Cough Against TB: HCW App

Cough Against TB: HCW App


These Terms of Use (‘Terms’) govern your use of the Cough against TB – HCW application for mobile and handheld devices (‘App’), and the services provided through the same. Please read these Terms carefully before you download, install, or use the App. By clicking on the “I Agree” button, you signify your acceptance of these Terms, and your agreement to be bound by them.

The Terms may be amended from time to time, with prior notice to App users, in which case, in order to continue using the App, you will be required to accept the revised Terms.

About Cough against TB HCW

The Cough against TB – HCW app is an AI-powered cough-sounds-based screening solution to assess the likelihood of pulmonary tuberculosis in individuals, for the early detection and treatment of tuberculosis (TB). This App is intended to be used by healthcare workers (HCW).

Who should use this App?

HCWs designated by the National TB Elimination Program (NTEP). The subjects can be the general population of India from 18–100 years of age, who are not on a TB treatment regimen. Informed consent from parents/ or guardians is required for the screening of subjects below 18 years of age.

Who should not use this App?

  • Individuals other than the HCWs designated by the NTEP.
  • Individuals below 7 years of age and above 100 years of age should not be screened.

Privacy Policy

We are firmly committed to protecting your privacy. Our privacy policy is available here.

The Use of this App

The HCW agrees that they will only use the App in good faith and will not provide false or misleading information about themselves, the subject, or their symptomatic and clinical status. The HCW agrees that they will not indulge in any act that may impair the performance or functionality of the App.

How to use the app


The app can be installed on any smartphone with the following minimum specifications:

  • Android smartphone running OS version 5 and newer.
  • iPhone running iOS 11 and newer.
  • A working microphone on the smartphone.
  • Internet connectivity on the smartphone.

The App authenticates the HCW using an OTP delivered on the registered mobile number via SMS.

Data Entry

The App registers and authenticates the HCW using personal information, NTEP programmatic information (location and level posting), and OTP delivered via SMS (as detailed in the Privacy Policy).

Personal and symptomatic data of the subject needs to be entered, as per the instructions provided in the form. HCWs should refer to Annexure 1 and Annexure 2 for safety measures.

Before recording the cough sounds, please ensure the following for each subject:


  • Record the sounds in a well-ventilated and noise-free area.
  • Ensure that the subject is wearing a mask.
  • Hold the smartphone at an arm’s length/3-feet distance from the subject’s face.


  • Do not let the subject directly cough into the smartphone. Hold it across from the subject at a 90-degree angle.
  • Do not connect any external audio input device, e.g., headphones, earphones, external mic.
Interpreting the results and taking action

The App processes the symptomatic data along with the cough audio and provides the results as follows (please refer to the Disclaimer section for more information about the results):

Likely to have pulmonary tuberculosis

Based on the automated inference, the individual’s chances of having pulmonary tuberculosis are high and they should consult a doctor and get tested to confirm the diagnosis.

Not likely to have pulmonary tuberculosis

Based on the automated inference, the individual’s chances of having pulmonary tuberculosis are low and they should consult a physician if symptoms continue.


  • The AI model in the app was trained on data captured at the facility-level (healthcare facilities).
  • The AI model has been trained on a data set containing subjects above 7 years of age and below 100 years of age. The model should not be used for individuals below 7 years of age or individuals above 100 years of age.
  • The Cough against TB – HCW AI model achieved a sensitivity of 90% and specificity of 30% on test data.
  • The sounds were recorded using smartphone microphones. No external attachments for audio input (e.g., for better clarity of audio signals) were used.
  • Internet connectivity is required for the model to be able to interpret the cough sounds.
  • For any issues related to the above, please email

No Warranties

Though efforts are made to ensure that the information and content provided as part of the App are correct at the time of inclusion on the App, there is no guarantee to the accuracy of the Information. We do not make representations or warranties as to the fairness, completeness or accuracy of the Information on the App. There is no commitment to update or correct any information that appears on the Internet or on the Website/ Application. Information is supplied upon the condition that the persons receiving the same will make their own determination as to its suitability for their purposes prior to use or in connection with the making of any decision.

