Karibu tena! The last time you tuned in, we were headed to Arusha to begin a four-day, three-night safari across three of Tanzania’s national parks. We’ve now been back for over a week, and I mourn the experience every single day.

On the first day, we visited Tarangire National Park, which I personally think was the best day of the safari. We saw countless elephants, as the park is known for its elephant sightings, but one unexpected highlight was a baboon troop moving along the road we were traveling on. We estimated around 250 baboons, and the best part was watching the babies ride on their mothers’ backs like little jockeys.

We had two very different nights in the Serengeti. The first was at a luxury tented safari camp, still not sure how that fit in our budget, and it was such a cool experience. The dinner tent was a short walk from our sleeping tents, but after dark, staff insisted on escorting us, just in case we ran into lions or hyenas. That made it feel so otherworldly. I was genuinely in awe, and a little in disbelief, that this was real life.

An elephant also wandered into our campsite, though maybe we were the ones who wandered into his. It’s crazy I can say I stood so close to an elephant without any barriers.

On the last day, we visited the Ngorongoro Crater and saw even more wildlife. A few highlights were the lone hyena strolling across the landscape, the warthogs, and especially the wildebeests, which honestly look so fake to me. As our safari wrapped up, I had a total epiphany moment, standing on my seat with the roof popped open as the safari truck sped through the plains, thinking about how incredibly lucky I am to have witnessed this kind of nature. Forever grateful.

 

As for my project, the week before last was full of important decisions. As I mentioned in my previous blog, there are a few limitations in the ambient temperature readings collected by the Hadli monitors. After investigating further, we found that most monitors are installed near the ceiling and that each unit typically has only one monitor, even in facilities with multiple rooms. In some cases, this means the readings may not fully represent the temperatures experienced by the majority of newborns.

That said, we do not discredit the data at all. These measurements are incredibly valuable in providing an initial picture of ambient conditions. Our goal is simply to build on this foundation to get the most accurate possible estimate of what the broader newborn population is likely experiencing. To do this, we decided to adjust the recorded data by 2–4°C, since the original numbers likely reflect air higher up in the room. My mentor John helped make this adjustment by simulating how temperature typically changes from floor to ceiling. Because colder air tends to settle near the floor, especially by doors or windows, he modeled this drop and factored in cot height, subtle room variations, and small sensor inaccuracies to generate an approximation of what babies might feel.

The graphs below compare monthly trends in facility-level minimum daily temperatures before and after adjusting the Hadli data. Each graph categorizes facilities based on whether their daily minimum temperatures remained within, exceeded, or fell below the ideal 25–35°C range. Each bar is color-coded: green indicates that a facility maintained temperatures within range every day of that month, yellow indicates at least one day above the range, and blue indicates at least one day below it. In the original Hadli data, green dominates the chart, suggesting that most facilities were able to maintain temperatures within the ideal range. However, after the adjustment, the proportion of green decreases and blue increases, revealing that more facilities may actually be experiencing days with below-range temperatures than previously observed.

The country name has been omitted from the chart.

 

We also revisited a previous decision regarding how we account for ambient temperatures after admission. Initially, we used an average from the seven days post-admission, but we decided to shift to using the median length of stay per country (Malawi, Kenya, Nigeria, and Tanzania). This led to slight improvements in our model.

Around this time, I began preparing for my final presentation with the KIT Key Interventions Technical Working Group at NEST. This group facilitates cross-country collaboration to spark discussion and catalyze programmatic action. I was nervous but also excited about the opportunity to share my findings.

The timing worked out perfectly, as my mentor Christine was traveling to Nairobi, Kenya to meet with the NEST team there, and she graciously invited me along. I’m so glad she did. Nairobi stole my heart. The city has so much to offer, and the Kenya team was incredibly warm and welcoming. Every day I had the chance to meet inspiring people who were contributing their unique talents to the same mission. I received incredibly valuable feedback ahead of my presentation, and felt truly supported.

John, my mentor and NEST data analyst, had especially helpful feedback on how to present statistical findings to a general audience. He was so patient with my many questions. Hannah also offered encouragement and great insight. Being surrounded by people who genuinely care about their work, collaboration, and my growth has been so meaningful. I know I’ll seek mentors and work environments like this for the rest of my life.

I’m sad that my in-person time is coming to an end, but so excited that my work with NEST will continue even after I return to Houston. I’m so thankful to Christine for believing in me and supporting my continued involvement. Nairobi gave me both a personal and professional experience I’ll never forget.

My presentation was yesterday, and it went really well thanks to my amazing team. I wanted to summarize a few of the key takeaways and the feedback I received. We built a model to assess associations between adjusted ambient temperature and newborn hypothermia after admission. We found a statistically significant association, both before and after temperature adjustment.

