Global Perspectives on Digital Health

What a pleasure it was to have Rohit Malpani and Peiling Yap on the show, editors of a new journal about AI in Global health. 

This one is for researchers, implementers of digital and AI tools in low resource settings. 

We cover:
The challenges for people in the so called Global South to have a leading voice in academia. 
Hype and reality on AI: premiums on speed to publish and oneupmanship vs investigating what really makes things work
Why publishing things that went wrong or unexpectedly is needed even more
How academic journals and publishing can do better
How people in digital health and AI in healthcare should approach evidence generation
The future of academic publishing in a world increasingly short of attention, patience and deep work
How Ronny Chieng’s Harvard address can make us think critically about what we should be optimising towards. 

Plus what the new RSTM AI in Global Health journal is looking for and what type of papers most excite them
Links!
Ronny Chieng Harvard address. Seriously, watch it.
IDRC funded AI4GH work mentioned by Peiling, also published in a great special collection in npj Digial Medicine
Big tech hiring philosophers article
Industry AI research article
Conversational agents are super communicative, not super intelligent article
New Video series!
Finally, check out a brand new Youtube video series about Tech for Global health challenges. The first one is on Tuberculosis, with the Wellcome Trust, QureAI, AI Diagnostics, Community Health Impact Coalition and Audere.
If you liked this episode, share with people who would learn from it! And head over to gpodh.org and check out a few related ones. Leave us a review or send us a message. 
1. Evaluation Level up with Shay Soremekun
2. Implementation 101 and how to fail well with Caroline Perrin
Want to sponsor a deep dive episode? Get in touch at gpodh.org

The most vulnerable moment in any human life is the first few hours. In this episode, Shubs talks with Dr. Josh Bress, pediatrician, President of Global Strategies and Medical Director of NoviGuide, a tool used nearly half a million times to help nurses in remote facilities across Africa manage critical newborn care. Josh shares his experiences and stories from Eastern Congo, why paper guidelines fail at the bedside, how configuration (not customization) is the key to scaling, what it actually looks like to delight frontline health workers, and what's kept his team going through 15 years of building at the last mile. Essential listening for anyone building for impact in global health.
"I'm not going to be better than these nurses. What can I do to help these nurses do their job better?"
Key takeaways
Paper guidelines end up on shelves, digital care pathways get to the bedside. Josh compares paper guidelines to an atlas and Novi Guide to Google Maps. Built right, digital can adapt to what you actually have, flow with real clinical decisions, and stay available at 3am.
Configuration, not customisation, is how you scale. Everyone told Josh he'd have to rebuild NoviGuide for every country. He didn't. Clinical guidelines differ in predictable ways. The real variation is at the site level: what drugs, equipment, and diagnostics are available. Build for that and you can scale without starting from scratch.
Delight your end user. Nurses turned NoviGuide into a verb. They trained others with more passion than Josh's own team could. They hit the feedback button asking for more. Treat frontline health workers as true customers, not passive recipients.
Local leadership is the engine of scale. Josh has personally met fewer than a dozen of NoviGuide's users across nearly half a million uses. Scale happened because local leaders like Dr. Nakakeeto in Uganda took ownership and made the tool their own.
This is practical, heartfelt and full of so much wisdom for people building, developing policy or funding tech solutions for healthcare in low resource settings. 

About Joshua

Dr. Joshua Bress is a pediatrician and leads the nonprofit Global Strategies, where he serves as the medical director of the NoviGuide clinical decision support platform. He completed his undergraduate studies at Harvard University, attended medical school at Vanderbilt University, and then completed his pediatric residency at the University of California, San Francisco. 
After residency, he moved to eastern Congo, living and working in the city of Goma from 2011 to 2012. That experience, and the challenges of sustaining high-quality care in resource-limited settings, led him to focus on clinical decision support. 
Today, he works with a multidisciplinary team to develop and scale NoviGuide, a point-of-care platform used by nurses and clinicians to deliver guideline-based care for newborns and children, helping bridge the gap between training, guidelines, and real-world clinical practice.​

