adventitious sounds. Through frequency analysis of a database of over 100 pre-recorded lung sounds, we identified two main features that could be used to classify normal and adventitious sounds. The first feature was a ratio of the energy in low versus high frequencies, and the second feature was based on the maximum energy in the 500-700 Hz range. Together these features formed two-dimensional classifier shown in the graph to the right.
Testing Outcomes
The classifier was validated using a leave-m-out testing protocol, and the sensitivity and specificity of our program were found to be consistently above 90%.
The ability of our device to localize regions of abnormal sound was tested by selectively playing a sound with a frequency characteristic of adventitious sounds at one location, while playing sounds with frequencies characteristic of normal sounds everywhere else. The success of this test proved that the device functions properly as a whole - from the wiring of the microphones and circuitry, to the analysis algorithms written in the code, to the visual output designed in the user interface.
Our final test was an assessment of the form factor of our device, or in other words, how easy it is to wear and how accurately it positions the transducers on patients of different sizes. We had several patients of varying heights, weights and genders try on our device and successfully concluded that the device could be easily adjusted to place the transducers at the correct locations across the lungs.
Integration into Current Practice
The users of our device will be physicians, nurses, and other healthcare technicians, and their needs and abilities shaped our design. However the customers we will be pitching our device to our hospitals and insurance companies, because they are the ones who will truly see the savings of this technology. Hospitals will be able to offer a higher standard of care, and insurance companies will save money by not having to pay for unnecessary treatment and testing.
Our direct competitors are the traditional and electronic stethoscope. AUSCULTAID provides more information than either of these systems, but we don't predict it will replace these current modes. Our goal is to offer a more comprehensive alternative for high-risk patients. Given that all adults over the age of 65 are considered high-risk for lung diseases like pneumonia, the high-risk patient still offers a significant market.
To lower barriers to adoption, we modeled our system on the equivalent process of performing an electrocardiogram. Like an ECG, AUSCULTAID comprises disposable chestpieces and reusable electronics. Doctors we spoke too were pleased by the familiar feel and form of this novel technology. The device will be offered at a competitive one-time, capital cost of $100, with the disposable diaphragms costing $5 per patient per use. In comparison, an electronic stethoscope sells for at least $300.
We anticipate our device falling under the Ambulatory Payment Classification New Technology Policy, which will allow our product to be added on to an existing reimbursement code - dramatically shortening the time to get approved for reimbursement to as few as four months after clinical benefit is shown.
Moving Forward
Our immediate future will be focused on optimizing and improving our prototype. A few specific things we're exploring are improving the resolution of our coverage of the lungs by adding more transducers, identifying more features to strengthen our classifier, and collecting and training our software on a larger pool of normal lung sounds.
We plan to apply for an FDA Class II Investigative Device Exemption in order to shorten the regulatory pathway to get our device approved. While the approval process is underway, we will get IRB approval to begin studying our device in the hospital setting. Clinical studies will allow us to evaluate how our device performs on actual sick patients, as well as how it's received by doctors and other healthcare workers. Based on these results, we will do further iterations of product development and testing until our customers needs are met.
After successful clinical trials and FDA approval, expect to see us on the market by 2017.
*****Neuroptics Device
Early Detection of Bronchitis / Skin Cancer
- Using sonar to model bronchioles
- skin cancer examination, compares image to thousands of pictures of skin cancer moles and indicates if a doctor should observe
Concussions in Sports
- Penn's concussion center
High Cost of Immunotherapy Infusion / Irregular IGG Levels
- IgG infusion pump
Homeless swollen limbs
- pants which improve bloodflow circulation
Developing a Medication Assistance Device
to Reduce Noncompliance With Prescription Medication
https://www.bme.cmu.edu/ugprog/design/2017Medbot2Go.pdf
Our mission: to solve the problem of noncompliance with
prescription medication and medical treatment.
Close to 70% of Americans take at least one prescription
medication, and more than half of them take two or more.
Our proposed solution includes:
a medical bracelet that will interface
a prescription medication storage system
a record of the patient’s medicine regimen
provide a reminder mechanism to ensure patients know
when to take their medication and the administration
mode.
After researching the potential users, we decided on
targeting the elderly generation, who had not been
exposed much to technology. Therefore, the device does
not operate on smartphones, or wifi, which most elderly
people are not comfortable using.The product consists of
two parts: a wristband, and a chain of pillboxes. A website
is also designed for the product. The user should wear the
wristband and carry the pillboxes that contain the pills they
are to take when they leave their home. The wristband can
be used as a watch and a reminder for medication taking.
1. When it is time to take a medication, the wristband will
vibrateand the corresponding LED on the pill box that
contains the pills to be taken will light up.
