micheledpierri-home-threshold-2026

micheledpierri.com

Notes, research and personal trajectories

Mais il est aussi de ceux qu'on peut comparer aux arbres parce que leur croissance obéit, non pas comme celle des constructions humaines, à une loi de l'addition de chaque jour et de chaque instant, mais à une force intérieure qui dépose, d'après un plan caché, au-dedans des anciens dépôts, des couches nouvelles.

But he is also one of those who may be compared to trees, because their growth obeys not, like that of human constructions, a law of daily and moment-by-moment addition, but an inner force which, according to a hidden design, lays new layers within the old deposits.

Marcel Proust, Le Temps retrouvé

Selected writings

From Hippocrates to Artificial Intelligence

I am a cardiac surgeon. My work is rooted in the operating room, in clinical decisions, and in the care of individual patients. At the same time, I have become deeply interested in medical data, statistics, coding, and artificial intelligence. My fascination with the history of medicine, however, has remained just as strong. At first...

Open-Weight Medical LLMs

There is a specific moment, familiar to anyone who has gone down this road, when you finish downloading a model with “Med” in its name and realise you have no idea whether it is actually any good. The name promises domain expertise. The model card promises benchmarks. Neither tells you what happens when you ask...

When “Not Worse” Is Enough: Understanding Non-Inferiority Trials in Medicine

Non-inferiority Trials in Medicine: Last updated: June 2026 Author: Michele D. Pierri Reading time: 15–20 minutes In clinical research, we are used to thinking that a new drug, device, or procedure should be tested by asking a simple question: Is it better than what we already have? This is the logic of a superiority trial....

Recent writings

How Well Can a Local 30B Model Answer Medical Questions? Benchmarking Meta Muse Glimmer on an RTX 3090

A reproducible 300-question evaluation across medical exams, biomedical literature, multilingual question answering, and clinical calculation Meta released Muse Glimmer on 10 August 2026: thirty billion parameters, open weights, built for agentic work on consumer hardware.[1,2] I tested a quantized version five days later on a single NVIDIA RTX 3090 — partly because it was the...

From Chart to Variable: Extracting Computable Clinical Features from the EHR

Vasoactive-Inotropic Score as a Worked Example Introduction: The Data Is There. The Variable Is Not. Every conversation about clinical AI opens on the same premise: hospitals are sitting on enormous quantities of data. True enough, and almost useless as a starting point. An electronic health record is a transactional system, built for documentation, for billing,...

Learning paths

Python

12 topics

  1. Why Python
  2. Python & VS Code Setup (From Zero to a Professional Environment)
  3. Variables, Naming Rules, and Basic Syntax
  4. Core Data Types in Python
  5. Control Flow: Conditions and Loops
  6. Functions and Code Reusability
  7. Collections: Lists, Tuples, Sets, and Dictionaries
  8. Modules, Packages, and File Handling
  9. Errors, Exceptions, and Robust Code
  10. Object-Oriented Programming (OOP) in Python
  11. Intermediate Python: Writing Clean, Pythonic Code
  12. Python Wrap-Up Lesson: A Mini Cardiology Risk-Factor Audit (Step-by-Step)

Statistics

22 topics

  1. Statistics in Medicine
  2. Data Type
  3. Statistical Distributions
  4. Central Limit Theorem
  5. Descriptive Statistics
  6. Study Design in Medicine
  7. Inferential Statistics: Hypothesis Testing
  8. Choose the Right Statistical Test
  9. T test
  10. One-way ANOVA
  11. Repeated measure ANOVA
  12. Correlations
  13. Linear Regression
  14. Logistic Regression 1
  15. Logistic Regression 2
  16. Chi Square
  17. ANCOVA
  18. Bayes’ Theorem
  19. Monte Carlo Simulation
  20. Nonparametric statistics
  21. Survival Analysis
  22. Propensity Score

Data Analysis

11 topics

  1. Introduction to Data Analysis
  2. Data Collection
  3. Data Formats
  4. Data Cleaning
  5. Data quality assessment
  6. Missing data
  7. Duplicate data
  8. Outliers
  9. Normalization, Standardization and Scalers
  10. Organization of Variables
  11. Exploratory Data Analysis

Machine Learning

16 topics

  1. Introduction to Machine Learning
  2. Dataset Division and Data Leakage
  3. Encoding of Categorical Variables
  4. Feature Engineering and Selection
  5. Dimensionality Reduction Techniques
  6. Machine Learning Models: A Complete Guide to Classification Approaches
  7. Linear Regression
  8. NonLinear Regression
  9. Machine Learning Distances
  10. K-Nearest Neighbors (KNN)
  11. Support Vector Machines
  12. Naive Bayes
  13. Decision Tree
  14. Ensemble Models
  15. Random Forest
  16. Machine Learning Model Evaluation