Cough for TB: HCW App


About Cough for TB HCW

The Cough for 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.

Who shouldn’t use this app?

  • Individuals other than the HCWs designated by the NTEP.
  • Individuals below 18 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.

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.
Registration and Authentication

The app registers and authenticates HCWs using personal information, NTEP programmatic information, and a one-time password (OTP) delivered via SMS.

Data Entry

Personal and symptomatic data for each subject needs to be input, as per the instructions provided in the app. 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.
Interpret the results and taking action

The app, based on the input cough sounds and data, provides results as follows:

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 18 years of age and below 100 years of age. The model should not be used for individuals below 18 years of age or individuals above 100 years.
  • The sounds were recorded using smartphone microphones. No external attachments for audio input (e.g., for better clarity of audio signals) were used.
  • The AI model runs on cloud/ on-prem server instances.
  • Internet connectivity is required for the model to be able to interpret the cough sounds.
  • The app should be used in selected geographies and demographics, taking into account the characteristics of the data that went into building the AI model providing the inference.
  • Any undetected/unknown biases in the model that haven’t surfaced yet need to be carefully observed after deployment and must be reported to

Annexure 1: Disinfection of Smartphones

For all smartphones used for data collection, we shall follow the below recommendations issued by the CDC.

1. CDC 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.
  • High-risk persons (i.e., individuals of old age, having comorbidities, etc.) will be excused from recruitment.
  • 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.