How to Describe a Cough?

Angelique Laaks
Acoustic Epidemiology
4 min readJun 15, 2020
patient describing cough to health professional

Language somehow is not sufficient to describe a cough

Have you ever listened to the sound of a bird’s call and tried to replicate it? Have you ever tried to describe it to someone? It’s really tricky, isn’t it?

As humans, we are wired to understand words and sounds that we can make with our mouths. This serves us fine in day to day life, but it does tend to pose a problem when we are trying to describe a cough.

When we visit the doctor with a rash or other visible symptom, it is easy for them to diagnose the problem. However, very often we must describe a cough to our medical professionals, either for ourselves or a family member — and this can be surprisingly hard to do.

The coronavirus is currently raging across the planet with a persistent cough being one of the main indicators of the illness. This point alone makes it important to identify and describe a cough as best as we can.

How we Classify Coughs

Thankfully, there is some terminology which is universally understood by doctors which will help us to identify and describe a cough.

Coughs are generally differentiated as

  • Dry
  • Wet or Productive
  • Acute
  • Chronic

Identifying Coughs

Describing what the cough sounds like alongside accompanying symptoms, can often help doctors in their diagnosis of an illness.

For example, a harsh, hacking cough with a whooping sound when inhaling can describe Whooping Cough (Pertussis.) Centres for Disease Control and Prevention describes the sound of Pertussis as follows, “Pertussis can cause violent and rapid coughing, over and over, until the air is gone from your lungs. When there is no more air in the lungs, you are forced to inhale with a loud “whooping” sound. This extreme coughing can cause you to throw up and be very tired.”

Alternatively, a dry and irritating cough which becomes wet as the illness progresses, along with discoloured mucus is a strong indicator of Pneumonia. The inflamed airways and excessive mucus production from asthma make breathing difficult and manifest in either a wet or dry cough which ends with a wheezing sound.

A persistent (chronic) cough from inflamed lungs and restricted airways is described as a hacking, wet cough with a substantial amount of mucus. These are symptoms of Chronic Obstructive Pulmonary Disease (COPD), often accompanied by wheezing, shortness of breath and a tight chest.

A sporadic dry or wet cough which becomes worse in the evening is a symptom of post-nasal drip and a painful, barking sound can be an indication of croup.

The Problem with Coughs

While the theory is sound, and many illnesses can be identified by an accurate description of a cough, this is by no means a fool-proof diagnosis.

In fact, a study was done on the language used by medical professionals when describing a cough to assess the accuracy of their assessment compared to acoustic analysis of the cough.

Interestingly, the comment was made, “Identifying clinical diagnosis from cough was poor at 34.0%. Cluster analysis showed coughs with the same acoustics properties rather than the same diagnoses attracted the same descriptions.”

The study concluded, “These results suggest that healthcare professionals can recognise some of the qualities of cough sounds but are poor at making diagnoses from them. It remains to be seen whether in the future cough sound acoustics will provide useful clinical information and whether their study will lead to the development of useful new outcome measures in cough monitoring.”

This article was published in 2006, and much has changed since then.

Big data, AI and machine learning have given us some incredibly useful information in recent years, and especially so in identifying and tracking the cough.

Data scientist Joe Brew makes a thought-provoking comment in his article on what a cough looks like. He says, “Converting the sound of a cough to a visual representation allows for the use of advanced image recognition techniques. This has applications not only in differentiating between a cough and background noise, but also potentially in using each cough’s acoustic signature to better understand the health of the person who coughs. By teaching AI how to distinguish between a cough and ambient noise, we can track cough frequency over time and space.”

He adds, “Whereas a human might categorize a cough in simplistic terms like “wet” or “dry”, a machine can generate categories which are imperceptible to humans, unbounded by our linguistic limitations, far beyond our abilities.”

Essentially, the sound of a cough cannot accurately be translated into words which will sufficiently describe the frequency, tone, volume, duration, and other invisible attributes to the extent where an accurate diagnosis can be attained.

smartphone with earphones used to track cough with hyfeapp

What is the solution?

Artificial intelligence built into the Hyfe app tracks the invisible elements of a cough and translates this information into usable data for health care professionals to download and interpret.

Now, there is no need to learn how to describe your cough or the colour of your mucus to your doctor.

--

--