Hardware components | ||||||
 |
| × | 1 | |||
 |
| × | 1 | |||
| × | 1 | ||||
| × | 1 | ||||
 |
| × | 1 | |||
Software apps and online services | ||||||
| ||||||
 |
| |||||
 |
| |||||
 |
| |||||
Hand tools and fabrication machines | ||||||
 |
| |||||
 |
| |||||
Menopause, also known as the climacteric, is the time in most women's lives when menstrual periods stop permanently, and they are no longer able to bear children. Menopause typically occurs between 45 and 55 years of age. Medical professionals often define menopause as having occurred when a woman has not had any menstrual bleeding for a year. It may also be defined by a natural decline in reproductive hormone production by the ovaries when a woman reaches her 40s or 50s.
Recent studies show that many of the symptoms are undetected as menopausal symptoms and a majority of women are unwilling to disclose their symptoms even to personal physicians and this makes the situation worse. Some of the symptoms are-
Night sweats
Osteoporosis
Hot Flashes
Incontinence
Mood Swings and many more...
Currently there is no definite cure to this condition and neither is there a way to alleviate certain specific symptoms
The underlying philosophy was to take all the good features in the products available in this market and design something that is -
- Affordable
- Minimalist
- Able to treat many symptoms
- Hardware complemented with insightful software
Most of the products currently available are-
- Expensive
- Target mainly one symptom
- Rely on data that the user has to feed in herself(quite annoying)
- Overly complicated and hence tough to mass-produce(Here I may be wrong)
- Placebo???
I want to build a device that tries to overcome all this by targeting many symptoms like hot flashes, osteoporosis, mood swings, incontinence, sexual discomfort, skipped periods and hormonal imbalance. It would log important biophysical parameters to implement augmented reality techniques to deliver valuable, anonymous and timely advice to the user. The user`s progress would be monitored and important notifications issued in pseudo-scientific manner through a connected mobile application and cloud facility and on the touch screen display that would double up as a smart band
The idea is to develop wearable modules in minimal form factors consisting of-
- 9DOF accelerometer
- Communication module(Wi-Fi, BT etc.)
- Temperature sensor
- Power source
- MCU for processing and sending data collected
- Cooling mechanism
Such modules would be placed at the extremities of the body in the form of rings to be worn on the fingers and the toes. One module attaches or clips to the inside of the user`s collar and one in the pelvic region. Please hold on!! I will explain the role of each part and the modules` placement. The extremities were specifically chosen as research shows that these are the regions that are most sensitive to temperature changes. From a more mechanical point of view, the movements at the extremities can be used to correctly estimate body posture and movement.
The accelerometer from all the modules would help create an AR model to calculate all movements in a particular time interval. At the end of the day, all the data would be analysed using DL models to estimate the number of calories burnt and the amount of exercise that is required for optimal hormonal balance. The app then recommends the user, the type of exercises based on data collected during the day. For example, if the user travelled a lot during the day the number of leg exercises would be reduced. This is just an example. More can be found in the attachments.
During exercise, again the hand and leg movements would be tracked and compared against physical limits set by an ideal virtual model doing the same exercise telling the user how to correct her movements for optimum benefits from the exercise. This takes augmented reality to the next level. Instead of other health apps that simply keep a count of the number of steps or rely on the user`s integrity to complete a particular exercise perfectly, this is a no-nonsense approach making exercise more effective than ever. Exercise, as research claims heals symptoms in 60-80% of women. It helps reduce osteoporosis, mood swings, skipped periods and hormonal imbalance. Huh!! So all you have done is made a better exercise app, making it more realistic, but why would people pay for it. Believe me, they will!!! Just hang on. The only problems we have to tackle now are incontinence, sexual discomfort and hot flashes. Most of the solutions in the market target these and they are complicated devices which are really costly. Let's take on them one by one.
The module/s in the lower back region would monitor vibrations in the region during periods or during urination. As research proves, during urination muscles at specific locations vibrate at certain frequencies with the flow of urine. An analysis of this pattern can give insights about potential issues in the system. Research also states that Kegel exercises to train the urinary system can dramatically improve incontinence for the better.
The app guides the user through the exercises and helps one see one`s progress. Following on the lines of the AR used by the generic exercise application, this too would be monitored with an option to share it with doctors on demand. This can also help alleviate sexual discomfort. Just one problem remains - hot flashes and they are probably the hardest to tackle as they require instant cooling solutions and a portable solution is difficult to realise.
Current systems are composed of a compact compressed air compartment that can realise minute quantities of air to cool the fingertips and the back of the neck MANUALLY. While this is practical as refills are readily available online, the manufacturing costs and hence the price tag is beyond a majority of the populace. Compound with this the trouble of remembering to refill and carry it in a purse(however small it maybe).
The sensors on the module mounted at the extremities in the form of rings would sense the temperature, the heart rate and the skin resistance and raise an alarm in case of an abnormality. An oximeter is used for the heart rate and for the skin resistance, two naked aluminium foil electrodes on the insides of the skin are used. This signal then triggers a cooling mechanism made of a peltier module(TEC) placed on the module that is placed behind the neck where(as research shows) the body is most susceptible to temperature changes, thus sending a positive signal to the brain which then stops the increased blood flow. This cooling sensation negates the effect of the flash and the body deals with it automatically. The time is logged for the user to ascertain what exactly triggers such flashes. Further, the heart rate is also monitored for a regulated cooling mechanism which is spontaneous, AUTOMATIC and energy-efficient.