2. When the user has taken the pill, the LED will turn off, and
the intake will be recorded. The website contains a schedule
that shows the time all medications are scheduled, and the
history of medication intake.
3. When the users get a new prescription, they will be able to
update the schedule and what medication is stored in which
pillbox. The medicine schedule could be performed on the
website by the caregiver, physician, family member or the
patient themselves.
Portable
Does not require technological background to use
Does not require to be connected to WiFi
Makes a medical intake history file
Automatic Medication Dispensing System
https://www.bme.cmu.edu/ugprog/design/2017MedBotHome.pdf
Motivation: •Medication organization and administration has
become a growing issue in the United States for
older adults (65 and older)
•~30% of hospital admission of older adults are
drug related
•>11% due to medication
noncompliance
•17% related to adverse drug reactions
•Noncompliance includes forgetting to take
medications or improper administration of the drug
– both behaviors that may be present in either
healthy or ill elderly individual
Current devices:
•Have a limited web interface that prevents elderly
adults from documenting their given medication
•Require presorting medication
•Frequent monitoring of device
Solution:
•A device that sorts and administers medications to the
patient at the appropriate time in an easily accessible
location, such as the kitchen
•MedBot-Home achieves this through a web application
and home device
Lifting Posture/Form Monitoring Device
- monitor curve of the spine
- monitor angle between the quads and back
- alert the user when their form is incorrect
Developing a Medication Assistance Device to Reduce Noncompliance With Prescription Medication
Lifting Posture/Form Monitoring Device
Improving Hospital Efficiency / CHOPtimization
- go to CHOP and ask for optimization-related senior design projects
- nurses are getting laid off. it is more important now than ever to improve hospital efficiencies
- goal is to help improve the way the facility performs
- analyze for improvement to create work standards
- help fine-tune processes and management of care
-organize pre- and post-operative care processes
- help improve OR efficiency through LEAN proversses and change management
-manage to standards to help ensure compliance
-report metrics
1) Real-Time Tracking
- host system interface supplies case and patient data
- RTLS tags track patients, staff and critical equipment
- tracks and manages patients, rooms, beds, providers, staff and equipment assignments in real-time
2) Proactive Alerting
- Alerts are issued proactively to coordinate activities before delays occur
3) Dynamic Rescheduling
- Continuously reschedules activities and assignments as day unfolds
- coordinates all personnel facility-wide and beyond
Personalized Solutions / Prosthetic / Implants
- Take a photogrammetric scanner to obtain surface geometry
- by pairing the right implant with a personalized fit, you get a truly tailored experience
- templating allows the healthcare provider to determine implant size in advance; this is designed to result in fewer implants and instruments, with a goal to increase operating room efficiencies.
- personalized positioning guides streamline total knee and total shoulder replacement surgery and reduce instrumentation by ensuring reproducible guide fixation.
- alignment technology helps the healthcare provider align implants to each patient's unique anatomy without preoperative imaging.
****Reducing the frequency of incorrect implant sizing
****Making cheaper prosthetics so available to poor in developing countries
There are approximately 5.5 million transfemoral,
or upper leg limb amputees in impoverished areas
worldwide. Usually caused by industrial or environmental
accidents, land-mines, and the lack of public health, a leg
amputation debilitates an individual in a way few other
amputations do, through immobilization and an increase
in their reliance on others.
The Foot Fighters created a low-cost transfemoral
prosthetic leg for amputees in developing countries, at an
estimated price point of $27. This project will offer users a
chance to continue their day-to-day activities like caring
for themselves and engaging in the workforce.
Above Elbow prosthetic
Fitness Respiration Monitor
In the current market of personal fitness monitors, there is not currently an
affordable and accurate device that notifies the user of dangerous breathing rates
and breathing depths as they occur.
To design a comfortable and functional
breathing monitor for use during exercise.
Exercise enthusiasts can wear this device
and be notified in real time through vibration
feedback if they are not breathing deeply
enough or often enough.
Solar Water Disinfection
Improving engineering skills in children
-build your own animal and have it develop a personality over time
-robots with personalities
Smart House Technology
- Automated / solar powered rumba
Wireless Power Desk
- demo with a mouse pad
- Countertop that detects a chargeable device and activates the magnetic field in that area, enable all my laptop's and keyboards and speaker and phones be charging at the same time on my desk, detects batteries and applies a magnetic field around it.
Fake News
Optimizing Penn's Events
- An app which optimizises any universities' events. Takes data from schedules and number of students enrolled. then optimizes the time at which faculty/school holds events based off of student course schedules. Takes data from penn in touch.
