April 29–30, 2026 · 2-Day Online Workshop

Clinical Machine Learning Workshop
Using the InsilicoΣ Platform: From Clinical Data to Trusted Models

Master the complete ML pipeline on the InsilicoΣ platform. No programming required. Real clinical context throughout. Walk away building, evaluating, and interpreting clinical ML models.

2
Days
9
Sessions
4
Hands-on Labs
30
Days Free Platform Access
Full access to all tools & pipeline steps
The ML Pipeline You'll Master
1
Prepare Data
Upload, clean, explore with EDA
2
Build Models
Choose algorithm, configure, train
3
Evaluate Performance
Accuracy, AUC, calibration, comparison
4
Interpret & Validate
SHAP values, bias detection, clinical DCA
What You'll Learn

8 Learning Objectives

From clinical data literacy to critical appraisal - a complete foundation

1
Clinical ML Foundations

Explain what clinical ML is, when it is appropriate, and when it is not

2
Exploratory Data Analysis

Perform systematic EDA on clinical tabular data

3
Data Preprocessing

Apply imputation, encoding, scaling, and feature selection strategies

4
Model Training

Train classification, regression, and survival models on the platform

5
Data Type Modules

Select the right module: structured, time-series, NLP, or imaging

6
Model Interpretation

Interpret outputs using SHAP values, feature importance, and decision curves

7
Bias Detection

Detect and quantify algorithmic bias across demographic subgroups

8
Critical Appraisal

Critically evaluate published clinical ML studies

Who Should Attend

You Have Data. We Give You the Tools.

This workshop is for anyone who has clinical data and wants to build ML models - no programming needed. Everything is done through an intuitive UI with point-and-click selections.

This workshop is for you if:
You have clinical data (patient records, lab results, images, notes)
You want to build ML models but have no coding experience
You need to understand why your model makes predictions
You want results you can trust and present to reviewers
Clinical Researchers

MDs and PhDs who have collected patient data and want to apply ML to predict outcomes, classify diseases, or find patterns - using a guided, code-free interface.

Medical & Pharmacy Students

Students working on research projects or theses who need to apply ML methods to their datasets. Learn by doing - no prior ML experience needed.

PhD Candidates

Biomedical and health sciences researchers who want to add ML analysis to their publications. The platform handles preprocessing, training, and interpretation for you.

Research Coordinators

Data managers and research nurses who collect clinical data and want to understand how it translates to ML models - and how data quality impacts results.

Prerequisites: Comfort with spreadsheets and basic statistics (p-values, sensitivity/specificity). No Python, R, or ML knowledge required.

The InsilicoΣ Platform

What the Tool Can Do

A complete clinical ML environment - from raw data to interpretable, validated models

4
Data Types
15+
ML Algorithms
30+
Output Metrics
6
Interpretation Methods

Supported Data Types

Upload your clinical data in any of these four formats

Structured / Tabular

Classic CSV or Excel datasets with rows (patients) and columns (features)

Patient demographics Lab results Clinical outcomes Biomarkers Vital signs
Time-Series

Temporal data with timestamps - ICU monitoring, wearable sensors, longitudinal records

ICU vitals ECG signals Blood glucose logs Wearable data
NLP / Text

Unstructured clinical text - notes, reports, discharge summaries for classification or NER

Clinical notes Radiology reports Discharge summaries Pathology reports
Medical Imaging Supported Soon

Image-based data for classification, segmentation, or detection tasks

X-rays Histopathology Retinal scans Dermatology CT slices

Algorithms & Models

Choose from 15+ algorithms - the platform handles the rest

Classification

Predict categories - disease vs healthy, drug response, risk stratification

Logistic Regression Random Forest XGBoost SVM Neural Network LightGBM KNN Naive Bayes
Regression

Predict continuous values - dosage, survival time, biomarker levels

Linear Regression Ridge / Lasso Elastic Net Random Forest Gradient Boosting XGBoost
Hyperparameter Tuning