(00:00) - Introduction to Global Health and Neonatology

(05:17) - The Unique Challenges of Newborn Care

(07:33) - Experiences in Eastern Congo

(10:21) - The Role of Nurses in Neonatal Care

(12:50) - Identifying Gaps in Neonatal Care

(15:19) - Developing the Novi Guide

(18:09) - Adapting Guidelines for Local Contexts

(20:50) - User-Centric Design in Healthcare Technology

(23:41) - Scaling the Novi Guide Across Regions

(26:32) - The Importance of Local Adaptation

(29:02) - Delighting Users with Effective Solutions

(37:50) - Scaling Challenges and Insights

(40:17) - The Importance of Local Leadership

(43:05) - Customization vs. Configuration in Digital Tools

(45:59) - Managing Complexity in Healthcare Applications

(48:55) - The Role of Feedback in Product Development

(51:34) - Balancing Trust and Scale in Healthcare

(54:29) - Lessons from a leader

(01:02:25) - What Policymakers and Funders can do better

(01:07:52) - This is a team sport

Joe Alderman has this great ability to break down complex things into a good hearty discussion. Joe is an Anaesthetist by night and AI academic by day. His insights on what it takes to deploy and monitor AI in healthcare with a lens on not leaving people behind are relevant wherever in the world you are.

We discussed some of the nuance and challenges around AI in healthcare, as well as some anti patterns 

If you are a data or AI scientist, or shipping AI products, what can you do starting tomorrow to begin thinking more proactively about underserved communities or ensure you’re not creating unintended harm to vulnerable groups. 
Stuff the industry is not doing great on: We’re starting with the dataset or the technology we happen to have, instead of working backwards from what we are fundamentally trying to achieve in the world. (If I nodded any more at this point my head would have rolled off)
A revisit on where things are with the Standing Together initiative, something Xiao Liu talked about in the very first episode.  In the UK, there are big areas where life expectancy is falling. Health inequalities are rising. Our datasets have bias. It’s tempting to fall into the narrative that this is a tech deficiency problem. It is not. It is a whole society problem and we’re not going to solve it with JUST tech. 
If govts, regulators and health systems find it challenging to be on top of the safety issues with LLMs, how are lay people going to? Joe covers how the upcoming work of the Healthcare Chatbot User Guide can help people navigate some of the key things they need to consider

We cover a LOT in this 1 hour discussion, including how patients and clinicians can think more critically about which tasks to best use Gen AI with, and how to think about safety and liability. 

This one is for AI and data scientists, product folk, developers and clinicians. Get it on your weekend playlist
Links:

MHRA’s National Commission into the Regulation of AI in Healthcare: https://www.gov.uk/government/groups/national-commission-into-the-regulation-of-ai-in-healthcare

Building The Health Chatbot Users’ Guide: https://healthchatbotguide.org/

The NHS Fellowship in Clinical AI: https://www.nhsfellowship.ai/

NHS Digital Clinical Safety Training: https://digital.nhs.uk/services/clinical-safety/clinical-risk-management-training

Chapters
00:00 Introduction and Joe's work
06:36 The Role of AI in Patient Care
07:52 Navigating AI Risks and Benefits
18:13 Addressing Health Data Poverty
24:28 Building Responsible AI Systems
30:18 Exploring Large Language Models in Healthcare
34:05 Addressing Bias and Representativeness in AI Models
40:04 Navigating Regulatory Challenges for AI Technologies
40:51 Empowering Patients in the Age of AI
44:32 Public Perception and Trust in Digital Health
47:00 Identifying Real Problems in Healthcare Technology
52:00 The Future of AI in Healthcare
55:29 Joe's insights for those building in low resource settings
56:57 A book recommendation and critical thinking for patients and clinicians
About Joe
Joe is an NHS anaesthetist in the UK and an NIHR clinical lecturer (assistant professor) in AI and digital health at the University of Birmingham, UK. 
He leads mixed-methods research and policy engagement to help get the most from AI in healthcare - including the STANDING Together initiative. He recently founded an international initiative to build ‘The Health Chatbot Users’ Guide’.

How do global organizations built to respond and aid in conflict respond to digital transformation? The International Committee of the Red Cross (ICRC) : you’re probably familiar with the work that happens here : emergencies, conflict zones, disasters, working at the last mile in difficult circumstances. How does an organization like even begin to approach “tech innovation” There’s clearly lots of need.

What do you prioritize when everyone needs improvements now? 

PLUS How do you adapt off the shelf LLM models for remote humanitarian contexts?

Javier Elkin spent 3 years as Director of Digital Innovation at the ICRC. He set the unit up from scratch. Coming in at a time, post COVID, the opportunities for tech addressing unmet need proliferated. And in parallel trying to create stability with multiple financial crises and organizational challenges.  

