Lecture 3.3.3: Prior Elicitation & MCMC Diagnostic + Hierarchical Models
The lecture introduces Bayesian statistics as a framework for health research, emphasizing how prior medical knowledge is formally combined with new patient data to produce posterior estimates of treatment effects. It outlines the step‑by‑step process—defining priors, collecting observations, and updating beliefs—using a blood‑pressure‑reduction example and demonstrates practical implementation with PyMC code. Key insights include the importance of prior elicitation from earlier trials or expert opinion, the reliance on Markov chain Monte Carlo (MCMC) methods when analytical solutions are infeasible, and the necessity of diagnostic tools such as trace and autocorrelation plots to confirm chain convergence. The presenter also explains hierarchical modeling, which simultaneously estimates overall treatment effects and group‑specific variations across hospitals. Illustrative snippets show a prior mean of 10 mm Hg updated to a posterior around 11 mm Hg, and a hierarchical model that captures both global mean and individual hospital effects. The speaker highlights PyMC functions like pm.normal for priors and pm.sample for posterior sampling, and references ArviZ for visual diagnostics. The material underscores that Bayesian approaches provide full probability distributions, handle small or fragmented datasets, and naturally accommodate multi‑level health data, making them valuable for clinical trials, drug evaluation, and health‑policy analysis.
Lecture 10: Dynamic Disease Modelling
The lecture introduces dynamic disease modeling as a tool for forecasting infection trajectories, estimating healthcare demand, and evaluating control measures such as vaccination, testing, and quarantine. It emphasizes that models translate epidemiological parameters—transmission rate (β), recovery rate (γ), incubation period...
Lecture 3.0.6: Risk Scores Charlson, Elixhauser, GBM, RNN, TabNet Models, REGULARISED REGRESSION
Lecture 3.0.6 of the Masters in Health Data Science program compares classic clinical risk scores—Charlson Comorbidity Index, Elixhauser Index, and NEWS2—with modern machine‑learning and deep‑learning models such as XGBoost, LightGBM, TabNet, RNN/LSTM. It walks through model selection, regularisation techniques, evaluation...
Lecture 1.6.11: Probability Tests in Action, Course Summary
The final lecture ties together the entire probability‑testing series, reviewing Z‑tests, T‑tests, and chi‑square analyses as practical tools for real‑world data problems. It emphasizes when each test is appropriate—large samples with known population variance for Z, small or unknown variance...
Lecture 1.6.3: Calculus Gradients & Gradient Descent
The lecture bridges classic calculus concepts—gradients and gradient descent—with real‑world clinical decision making. It explains how the central law of optimization, which hinges on zero‑slope points, can be used to pinpoint the best drug dose or the optimal timing of...
1.4.9 Ethics and Sludge | Masters in Health Economics
The session titled “Ethics and Sludge” explains how hidden friction—called sludge—undermines the promise of choice architecture and why designers must treat it as a moral issue. Sludge is defined as excessive, unjustified barriers such as long forms, waiting times, or mandatory...
1.3.5 Event-Study Designs | Masters in Health Economics
The video introduces event‑study designs as a powerful extension of difference‑in‑differences, allowing researchers to trace policy impacts period by period rather than relying on a single average effect. It explains how to convert a static DID model into a dynamic...
Lecture 3.2.11: Reimbursement Regulatory Sandbox Pathways
The lecture examines how digital therapeutics move from concept to market through three pillars: reimbursement pathways, agile development, and regulatory sandboxes. It outlines the flow from physician prescription to insurer payment and highlights regional models such as Germany’s DiGA, U.S....
Lecture 1.3.4 | Probability, Statistics & Bayesian Inference | Masters in Medical Robotics
The lecture introduces the foundational trio—probability, statistics, and Bayesian inference—tailored for students in medical robotics. It explains how probability measures uncertainty before any data is observed, statistics extracts meaning from collected data, and Bayesian inference revises beliefs as new evidence...
Lecture 3.2.8: FDA Digital Health & CE Mark Pathways
The lecture walks developers through the regulatory maze for software‑based medical devices, comparing the U.S. FDA framework with the European CE‑mark pathway. It defines "software as a medical device" (SaMD), outlines the FDA’s three‑tier risk classification, and explains how each...
Lecture 3.2.5: Signal Preprocessing ECG, PPG + Feature Extraction, Windowing & HRV Spectral Features
The lecture walks through converting raw ECG and PPG voltages into actionable physiological metrics, focusing on preprocessing, feature extraction, and heart‑rate‑variability (HRV) spectral analysis. Aksha outlines three dominant noise sources—power‑line interference, baseline wander, and EMG artifacts—and recommends a “Goldilocks” filter chain:...
Lecture 3.2.3: Transfer Learning & Domain Adaptation , Class Imbalance & Augmentation
The lecture focuses on practical strategies—transfer learning, domain adaptation, class‑imbalance handling, and data augmentation—to build reliable AI systems for healthcare, where data are often noisy, biased, and scarce. Key insights include leveraging pre‑trained models by freezing early convolutional layers and fine‑tuning...
Lecture 3.2.2: U Net Segmentation Variants
The lecture introduces U‑Net segmentation variants for medical imaging, emphasizing need for pixel‑wise tumor delineation rather than simple presence detection. It reviews core U‑Net architecture—contracting encoder for context, expanding decoder for localization, and skip connections that transmit high‑resolution details. It then...
2.2.3 | Stakeholder Mapping | Masters in Health Economics
The video introduces stakeholder mapping as a core tool in health economics, defining it as a systematic way to list every individual or group that can affect or be affected by health policy decisions. It explains why mapping matters: it...
2.2.4 Theory of Change | Masters in Health Econmics
The video introduces Theory of Change (TOC) as a roadmap that connects health program inputs, activities, outputs, outcomes, and ultimate impact. It explains that TOC answers the how and why a program should work, turning abstract goals into a logical...