The final hurdle was the cooling mechanism design. I took a peltier module and affixed a heat sink salvaged from an old Raspberry Pi. I found after lots of experimentation with the placement of the module and power measurements that a fan was not necessary(in fact with the fan on it felt really chilly, not to mention the reduced power draw). The CAD of the design is enclosed herewith.
Symptoms like panic attacks and dizziness can be tackled by including a small push button on any of the ring modules on the fingers. On pressing a signal would be sent to the app which would then send a notification to near ones of the user so that they can take necessary action. In case the user faints or any strange patterns are observed in the heart rate or breathing, immediately the nearest medical facility is informed.
The first five parts in the list I have above are generic and practically all wearables have them and with the advancements in semiconductor technology, it is possible to fit all of this on a PCB the size of a coin(let`s make it flexible). Yet, to convince myself with the concept I did some research and put together a list. I even designed a PCB. You can find it here.
The communication protocol is Bluetooth Low Energy(BLE) to easily connect with a smartphone and to increase the battery life of the module. The accelerometer is a high-precision and high sample rate 9DOF one and includes a temperature sensor. For heart rate generic oximeter module is used.
Getting up and running with the NRF5340 DK
Download the NRF COnnect application on your system
Open the Toolchain Manager. Here we install the latest SDK which comes with the SEGGER Embedded Studio IDE
After installation is done, read through the instructions "First steps to build" and click on "Open IDE".
We will test the nRF5340 DK board by downloading the Blinky sample code onto the board. These samples are a part of nRF Connect SDK.
To import the sample:
File → Open nRF Connect SDK Project…
Choose "blinky" as the project and "nrf5430dk_nrf5430_cpuapp" as the board.
Build the project hex file
Build → Build zephyr/zephyr.elf (F7)
Connect the board to the PC and connect it to the IDE:
Target → Connect J-Link (Ctrl+T, C)
Download the hex file onto the board:
Target → Download zephyr/zephyr.elf (Ctrl+T, L)
Check that the LED on the top-right of the board blinks
To make your application, there are two options. You can bang your head and code everything from scratch or could modify from the example and build up from there.
I found it wiser to choose the second option.
Copy the blinky project from this location:
- C:\Users\[USERNAME]\ncs\v1.5.0\zephyr\samples\basic\
Now we shall modify the project to include some libraries for our application.
These projects use the Zephyr RTOS which has a very powerful build system. It has many configurations which you can add in the prj.conf.
From here, it is important to think through the project needs. In this project, I decided to use the GPIO,and I2C device peripherals(though there are many other bells and whistles). In addition, I will make use of the Adafruit TFT display library which has to be added separately.
Refer to this page is the full list of configuration options:- Zephyr Configuration Options (Nordic Semiconductor)
Go back to Open nRF Connect SDK Project again, this time you will see your project folder.
Choose the board name to be nrf5430dk_nrf5430_cpuapp. Also change the build directory to a shorter path (I put it in the root of the C:/ drive)
After importing the project, you can test if you can compile and download it to the board.
Note: that if you do further modifications to the prj.conf file, you need to reimport the project again in order to update the dependencies.
For flashing the code to the board an easy method is provided by the NRF Connect application. The steps that need to be followed are -
- Build the project on Segger Embedded studio and copy the hex file generated
- Open NRF COnncet and download the Programmer
- Open Programmer and click on the Add Hex file option
- Paste the hex file for the project in the window
- Code would be uploaded automatically
The main control unit would be the NRF5340 dev board powered off a 3.7V/1100mAh LiPo battery. All patient parameters including the temperature, the Sp02 reading and the IMU readings are sent to the main controller that logs the data and sends some anomalous packets to the cloud for analysis using an ESP 12F module attached to the dev board. If a hot flash is detected, the controller immediately activates the peltier module for producing a cooling sensation.
If a fall is detected due to dizziness, a message is sent by a web app running in the cloud to family members. The gait pattern and the exercises are analysed with the help of the IMU readings to determine the effect of exrecise on the patient`s body. Relevant notifications and data analysis is dissplayed on the touchscreen display. Further, the vibration sensor readings from the hip area are analysed to help the patient coordinate Kegel exercises.
The IMU readings would be compared with a readily available AR model of an exercise being performed by a professional trainer and the patients` body movements compared. If the patient does not do the exercise properly, messages are issued on the display to help the patient correct herself. The data stored on the cloud can be used later for seeking medical advice and to track one`s progress.
The main product is the combination of all the six modules (the four at the extremities, the one in the pelvic region and the one at the neck) along with the software stack including the app, the data analytics and the AR backend. The sensors on the modules would monitor conditions in real-time, log that data and send it over to the cloud-based analytics engine for processing. On the basis of the data acquired, relief is provided by means explained before.
In summary the working is
• IMU modules sense body posture and movement that is used in assistive exercises(proven to relieve menopause)
• The pelvic module helps co-ordinate Kegel exercises
• The neck module manages hot flashes
• Data is logged on the web app and can be used for reference or medical advice
• SOS alarms warn family members and medical staff in time Auxiliary services include in-app medical advice, notifications, stress relief games and exercises.
The features of the NRF5340 development kit that make it stand out here is the high processing power and the BLE capabilities. The touchscreen display ads a new dimension to the application and would help increase the interactivity of the solution.
References
https://www.hackster.io/zst123/tremor-health-analytics-with-nrf5340-dk-for-dsp-processing-feb44e
https://www.nordicsemi.com/Software-and-tools/Software/nRF-Connect-SDK
https://www.nordicsemi.com/Software-and-tools/Development-Kits/nRF5340-DK
Comments