There are plenty of problems that are easy for humans to solve, but are almost impossibly difficult for computers. Even though it seems that with modern computing power being what it is we should be able to solve a lot of these problems, things like identifying objects in images remains fairly difficult. Similarly, identifying specific sounds within audio samples remains problematic, and as [Eivind] found, is holding up a lot of medical research to boot. To solve one specific problem he created a system for counting coughs of medical patients.

This was built with the idea of helping people with chronic obstructive pulmonary disease (COPD). Most of the existing methods for studying the disease and treating patients with it involves manually counting the number of coughs on an audio recording. While there are some software solutions to this problem to save some time, this device seeks to identify coughs in real time as they happen. It does this by training a model using tinyML to identify coughs and reject cough-like sounds. Everything runs on an Arduino Nano with BLE for communication.

While the only data the model has been trained on are sounds from [Eivind], the existing prototypes do seem to show promise. With more sound data this could be a powerful tool for patients with this disease. And, even though this uses machine learning on a small platform, we have seen before that Arudinos are plenty capable of being effective machine learning solutions with the right tools on board.

There are a lot of side effects of living with medical conditions, and not all of them are obvious. For Parkinson’s disease, one of the conditions is a constant hand tremor. This can obviously lead to frustration with anything that involves fine motor skills, but also includes eating, which can be even more troublesome than other day-to-day tasks. There are some products available that help with the tremors, but at such a high price [Rupin] decided to build a tremor-compensating utensil with off the shelf components instead.

The main source of inspiration for this project was the Liftware Steady, but at around $200 this can be out of reach for a lot of people. The core of this assistive spoon has a bill of material that most of us will have lying around already, in order to keep costs down. It’s built around an Arduino and an MPU6050 inertial measurement unit with two generic servo motors. It did take some 3D printing and a lot of math to get the utensil to behave properly, but the code is available on the project site for anyone who wants to take a look.

This project tackles a problem that we see all the time: a cost-effective, open-source solution to a medical issue where the only alternatives are much more expensive. Usually this comes up around prosthetics, but can also help out by making biological compounds like insulin directly for less than a medical company can provide it.

These days we are a little spoiled. There are many sensors you can grab, hook up to your favorite microcontroller, load up some simple library code, and you are in business. When [Raivis] got a MAX30100 pulse oximeter breakout board, he thought it would go like that. It didn’t. He found it takes a lot of processing to get useful results out of the device. Lucky for us he wrote it all down with Arduino code to match.

A pulse oximeter measures both your pulse and the oxygen saturation in your blood. You’ve probably had one of these on your finger or earlobe at the doctor’s office or a hospital. Traditionally, they consist of a red LED and an IR LED. A detector measures how much of each light makes it through and the ratio of those two quantities relates to the amount of oxygen in your blood. We can’t imagine how [Karl Matthes] came up with using red and green light back in 1935, and how [Takuo Aoyagi] (who, along with [Michio Kishi]) figured out the IR and red light part.

The MAX30100 manages to alternate the two LEDs, regulate their brightness, filter line noise out of the readings, and some other tasks. It stores the data in a buffer. The trick is: how do you interpret that buffer?

[Raivis] shows the code to take the output from the buffer, remove the DC component, pass it through a couple of software filters, and detect the heart rate. To read the oxygen reading, you have even more work to do. You can find the code for the device on GitHub.

If you want to build your own without a dedicated IC, grab a clothespin. Or try this more polished build.

[Diego Marino] and his colleagues at the Politecnico di Torino (Polytechnic University of Turin, Italy) designed a prototype that allows for patients with motor deficits, such as spinal cord injury (SCI), to do rehabilitation via Functional Electrical Stimulation. They devised a system that records and interprets muscle signals from the physiotherapist and then stimulates specific muscles, in the patient, via an electro-stimulator.

The acquisition system is based on a BITalino board that records the Surface Electromyography (sEMG) signal from the muscles of the physiotherapist, while they perform a specific exercise designed for the patient’s rehabilitation plan. The BITalino uses Bluetooth to send the data to a PC where the data is properly crunched in Matlab in order to recognize and to isolate the muscular activity patterns.

After that, the signals are ‘replayed’ on the patient using a relay-board connected to a Globus Genesy 600 electro-stimulator. This relay board hack is mostly because the Globus Genesy is not programmable so this was a fast way for them to implement the stimulator. In their video we can see the muscle activation being replayed immediately after the ‘physiotherapist’ performs the movement. It’s clearly a prototype but it does show promising results.

It reminds us of the Myoelectric Hand, with humans instead. We featured an EMG tutorial a while back for those curious about this topic. Without taking the merit out of excellent and needed medical research, we all wait for the day that all our bio-signals can be easy read and translated to, let’s say, a huge avatar robot like METHOD-2. Right? Right?…

There are many ways to detect a heartbeat electronically. One of the simpler ways is to take [Orlando’s] approach. He’s built a finger-mounted pulse detector using a few simple components and an Arduino.

This circuit uses a method known as photoplethysmography. As blood is pumped through your body, the volume of blood in your extremities increases and decreases with each heartbeat. This method uses a light source and a detector to determine changes in the amount of blood in your extremities. In this case, [Orlando] is using the finger.

[Orlando] built a finger cuff containing an infrared LED and a photodiode. These components reside on opposite sides of the finger. The IR LED shines light through the finger while the photodiode detects it on the other side. The photodiode detects changes in the amount of light as blood pumps in and out of the finger.

The sensor is hooked up to an op amp circuit in order to convert the varying current into a varying voltage. The signal is then filtered and amplified. An Arduino detects the voltage changes and transmits the information to a computer via serial. [Orlando] has written both a LabVIEW program as well as a Processing program to plot the data as a waveform. If you’d rather ditch the PC altogether, you might want to check out this standalone heartbeat sensor instead.

Last week I decided to buy some stuff from local reseller of Arduino. I bought a Kyto Heart Sensor that transmits heart pulses to a receiver via radio frequency. The RF receiver can then be interfaced to an arduino and then pass the results to an Android device for visualization.