For some spaced repetition, here’s a review of this week’s content:
- As we try to minimize the medications and drips patients get in the intensive care unit, we should also work to minimize the amount of oxygen patients receive.
- Make titrating down the FiO2 a daily practice of yours and your team, and always remember that oxygen supplemental is a “drug” that is VERY commonly used in the ICU!
- There is no definitive evidence that SB works to improve outcomes in cardiac arrest
- If a TCA overdose is suspected, then SB should be administered
- Another potential harm of SB administration is it adds a cognitive load to the team leader, distracting them from interventions that could improve survival.
Machine Learning in Medicine by Sharad Patel
Our Mortality Predictor Tool shows promise as a way to gauge initial trajectories of ICU patients to help families and providers make difficult decisions in a complex landscape. The future direction is to validate our app prospectively. The app should not be used as the primary means for clinical decision-making as patient care is multi-faceted and should not be driven by one result.
- ICU patient trajectory can be difficult to ascertain.
- Fatigue and cognitive stressors can increase the degree of bias in clinical decision-making.
- Machine learning can be helpful as clinical support tools.
- Complex machine learning models have been seen as black boxes, but our models provide a degree of transparency via an explanation plot.
- Providing uncertainty is a strength of the model, as with a low confidence score, you should be more cautious with the output.
- Mortality Prediction Tool link: https://mortalitytool.com/
Mentorship: What’s Your Flavor by Danya Khoujah
- Whether you’re a mentor or a mentee, ask the question: what is the goal of this relationship?
- Be clear about the goals of the mentoring relationship: all-encompassing mentorship, coaching, advising, sponsorship, or connecting.
To Dive or Not to Dive by Mike Tom
- Reduction in the incidence of DNS is the primary goal of using HBOT for CO poisoning.
- Acute CO poisoning starts an inflammatory cascade, which ultimately causes the delayed neurologic injury. This cascade can be attenuated with HBOT.
- The decision to treat CO poisoned patients with HBOT can be a difficult one. HBOT should be recommended if the history, exam, or workup reveals evidence of end-organ damage.
- While the evidence for HBOT in the reduction of DNS in CO poisoned patients is limited and mixed, it is important to consider that undue weight has historically been given to one of two existing double-blinded RCT’s which was riddled with major flaws
NAVA: Neurally Assisted Ventilatory Assist by Danelle Howard
- Synchrony between patient and ventilator helps minimize patient discomfort and VILI
- May reduce ventilator days, improve hemodynamic stability, and reduce use of sedatives
- Edi measurement allows bedside monitoring of diagram activity
The Vitals: Central Venous Pressure by Michael Javid
CVP is not appropriate for guiding fluid therapy.
However, if you know the limitations of central venous pressure and the different factors that can affect it, combined with your patient’s clinical information and other hemodynamic context, then you can use CVP in a more appropriate way.
- RRI is a bedside ultrasound Doppler test that may help predict AKI in critically ill ICU patients.
- Some studies have shown that RRI can help predict AKI in patients post-cardiac surgery and in septic shock. Larger studies are ongoing.
- More research is needed, but RRI may help predict and prognosticate AKI in patients with COVID 19.