If you’re in digital health and wrestling with the global scale and local trust and value tradeoffs, have a listen to how an actual global organization dealt with it. 

Some standouts for me from our convo:

We spoke about context : correctness vs being useful

If you ask a LLM : What do I do for this gunshot or limb trauma, it might be reasonable to say that a response like : call emergency services is universally correct. 
But in a conflict zone or very rural setting, that has zero value compared to “take two pieces of wood to act as a splint”, or try X to stem blood loss.
How did the ICRC digital team work (with partners at EPFL) on their validation and evaluation to get better at these aspects?

Your LLM might be technically, and even medically correct, but completely useless on the ground for someone. 

2. Prioritization based on outcomes, constraints, feasibility

3. We get some proper concrete examples that cover:

How they used tech to aid a handover to a local healthcare system in Western Nigeria after years of being there. 
How they used an open source tool already being used in the field to help spin up digital workflow solutions FAST
How they partnered with EPFL to develop testing, validation and evaluation pipelines for LLM decision support specific and relevant for conflict settings (some absolute gold in here)

We also get Javier’s honest reflections about the humanitarian sector in general : how the financial crises (esp the last year with huge funding challenges) have manifested, what next for the humanitarian sector and what could be done differently. 

Packed with lessons this one, do not miss it.

Chapters:
00:00 Introduction to Digital Health and Javier's Journey
07:55 Approach to creating a digital health unit from scratch
13:53 Prioritization Framework at the digital health
22:32 Innovative Solutions in Humanitarian Health
29:21 Strategic Handover and Local Ownership
35:20 Integrating Digital Health in Conflict Zones
41:21 Evaluating AI in Humanitarian Settings
53:26 Reflections on Trust and the Humanitarian Sector

At the end of last year I got the chance to record the first episode of the show in an actual studio. Still a lot to learn about this versus virtually, but Patty Mecheal was a gracious and very awesome guest. 

Patty, CEO of healthenabled brings nearly three decades of mHealth and digital health experience into this discussion we recorded during the Global Digital Health Forum in Nairobi in December 2025.  
After a tumultuous year of policy shifts with USAID funding, WHO shifts and the cascading challenges globally, our conversation examines how we got here and where we need to go when ethics and inclusivity are politically sidelined.

What we cover:
The state of 2025 - USAID cuts and their ripple effects on healthcare and digital health in underserved communities
Lessons from the 1990s to now - what patterns keep repeating, and what fundamental mistakes we're still making
Women as decision-makers AND consumers - why this isn't just the "right thing to do" (though it is), but represents massive unmet market opportunity
Value and context in evaluation - how to actually assess digital health and AI tools in ways that matter
Leadership with values - Patty's honest reflections on what she's learned and gotten wrong
Building responsibly when the incentives don't reward it - what does ethical implementation look like now?

This episode is for you if you:
Build digital health or AI solutions
Make policy or funding decisions
Research or evaluate health interventions
Are working on impact in women’s health

Unfiltered, real insights from someone who's seen it all. 

Chapters and Timestamps

00:00 Introduction to Global Perspectives on Digital Health
01:24 Reflections on the Global Digital Forum
04:03 Patti's Journey and Background
08:20 Aha Moments in Public Health
11:46 The Importance of Data in Health Interventions
16:01 Learning from low resource settings
21:55 Building Trust in Digital Health Solutions
24:50 Balancing Scalability and Trust
30:22 The Role of Compassion in Healthcare
40:53 The Theory of Change in Digital Health
46:13 Bootstrapping Innovations in Digital Health
52:49 Compassionate Leadership and Ethical Practices
57:08 The Role of Women in Health and Technology
About Patty:
Dr. Patricia (Patty) Mechael is a global digital health leader, speaker, and award-winning author with nearly 30 years of experience shaping equity-centered health and technology initiatives across more than 45 countries. She is Co-Founder and CEO of health.enabled, where she leads the Global Digital Health Monitor and Digital Health and AI Strategy efforts with Gavi, the Vaccine Alliance, WHO, UNICEF, and others. She is also a Senior Associate Professor at the Johns Hopkins Bloomberg School of Public Health where she serves as the Co-Principal Investigator for the Gates Foundation’s Digital Health Exemplars and where she also teaches a course on Gender-intentional Digital Health. Known for translating complex ideas into human, actionable insights, Patty writes and speaks widely on responsible AI, gender equity, and the future of work and health—bringing a grounded, compassion-driven leadership lens shaped by both evidence and lived experience.