Temperatures above 28°C had a protective effect against hypothermia (OR = 0.902; 9.8% reduction in odds compared to 27–28°C). Temperatures at or below 26°C were associated with increased odds of hypothermia (OR = 1.077; 7.7% increase compared to 27–28°C). These tertiles (≤ 26°C, 27–28°C, > 28°C) and were created to ensure groups had roughly equal sample sizes. That said, the effect sizes are small, and we must be cautious about making recommendations. While warmer temperatures may be beneficial, the results should be interpreted with care.

We also confirmed that ambient temperature alone doesn’t explain the hypothermia burden. Other variables like birth weight, birth location, month of admission, and heater availability help explain additional variability. Our takeaway is that clinical practices, especially maintaining the warm chain, are essential. But more covariates and further data, like satellite temperature trends, may improve the model even further.

 

Overall, the presentation was a very positive and thought-provoking experience. I’m excited to incorporate the feedback and explore new directions for the project. This week, I’ll also begin drafting the methods section for our eventual publication, and I’m looking forward to summarizing my work in detail and reflecting on this journey professionally.

This is actually my final entry from Dar es Salaam, and I hope to make the most of my last week here. Thank you for reading my blog this summer. Tuonane!

Last time I checked in, we were packing for Zanzibar, and I can confidently say it was just as magical as I had hoped. We started in Stone Town, a place that instantly won me over. There’s something about coastal towns that always pulls me in, and Stone Town, with its narrow alleyways, historic charm, and buzzing local life, was no exception. On day two, we visited the spice market, which felt like a rite of passage. Zanzibar isn’t called “The Spice Island” for nothing, and I made sure to pick up some local spices to bring back. Then it was off to the Jozani Forest, where we saw blue monkeys and rare red colobus monkeys, endemic to the island. That night, we celebrated my birthday on Nungwi Beach with dinner.

The next day brought my favorite adventure yet: snorkeling off the coast of Mnemba Island. I’vealways loved it, but what I didn’t love, until now, was the idea of swimming near dolphins. But when our boat driver suddenly spotted some and told us to jump in, I did. I think the spontaneity helped override my fear of sea creatures larger than fish. And I’m glad I went for it, it ended up being one of the coolest things I’ve ever done. The fish were incredibly colorful, and thedolphins, though intimidating, were mesmerizing to watch in the wild. On our last day, we visited Prison Island, famous for its giant tortoises, which was a really cool experience. What surprised me even more was learning about the island’s history: despite its name, Prison Island was never actually used as a prison. Instead, it served as a quarantine station for people suspected of carrying Yellow Fever and other contagious diseases before they were allowed to enter Zanzibar. Before we headed back to Dar, we returned to Stone Town for a rooftop lunch and visited the East African Slave Trade Exhibition. It gave us a deeper understanding of the island’s history, especially Zanzibar’s role in the transatlantic and Indian Ocean slave trades. Seeing the holding chambers and reading personal accounts was heartbreaking, but it also emphasized the significance of remembering and learning from the past. After such a full weekend, it was time to dive back into my research project. Over the past two weeks, I’ve made significant progress in understanding and visualizing ambient temperature trends for our partner facilities. One of my first visualizations tracked whether each facility stayed within the recommended 25–35°C range during any given month. The rule was strict: if even one daily minimum temperature reading fell below or above this range, the facility was flagged.   (Facility IDs have been removed from this visualization.) From there, I moved on to exploring ambient and newborn temperature data together. This integration step took a lot of time and quite a few data revisions. When I finally visualized the combined data, I found something surprising: most cases showed babies with low body temperatures (hypothermia) even when the ward temperatures were within or above the recommended range. This unexpected result sparked some important conversations. One possibility? The location of ambient monitors. Many are installed near the ceiling to avoid interference, but heat rises, so the baby’s actual environment at bed level could be significantly cooler. That gap might explain the mismatch. It also raises the question of whether we need to make a data adjustment to better reflect the temperatures experienced by the newborns. There are further limitations in the data: ambient readings include daily minimums, maximums, and averages, while baby temperatures are usually captured as a single lowest reading after admission, with no specific timestamp. To bridge this gap, I used an average of ambient temperatures from the seven days following each baby’s admission based on NEST360’s collected data, which shows that most ward stays across the countries last under a week. While this assumption isn’t perfect, it allows for a more consistent comparison between ambient and newborn temperatures. Working through this has shown me just how much nuance and decision-making goes into data science, and I’ve been so grateful for my mentor John’s guidance throughout.   With a cleaner dataset, I began running correlation analyses and found statistically significant, but weak, relationships between ambient and newborn temperatures. This suggests that while ambient conditions do matter, other factors (like birth weight, season, or facility practices) likely play big roles too. Adding controls for birth weight and seasonal changes strengthened the model, and I’m optimistic that when we introduce satellite-derived data, we’ll see even more robust relationships. I’m also hoping to explore time series models soon, so I’ve been brushing up on my forecasting skills! Alongside the temperature analysis, I’ve also identified a new need-finding project at DIT. Joel mentioned he’s collected a ton of visitor data for the DIT Design Studio (why people visit, what resources they use) but hasn’t had a good way to process or use it. So I will begin designing a dashboard that automatically updates using a Google Form and summarizes visitor activity. The goal is to help the lab understand how it’s being used and identify areas where students may need more support. If successful, it could also help make the case for additional funding or resources. And what would a blog be without a glimpse of the next adventure? As I write this, we’re on our way to Arusha, a gateway to Tanzania’s most famous national parks. Over the next few days, we’ll be visiting Tarangire, Ngorongoro Crater, and the Serengeti. It’s a dream come true, and I already know I’ll have so much to write about in the next post. Hadi wakati huo!

