Papers by Neha Madhiwalla
Expanding impact of mobile health programs: SAHELI for maternal and child care
Ai Magazine, Oct 11, 2023
Social Roots of Medical Education
Oxford University Press eBooks, Jun 28, 2018
Allopathy has become the dominant system of medicine in India today. Since mid-nineteenth century... more Allopathy has become the dominant system of medicine in India today. Since mid-nineteenth century, allopathic medical education institutions have grown exponentially. However, its growth has been problematic. Further, the political influence of modern medicine practitioners has enabled them to gain monopolistic control of state health system, even though they remain marginal to the provision of primary care in the rural areas.
Women's illnesses: life cycle approach
PubMed, 2003
National meeting on ethical guidelines for social science research
PubMed, Dec 6, 2005
To Report? Or Not to Report?: That is the Dilemma
Asian Bioethics Review, 2010
This is a complex study involving various stakeholders, some of whom do not directly participate ... more This is a complex study involving various stakeholders, some of whom do not directly participate in the research process. Firstly, there is a research agency which initiates the study, clearly driven by its concern for reproductive rights. The medical practitioners represent the other stakeholders. Access to them has been obtained through peers who are directly involved in the reproductive rights movement. Thus, in this case, it is clear that a subgroup of medical practitioners who are concerned with the advocacy of reproductive rights has been included in the study. In classical terms, they do not constitute a vulnerable population as they are fairly well organised, highly educated and socially respected. They can be expected to have a high level of autonomy and control over the research process. There are other stakeholders in this study. This study has direct consequences for women, representing an opportunity to enter the debate on abortion. Such a study can help to bring to the public forum several uncomfortable facts that are probably well known, but which the state is unwilling to acknowledge. We find that a legislative decision to ban the use of misoprostol has been instituted in the face of all available evidence that indicates a high need for abortion services. As a response to this, women and medical practitioners have colluded to allow the unofficial use of misoprostol. Thus, although they are not the focus of the study, women are also implicated in an illegal act. The state itself is a stakeholder in this study. As a reconciliatory measure, to address the serious problem of abortion-related morbidity and mortality without disturbing the anti-abortion policy, it has instituted a programme for post-abortion care. Undoubtedly this represents its attempt to bring about a compromise between the politically powerful anti-abortion lobby and women’s
Experiences in health research with women
Issues in medical ethics, 2001
Dr AM Pai
Indian Journal of Medical Ethics, Jul 1, 2005
A terminally ill child in a public hospital
Indian Journal of Medical Ethics, Oct 1, 2007
Indian Journal of Medical Ethics, 2005
Shwaas is the first Marathi film sent as the Indian entry to the Oscars. Directed and produced by... more Shwaas is the first Marathi film sent as the Indian entry to the Oscars. Directed and produced by Sandeep Sawant, this human drama revolves around the story of a small boy who will become blind as a result of life-saving surgery.
The ethics of truth telling
South Asian Journal of Cancer, 2013
Protocols and Set-Ups
Oxford University Press eBooks, Nov 18, 2021
Within the larger context of commodified medical practice and compromised standards in under-reso... more Within the larger context of commodified medical practice and compromised standards in under-resourced government services, premier government medical colleges are reputed to be the enclaves where ‘scientific medicine’ is practised. In the past decade, these have begun to admit a significant proportion of less socially privileged students. This chapter examines the contribution to the production of knowledge of obstetricians graduating from two such institutions who have returned to the ‘periphery’. These students approach medical education without the cultural resources to engage with medicine as a knowledge system. The focus is on instilling discipline and imparting skill in technique, which students imbibe as protocols, without acquiring a broader understanding of the field, an affinity for research, or an exposure to evidence-based practice. Unable to visualize their practice as a conscious engagement with their context, they define their adaptations as violations of the ‘protocolic practice’, undermining their self-assessment as practitioners of science.