Intellectual Property Rights

Wadhwani AI shall own all rights, titles and interests, including all related intellectual property rights, in and pertaining to (i) the App and any suggestions, ideas, enhancement requests, feedback, recommendations or any other offerings; (ii) the text, graphics, user interfaces, visual interfaces, photographs, trademarks, logos, sounds, music, artwork and computer code; or (iii) other information provided by You, however, in accordance with the applicable laws.

Third-party trademarks, if any, may appear on this App and all rights therein are reserved to the registered owners of those trademarks.

You, the user of the App, shall be solely responsible for any violations of any laws and for any infringements of any intellectual property rights caused by your use of the App.


By accepting these Terms of Use, You agree that You shall defend, indemnify and hold us, our affiliates, our licensors, and each of its officers, directors, other users, employees, attorneys, third party service providers, if any, and agents harmless from and against any and all claims, costs, damages, losses, liabilities and expenses (including attorneys’ fees and costs) arising out of or in connection with: (a) Your violation or breach of any term of these Terms of Use or any Applicable Law or regulation, whether or not referenced herein; (b) Your use or misuse of the App.

Defect Reporting

You can report any defects or bugs in the App or the Services to We will make every endeavor to address all reported bugs and defects.

Governing Law

These Terms shall be governed by the laws of India.

Annexure 1: Disinfection of Smartphones

For all devices used for data collection, we shall follow the below recommendations, as issued by the Ministry of Health and Family Welfare (MoHFW).

1. MoHFW guidelines
  • For electronics such as smartphones, tablets, touch screens, remote controls, and keyboards, remove visible contamination if present.
  • Follow the manufacturer’s instructions for all cleaning and disinfection products.
  • Use of wipeable covers for electronics.
  • If no manufacturer guidance is available, consider the use of alcohol-based wipes or sprays containing at least 70% alcohol to disinfect touch screens. Dry surfaces thoroughly to avoid pooling of liquids.
2. Guidelines issued by leading smartphone manufacturers
  • Before you begin, power down your device, remove any case or cover and unplug any accessories.
  • Wipe the exterior surface of the phone with a soft, lint-free microfibre cloth.
  • Manufacturers warn against applying liquid cleaning solutions directly on the phone as that may damage the device, particularly the oleo phobic coating which helps protect the display from fingerprint smudges.
  • Liquids and water could even get into open spaces, particularly on devices that don’t have an IP rating, so you could end up damaging your phone.
  • For disinfecting the phone, dampen the corner of your cleaning cloth with a small amount of distilled water or disinfectant.
  • You can use a hypochlorous acid-based (50-80ppm) or alcohol-based (formulated with more than 70% ethanol or isopropyl alcohol) product and wipe the front and back of your phone gently without too much pressure.
  • Avoid wiping the device excessively. Manufacturers also caution against using compressed air or applying spray bleaches or liquid solutions directly on the phone.
  • These cleaning guidelines are meant for glass, ceramic and metal surfaces, not for soft accessories that are made from materials like plastic, rubber or leather.
  • If you use cases or covers on your phone, it would be a good idea to disinfect them as well, since they tend to capture a lot of dirt and grime anyway over time.

Annexure 2: Safety Measures for HCWs

The following measures will be undertaken to prevent infection during data collection.

  • Persons with the willingness and dedication to work in this situation will only be recruited with written informed consent.
  • The staff will be trained by qualified trainers on infection prevention and control practices before joining duty to attend health facility.
  • Infection prevention measures during data collection will be ensured, such as:
    • Cough sound will be collected at a well-ventilated place and away from other people.
    • Individuals will cough with a mask on their face and all the cough hygiene measures.
    • Data collection devices will be disinfected as per the instruction of the manufacturer or as per Annexure 1.
  • Staff will be allowed to work in health facilities for not more than 6 hours, and all precaution measures will be followed as per the IPC guidelines.
  • Any staff that develops respiratory symptoms will be removed from their data collection duties.
Implementation of appropriate infection prevention and control (IPC) measures

IPC is a critical and integral part of data collection from patients, as per the guidelines of the Ministry of Health and Family Welfare (MoHFW).

