Data Science x Public Health

Cross-validation is one of the most common tools in machine learning. It is supposed to give you a reliable estimate of how your model will perform. But what if that estimate is quietly misleading you? In this episode, we break down why cross-validation often fails in real-world healthcare and public health data. From data leakage and time dependence to population shifts and deployment mismatch, y...

Screening programs are often seen as one of the clearest wins in public health. Find disease earlier, intervene sooner, and improve outcomes. But what if some screening programs only appear effective because of bias, overdiagnosis, and misleading outcome measures? In this episode, we break down why screening can fail, how lead-time bias and overdiagnosis distort interpretation, and why finding dis...

Confidence intervals are everywhere in research. They are supposed to show uncertainty, improve interpretation, and give more context than a single point estimate. But what if confidence intervals are creating a false sense of certainty instead?  In this episode, we break down what confidence intervals actually mean, why narrow intervals can still be misleading, and how people in research, medicin...

Risk scores are used everywhere in healthcare and public health. They are designed to identify who is most at risk and where interventions should be targeted. But what if those scores are quietly reflecting unequal systems of care rather than true need? In this episode, we break down how bias enters risk models through utilization, access, and data structure—and why even high-performing models can...

Confounding adjustment is one of the most common phrases in epidemiology and observational research. It is often treated as proof that a study has handled bias and moved closer to a causal answer. But what if adjustment is creating more confidence than the data actually deserve?  In this episode, we break down why confounding adjustment often fails, how poorly measured or incorrectly chosen variab...

Regression adjustment is one of the most common tools in biostatistics and health research. It is often treated as proof that a study has properly controlled for differences and moved closer to the truth. But what if regression adjustment is creating more confidence than validity?  In this episode, we break down why regression models often fail to remove bias, how adding more covariates can someti...

Dashboards are supposed to make decision-making easier. They make data visible, trends accessible, and performance look measurable in real time. But what if that visibility is giving leaders the wrong kind of confidence? In this episode, we break down why dashboards often fail to improve real decision-making—especially in public health and data science. From missing context and misleading metrics...

Infectious disease models shape some of the biggest public health decisions in the world—from vaccine strategy to lockdown timing to hospital surge planning.  But what do these models actually do? How do SIR models work? Why do forecasts change? And why do so many people misunderstand what a model is supposed to tell us? In this episode, we break down infectious disease modeling in plain English:...

P-values are everywhere in research. They are treated as the standard for determining whether a result is real, meaningful, or worth acting on. But what if statistical significance is answering the wrong question?  In this episode, we break down why p-values often fail when the real goal is causal inference. You will learn what a p-value actually measures, why it cannot establish causality, and ho...

AI can now write like an experienced epidemiologist. Clear. Structured. Confident. But what happens when it’s wrong? In this episode, we break down how large language models (LLMs) are being used in public health — from surveillance summaries to clinical decision support — and why their biggest strength is also their biggest risk. You’ll learn: What LLMs actually are (and what they’re not) Where t...

Every 7 seconds, a preventable maternal death occurs worldwide. And in the United States, the numbers are getting worse—not better. So what’s really going on? In this episode, we break down maternal and perinatal epidemiology—the field that reveals the true state of a nation’s health system. From rising maternal mortality rates to racial disparities and healthcare access gaps, the data tells a sto...

What if one of the most common methods in medical research is quietly giving you the wrong answer? In studies where patients can experience more than one outcome, standard survival analysis methods like Kaplan-Meier can overestimate risk—sometimes by a lot. In this episode, we break down competing risks analysis, why traditional approaches fail, and how methods like cause-specific hazards and the...

Everyone talks about neural networks. But the systems quietly running public health? They don’t learn — they follow rules. In this episode, we break down symbolic AI — the rule-based systems behind clinical decision support, disease surveillance, and health regulations. You’ll learn: What symbolic AI actually is Where it’s already used in healthcare and public health Why neural networks fall short...

We’ve known the major causes of heart disease for decades. Smoking. Cholesterol. Blood pressure. Diabetes. So why is it still the leading cause of death worldwide? In this episode, we break down cardiovascular epidemiology — from the Framingham Heart Study to modern advances in genetics, wearables, and AI. You’ll learn: How risk factors were discovered Why “residual risk” still exists How genetics...

Healthcare is producing more data than ever before — electronic health records, wearables, genomic data, insurance claims, and real-time patient monitoring. But data alone doesn’t solve problems. In this episode, we break down health data science — the field where biostatistics, machine learning, and modern healthcare systems come together. You’ll learn what health data science actually is, how it...

AI models in healthcare are making critical decisions every day… Who gets flagged as high-risk. Where resources are sent. Who gets care first. But there’s a problem: Many of these models can’t explain their decisions. In this episode, we break down Explainable AI (XAI) and why black-box models are a serious risk in public health. You’ll learn how tools like SHAP and LIME reveal what’s really happe...

Cancer cases are still rising… But cancer deaths have dropped 34% since 1991 — preventing millions of deaths. So what changed? In this episode, we break down cancer epidemiology — the hidden system of data, registries, and research that reveals who gets cancer, why it happens, and how we prevent it at scale. From risk factors like smoking to screening programs and health disparities, this is the s...

What if you could run a clinical trial… without randomizing anyone? In this episode, we break down propensity score methods — one of the most important tools in biostatistics for turning messy observational data into something closer to a fair comparison. You’ll learn: Why observational studies are biased by default How propensity scores balance treated vs untreated groups The 4 major methods (mat...

AI models trained in top hospitals often fail when deployed elsewhere. Different populations. Different data. Different outcomes. So how do you make AI work in places with limited data? In this episode, we break down transfer learning — the technique that lets models reuse what they’ve already learned and adapt to new environments. From rural clinics to global health systems, this method is helpin...

Every year, millions of people die from injuries — and most of us call them “accidents.” But what if that’s completely wrong? In this episode, we break down injury epidemiology — the science of understanding and preventing harm before it happens. From car crashes to falls to workplace injuries, these events follow patterns, risk factors, and can be systematically reduced. 👉 Enjoyed the episode? F...

Before any study begins, one question determines everything: How many participants do you need? Get it wrong, and your study can miss real effects… or waste time, money, and lives. In this episode, we break down sample size and power analysis — the foundation of every clinical trial and research study. You’ll learn how effect size, power, variability, and significance level all come together to de...

Most AI models in public health focus on prediction. Reinforcement learning takes it a step further—it learns what actions to take and improves over time through feedback. In this episode, we break down how reinforcement learning works, why it is a natural fit for public health decision-making, and how it is being applied to outbreak response, resource allocation, and personalized treatment strate...

Why can two neighborhoods in the same city have a 15-year difference in life expectancy? This episode explains social epidemiology—the field that studies how income, education, housing, and social structures shape health outcomes. We break down key frameworks, real-world examples, and why understanding social determinants of health is essential for modern public health practice. 👉 Enjoyed the epi...

Functional MRI (fMRI) lets scientists see your brain in action. This beginner-friendly episode breaks down the core concepts—BOLD contrast, hemodynamic response, task-based vs. resting-state fMRI—and walks through the statistical analysis pipeline. Learn the challenges researchers face and why fMRI is so valuable in biostatistics and neuroscience. 👉 Enjoyed the episode? Follow the show to get new...

Most AI systems only make predictions. Agentic AI goes further—it can plan, act, and respond autonomously using real-time data. This episode explains how agentic AI is being used in public health for disease surveillance, outbreak detection, and emergency response, along with the ethical and governance challenges that come with autonomous systems. 👉 Enjoyed the episode? Follow the show to get new...