Proceedings of the ... AAAI Conference on Artificial Intelligence, Jun 26, 2023
In 2020, maternal mortality in India was estimated to be as high as 130 deaths per 100K live birt... more In 2020, maternal mortality in India was estimated to be as high as 130 deaths per 100K live births, nearly twice the UN's target. To improve health outcomes, the non-profit AR-MMAN sends automated voice messages to expecting and new mothers across India. However, 38% of mothers stop listening to these calls, missing critical preventative care information. To improve engagement, ARMMAN employs health workers to intervene by making service calls, but workers can only call a fraction of the 100K enrolled mothers. Partnering with ARMMAN, we model the problem of allocating limited interventions across mothers as a restless multi-armed bandit (RMAB), where the realities of large scale and model uncertainty present key new technical challenges. We address these with GROUPS, a double oracle-based algorithm for robust planning in RMABs with scalable grouped arms. Robustness over grouped arms requires several methodological advances. First, to adversarially select stochastic group dynamics, we develop a new method to optimize Whittle indices over transition probability intervals. Second, to learn grouplevel RMAB policy best responses to these adversarial environments, we introduce a weighted index heuristic. Third, we prove a key theoretical result that planning over grouped arms achieves the same minimax regret-optimal strategy as planning over individual arms, under a technical condition. Finally, using real-world data from ARMMAN, we show that GROUPS produces robust policies that reduce minimax regret by up to 50%, halving the number of preventable missed voice messages to connect more mothers with life-saving maternal health information.
Proceedings of the ... AAAI Conference on Artificial Intelligence, Jun 26, 2023
Underserved communities face critical health challenges due to lack of access to timely and relia... more Underserved communities face critical health challenges due to lack of access to timely and reliable information. Nongovernmental organizations are leveraging the widespread use of cellphones to combat these healthcare challenges and spread preventative awareness. The health workers at these organizations reach out individually to beneficiaries; however such programs still suffer from declining engagement. We have deployed SAHELI, a system to efficiently utilize the limited availability of health workers for improving maternal and child health in India. SAHELI uses the Restless Multiarmed Bandit (RMAB) framework to identify beneficiaries for outreach. It is the first deployed application for RMABs in public health, and is already in continuous use by our partner NGO, ARMMAN. We have already reached ∼ 100K beneficiaries with SAHELI, and are on track to serve 1 million beneficiaries by the end of 2023. This scale and impact has been achieved through multiple innovations in the RMAB model and its development, in preparation of real world data, and in deployment practices; and through careful consideration of responsible AI practices. Specifically, in this paper, we describe our approach to learn from past data to improve the performance of SAHELI's RMAB model, the real-world challenges faced during deployment and adoption of SAHELI, and the end-to-end pipeline.
arXiv (Cornell University), Mar 7, 2021
India has a maternal mortality ratio of 113 and child mortality ratio of 2830 per 100,000 live bi... more India has a maternal mortality ratio of 113 and child mortality ratio of 2830 per 100,000 live births. Lack of access to preventive care information is a major contributing factor for these deaths, especially in low-income households. We work with ARMMAN, a non-profit based in India, to further the use of call-based information programs by early-on identifying women who might not engage with these programs that are proven to affect health parameters positively. We analyzed anonymized call-records of over 300,000 women registered in an awareness program created by ARMMAN that uses cellphone calls to regularly disseminate health related information. We built machine learning based models to predict the long term engagement pattern from call logs and beneficiaries' demographic information, and discuss the applicability of this method in the real world through a pilot validation. Through a randomized controlled trial, we show that using our model's predictions to make interventions boosts engagement metrics by 14.3%. We then formulate the intervention planning problem as restless multi-armed bandits (RMABs), and present preliminary results using this approach.
Proceedings of the ... AAAI Conference on Artificial Intelligence, Jun 28, 2022
The widespread availability of cell phones has enabled nonprofits to deliver critical health info... more The widespread availability of cell phones has enabled nonprofits to deliver critical health information to their beneficiaries in a timely manner. This paper describes our work to assist non-profits that employ automated messaging programs to deliver timely preventive care information to beneficiaries (new and expecting mothers) during pregnancy and after delivery. Unfortunately, a key challenge in such information delivery programs is that a significant fraction of beneficiaries drop out of the program. Yet, non-profits often have limited health-worker resources (time) to place crucial service calls for live interaction with beneficiaries to prevent such engagement drops. To assist non-profits in optimizing this limited resource, we developed a Restless Multi-Armed Bandits (RMABs) system. One key technical contribution in this system is a novel clustering method of offline historical data to infer unknown RMAB parameters. Our second major contribution is evaluation of our RMAB system in collaboration with an NGO, via a real-world service quality improvement study. The study compared strategies for optimizing service calls to 23003 participants over a period of 7 weeks to reduce engagement drops. We show that the RMAB group provides statistically significant improvement over other comparison groups, reducing ∼ 30% engagement drops. To the best of our knowledge, this is the first study demonstrating the utility of RMABs in real world public health settings. We are transitioning our RMAB system to the NGO for real-world use.
