arXiv subjects

Maryam Mustafa

Publications and source records attributed to Maryam Mustafa.

8 recordsLinked to original sources

arXiv2026

How GenAI is Helping Reimagine Antenatal Care in A Low-Resource Setting: From Provider Enablement to Patient Empowerment

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.

cs.HC↗

arXiv2026

Designing Around Stigma: Human-Centered LLMs for Menstrual Health

Menstrual health education (MHE) in Pakistan is constrained by cultural taboos and inadequate formal curricula, leaving women with few trusted resources to lean on. In response to these challenges, we introduce a WhatsApp-based chatbot powered by a large language model (LLM) and Retrieval Augmented Generation (RAG), co-designed with Pakistani college women. Workshops (N=30) revealed key design requirements -- support for Roman Urdu, use of subsidized platforms, and an expert -- curated knowledge base. We then deployed the chatbot with 13 participants for two weeks (403 messages and interviews). Women used it to challenge cultural taboos, legitimize health concerns often dismissed as normal, and build reproductive health knowledge through iterative questioning. Yet, interactions also exposed tensions: reliance on cultural explanatory models, questions of trust and validation, and gendered persona of the chatbot itself. We contribute empirical insights, a stigma-aware design framework for culturally sensitive conversational AI, and a methodological lens foregrounding expert validation in intimate health domains.

cs.HC↗

arXiv2026

Kissan-Dost: Bridging the Last Mile in Smallholder Precision Agriculture with Conversational IoT

We present Kissan-Dost, a multilingual, sensor-grounded conversational system that turns live on-farm measurements and weather into plain-language guidance delivered over WhatsApp text or voice. The system couples commodity soil and climate sensors with retrieval-augmented generation, then enforces grounding, traceability, and proactive alerts through a modular pipeline. In a 90-day, two-site pilot with five participants, we ran three phases (baseline, dashboard only, chatbot only). Dashboard engagement was sporadic and faded, while the chatbot was used nearly daily and informed concrete actions. Controlled tests on 99 sensor-grounded crop queries achieved over 90 percent correctness with subsecond end-to-end latency, alongside high-quality translation outputs. Results show that careful last-mile integration, not novel circuitry, unlocks the latent value of existing Agri-IoT for smallholders.

cs.HC↗

arXiv2026

LLM-Enhanced Wearables for Comprehensible Health Guidance in LMICs

Personal health monitoring via IoT in LMICs is limited by affordability, low digital literacy, and limited health data comprehension. We present Guardian Angel, a low-cost, screenless wearable paired with a WhatsApp-based LLM agent that delivers plain-language, personalized insights. The LLM operates directly on raw, noisy sensor waveforms and is robust to the poor signal quality of low-cost hardware. On a benchmark dataset, a standard open-source algorithm produced valid outputs for only 70.29% of segments, whereas Guardian Angel achieved 100% availability (reported as coverage under field noise, distinct from accuracy), yielding a continuous and understandable physiological record. In a 96-hour study involving 20 participants (1,920 participant-hours), users demonstrated significant improvements in health data comprehension and mindfulness of vital signs. These results suggest a practical approach to enhancing health literacy and adoption in resource-constrained settings.

cs.HC↗

arXiv2025

System X: A Mobile Voice-Based AI System for EMR Generation and Clinical Decision Support in Low-Resource Maternal Healthcare

We present the design, implementation, and in-situ deployment of a smartphone-based voice-enabled AI system for generating electronic medical records (EMRs) and clinical risk alerts in maternal healthcare settings. Targeted at low-resource environments such as Pakistan, the system integrates a fine-tuned, multilingual automatic speech recognition (ASR) model and a prompt-engineered large language model (LLM) to enable healthcare workers to engage naturally in Urdu, their native language, regardless of literacy or technical background. Through speech-based input and localized understanding, the system generates structured EMRs and flags critical maternal health risks. Over a seven-month deployment in a not-for-profit hospital, the system supported the creation of over 500 EMRs and flagged over 300 potential clinical risks. We evaluate the system's performance across speech recognition accuracy, EMR field-level correctness, and clinical relevance of AI-generated red flags. Our results demonstrate that speech based AI interfaces, can be effectively adapted to real-world healthcare settings, especially in low-resource settings, when combined with structured input design, contextual medical dictionaries, and clinician-in-the-loop feedback loops. We discuss generalizable design principles for deploying voice-based mobile healthcare AI support systems in linguistically and infrastructurally constrained settings.

