Acute Respiratory Distress Syndrome (ARDS)
Smart Medical Information Technology for Healthcare (SMITH) Project
Online Links
Selected ARDS Facts
- Also called noncardiogenic pulmonary edema
- It is a severe condition that affects around 1 in 10,000 people every year with life threatening consequences [reference: The ALIEN study]
- Its pathophysiology is characterized by bronchoalveolar injury and alveolar collapse (i.e., ‘atelectasis’) [reference: 1, 2, 3, 4]
Common Practice in Intensive Care Units (ICUs)
- Using lung recruitment maneuvers (RMs) in ARDS to open up unstable, collapsed alveoli using a brief increase in transpulmonary pressure [reference: 1]
- A large variety of RMs has been proposed in the literature
- The most frequently used recruitment maneuver in ARDS Treatment is Sustained Inflation (SI) [reference: 1]
Lung Recruitment Maneuvers (RMs) Challenges
- Because there is a large variety of RMs available there is also confusion regarding the optimal way to achieve and maintain alveolar recruitment in ARDS
- Examples of RMs are Sustained Inflation (SI), Maximal Recruitment Strategy (RMS), and Prolonged Recruitment Maneuver (PRM)
- The Maximal Recruitment Strategy (MRS) was evaluated via several patient trials [references: 1, 2 ]
- It is very likely that the MRS caused high Degrees of alveolar stress and strain in some patients [reference: 1]
- The Prolonged Recruitment Maneuver (PRM) is a more recent strategy in which PEEP is fixed to a higher than baseline Level and the positive inspiratory pressure is progressively increased [reference: 1]
- In many cases the precise mode of action of particular RMs is not well understood [reference: 1 ]
Selected Pulmonary Edema Facts
- Acute medical emergency due to an increase in pulmonary capillary venous pressure
- Leads to fluid in the alveoli usually due to acute left ventricular failure
Selected Pulmonology Facts
- Pulmonology is considered a subspecialty of internal Medicine related to lungs
- A pulmonologist is a medical doctor that has specialized knowledge and skill in the diagnosis and treatment of conditions and diseases of the lungs
Selected Alveoli Facts
- Tiny air sacs at the end of the bronchioles (tiny branches of air tubes) in the lungs
- NCI Dictionairy: Alveoli
Virtual Patient Related Work: Extended MATLAB Implementation based on Nottingham Physiology Simulator
- Das, A., Cole, O., Chikhani, M., Wang, W., Ali, T., Haque, M., Bates, D.G., Hardman, J.G.: Evaluation of Lung Recruitment Maneuvers in Acute Respiratory Distress Syndrome using Computer Simulation, in Critical Care, Vol 19(8), p.8., 2015
[ DOI ] [ RESEARCHGATE ]- Uses Computational Simulation to evaluate and understand the mode of operation of RMs for ARDS patients
- Employs a high-fidelity computational simulator that reproduces the static and dynamic characteristics of several ARDS patients
- Study compares the efficacy of three RMs in improving key patient parameters describing oxygenation, CO2 retention, and dynamic compliance
- Study also investigates the effects of different PEEP settings in maintaining effective lung recruitment across a representative patient spectrum
- Uses patient-specific computational simulation to analyze how three different lung recruitment maneuvers act to improve physiological responses and investigate how different levels of PEEP contribute to maintaining effective lung recruitment
- Employs a simulation model that is an Extended MATLAB implementation of several physiological models originally developed within the Nottingham Physiology Simulator [references: 1, 2, 3 ]
- Design of simulator core models represent a dynamic in vivo cardio-vasculo-pulmonary state using a set of mass-conserving equations based on well established physiological principles
- Simulates a lung divided into 100 alveolar compartments, with each compartment having a corresponding set of parameters accounting for stiffness, threshold opening pressures and extrinsic pressures as well as airway and vascular resistances – How realistic is this model with 100 alveolar compartments, is the abstraction correct or can it be enhanced?
- Uses mathematical principles and equations on which the simulator is based and that have been detailed in previous studies and thus validated the ability to accurately represent pulmonary disease states [references: 1, 2 ]
- Models the recruitment as a time-dependent process by the introduction of a ‘time-constant’ parameter for each collapsed alveolar compartment, denoting the time it takes for the collapsed alveolus to open after a threshold pressure has been reached
Virtual Patient Related Work: Physiology Based Pharmacokinetics/Pharmacodynamics (PBPK/PD) Models – Tutorial
- Kuepfer, L., Niederalt, L., Wendl, T., Schlender, J., Willmann, S., Lippert, J., BLock, M., Eissing, T., Teutonico, D.: Applied Concepts in PBPK Modeling: How to Build a PBPK/PD Model, in CPT Pharmacometrics Systems Pharmacology, Vol. 5, Issue 10, pp. 516–531, 2016
[ DOI ] [ RESEARCHGATE ]- Provides a good tutorial for Physiology Based Pharmacokinetics/Pharmacodynamics (PBPK/PD)
- Introduces to a practical implementation in a typical PBPK model building workflow
