AI in Medicine — Summer Course 2026

Conventional
Machine Learning

Build, evaluate, and interpret ML models for biomedical data —
from logistic regression to random forests in one session

28 July 2026 9:00–12:15 Google Colab
🧑‍💻
Your Instructor

Koay Hong Vin

Education
B.Eng. Electrical Engineering
PhD in Artificial Intelligence — Autonomous Vehicles
Current
Risk Modelling and Data Scientist
Ant International
Links
linkedin.com/in/koayhv
hongvin.me
01 / Concept

What is Machine Learning?

  • Algorithms that learn from data — instead of being explicitly programmed with rules
  • Classification — predict a category (malignant vs benign tumor)
  • Regression — predict a number (disease progression score)
  • Supervised learning — we have labeled examples to learn from. Both classification and regression are supervised.
  • The golden rule — never evaluate on training data. Always hold out a test set.
02 / scikit-learn

scikit-learn — The ML Workhorse

  • One API pattern — every model follows fit() → predict()
  • Dozens of algorithms — logistic regression, decision trees, random forests, SVM, k-NN
  • Built-in evaluation — accuracy, precision, recall, ROC curves, confusion matrices
  • Preprocessing tools — scaling, encoding, imputation, feature selection
# The 4-step recipe
from sklearn import SomeModel

model = SomeModel()
model.fit(X_train, y_train)
preds = model.predict(X_test)
03 / Classification

Logistic Regression — Your First Model

  • Despite the name — logistic regression is a classification algorithm
  • Outputs a probability — "89% chance this tumor is malignant"
  • Fast, interpretable, and often excellent — always try it first
  • Dataset: Breast Cancer Wisconsin — 569 samples, 30 cell-nuclei features → predict malignant vs benign
04 / Evaluation

Is Our Model Any Good?

🎯
Confusion Matrix
Shows exactly where errors happen. False negatives (missed cancers) vs false positives (false alarms).
📈
ROC Curve & AUC
Tradeoff between sensitivity and specificity at every threshold. AUC = 1.0 is perfect; 0.5 is random.
⚖️
Precision & Recall
Precision: of predicted positives, how many are real?
Recall: of real positives, how many did we catch?
🔬
Clinical Context
In cancer screening, recall > precision. Missing a cancer (false negative) is far worse than a false alarm.
05 / Overfitting

Overfitting vs Underfitting

📉
Underfitting
Model is too simple. Misses real patterns in the data. High bias, poor performance on both train and test sets.
🎯
Just Right
Model captures genuine patterns without memorizing noise. Good generalization — performs well on unseen data.
⚠️
Overfitting
Model is too complex. Memorizes training data including noise. Great on training, terrible on test. The most common ML mistake.
💊
In Medicine
An overfit model might learn that "patients with ID #47 all have cancer" — a coincidence, not a pattern. Devastating in clinical use.
06 / Trees

Decision Trees & Random Forest

  • Decision Tree — flowchart-like model. Splits data by asking yes/no questions about features. Fully interpretable.
  • Random Forest — an ensemble of 100+ decision trees, each trained on a random subset. Averages predictions → more robust.
  • Feature importance — random forests tell you which features matter most. Vital for biomedical insight.
from sklearn.ensemble import RandomForestClassifier

rf = RandomForestClassifier(
  n_estimators=100,
  max_depth=5
)
rf.fit(X_train, y_train)

# Which features matter?
rf.feature_importances_
07 / Validation

Cross-Validation — Trust but Verify

  • One split isn't enough — a single train/test split can be lucky (or unlucky). Cross-validation fixes this.
  • K-fold CV — split data into K parts. Train on K-1, test on 1. Repeat K times. Average the scores.
  • Typical K = 5 or 10 — gives a robust estimate of real-world performance.
  • In medicine — always report CV scores, not just one split. It shows whether your model is stable.
from sklearn.model_selection import cross_val_score

rf = RandomForestClassifier()
scores = cross_val_score(
  rf, X, y, cv=5
)

# 5 scores, one per fold
scores # eg [0.96, 0.98, 0.95, ...]
scores.mean() # robust estimate
08 / Regression

Linear Regression — Predict a Number

  • Dataset: Diabetes — 442 patients, 10 baseline variables → predict disease progression after 1 year
  • R² (R-squared) — what fraction of variance does your model explain? 0 = useless, 1 = perfect
  • Coefficients — each feature has a weight. Positive = increases prediction, negative = decreases it
  • Clinical insight — BMI and blood pressure are the strongest predictors. This matches clinical knowledge → builds trust.
09 / Datasets

Our Biomedical Datasets

🔬
Breast Cancer Wisconsin
569 samples, 30 features from cell nuclei images. Predict malignant vs benign. The classic biomedical ML benchmark.
💉
Diabetes Dataset
442 patients, 10 baseline variables (BMI, BP, blood serum). Predict disease progression 1 year later. Real clinical data.
📦
Built into scikit-learn
Both datasets come pre-installed with scikit-learn. One line of code loads them — no downloading, no cleaning needed.
🏥
Why These Matter
These are the same datasets used in ML textbooks and research papers worldwide. You're learning on real, published data.
10 / Insight

Model Interpretation & Common Pitfalls

  • Feature importance — random forests tell you which biomarkers matter most. This is often more valuable than the prediction itself.
  • Coefficients — in logistic/linear regression, each coefficient says: "for every 1-unit increase in X, outcome changes by Y"
  • Data leakage — accidentally using future information to predict the past. Example: scaling BEFORE splitting.
  • Class imbalance — 99% benign, 1% malignant? A model that says "always benign" gets 99% accuracy but is clinically useless.
  • Correlation ≠ causation — the model found that ice cream sales predict drownings. Doesn't mean ice cream causes drowning.
  • Always ask: Would I trust this model with a patient's life? If not, what would make you trust it?
11 / Setup

How We'll Work

🌐
Google Colab
No installation. scikit-learn, NumPy, Pandas, and Matplotlib all pre-installed. Runs in your browser.
⌨️
Code-Along
I'll type, you follow. Every cell runs. You'll see models train in real time and predictions appear immediately.
✏️
Exercises
Build your own models. Compare algorithms. Decide which model you'd trust in a clinical setting.
💬
Ask Anytime
ML has jargon — if a term doesn't make sense, ask. Chances are others have the same question.
12 / Recap

The ML Pipeline

Split
Train/test before anything else
Fit
model.fit(X_train, y_train)
Evaluate
Confusion matrix, ROC, precision, recall
"Every ML pipeline is the same: split → fit → predict → evaluate. Master this pattern and you can use any algorithm."
🤖

Let's Build Models!

Open your notebook. Time to train your first classifier.

Open in Google Colab
1 / 15