Data Science x Public Health

How do diseases really spread through populations? In this episode, we break down graph networks and show how public health researchers use them to model disease transmission. You’ll learn how connections like social contacts, transportation systems, and superspreading events shape outbreaks, and how network-based models help with forecasting, contact tracing, and intervention planning. This begin...

Why do epidemiologists care so much about insects? In this episode, we explain entomology in simple terms and show how it connects directly to epidemiology through vector-borne diseases. You’ll learn how mosquitoes, ticks, and other insects drive disease transmission, how scientists track and control vectors, and why understanding insects is essential for preventing outbreaks and protecting public...

How do researchers turn raw data into reliable evidence? In this episode, we break down statistical inference in simple terms and explain how biostatisticians use both classical and modern methods to draw conclusions from data. You’ll learn how uncertainty, randomness, and probability are handled in real-world studies—and why proper statistical inference is essential for clinical trials, epidemiol...

Why do diseases change as countries develop? In this episode, we explore the epidemiological transition model—a core concept in epidemiology that explains how patterns of disease shift over time as societies industrialize, urbanize, and modernize. You’ll learn the five stages of the model, what drives these transitions, and why many countries today face a double burden of disease, dealing with bot...

Matrices are the hidden engine behind modern biostatistics. In this episode, we break down matrix analysis in simple terms and show how it powers statistical models, multivariate analysis, and modern data-driven methods. You’ll learn how matrices support regression, PCA, and machine learning—and why tools like eigenvalues and Singular Value Decomposition (SVD) are essential for working with high-d...

Python or SAS—which one actually matters in public health? In this episode, we break down the differences between Python and SAS, when each tool is used, and why both remain critical in modern public health practice. You’ll learn where Python shines in data science and analytics, why SAS continues to dominate biostatistics, clinical research, and government health agencies, and how knowing both to...

Epidemiology isn’t just about outbreaks—it’s also about the diseases we’ve already beaten. In this episode, we explore some of the biggest successes in epidemiology, including cholera control, smallpox eradication, reduced infant mortality, and the prevention of Legionnaires’ disease and toxic shock syndrome. Learn how these breakthroughs shaped modern public health and why continued epidemiologic...

When will something fail—and how can we predict it? In this episode, we break down failure time data and explain how biostatisticians analyze time-to-event outcomes to understand risk, reliability, and survival. You’ll learn what failure time data is, why censoring occurs, which statistical models are commonly used, and how these methods apply to engineering, medicine, and public health. 👉 Enjoye...

Dashboards turn complex data into clear, actionable insights. In this episode, you’ll learn what dashboards are, how they’re built, and how they’re used across public health and data science. We cover popular dashboard tools like Power BI, Tableau, Looker Studio, and Dash (Plotly), and explain how dashboards support disease surveillance, population health tracking, health equity analysis, and data...

AI agents are increasingly being used behind the scenes in public health—analyzing data, monitoring outbreaks, supporting decisions, and improving how health systems operate. In this episode, we explain what AI agents are, how they work, and why they are becoming an important tool in modern public health practice. You’ll learn how AI agents support disease surveillance, data analysis, health commu...

Many real-world health datasets violate one of statistics’ biggest assumptions: independence. In this episode, we explain why repeated and correlated data break standard statistical methods—and how biostatistics handles it. You’ll learn what longitudinal data are, how longitudinal study designs differ from cross-sectional studies, and why models like mixed-effects models, generalized estimating eq...

Epidemiologists rarely have perfect data—yet decisions still must be made. This episode explains how public health experts act under uncertainty, the methods used to handle incomplete data, and why waiting for “perfect” information can cost lives. Learn how epidemiology balances evidence, risk, and urgency when the stakes are high. 👉Enjoyed the episode? Follow the show to get new episodes automat...

