Bilal A Mateen

Maryam Mustafa, Imaan Hameed, Amna Shahnawaz et al.

Despite steady global advances, maternal mortality remains alarmingly high in Pakistan (155 deaths per 100,000 live births in 2023); largely as a consequence of fragmented paper records, low literacy, poor access to quality healthcare, and gendered barriers that compromise care continuity. Over three years, we designed, deployed, and iteratively developed Awaaz-e-Sehat, a speech-based artificial intelligence (AI) system that generates electronic medical records (EMRs) and supports decision-making in maternal health. The tool evolved from a clinician-facing AI assistant that automated Urdu speech-to-EMR generation into a patient-centred WhatsApp-based platform, enabling women to generate their own structured clinical notes, receive AI-generated antenatal guidance, and share QR-coded records with providers anywhere in the country. This case study documents that translational journey, i.e., how the ground realities of workload, linguistic nuance, and infrastructural constraints reshaped our design. The result is not merely a new method of record-keeping, but a reimagining of antenatal care and electronic medical records themselves. In settings where clinicians are time-constrained and have little institutional incentive to document, Awaaz-e-Sehat proposes a model of care that centres patients as active participants in generating and owning their health data. By keeping patients informed about their own risk factors and integrating them into the clinical decision-support loop, the system transforms EMRs and CDSS from static institutional artefacts into dynamic tools for self-advocacy and shared accountability in maternal health.

James Liley, Samuel R Emerson, Bilal A Mateen et al.

Machine learning is increasingly being used to generate prediction models for use in a number of real-world settings, from credit risk assessment to clinical decision support. Recent discussions have highlighted potential problems in the updating of a predictive score for a binary outcome when an existing predictive score forms part of the standard workflow, driving interventions. In this setting, the existing score induces an additional causative pathway which leads to miscalibration when the original score is replaced. We propose a general causal framework to describe and address this problem, and demonstrate an equivalent formulation as a partially observed Markov decision process. We use this model to demonstrate the impact of such `naive updating' when performed repeatedly. Namely, we show that successive predictive scores may converge to a point where they predict their own effect, or may eventually tend toward a stable oscillation between two values, and we argue that neither outcome is desirable. Furthermore, we demonstrate that even if model-fitting procedures improve, actual performance may worsen. We complement these findings with a discussion of several potential routes to overcome these issues.