The past two weeks have been busy, eventful, and honestly, really rewarding. We’ve settled into a daily routine that I’ve come to enjoy, but now that I’m fully adjusted to life in Dar, I’ve started to make a few tweaks here and there. My host project, as I briefly mentioned in my last post, is primarily computational. So rather than climbing the seven flights of stairs to the DIT Design Studio every day, I’ve started working from local coffee shops on some mornings. It’s been a fun way to explore the city, enjoy a good breakfast, and take advantage of strong WiFi while still getting my work done. It’s also helped me stay motivated, which can sometimes be tricky with screen-heavy, data-intensive work.

As for the project itself, these last two weeks have been full of learning. I’ve deepened my understanding of hypothermia trends in newborns across four countries: Malawi, Tanzania, Kenya, and Nigeria. I’ve been working closely with my mentors, Dr. Bohne and John, and even got to collaborate with a NEST360 team member affectionately nicknamed Hypothermia Hannah, who has helped me translate findings into clear, impactful visualizations. The goal is to give facility partners meaningful context around their progress and needs.

One visualization I created tracks transitions in newborn thermal states—for example, showing how many babies are admitted normothermic and become hypothermic, or the reverse. While I’ve removed the facility name for data safety reasons, I hope to share more formally with Rice360 later on since this work is part of a larger publication!

Another big focus has been analyzing ambient temperature data collected via the HADLI monitor—a NEST360-qualified technology used to track ward temperatures (among other environmental conditions) in low-resource settings. I’ve been visualizing temperature trends across facilities in all four countries, and one big question we’re exploring is: What counts as an ideal ward temperature? WHO recommends temperatures between 25–28°C, but some literature suggests slightly higher temps may be even better, depending on the circumstances of birth. I’ve been experimenting with a broader range, like 25–35°C, to help facilities understand when they’re falling outside of safe parameters, especially when it comes to preventing newborn hypothermia.

Next, I’ll be diving into research to explore the relationship between ward temperature and newborn thermal states. Now that I know both datasets well, I’m excited (and slightly intimidated) to dig into past literature and methodology. This is where the advanced statistics come in: testing approaches, refining models, and going through cycles of trial, error, and revision. It’s a challenge I’m genuinely looking forward to, and one that will push me to think critically about how to best capture and communicate these associations, but I know I am greatly supported. John, my mentor and a data analyst for NEST, is so, so brilliant, and I’m confident he’ll have some valuable direction for me.

Outside of work, we’ve had some amazing moments too. A few weekends ago, we visited Bongoyo Island, just off the coast of Dar. It was serene and absolutely magical. Last weekend, we spent time in the south of Dar at a beach in Kigamboni near our DIT mentor Joel’s home, alongside many DIT students and staff we see every day. It was refreshing to see everyone outside of the workshop, playing beach games and swimming.

We also celebrated Shreya’s birthday this week! Andy and I worked with a few DIT students to surprise her with a cake at dinner. I didn’t expect so many of them to come, but it was genuinely heartwarming to see them all show up. We celebrated at one of our favorite restaurants (yes, we have favorites now!), an Indian spot called Chowpatty. I still can’t believe we’ve been here long enough to say that! Living in the city center and working closely with local mentors has taught me so much about Dar and Tanzania’s history. One fascinating piece has been learning about the large Indian immigrant population here, especially concentrated in parts of the city like Kisutu. 

 

 

 

 

 

On the language front, I’m trying to keep learning Swahili, though I’ll admit my memory isn’t the best. I’ve mastered basic greetings and food terms (priorities!), and my mentor recommended a book that I plan to pick up next week to deepen my learning.

But first… Zanzibar!!! We’re heading there this weekend for a little escape, and it just so happens that the trip begins tomorrow… on my 22nd birthday! I can’t wait to write all about it in the next blog post.

Asante kwa kusoma!