Pandemics don’t emerge at random — patterns form long before the crisis becomes visible. In this episode, we explain how AI models support pandemic preparedness, from scenario modeling and early warning systems to vaccine planning and healthcare resource allocation. You’ll learn how artificial intelligence helps public health experts anticipate outbreaks, test response strategies, and detect emerg...

Your immune system doesn’t just react — it learns. In this episode, we break down adaptive immunity in simple terms and explain how it works, how it differs from innate immunity, and why adaptive immunity is essential in epidemiology and public health. You’ll learn how the body builds immune memory, responds to specific pathogens, and plays a critical role in disease prevention and population-leve...

Bias doesn’t look like a mistake — and that’s why it’s so dangerous. In this episode, we explain how bias enters statistical studies, why bias is fundamentally different from random error, and why it is often difficult to detect and remove. You’ll learn how bias can be built into data collection, study design, and real-world systems, even when advanced statistical or machine learning methods are u...

How can public health experts predict disease outbreaks before they spread? In this episode, you’ll learn how time-series analysis and machine learning are used in public health to monitor trends, detect anomalies, and forecast disease outbreaks. We break down classical time-series models like ARIMA, Holt, and Holt-Winters, explore how machine learning enhances outbreak prediction, and explain how...

Who actually decides whether a drug works? In this episode, you’ll learn how biostatisticians play a critical role in clinical trials and FDA regulatory decisions. We break down how biostatisticians support Phase I–IV clinical trials, shape study design, determine sample sizes, analyze trial data, and influence regulatory approval. You’ll also learn what happens on both sides of the table—where in...

What’s the real difference between an endemic, epidemic, and pandemic—and why does it matter? In this episode, we break down these key epidemiology terms in simple, easy-to-understand language. You’ll learn how epidemiologists classify disease spread, what these situations look like in the real world, and why severity isn’t just about which label sounds “worse.” We also discuss how diseases transi...

Natural Language Processing (NLP) is transforming how public health trends are detected from text data. In this episode, we explain how NLP analyzes health reports, clinical notes, and public health documents to uncover patterns that traditional methods often miss. You’ll learn how word frequency analysis, topic modeling, and Latent Dirichlet Allocation (LDA) help identify emerging health trends,...

Your body begins defending itself against disease before you’re even aware of it. In this episode, we explain what innate immunity is, how it works as the body’s first line of defense, and why it plays a critical role in epidemiology and public health. You’ll learn how innate immunity protects everyone from birth through physical barriers and cellular responses, and why understanding it matters at...

Medical images often contain hidden details that aren’t visible at first glance. In this episode, we explain how image analysis combined with Bayesian models helps enhance, reconstruct, and interpret medical images. You’ll learn the basics of image analysis, how Bayes’ theorem fits into medical imaging, and why these methods are essential in biostatistics for applications like tumor detection, bra...

How do diseases actually begin—and why does that matter to epidemiologists? In this episode, we explain what pathogenesis is, how diseases develop at the biological level, and why understanding pathogenesis is essential in epidemiology. You’ll learn how pathogenesis connects with epidemiology through molecular pathological epidemiology (MPE), how molecular mechanisms influence disease progression,...

Correlation alone isn’t enough to make real-world decisions. In Part 2 of this series, we explore advanced causal inference concepts used in biostatistics, including propensity score methods, dynamic treatment regimes, missing data, unmeasured confounding, and nonparametric and semiparametric estimation. This episode explains how these tools help researchers strengthen causal interpretation, impro...

SQL is one of the most important tools behind modern public health decision-making. In this episode, we explain what SQL (Structured Query Language) is, why it plays a critical role in public health, and how it’s used to manage and analyze large health datasets. You’ll learn how SQL supports disease surveillance, outbreak tracking, population health management, clinical research, and predictive an...

Stata is one of the most widely used tools in public health and epidemiology research—but what exactly does it do? In this episode, we break down what Stata is, why it matters in public health, and how it’s used across fields like biostatistics, epidemiology, economics, education, and medical research. This beginner-friendly overview focuses on practical understanding, not coding experience. Youtu...