Optimize your model automatically with smart search strategies

Grid Search Random Search Bayesian (Optuna)

Outputs & Insights

Everything you need to understand, trust, and present your model

Performance Metrics

Comprehensive evaluation with confidence intervals

AUC-ROC Accuracy F1 Score Sensitivity Specificity PPV / NPV RMSE Brier Score
Model Interpretation

Understand why your model makes each prediction

SHAP Values Feature Importance Partial Dependence LIME Decision Curves Counterfactuals
Fairness & Clinical Validation

Ensure your model is fair, calibrated, and clinically useful

Bias Detection Demographic Parity Calibration Curves DCA Curves Subgroup Analysis Bootstrap CI
Visualizations

Publication-ready charts and plots generated automatically

ROC Curve Confusion Matrix Calibration Plot Learning Curves Residual Plots Forest Plot
Model Comparison

Compare multiple algorithms side-by-side with statistical tests

Head-to-Head Metrics CV Comparison Wilcoxon Test Effect Size
Full Programme

2-Day Online Workshop Schedule

April 29–30, 2026 · Lectures in the morning, hands-on labs in the afternoon

Day 1 (April 29) - Foundations: Data, EDA, Preprocessing & First Model
TimeSessionTopic
08:30 - 09:00RegistrationWelcome, credentials, dataset download
09:00 - 09:30PlenaryIntroduction: Why Clinical ML Now?
09:30 - 10:30Session 1The Clinical ML Landscape - terminology, workflow, common pitfalls
10:30 - 10:50Break
10:50 - 12:00Session 2Understanding Your Clinical Data - types, quality, bias sources
12:00 - 13:00Break
13:00 - 14:00Session 3EDA on the Platform - demo + guided lab
14:15 - 15:15Session 4Preprocessing: Imputation, Encoding, Scaling
15:30 - 16:30Session 5Your First Model: Train, Evaluate, Export
16:30 - 17:30Labs 1 & 2Hands-on: EDA + Preprocessing + First Model (heart failure dataset)
17:30 - 18:00DebriefQ&A, discussion, preview of Day 2
Day 2 (April 30) - Advanced: Optimization, Interpretation & Fairness
TimeSessionTopic
08:30 - 09:00WelcomeDay 1 recap, Q&A from overnight
09:00 - 10:00Session 6Choosing the Right Module - structured vs time-series vs NLP vs imaging
10:20 - 11:20Session 7Optimization: Cross-validation, hyperparameters, class imbalance
11:20 - 12:00Lab 3Hands-on: Optimization Lab (sepsis dataset)
12:00 - 13:00Break
13:00 - 14:00Session 8Model Interpretation: SHAP, PDP, Decision Curve Analysis
14:00 - 15:00Session 9Bias, Fairness & Subgroup Performance
15:20 - 16:00Lab 4Hands-on: Interpretation + Bias Lab
16:45 - 17:15Case DiscussionLive critique of a published clinical ML paper
17:15 - 18:00ClosingKey takeaways, next steps, certificates
Investment

Workshop Pricing

Includes 30-day full access to the InsilicoΣ Clinical ML platform after the workshop

International

$125 USD

Per participant

  • 2-day workshop (10 sessions + 4 labs)
  • 30-day InsilicoΣ platform access
  • Sample clinical datasets
  • Workshop materials & slides
  • Certificate of completion
  • Online delivery - attend from anywhere
Register Now
Registration

Secure Your Spot

April 29–30, 2026

Complete the form below. We'll send confirmation and payment details to your email.

Personal Information
Pricing Tier
Your Primary Dataset Type

What kind of clinical data will you primarily work with? This helps us prepare relevant examples for you.

Additional Information

Payment instructions will be sent to your email after registration.

Before You Arrive

Prerequisites

Laptop + Browser

Chrome, Firefox, or Edge. The platform is fully browser-based, no installations needed.

Basic Statistics

Comfortable with p-values, confidence intervals, sensitivity/specificity concepts.

Curiosity

No prior ML experience required. We start from zero and build up systematically.

Register Now