Data-Driven Approach in Treating a Medical Condition
summary
Parents log every diaper, medication, meal and symptom into synced cloud storage, build dashboards from an ETL pipeline and a 350-column table, try correlations and decision trees (they give false positives), then pivot to clustering good versus bad days and a weekly fixed menu. Removing meat+grains and high-protein days cuts seizures; pathological EEG spikes disappear after five months, nightly sleep rises from ~2 to ~8 hours and monthly night wakings fall from ~72. Reanalysis finds DAO enzyme deficiency (histamine intolerance) as the likely trigger.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 1:04Epilepsy diagnosis struggles
- 4:15Collecting real-life data
- 7:48Math failed to solve
- 9:31Logic and clustering cases
- 11:15Food triggers via menu
- 13:23Nutrition triggers seizures
- 14:09Switching to solid food
- 15:14Sleep and seizures progress
- 16:16Nervousness dietary causes
- 17:01Histamine intolerance diagnosis
- 17:43Gut flora role
- 18:03Q&A
related talks
17mKnow Thyself: Introspective Personal Data Mining
45mComplexity in Living Systems
37mNew Era of Data Insights with Samsung Health
34mLongitudinal Phenotypes and Disease Trajectories at Population Scale
01h 51mMorning Session: Genomics, Medicine, Epidemiology and Data Interpretation
27mMining social media data of people with rare diseases
07mBig Data and Cardiac Rehabilitation
16mThe Secret Life of Data - Part 3