Machine Learning
Physiological Modeling Research
Explores computational hemodynamic modeling and Optic-Trigeminal physiological systems with transparent preservation of null and mixed experimental results.
Research question
Does incorporating patient-specific vascular elastance parameters yield statistically and clinically meaningful improvements in Mean Arterial Pressure (MAP) forecasting over baseline autoregression?
Method & architecture
A dynamic mathematical model combining continuous arterial pressure waveforms with lumped-parameter vascular compliance circuits to forecast arterial blood pressure trajectories and assess autonomic drug responses.
- Preservation of Negative Results: Transparent reporting of statistical nulls is essential to scientific integrity.
- Distinction of Signal vs Utility: Statistical significance under restricted permutations does not equal practical predictive utility.
- Evolutionary Research Lineage: Question ➔ Implementation ➔ Experiment ➔ Result ➔ Failure/Lesson ➔ Iteration ➔ Public Research Log.
Results & findings
Statistical Significance != Clinical Utility
OBSERVEDA within-patient permutation p = 0.0479 coexists with a negligible +0.0078 mmHg improvement.
Held-Out Predictive Superiority
FAILEDFailed to demonstrate practical forecasting advantage over simple lag-1 autoregression.
Autonomic Baroreflex Compensation
OBSERVEDHeart rate dynamics revealed compensatory autonomic reflex mechanisms that counteract direct drug vasoconstriction.