LAHORE: Dr. Maryam Mustafa, Director, Saida Waheed Gender Initiative and Assistant Professor of Computer Science at LUMS, recently presented her project, ‘Awaaz-e-Sehat: Empowering Maternal Healthcare with Voice-Enabled Electronic Record Management’ at the 78th United Nations General Assembly. She was part of the session on ‘Artificial Intelligence for Accelerating Progress on the Sustainable Development Goals: Addressing Society’s Greatest Challenges’.
Dr. Mustafa’s project won a grant from the Bill and Melinda Gates Foundation out of over 1,300 global proposals for its Grand Challenges Catalysing Equitable Artificial Intelligence (AI) Use award. Her co-researchers on the project are Dr. Hassan Mohy Ud Din (Project Co-PI, LUMS), Dr. Beena Ahmed (Project Co-PI, UNSW) and Dr. Fozia Umber (Project Co-PI, Shalamar Hospital).
As a nation struggling with subpar pregnancy outcomes, the absence of documented medical records for expectant women seeking care poses a significant challenge for healthcare professionals. This lack of information hampers doctors’ ability to offer precise diagnoses and tailored care that takes into account socio-economic and lifestyle factors. These factors also play a vital role in maternal health outcomes. Dr. Mustafa and her team are building a voice-enabled, mobile phone-based, conversational AI assistant, Awaaz-e-Sehat to enable maternal healthcare workers in Pakistan to create and keep track of detailed electronic medical records.
Awaaz-e-Sehat will record audio responses in different languages following specific prompts through a proof-of-concept system comprising an intuitive user interface speech recognition module and a text recognition module. The system will then convert responses into text and populate a template electronic medical record in Urdu. It will be evaluated by maternal healthcare workers at Shalamar Hospital in Lahore for its ability to collect records from 500 patients.
Improving maternal health outcomes in Pakistan was the primary motivation behind Dr. Mustafa’s research proposal. “Our country has among the poorest pregnancy outcomes worldwide, significantly worse than many other low-income countries with a maternal mortality ratio of 186 deaths per 100,000 live births, as compared to the developed-country average of just 12 deaths per 100,000. The maternal healthcare system in Pakistan is severely under-resourced with no available tools to support electronic record keeping,” she shared.
She added that her ultimate objective is to roll out Awaaz-e-Sehat across maternal healthcare facilities in Pakistan. “It has the potential to significantly improve not just patient treatment but also create datasets to train diagnostic AI tools that tackle maternal health outcomes in Pakistan.”