cs.HC↗

arXiv2025

"Koyi Sawaal Nahi Hai": Reimagining Maternal Health Chatbots for Collective, Culturally Grounded Care

In recent years, LLM-based maternal health chatbots have been widely deployed in low-resource settings, but they often ignore real-world contexts where women may not own phones, have limited literacy, and share decision-making within families. Through the deployment of a WhatsApp-based maternal health chatbot with 48 pregnant women in Lahore, Pakistan, we examine barriers to use in populations where phones are shared, decision-making is collective, and literacy varies. We complement this with focus group discussions with obstetric clinicians. Our findings reveal how adoption is shaped by proxy consent and family mediation, intermittent phone access, silence around asking questions, infrastructural breakdowns, and contested authority. We frame barriers to non-use as culturally conditioned rather than individual choices, and introduce the Relational Chatbot Design Grammar (RCDG): four commitments that enable mediated decision-making, recognize silence as engagement, support episodic use, and treat fragility as baseline to reorient maternal health chatbots toward culturally grounded, collective care.

cs.HC↗

arXiv2025

Between Myths and Metaphors: Rethinking LLMs for SRH in Conservative Contexts

Low-resource countries represent over 90% of maternal deaths, with Pakistan among the top four countries contributing nearly half in 2023. Since these deaths are mostly preventable, large language models (LLMs) can help address this crisis by automating health communication and risk assessment. However, sexual and reproductive health (SRH) communication in conservative contexts often relies on indirect language that obscures meaning, complicating LLM-based interventions. We conduct a two-stage study in Pakistan: (1) analyzing data from clinical observations, interviews, and focus groups with clinicians and patients, and (2) evaluating the interpretive capabilities of five popular LLMs on this data. Our analysis identifies two axes of communication (referential domain and expression approach) and shows LLMs struggle with semantic drift, myths, and polysemy in clinical interactions. We contribute: (1) empirical themes in SRH communication, (2) a categorization framework for indirect communication, (3) evaluation of LLM performance, and (4) design recommendations for culturally-situated SRH communication.

cs.CY↗

arXiv2025

A global log for medical AI

Modern computer systems rely on syslog, a universal protocol that records critical events across heterogeneous infrastructure. Medicine's rapidly growing AI stack has no equivalent. As medicine deploys AI tools at scale, there is no standard way to record how, when, by whom, and for whom these models are used. Without such records, it is difficult to measure real-world performance and outcomes, detect adverse events, or identify bias and dataset drift. Here we introduce MedLog, a protocol for event-level logging of medical AI. Each time an AI model interacts with a human, another algorithm, or an automated workflow, MedLog creates a record. Each record contains nine core fields: header, model, user, target, inputs, artifacts, outputs, outcomes, and feedback. We apply MedLog across four deployments in the US, Switzerland, and Vietnam: ICU deterioration prediction, tetanus progression monitoring from wearable signals, automated sepsis quality reporting, and patient attendance prediction. MedLog records capture model behavior, workflow interactions, and downstream outcomes, including AI performance degradation during severe weather events in patient attendance prediction and increased laboratory testing after ICU deterioration alerts. MedLog limits the data footprint through risk-based sampling, lifecycle-aware retention policies, and write-behind caching, enabling deployment in low-resource settings. It also supports detailed traces for complex, agentic, or multi-stage workflows, creating a foundation for continuous monitoring, auditing, and improvement of medical AI.

cs.AI↗