Improving Rural Healthcare Delivery via Transparent Monitoring Bill Thies Microsoft Research India In collaboration with Manish Bhardwaj 1,2, Sara Cinnamon 2,3, Goutam Reddy 2,3, Emma Brunskill 1,2, Somani Patnaik 1,2, Seema Kacker 1,2, Sourav Dey 1,2 and Ajit Dash 1,2 1 Massachusetts Institute of Technology 2 Innovators In Health 3 Abiogenix, Inc. MEDITEL / December 20, 2008

Microsoft Research India Established January, 2005 Seven research areas –Algorithms –Cryptography, Security & Applied Math –Digital Geographics –Mobility, Networks, and Systems –Multilingual Systems –Rigorous Software Engineering –Technology for Emerging Markets Contributions to Microsoft: –MultiPoint, Netra, Virtual India Currently ~55 full-time staff, growing Collaborations with government, academia, industry, and NGOs in India Microsoft Research India Sadashivnagar, Bangalore

“Technology for Emerging Markets” Understand potential technology users in developing communities Design and evaluate technology and systems that contribute to socio-economic development of poor communities worldwide Collaborate with development- focused organizations for sustained, scaled impact Computer-skills camp in Nakalabande, Bangalore (MSR India, Stree Jagruti Samiti, St. Joseph’s College) Research Group Goals

Multidisciplinary Research Aishwarya Lakshmi Ratan – Public Administration and International Development Jonathan Donner –Communications Nimmi Rangaswamy – Social Anthropology Indrani Medhi – Design Kentaro Toyama (Group Lead) – Computer Science Society Group Technology Individual Society Group Technology Individual Innovation Understanding Impact Innovation Understanding Impact Rikin Gandhi – Astrophysics Bill Thies - Computer science Saurabh Panjwani - Computer science David Hutchful – Human Computer Interaction

Kelsa+ Microfinance & TechnologyIT and Microentrepreneurs Information ecology of very small businesses Potential of technology to support microfinance Microenterprise PC + mobile Mixed-method study Research only Text-Free UI Text-free user interfaces for non-literate users User interfaces PC Design User studies Guidelines Microfinance PC + mobile Qualitative studies Business analysis Research only Sample Projects Information access PC Qualitative study Usage analysis Pilot Featherweight Multimedia Paper and cheap electronics for low-cost multimedia General education Electronics HCI User studies Prelim research Simultaneous Shared Access Primary education PC HCI User studies Software SDK Warana UnwiredDigital Green Video and mediated instruction for agriculture extension Substitution of mobile phones for rural PC kiosks Agriculture Video Intervention Control trials Pilot Info systems Mobile Intervention Rural kiosks Pilot Free access PCs for low- income office staff Multi-user systems for educational

6 Drug Delivery: Last-Mile is Often Broken TB treatment: 4 drugs, 6-8 months  Worker supervises ingestion 3 times/week (DOT) Rural programs operate in the dark  Interaction: Are workers reaching patients?  Adherence: Are patients taking medication?  Health: Are patients getting better? Mission: Track Interaction, Adherence, Health Drug Developers Distributors Rural Patients Local Clinics  Courtesy PIH

7 The uBox: A Smart Pillbox Developed by Abiogenix, MIT, and Innovators In Health The uBox monitors  Delivery, by logging worker visits  Adherence, by logging pills dispensed uBox impact  Worker supervision and incentives  Timely and targeted intervention  Lowers adherence burden uKey (for worker) uBox (for patient) PatientsWorkersClinic

8 Worker enters vital patient health indicators into cell phone Nurse analyzes data, identifies problems Physician sends advice to patients, schedules field visits Patient lives in a remote area The uPhone: Monitoring Patient Health

9 Is Technology Really the Answer? Often ignores systemic and societal issues But, delivery is overwhelmingly about diligence  Today: 2.4M doses/day, 187 countries, 77% reliability  Need: 7M doses/day, 100% reliability  FedEx: 7.5M shipments/day, 220 countries, 97.7% reliability Our goal is to reduce the burden of diligence  Change the culture: 85% is not enough  Need to respond to every failed transaction  Identify superstar workers early and replicate techniques

10 uBox Training Class was proficient in < 3 hours Overcame prototype shortcomings Gave very good suggestions Bihar, Spring 2008 By MIT and Innovators In Health

11 uPhone Training uPhone more challenging – literacy and prior cell phone experience needed Lesson learned: - Even with intensive training, many errors on menu-based interface Bihar, Spring 2008 By MIT and Innovators In Health

12 Evaluating the Accuracy of Mobile Data Collection With Somani Patnaik and Emma Brunskill, to appear at the 2009 International Conference on ICTs and Development (ICTD 2009) PDAsCell Phones Published error rates Malaria monitoring in Gambia (Forster et al.) Clinical study in Gabon (Missinou et al.) Tuberculosis records in Peru (Blaya & Fraser) Sexual behavior surveys in Peru (Bernabe-Ortiz et al.)None? Others SATELLIFE (Groves et al.) DataDyne EpiSurveyor (Selanikio & Donna) EpiHandy (Engebretsen) Infant health in Tanzania (Shirima et al.) e-IMCI project in Tanzania (DeRenzi et al.) Respiratory health in Kenya (Diero et al.) Tobacco survey in India (Gupta) Ca:sh project in India (Anantraman et al.) Cell-Life in South Africa (Fynn) Jiva TeleDoc in India (UN Publications) Pesinet in Mali (Balancing Act News) Malaria monitoring in Kenya (Nokia Newsletter) Voxiva Cell-PREVEN in Peru (Curioso et al.)

13 1. Electronic Forms Interface

14 2. SMS Interface

15 3. Voice Interface

16 User Study Gujarat, Summer 2008 Conducted by Somani Patnaik, MIT Evaluated three user interfaces: - Electronic forms - SMS - Voice operator Results: - Forms error rate: 4.2% - SMS error rate: 4.5% - Voice error rate: 0.45% Other benefits of voice: - Easy to verify - Easy to replicate - Less expensive These results caused us to change our program to use a voice interface

17 Conclusions Potential for simple technologies to offer large benefits for improving rural healthcare delivery Low-tech interfaces may be highest-impact  uBox provides transparent interface  Operator-assisted reporting better than automated SMS, Forms Most exciting aspects of work coming in next steps  Can technology improve health outcomes in controlled trial?  Is operator interface effective in practice? Seeking additional partners!

18 Innovators In Health: Ensuring Reliable Medication Delivery in the Developing World Community Partner Sponsors … and many generous individuals! The Prajnopaya Foundation Prior Contributors  Alex Krull  Oliver Venn  Jessica Leon  Nikhil Nadkarni  Catherine Dunn