Standard precautions will always be routinely applied, including hand hygiene, avoiding direct contact with patients’ respiratory secretions, standard precautions for safe waste management and cleaning and disinfection of equipment (including data collection devices).

Implementation of infection prevention and control measures for patients with suspected or confirmed nCoV infection as per the guidelines of the MoHFW.

ML Engineer


An ML Engineer at Wadhwani AI will be responsible for building robust machine learning solutions to problems of societal importance; usually under the guidance of senior ML scientists, and in collaboration with dedicated software engineers. To our partners, a Wadhwani AI solution is generally a decision making tool that requires some piece of data to engage. It will be your responsibility to ensure that the information provided using that piece of data is sound. This not only requires robust learned models, but pipelines over which those models can be built, tweaked, tested, and monitored. The following subsections provide details from the perspective of solution design:

Early stage of proof of concept (PoC)

  • Setup and structure code bases that support an interactive ML experimentation process, as well as quick initial deployments
  • Develop and maintain toolsets and processes for ensuring the reproducibility of results
  • Code reviews with other technical team members at various stages of the PoC
  • Develop, extend, adopt a reliable, colab-like environment for ML

Late PoC

This is early to mid-stage of AI product development

  • Develop ETL pipelines. These can also be shared and/or owned by data engineers
  • Setup and maintain feature stores, databases, and data catalogs. Ensuring data veracity and lineage of on-demand pulls
  • Develop and support model health metrics

Post PoC

Responsibilities during production deployment

  • Develop and support A/B testing. Setup continuous integration and development (CI/CD) processes and pipelines for models
  • Develop and support continuous model monitoring
  • Define and publish service-level agreements (SLAs) for model serving. Such agreements include model latency, throughput, and reliability
  • L1/L2/L3 support for model debugging
  • Develop and support model serving environments
  • Model compression and distillation

We realize this list is broad and extensive. While the ideal candidate has some exposure to each of these topics, we also envision great candidates being experts at some subset. If either of those cases happens to be you, please apply.


Master’s degree or above in a STEM field. Several years of experience getting their hands dirty applying their craft.


  • Expert level Python programmer
  • Hands-on experience with Python libraries
    • Popular neural network libraries
    • Popular data science libraries (Pandas, numpy)
  • Knowledge of systems-level programming. Under the hood knowledge of C or C++
  • Experience and knowledge of various tools that fit into the model building pipeline. There are several – you should be able to speak to the pluses and minuses of a variety of tools given some challenge within the ML development pipeline
  • Database concepts; SQL
  • Experience with cloud platforms is a plus

ML Scientist


As an ML Scientist at Wadhwani AI, you will be responsible for building robust machine learning solutions to problems of societal importance, usually under the guidance of senior ML scientists. You will participate in translating a problem in the social sector to a well-defined AI problem, in the development and execution of algorithms and solutions to the problem, in the successful and scaled deployment of the AI solution, and in defining appropriate metrics to evaluate the effectiveness of the deployed solution.

In order to apply machine learning for social good, you will need to understand user challenges and their context, curate and transform data, train and validate models, run simulations, and broadly derive insights from data. In doing so, you will work in cross-functional teams spanning ML modeling, engineering, product, and domain experts. You will also interface with social sector organizations as appropriate.  


Associate ML scientists will have a strong academic background in a quantitative field (see below) at the Bachelor’s or Master’s level, with project experience in applied machine learning. They will possess demonstrable skills in coding, data mining and analysis, and building and implementing ML or statistical models. Where needed, they will have to learn and adapt to the requirements imposed by real-life, scaled deployments. 

Candidates should have excellent communication skills and a willingness to adapt to the challenges of doing applied work for social good. 


  • B.Tech./B.E./B.S./M.Tech./M.E./M.S./M.Sc. or equivalent in Computer Science, Electrical Engineering, Statistics, Applied Mathematics, Physics, Economics, or a relevant quantitative field. Work experience beyond the terminal degree will determine the appropriate seniority level.
  • Solid software engineering skills across one or multiple languages including Python, C++, Java.
  • Interest in applying software engineering practices to ML projects.
  • Track record of project work in applied machine learning. Experience in applying AI models to concrete real-world problems is a plus.
  • Strong verbal and written communication skills in English.