arXiv (Cornell University), Mar 7, 2021
India has a maternal mortality ratio of 113 and child mortality ratio of 2830 per 100,000 live bi... more India has a maternal mortality ratio of 113 and child mortality ratio of 2830 per 100,000 live births. Lack of access to preventive care information is a major contributing factor for these deaths, especially in low resource households. We partner with ARMMAN, a nonprofit based in India employing a call-based information program to disseminate health-related information to pregnant women and women with recent child deliveries. We analyze call records of over 300,000 women registered in the program created by ARMMAN and try to identify women who might not engage with these call programs that are proven to result in positive health outcomes. We built machine learning based models to predict the long term engagement pattern from call logs and beneficiaries' demographic information, and discuss the applicability of this method in the real world through a pilot validation. Through a pilot service quality improvement study, we show that using our model's predictions to make interventions boosts engagement metrics by 61.37%. We then formulate the intervention planning problem as restless multiarmed bandits (RMABs), and present preliminary results using this approach.
arXiv (Cornell University), Jun 13, 2020
India accounts for 11% of maternal deaths globally where a woman dies in childbirth every fifteen... more India accounts for 11% of maternal deaths globally where a woman dies in childbirth every fifteen minutes. Lack of access to preventive care information is a significant problem contributing to high maternal morbidity and mortality numbers, especially in low-income households. We work with ARM-MAN, a non-profit based in India, to further the use of call-based information programs by earlyon identifying women who might not engage on these programs that are proven to affect health parameters positively. We analyzed anonymized callrecords of over 300,000 women registered in an awareness program created by ARMMAN that uses cellphone calls to regularly disseminate health related information. We built robust deep learning based models to predict short term and long term dropout risk from call logs and beneficiaries' demographic information. Our model performs 13% better than competitive baselines for short-term forecasting and 7% better for long term forecasting. We also discuss the applicability of this method in the real world through a pilot validation that uses our method to perform targeted interventions.
Sex selection: ethics in the context of development
Issues in medical ethics
Drug promotional practices in Mumbai: a qualitative study
Indian Journal of Medical Ethics, Apr 1, 2007
We conducted a qualitative study to determine the range of promotional practices influencing drug... more We conducted a qualitative study to determine the range of promotional practices influencing drug usage in Mumbai. Open-ended interviews were conducted with 15 senior executives in drug companies, 25 chemists and 25 doctors; focus group discussions were held with 36 medical representatives. The study provided a picture of what might be described as an unholy alliance: manufacturers, chemists and doctors conspire to make profits at the expense of consumers and the public's health, even as they negotiate with each other on their respective shares of these profits. Misleading information, incentives and unethical trade practices were identified as methods to increase the prescription and sale of drugs. Medical representatives provide incomplete medical information to influence prescribing practices; they also offer incentives including conference sponsorship. Doctors may also demand incentives, as when doctors' associations threaten to boycott companies that do not comply with their demands for sponsorship. Manufacturers, chemists and medical representatives use various unethical trade practices. Of particular interest was the finding that chemists are major players in this system, providing drug information directly to patients. The study also reinforced our impression that medical representatives are the least powerful of the four groups.
Indian Journal of Medical Ethics, Apr 1, 2006
Open-ended interviews with providers, administrative staff and patients in one teaching hospital ... more Open-ended interviews with providers, administrative staff and patients in one teaching hospital and two peripheral hospitals in Mumbai were conducted to investigate the triggers to violence against hospital staff, the underlying conditions that give rise to such conflicts, the structural and organisational factors that contribute to these conditions, the steps taken to reduce the hostility towards the public health system and what needs to be done. Our findings indicate that the violent incidents are usually triggered by sudden deaths. Patients are frustrated by rude health providers and a lack of essential drugs and diagnostic equipment. On their part, resident doctors must provide life-saving treatment while also handling agitated crowds. They live and work in conditions that put them under pressure and keep them demoralised. Bad working conditions, overcrowding and inadequate facilities are responsible for the increased friction between patients and providers.
Uploads
Papers by Neha Madhiwalla