- Gives the example of a PBPK model for ciprofloxacin coupled to a pharmacodynamic model to simulate the antibacterial activity of ciprofloxacin treatment
- Ciprofloxacin is an antibiotic used to treat a number of bacterial infections and works by stopping the growth of bacteria
- Ciprofloxacin therefore treats only bacterial infections and does not work for virus infections (e.g., common cold, flu)
- Ciprofloxacin is known for the fact (like for any antibiotic) that its overuse can lead to its decreased effectiveness
Social Media
Virtual Patient seminar with PhD students: disease models like Nottingham & physiologically based pharmacokinetic models to understand ARDS in #SMITH @JRC_COMBINE using modular HPC by @fzj_jsc @fz_juelich @Haskoli_Islands @uisens @uni_iceland @DEEPprojects https://t.co/r7KMBtFxi0 pic.twitter.com/jsqjpBNT5V
— Morris Riedel (@MorrisRiedel) July 3, 2019
On discussing a Medical Data Science MSc @UniklinikAachen & a strong #MachineLearning dragon in Intensive Care Units against ARDS in project #SMITH @JRC_COMBINE via modular HPC by @fzj_jsc @fz_juelich @Haskoli_Islands @uisens @uni_iceland @DEEPprojects – https://t.co/r7KMBtFxi0 pic.twitter.com/bt0lpAaWEv
— Morris Riedel (@MorrisRiedel) June 27, 2019
Smart Medical Information Technology for Healthcare #SMITH ASIC event with @UniklinikAachen @JRC_COMBINE & PhD Student C. Barakat presents speed-ups via modular supercomputing by @fzj_jsc @fz_juelich @Haskoli_Islands @uisens @uni_iceland @DEEPprojects see https://t.co/r7KMBtFxi0 pic.twitter.com/IPzrFFCHP5
— Morris Riedel (@MorrisRiedel) June 14, 2019
Smart Medical Information Technology for Healthcare #SMITH meeting last week on Algorithmic Surveillance of Intensive Care Unit Patients approaches by @UniklinikAachen @JRC_COMBINE @fzj_jsc @fz_juelich @Haskoli_Islands @uisens @uni_iceland @DEEPprojects – https://t.co/r7KMBtFxi0 pic.twitter.com/n4Tlsknb2U
— Morris Riedel (@MorrisRiedel) May 12, 2019
Discussing clustering methods to detect Acute Respiratory Distress Syndrome (ARDS) in patients in SMITH ASIC workshop @UniklinikAachen @JRC_COMBINE via modular supercomputing by @DEEPprojects @fzj_jsc @fz_juelich @Haskoli_Islands @uisens @uni_iceland – see https://t.co/r7KMBtFxi0 pic.twitter.com/1fdLsuRAJ5
— Morris Riedel (@MorrisRiedel) April 10, 2019
SMITH Algorithmic Surveillance of Intensive Care Unit Patients (ASIC) workshop @UniklinikAachen @JRC_COMBINE discussing parallel DBSCAN clustering via modular supercomputing by @DEEPprojects @fzj_jsc @fz_juelich @Haskoli_Islands @uisens @uni_iceland – see https://t.co/ZeOko01yZK pic.twitter.com/zm3j3s0kE9
— Morris Riedel (@MorrisRiedel) March 13, 2019
Smart Medical Information Technology for Healthcare (SMITH) project meeting at #UniversitätsklinikLeipzig with a great dinner & presentation of the Algorithmic Surveillance of Intensive Care Unit Patients (ASIC) use case of @UniklinikAachen @fzj_jsc @fz_juelich @Haskoli_Islands pic.twitter.com/1CxIn2dHEN
— Morris Riedel (@MorrisRiedel) February 21, 2019
SMITH Algorithmic Surveillance of Intensive Care Unit Patients (ASIC) workshop @UniklinikAachen discussing virtual patient models like @VPH_Institute using modular supercomputing of @DEEPprojects @fzj_jsc @fz_juelich @Haskoli_Islands @uisens @uni_iceland – https://t.co/xCDitaxS71 pic.twitter.com/3Cw2vKKBux
— Morris Riedel (@MorrisRiedel) February 18, 2019
Smart Medical Information Technology for Healthcare (SMITH) – Algorithmic Surveillance of Intensive Care Unit Patients (ASIC) workshop last week; @Oliver_Maassen of @UniklinikAachen kick-off the event & Prof. Schuppert & Prof. Marx discuss relevance of HPC @fzj_jsc @fz_juelich pic.twitter.com/1dCkzUCz23
— Morris Riedel (@MorrisRiedel) January 14, 2019
Traveling to the Smart Medical Information Technology for Healthcare (SMITH) meeting in Leipzig with nice discussions on using machine learning and/or HPC in different medical use cases @fzj_jsc @fz_juelich pic.twitter.com/iHUBfOSElk
— Morris Riedel (@MorrisRiedel) August 28, 2018
Smart Medical Information Technology for Healthcare (SMITH) – Algorithmic Surveillance of Intensive Care Unit Patients (ASIC) workshop at Duesseldorf; Prof. Marx & @Oliver_Maassen of @UniklinikAachen kick-off the event & Prof. Schuppert & H. Mayer of Bayer show results @fzj_jsc pic.twitter.com/JiFxWdo3Pr
— Morris Riedel (@MorrisRiedel) August 22, 2018
Great workshop @UniklinikAachen today discussing next steps with Bayer towards the realization of a virtual patient hybrid model structure using markov chains monte carlo, machine learning & HPC @fzj_jsc as part of the Smart Medical Information Technology for Healthcare project pic.twitter.com/Tery4GBrSP
— Morris Riedel (@MorrisRiedel) March 28, 2018
Prof. Gernot Marx and Oliver Maassen from university hospital Aachen started a great workshop of the Smart Medical Information Technology for Healthcare Project with a focus on Algorithmic Surveillance of Intensive Care Unit Patients – Truly Interesting Event! pic.twitter.com/b4IC97m25G
— Morris Riedel (@MorrisRiedel) March 5, 2018
Excellent kick-off meeting of the SMITH project – Smart Medical Information Technology for Healthcare – Juelich Supercomputing Centre works on HPC with data-intensive applications together with RWTH Aachen and Bayer pic.twitter.com/G2EohKHQkF
— Morris Riedel (@MorrisRiedel) February 20, 2018