Home/Smart Formulary & Orders/Smart Orders
AI MedAgent Smart Orders Part of AI MedAgent Smart Formulary and Order Management. The chart configures the body, the model does the math, the reasoning explains it, and the order carries the flow pattern. Built on the lesson of Dr. N. Ty Smith's BODY.

1. The patient

2. The order being considered

Chosen by the clinician. The demo does not choose the clinical goal.

The usual way

The model-informed way

Public data: FDA labeling

3. What the model predicts

Usual way Model-informed Uncertainty band (model-informed)
Table view of the chart

4. The individualized order, with its flow pattern

What the pump would run (10 mg/mL)

The same order as a standard FHIR MedicationRequest (draft)

  

  

    
5. Reasoning

    

    

    

  







  
How this works, and what it is not

  
Decades ago Ty Smith's BODY let a teacher build a patient by hand and watch a drug land differently in a different body. It could not be used on real patients. Here the patient's own chart supplies the settings, a published pharmacokinetic model does the math, the reasoning layer explains the result and checks it against the chart, and the order is written with a goal and a flow pattern instead of a single number.

  
What it is not. The pharmacokinetics are the Schnider propofol model, built from 24 adult volunteers aged 25 to 81. The cardiac-output adjustment (slower arrival, smaller initial mixing volume, flow-limited distribution) is an illustrative extension based on published findings, not a validated model. There is no inter-drug interaction, no hemodynamic response, and no individual variability beyond the uncertainty band shown. A system that recommended doses for real patients would be a medical device and would need clinical validation and a regulatory path with FDA.

  
    
    
  1. Schnider TW, Minto CF, Gambus PL, et al. The influence of method of administration and covariates on the pharmacokinetics of propofol in adult volunteers. Anesthesiology 1998;88:1170-1182. Parameters as tabulated in Absalom AR, Mani V, De Smet T, Struys MMRF. Br J Anaesth 2009;103(1):26-37.
    2. 
    
  2. Upton RN, et al. Cardiac output is a determinant of the initial concentrations of propofol after short-infusion administration. Anesth Analg 1999;89:545-552.
    3. 
    
  3. Krejcie TC, Avram MJ. What determines anesthetic induction dose? It's the front-end kinetics, doctor! Anesth Analg 1999;89:541-544.
    4. 
    
  4. Adachi YU, Satomoto M, Higuchi H, Watanabe K. The determinants of propofol induction time in anesthesia. Korean J Anesthesiol 2013;65:121-126.
    5. 
    
  5. DIPRIVAN (propofol) prescribing information, via openFDA drug label API.
    6. 
    
  6. Smith NT. PC-based "BODY" simulation presents anesthesia learning chance, challenge. APSF Newsletter 1999;14(2).
    7.