Occupational Disease Analytics

Understand the epidemiology of occupational diseases and the effectiveness of controls

Occupational Diseases are a significant expense for a company in terms of potential reputational damage, lost productivity, medical treatment, rehabilitation and compensable disease. These are largely preventable where effective risk mitigation, and early (ideally preclinical) biological changes are recognised and managed. 

chest x-ray

The development of Occupational Diseases can result from workplace hazard exposures, and tends to occur insidiously and progressively over many years. For example, continuous exposure to noise above 85 dB(A) causes damage to the ear resulting in noise-induced hearing loss (NIHL) and tinnitus (ringing in the ears) and has been linked to increased stress, fatigue, high blood pressure and, indirectly, to heart disease. Some diseases occur long after the exposure has ceased for example cancers such as mesothelioma from asbestos exposure. 

Here at Wimmy, we analyse audiogram results combined with patient medical records, in order to understand the trends in hearing deterioration over time, taking into account variation between and within individuals, as well as the effects of noise exposure and other environmental and medical factors that affect hearing ability. 

Other occupational disease analytics include Cancer, Lung Disease, Musculoskeletal Disorders and Mental Health Disorders.

Computer-assisted diagnosis of Occupational lung diseases



forecasting & management of compensation cases 

Biological monitoring for chemical exposures

A case study


hearing test

Noise-induced hearing loss (NIHL) is the second most common occupational disease in South Africa, after tuberculosis. This is a particular challenge for industries such as mining, where heavy equipment, rock drilling, and a confined work environment all expose employees to high noise levels.

A 2011-2012 CDC study noted that up to 24% of adults under the age of 70 had a degree of NIHL in the USA. Companies are required by law to do annual audiograms on employees exposed to noise in within the workplace, to monitor for possible hearing loss.  

Wimmy is applying data science to a data source of tens of thousands audiogram results carried out by a company over several years. The aim is to ensure that in future, early signs of NIHL are picked up and actioned, false diagnoses minimised, and more serious cases prioritised. Furthermore, risks are identified and quantified and the efficiency of existing controls are evaluated so that areas where they are failing can be improved upon.  

An additional aim is to determine whether the use of Artificial Intelligence (AI) and diagnostic algorithms can significantly improve the speed and accuracy of the interpretation of hearing tests, especially when used alongside clinicians. This matters, because interpreting audiograms requires highly skilled audiologists – a scarce resource – and the interpretation of audiograms and recognition of early signs of NIHL can vary greatly. Through this work Wimmy aims to develop an initial screening tool, to cut down the volume of work. This could also serve as a form of quality control, reducing human error that leads to false positives and false negatives.  

Lastly, if automated interpretation proves to be more accurate than human practitioners, it could be used to do all the interpretation of audiograms. Evidence-based recommendations will be generated to improve the hearing conservation programme by providing objective, shareable insights into the hearing health of the organisation, so that it is in a better position to act. 


For a customised solution